0%| | 0/1784 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9004, 'learning_rate': 0.0, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:25,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%| | 1/1784 [00:04<2:06:52, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:27,846 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.028, 'learning_rate': 0.0, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:29,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%| | 2/1784 [00:08<1:59:06, 4.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:31,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:45:33,485 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.1215, 'learning_rate': 2e-06, 'epoch': 0.0} 0%|▏ | 3/1784 [00:12<1:58:52, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:35,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6759, 'learning_rate': 4e-06, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:37,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▏ | 4/1784 [00:15<1:55:28, 3.89s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:39,346 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7525, 'learning_rate': 6e-06, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:41,156 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▏ | 5/1784 [00:19<1:53:57, 3.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:43,076 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7486, 'learning_rate': 8e-06, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:44,869 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 6/1784 [00:23<1:52:35, 3.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:46,761 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5801, 'learning_rate': 1e-05, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:48,914 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 7/1784 [00:27<1:55:33, 3.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:51,556 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6594, 'learning_rate': 1.2e-05, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:53,353 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 8/1784 [00:31<1:59:55, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:55,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.831, 'learning_rate': 1.4e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:45:56,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 9/1784 [00:35<1:55:58, 3.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:45:58,828 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:00,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 10/1784 [00:38<1:52:50, 3.82s/it] 1%|▍ | 10/1784 [00:38<1:52:50, 3.82s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:02,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.513, 'learning_rate': 1.8e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:46:04,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 11/1784 [00:42<1:50:38, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:05,979 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:07,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 12/1784 [00:46<1:48:30, 3.67s/it] 1%|▌ | 12/1784 [00:46<1:48:30, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:09,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:11,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 13/1784 [00:49<1:47:08, 3.63s/it] 1%|▌ | 13/1784 [00:49<1:47:08, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:13,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2523, 'learning_rate': 2.4e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:46:14,664 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 14/1784 [00:53<1:45:40, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:16,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:18,133 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▋ | 15/1784 [00:56<1:44:37, 3.55s/it] 1%|▋ | 15/1784 [00:56<1:44:37, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:19,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:21,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▋ | 16/1784 [00:59<1:43:33, 3.51s/it] 1%|▋ | 16/1784 [00:59<1:43:33, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:23,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4427, 'learning_rate': 3e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:46:25,019 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 17/1784 [01:03<1:42:56, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:26,753 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:28,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 18/1784 [01:06<1:41:48, 3.46s/it] 1%|▊ | 18/1784 [01:06<1:41:48, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:30,135 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:31,775 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 19/1784 [01:10<1:41:04, 3.44s/it] 1%|▊ | 19/1784 [01:10<1:41:04, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:33,480 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:35,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▉ | 20/1784 [01:13<1:40:16, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:36,870 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6023, 'learning_rate': 3.6e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:46:38,474 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▉ | 21/1784 [01:16<1:39:38, 3.39s/it] 1%|▉ | 21/1784 [01:16<1:39:38, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:40,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:41,865 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▉ | 22/1784 [01:20<1:39:35, 3.39s/it] 1%|▉ | 22/1784 [01:20<1:39:35, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:43,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4214, 'learning_rate': 4.2000000000000004e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:46:45,216 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█ | 23/1784 [01:23<1:39:09, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:46,917 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:48,494 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█ | 24/1784 [01:26<1:38:13, 3.35s/it] 1%|█ | 24/1784 [01:26<1:38:13, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:50,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:51,737 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█ | 25/1784 [01:30<1:37:15, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:53,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3643, 'learning_rate': 4.6e-05, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-03 00:46:54,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█▏ | 26/1784 [01:33<1:36:15, 3.28s/it] 1%|█▏ | 26/1784 [01:33<1:36:15, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:56,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:46:58,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▏ | 27/1784 [01:36<1:35:41, 3.27s/it] 2%|█▏ | 27/1784 [01:36<1:35:41, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:46:59,863 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.032, 'learning_rate': 5.2e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:01,455 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▏ | 28/1784 [01:39<1:35:45, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:03,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.341, 'learning_rate': 5.4e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:04,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▎ | 29/1784 [01:43<1:35:40, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:06,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:07,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▎ | 30/1784 [01:46<1:34:55, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:09,562 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2808, 'learning_rate': 5.6e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:11,085 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▎ | 31/1784 [01:49<1:34:11, 3.22s/it] 2%|█▎ | 31/1784 [01:49<1:34:11, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:12,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:14,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▍ | 32/1784 [01:52<1:33:17, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:15,799 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5311, 'learning_rate': 6e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:17,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▍ | 33/1784 [01:55<1:31:47, 3.15s/it] 2%|█▍ | 33/1784 [01:55<1:31:47, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:18,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:20,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 34/1784 [01:58<1:30:19, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:21,763 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.107, 'learning_rate': 6.4e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:23,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 35/1784 [02:01<1:28:56, 3.05s/it] 2%|█▌ | 35/1784 [02:01<1:28:56, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:24,706 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:26,108 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 36/1784 [02:04<1:27:54, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:27,586 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.674, 'learning_rate': 6.800000000000001e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:28,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 37/1784 [02:07<1:26:10, 2.96s/it] 2%|█▋ | 37/1784 [02:07<1:26:10, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:30,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:31,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 38/1784 [02:10<1:24:52, 2.92s/it] 2%|█▋ | 38/1784 [02:10<1:24:52, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:33,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:34,467 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 39/1784 [02:12<1:23:05, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:35,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5041, 'learning_rate': 7.4e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:37,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 40/1784 [02:15<1:21:09, 2.79s/it] 2%|█▊ | 40/1784 [02:15<1:21:09, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:38,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:39,695 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 41/1784 [02:18<1:19:17, 2.73s/it] 2%|█▊ | 41/1784 [02:18<1:19:17, 2.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:40,980 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:42,126 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 42/1784 [02:20<1:16:42, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:43,378 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1578, 'learning_rate': 8e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:44,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▉ | 43/1784 [02:22<1:13:51, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:45,609 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4119, 'learning_rate': 8.2e-05, 'epoch': 0.02} {'loss': 4.2466, 'learning_rate': 8.400000000000001e-05, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:46,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▉ | 44/1784 [02:25<1:10:30, 2.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:47,695 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:48,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|█▉ | 45/1784 [02:27<1:06:42, 2.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:49,565 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:50,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5696, 'learning_rate': 8.599999999999999e-05, 'epoch': 0.03} 3%|██ | 46/1784 [02:28<1:01:46, 2.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:51,209 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:51,930 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▏ | 47/1784 [02:30<56:54, 1.97s/it] {'loss': 4.5456, 'learning_rate': 8.8e-05, 'epoch': 0.03} 3%|██▏ | 47/1784 [02:30<56:54, 1.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:52,706 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:53,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▏ | 48/1784 [02:31<52:01, 1.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:54,016 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8245, 'learning_rate': 9.2e-05, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-03 00:47:54,576 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▏ | 49/1784 [02:33<47:11, 1.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:55,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:47:56,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 50/1784 [02:34<47:43, 1.65s/it] 3%|██▎ | 50/1784 [02:34<47:43, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:58,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 50/1784 [02:34<47:43, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:47:58,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 51/1784 [02:38<1:07:56, 2.35s/it]g-point operations will not be computed-03 00:47:58,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 51/1784 [02:38<1:07:56, 2.35s/it]g-point operations will not be computed-03 00:47:58,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 51/1784 [02:38<1:07:56, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:02,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 51/1784 [02:38<1:07:56, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:02,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 52/1784 [02:42<1:20:27, 2.79s/it]g-point operations will not be computed-03 00:48:02,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 52/1784 [02:42<1:20:27, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:06,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 52/1784 [02:42<1:20:27, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:06,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 53/1784 [02:46<1:28:53, 3.08s/it]g-point operations will not be computed-03 00:48:06,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 53/1784 [02:46<1:28:53, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:09,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 53/1784 [02:46<1:28:53, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:09,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 54/1784 [02:49<1:34:09, 3.27s/it]g-point operations will not be computed-03 00:48:09,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 54/1784 [02:49<1:34:09, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:13,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 55/1784 [02:53<1:37:30, 3.38s/it]g-point operations will not be computed-03 00:48:13,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 55/1784 [02:53<1:37:30, 3.38s/it]g-point operations will not be computed-03 00:48:13,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:48:18,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:48:17,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:48:18,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:48:17,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4468, 'learning_rate': 0.000108, 'epoch': 0.03} 3%|██▍ | 56/1784 [02:57<1:39:29, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:20,680 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:48:22,445 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 57/1784 [03:00<1:41:01, 3.51s/it] 3%|██▌ | 57/1784 [03:00<1:41:01, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:24,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 58/1784 [03:04<1:41:32, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:24,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 58/1784 [03:04<1:41:32, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:24,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 58/1784 [03:04<1:41:32, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:27,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 59/1784 [03:08<1:41:46, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:27,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 59/1784 [03:08<1:41:46, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:27,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 59/1784 [03:08<1:41:46, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:31,479 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 59/1784 [03:08<1:41:46, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:31,479 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 60/1784 [03:11<1:42:35, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:35,075 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 61/1784 [03:15<1:42:06, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:35,075 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 61/1784 [03:15<1:42:06, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:35,075 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 61/1784 [03:15<1:42:06, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:38,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 62/1784 [03:18<1:41:25, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:38,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 62/1784 [03:18<1:41:25, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:38,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 62/1784 [03:18<1:41:25, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:42,043 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 63/1784 [03:22<1:41:18, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:42,043 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 63/1784 [03:22<1:41:18, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:42,043 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 64/1784 [03:25<1:41:01, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:45,563 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 64/1784 [03:25<1:41:01, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:45,563 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 64/1784 [03:25<1:41:01, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:49,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 65/1784 [03:29<1:40:24, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:49,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 65/1784 [03:29<1:40:24, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:49,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 65/1784 [03:29<1:40:24, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:52,491 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 66/1784 [03:32<1:39:47, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:52,491 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 66/1784 [03:32<1:39:47, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:52,491 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 67/1784 [03:36<1:39:26, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:55,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 67/1784 [03:36<1:39:26, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:55,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 67/1784 [03:36<1:39:26, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:59,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 68/1784 [03:39<1:38:23, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:59,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 68/1784 [03:39<1:38:23, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:48:59,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 68/1784 [03:39<1:38:23, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:02,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 69/1784 [03:42<1:37:56, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:02,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 69/1784 [03:42<1:37:56, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:02,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 70/1784 [03:46<1:37:49, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:06,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 70/1784 [03:46<1:37:49, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:06,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 70/1784 [03:46<1:37:49, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 71/1784 [03:49<1:37:01, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 71/1784 [03:49<1:37:01, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 71/1784 [03:49<1:37:01, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:12,861 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 72/1784 [03:52<1:36:31, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:16,203 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 72/1784 [03:52<1:36:31, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:16,203 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 73/1784 [03:56<1:36:09, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:16,203 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 73/1784 [03:56<1:36:09, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:16,203 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 73/1784 [03:56<1:36:09, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:19,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 74/1784 [03:59<1:35:10, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:19,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 74/1784 [03:59<1:35:10, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:19,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 75/1784 [04:02<1:34:40, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:22,786 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 75/1784 [04:02<1:34:40, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:22,786 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 75/1784 [04:02<1:34:40, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:26,062 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 76/1784 [04:06<1:34:10, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:26,062 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 76/1784 [04:06<1:34:10, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:26,062 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 76/1784 [04:06<1:34:10, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:29,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 76/1784 [04:06<1:34:10, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:29,349 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 77/1784 [04:09<1:33:17, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:32,532 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 78/1784 [04:12<1:32:48, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:32,532 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 78/1784 [04:12<1:32:48, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:32,532 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 78/1784 [04:12<1:32:48, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:35,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 79/1784 [04:15<1:31:47, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:38,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 79/1784 [04:15<1:31:47, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:38,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 80/1784 [04:18<1:30:56, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:38,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 80/1784 [04:18<1:30:56, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:38,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 80/1784 [04:18<1:30:56, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:41,978 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 81/1784 [04:21<1:30:06, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 81/1784 [04:21<1:30:06, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 82/1784 [04:24<1:28:47, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 82/1784 [04:24<1:28:47, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 82/1784 [04:24<1:28:47, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:48,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 82/1784 [04:24<1:28:47, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:48,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 83/1784 [04:28<1:28:16, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:51,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 83/1784 [04:28<1:28:16, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:51,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 84/1784 [04:30<1:26:49, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:51,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 84/1784 [04:30<1:26:49, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:54,018 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 84/1784 [04:30<1:26:49, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:54,018 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 85/1784 [04:33<1:24:55, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:56,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 85/1784 [04:33<1:24:55, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:56,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 86/1784 [04:36<1:23:30, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:56,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 86/1784 [04:36<1:23:30, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:56,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 87/1784 [04:39<1:22:22, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:49:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 87/1784 [04:39<1:22:22, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:02,453 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 87/1784 [04:39<1:22:22, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:02,453 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 88/1784 [04:42<1:21:28, 2.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:05,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 88/1784 [04:42<1:21:28, 2.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:05,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 89/1784 [04:44<1:19:06, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:05,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 89/1784 [04:44<1:19:06, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:05,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 90/1784 [04:47<1:17:05, 2.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:07,817 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 90/1784 [04:47<1:17:05, 2.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:07,817 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 91/1784 [04:49<1:14:12, 2.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:10,284 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 92/1784 [04:52<1:11:23, 2.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:12,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 92/1784 [04:52<1:11:23, 2.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:12,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 93/1784 [04:54<1:08:10, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:14,880 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 93/1784 [04:54<1:08:10, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:14,880 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 94/1784 [04:56<1:04:02, 2.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:16,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 94/1784 [04:56<1:04:02, 2.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:16,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8955, 'learning_rate': 0.000184, 'epoch': 0.05} 5%|████▎ | 95/1784 [04:57<59:26, 2.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:18,774 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 95/1784 [04:57<59:26, 2.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:18,774 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 96/1784 [04:59<55:08, 1.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:21,941 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 96/1784 [04:59<55:08, 1.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:21,941 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▍ | 98/1784 [05:02<46:19, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:23,307 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▍ | 98/1784 [05:02<46:19, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:23,307 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6766, 'learning_rate': 0.000192, 'epoch': 0.05} 6%|████▍ | 99/1784 [05:03<42:28, 1.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:25,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 99/1784 [05:03<42:28, 1.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:25,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 100/1784 [05:05<43:49, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:25,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 100/1784 [05:05<43:49, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 100/1784 [05:05<43:49, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 101/1784 [05:09<1:03:00, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 102/1784 [05:12<1:14:49, 2.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 102/1784 [05:12<1:14:49, 2.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 102/1784 [05:12<1:14:49, 2.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:36,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 103/1784 [05:16<1:22:45, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:36,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 103/1784 [05:16<1:22:45, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:36,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 103/1784 [05:16<1:22:45, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:39,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 103/1784 [05:16<1:22:45, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:39,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 104/1784 [05:19<1:28:38, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:39,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 104/1784 [05:19<1:28:38, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:43,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 104/1784 [05:19<1:28:38, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:43,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 105/1784 [05:23<1:31:48, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:43,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 105/1784 [05:23<1:31:48, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:46,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 105/1784 [05:23<1:31:48, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:46,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 106/1784 [05:27<1:34:01, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:46,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 107/1784 [05:30<1:35:33, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:50,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 107/1784 [05:30<1:35:33, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:50,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 107/1784 [05:30<1:35:33, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:54,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 107/1784 [05:30<1:35:33, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:54,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 108/1784 [05:34<1:36:41, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:54,034 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 108/1784 [05:34<1:36:41, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:57,573 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 108/1784 [05:34<1:36:41, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:57,573 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 109/1784 [05:37<1:37:23, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:50:57,573 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 110/1784 [05:41<1:37:44, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:01,135 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 110/1784 [05:41<1:37:44, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:01,135 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 110/1784 [05:41<1:37:44, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:04,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 111/1784 [05:44<1:37:39, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:04,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 111/1784 [05:44<1:37:39, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:04,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 111/1784 [05:44<1:37:39, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:08,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 111/1784 [05:44<1:37:39, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:08,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 112/1784 [05:48<1:37:02, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:08,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 112/1784 [05:48<1:37:02, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:11,507 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 112/1784 [05:48<1:37:02, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:11,507 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 113/1784 [05:51<1:35:59, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:14,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 113/1784 [05:51<1:35:59, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:14,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 114/1784 [05:55<1:36:08, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:14,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 114/1784 [05:55<1:36:08, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:18,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 114/1784 [05:55<1:36:08, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:18,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 115/1784 [05:58<1:35:24, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:18,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:51:21,744 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:51:21,744 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████ | 116/1784 [06:01<1:34:54, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:25,118 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████ | 116/1784 [06:01<1:34:54, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:25,118 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████ | 117/1784 [06:05<1:34:53, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:25,118 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████ | 117/1784 [06:05<1:34:53, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:28,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████ | 117/1784 [06:05<1:34:53, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:28,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 118/1784 [06:08<1:34:00, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:28,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 118/1784 [06:08<1:34:00, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:31,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 118/1784 [06:08<1:34:00, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:31,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 119/1784 [06:11<1:34:26, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:35,241 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 119/1784 [06:11<1:34:26, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:35,241 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 120/1784 [06:15<1:33:31, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:35,241 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 120/1784 [06:15<1:33:31, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:38,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 120/1784 [06:15<1:33:31, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:38,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 121/1784 [06:18<1:32:52, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:41,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 122/1784 [06:21<1:33:00, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:41,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 122/1784 [06:21<1:33:00, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:41,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 122/1784 [06:21<1:33:00, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:45,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 122/1784 [06:21<1:33:00, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:45,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 123/1784 [06:25<1:31:47, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:45,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 124/1784 [06:28<1:31:06, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:48,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 124/1784 [06:28<1:31:06, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:48,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 124/1784 [06:28<1:31:06, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:51,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 124/1784 [06:28<1:31:06, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:51,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 125/1784 [06:31<1:30:35, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:51,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 125/1784 [06:31<1:30:35, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:54,839 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 125/1784 [06:31<1:30:35, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:54,839 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 126/1784 [06:34<1:29:43, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:54,839 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 126/1784 [06:34<1:29:43, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:54,839 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 127/1784 [06:37<1:29:07, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:51:58,035 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 127/1784 [06:37<1:29:07, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:01,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 127/1784 [06:37<1:29:07, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:01,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 128/1784 [06:41<1:28:29, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:01,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 128/1784 [06:41<1:28:29, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:01,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 129/1784 [06:44<1:27:52, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:04,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 129/1784 [06:44<1:27:52, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:07,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 129/1784 [06:44<1:27:52, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:07,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 130/1784 [06:47<1:26:51, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:07,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 131/1784 [06:50<1:26:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:10,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 131/1784 [06:50<1:26:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:10,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 131/1784 [06:50<1:26:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:13,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 131/1784 [06:50<1:26:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:13,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 132/1784 [06:53<1:25:48, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:13,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 133/1784 [06:56<1:25:35, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:16,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 133/1784 [06:56<1:25:35, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:16,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 133/1784 [06:56<1:25:35, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:19,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 133/1784 [06:56<1:25:35, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:19,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▊ | 134/1784 [06:59<1:23:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:22,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▊ | 134/1784 [06:59<1:23:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:22,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 135/1784 [07:02<1:22:26, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:22,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 135/1784 [07:02<1:22:26, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:25,483 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 135/1784 [07:02<1:22:26, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:25,483 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 136/1784 [07:05<1:21:33, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:28,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 136/1784 [07:05<1:21:33, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:28,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 137/1784 [07:08<1:20:11, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:28,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 138/1784 [07:10<1:18:49, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:31,136 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 138/1784 [07:10<1:18:49, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:31,136 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 138/1784 [07:10<1:18:49, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:33,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 138/1784 [07:10<1:18:49, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:33,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 139/1784 [07:13<1:17:00, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:36,439 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 139/1784 [07:13<1:17:00, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:36,439 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 140/1784 [07:16<1:14:57, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:36,439 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 140/1784 [07:16<1:14:57, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:36,439 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▏ | 141/1784 [07:18<1:12:41, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:38,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▏ | 142/1784 [07:20<1:10:02, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:41,386 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▏ | 142/1784 [07:20<1:10:02, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:41,386 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 143/1784 [07:23<1:07:18, 2.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:43,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 143/1784 [07:23<1:07:18, 2.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:43,661 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 144/1784 [07:25<1:03:38, 2.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:45,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 144/1784 [07:25<1:03:38, 2.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:45,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 145/1784 [07:27<1:00:02, 2.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:47,722 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 145/1784 [07:27<1:00:02, 2.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:47,722 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2152, 'learning_rate': 0.00028599999999999996, 'epoch': 0.08} 8%|██████▌ | 146/1784 [07:28<56:37, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:49,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 146/1784 [07:28<56:37, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:49,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 147/1784 [07:30<51:57, 1.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:52,719 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 147/1784 [07:30<51:57, 1.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:52,719 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 149/1784 [07:32<43:37, 1.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:55,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 149/1784 [07:32<43:37, 1.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:55,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2187, 'learning_rate': 0.000294, 'epoch': 0.08} 8%|██████▋ | 150/1784 [07:34<43:48, 1.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:55,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 150/1784 [07:34<43:48, 1.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:58,245 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 150/1784 [07:34<43:48, 1.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:58,245 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 151/1784 [07:38<1:01:53, 2.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:52:58,245 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 151/1784 [07:38<1:01:53, 2.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:01,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 151/1784 [07:38<1:01:53, 2.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:01,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 152/1784 [07:42<1:13:34, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:01,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 152/1784 [07:42<1:13:34, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:05,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 152/1784 [07:42<1:13:34, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:05,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 153/1784 [07:45<1:21:41, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:05,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 153/1784 [07:45<1:21:41, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:09,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 153/1784 [07:45<1:21:41, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:09,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 154/1784 [07:49<1:27:34, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:13,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 154/1784 [07:49<1:27:34, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:13,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 155/1784 [07:53<1:31:12, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:13,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 155/1784 [07:53<1:31:12, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:16,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 155/1784 [07:53<1:31:12, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:16,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 156/1784 [07:56<1:33:34, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:16,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 156/1784 [07:56<1:33:34, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:20,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 156/1784 [07:56<1:33:34, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:20,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 157/1784 [08:00<1:34:35, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:20,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 157/1784 [08:00<1:34:35, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:23,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 158/1784 [08:04<1:35:09, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:23,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 158/1784 [08:04<1:35:09, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:23,916 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9038, 'learning_rate': 0.000312, 'epoch': 0.09} 9%|██████▉ | 159/1784 [08:07<1:35:20, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:27,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 159/1784 [08:07<1:35:20, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:31,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 159/1784 [08:07<1:35:20, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:31,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 160/1784 [08:11<1:35:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:31,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 160/1784 [08:11<1:35:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 160/1784 [08:11<1:35:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 161/1784 [08:14<1:35:40, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 161/1784 [08:14<1:35:40, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 161/1784 [08:14<1:35:40, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 162/1784 [08:18<1:35:20, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 162/1784 [08:18<1:35:20, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:53:43,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:53:43,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:53:43,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 164/1784 [08:25<1:34:19, 3.49s/it]g-point operations will not be computed-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 164/1784 [08:25<1:34:19, 3.49s/it]g-point operations will not be computed-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 164/1784 [08:25<1:34:19, 3.49s/it]g-point operations will not be computed-03 00:53:34,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 165/1784 [08:28<1:33:51, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 165/1784 [08:28<1:33:51, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 166/1784 [08:32<1:33:41, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 166/1784 [08:32<1:33:41, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 166/1784 [08:32<1:33:41, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 167/1784 [08:35<1:32:50, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 167/1784 [08:35<1:32:50, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 167/1784 [08:35<1:32:50, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:53:51,973 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 168/1784 [08:38<1:32:19, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 168/1784 [08:38<1:32:19, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▍ | 169/1784 [08:42<1:31:34, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▍ | 169/1784 [08:42<1:31:34, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▍ | 169/1784 [08:42<1:31:34, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 170/1784 [08:45<1:31:05, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:10,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:10,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9869, 'learning_rate': 0.00033800000000000003, 'epoch': 0.1} [WARNING|modeling_utils.py:388] 2022-03-03 00:54:10,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 172/1784 [08:52<1:30:46, 3.38s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 172/1784 [08:52<1:30:46, 3.38s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 172/1784 [08:52<1:30:46, 3.38s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 173/1784 [08:55<1:30:11, 3.36s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 173/1784 [08:55<1:30:11, 3.36s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:20,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:20,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:20,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 175/1784 [09:02<1:28:52, 3.31s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:26,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:26,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6924, 'learning_rate': 0.000348, 'epoch': 0.1} [WARNING|modeling_utils.py:388] 2022-03-03 00:54:26,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 177/1784 [09:08<1:26:59, 3.25s/it]g-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:33,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:33,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8362, 'learning_rate': 0.000352, 'epoch': 0.1} [WARNING|modeling_utils.py:388] 2022-03-03 00:54:33,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:36,292 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:36,292 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:36,292 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:02,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 180/1784 [09:17<1:24:09, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:40,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 180/1784 [09:17<1:24:09, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:40,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 181/1784 [09:20<1:24:03, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:40,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 181/1784 [09:20<1:24:03, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:40,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 181/1784 [09:20<1:24:03, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:40,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 182/1784 [09:24<1:23:36, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:47,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 182/1784 [09:24<1:23:36, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:47,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 183/1784 [09:27<1:23:08, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:47,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 183/1784 [09:27<1:23:08, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:47,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 183/1784 [09:27<1:23:08, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:47,218 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 184/1784 [09:30<1:21:41, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:53,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 184/1784 [09:30<1:21:41, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:53,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 185/1784 [09:33<1:20:50, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:54:53,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:57,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:53,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:54:57,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:53,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6795, 'learning_rate': 0.000368, 'epoch': 0.1} [WARNING|modeling_utils.py:388] 2022-03-03 00:54:57,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:54:53,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████▏ | 187/1784 [09:38<1:18:57, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:01,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 188/1784 [09:41<1:18:07, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:01,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 188/1784 [09:41<1:18:07, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:01,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:05,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:01,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:05,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:01,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2655, 'learning_rate': 0.000374, 'epoch': 0.11} [WARNING|modeling_utils.py:388] 2022-03-03 00:55:05,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:01,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 190/1784 [09:46<1:14:05, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 190/1784 [09:46<1:14:05, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 191/1784 [09:49<1:11:30, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 191/1784 [09:49<1:11:30, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:13,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:13,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:15,570 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:15,570 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:17,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:17,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:19,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:19,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:21,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:21,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:24,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:24,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9989, 'learning_rate': 0.00039200000000000004, 'epoch': 0.11} [WARNING|modeling_utils.py:388] 2022-03-03 00:55:25,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:25,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:27,311 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:27,311 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:27,311 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 202/1784 [10:13<1:11:54, 2.73s/it]g-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 202/1784 [10:13<1:11:54, 2.73s/it]g-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 202/1784 [10:13<1:11:54, 2.73s/it]g-point operations will not be computed-03 00:55:09,862 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 203/1784 [10:17<1:19:32, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 204/1784 [10:20<1:24:16, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 204/1784 [10:20<1:24:16, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4006, 'learning_rate': 0.000404, 'epoch': 0.11} 11%|████████▉ | 204/1784 [10:20<1:24:16, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 205/1784 [10:24<1:26:54, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 205/1784 [10:24<1:26:54, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 205/1784 [10:24<1:26:54, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 206/1784 [10:27<1:28:43, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:52,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:55:52,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0031, 'learning_rate': 0.00041, 'epoch': 0.12} 12%|█████████ | 208/1784 [10:34<1:31:04, 3.47s/it]g-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 208/1784 [10:34<1:31:04, 3.47s/it]g-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.7179, 'learning_rate': 0.000412, 'epoch': 0.12} 12%|█████████ | 208/1784 [10:34<1:31:04, 3.47s/it]g-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 209/1784 [10:38<1:31:14, 3.48s/it]g-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 209/1784 [10:38<1:31:14, 3.48s/it]g-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 209/1784 [10:38<1:31:14, 3.48s/it]g-point operations will not be computed-03 00:55:40,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 210/1784 [10:41<1:31:16, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:05,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 211/1784 [10:45<1:30:43, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:05,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 211/1784 [10:45<1:30:43, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:05,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9536, 'learning_rate': 0.00041799999999999997, 'epoch': 0.12} 12%|█████████▎ | 212/1784 [10:48<1:30:33, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:05,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 212/1784 [10:48<1:30:33, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:05,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6715, 'learning_rate': 0.00042, 'epoch': 0.12} 12%|█████████▎ | 212/1784 [10:48<1:30:33, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:05,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 213/1784 [10:52<1:30:38, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:15,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 214/1784 [10:55<1:30:19, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:15,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 214/1784 [10:55<1:30:19, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:15,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7195, 'learning_rate': 0.000424, 'epoch': 0.12} 12%|█████████▍ | 215/1784 [10:58<1:29:56, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:15,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▍ | 215/1784 [10:58<1:29:56, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:15,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8662, 'learning_rate': 0.000426, 'epoch': 0.12} 12%|█████████▍ | 215/1784 [10:58<1:29:56, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:15,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▍ | 216/1784 [11:02<1:29:49, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▍ | 217/1784 [11:05<1:29:16, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▍ | 217/1784 [11:05<1:29:16, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5386, 'learning_rate': 0.00043, 'epoch': 0.12} 12%|█████████▍ | 217/1784 [11:05<1:29:16, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 218/1784 [11:09<1:29:14, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 218/1784 [11:09<1:29:14, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 218/1784 [11:09<1:29:14, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:25,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 219/1784 [11:12<1:28:43, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 220/1784 [11:15<1:27:53, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 220/1784 [11:15<1:27:53, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9084, 'learning_rate': 0.000436, 'epoch': 0.12} 12%|█████████▋ | 221/1784 [11:19<1:27:12, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▋ | 221/1784 [11:19<1:27:12, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:56:44,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:56:44,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9058, 'learning_rate': 0.00044, 'epoch': 0.12} 12%|█████████▊ | 223/1784 [11:25<1:26:57, 3.34s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 223/1784 [11:25<1:26:57, 3.34s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9857, 'learning_rate': 0.000442, 'epoch': 0.12} 12%|█████████▊ | 223/1784 [11:25<1:26:57, 3.34s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▊ | 224/1784 [11:29<1:26:55, 3.34s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:56:53,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:56:53,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.1024, 'learning_rate': 0.000446, 'epoch': 0.13} [WARNING|modeling_utils.py:388] 2022-03-03 00:56:53,983 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 226/1784 [11:35<1:25:44, 3.30s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 226/1784 [11:35<1:25:44, 3.30s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 226/1784 [11:35<1:25:44, 3.30s/it]g-point operations will not be computed-03 00:56:35,832 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 227/1784 [11:38<1:24:43, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:02,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 228/1784 [11:42<1:23:59, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:02,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 228/1784 [11:42<1:23:59, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:02,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.799, 'learning_rate': 0.00045200000000000004, 'epoch': 0.13} 13%|█████████▉ | 228/1784 [11:42<1:23:59, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:02,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 229/1784 [11:45<1:23:02, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:08,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 230/1784 [11:48<1:22:07, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:08,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 230/1784 [11:48<1:22:07, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:08,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9686, 'learning_rate': 0.000456, 'epoch': 0.13} 13%|██████████ | 230/1784 [11:48<1:22:07, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:08,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 231/1784 [11:51<1:21:40, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:14,570 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 232/1784 [11:54<1:21:00, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:14,570 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 232/1784 [11:54<1:21:00, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:14,570 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2565, 'learning_rate': 0.00046, 'epoch': 0.13} 13%|██████████▏ | 232/1784 [11:54<1:21:00, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:14,570 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 233/1784 [11:57<1:19:25, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 234/1784 [12:00<1:17:57, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 234/1784 [12:00<1:17:57, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:57:24,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:57:24,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:57:27,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:57:27,540 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6232, 'learning_rate': 0.00046800000000000005, 'epoch': 0.13} 13%|██████████▎ | 237/1784 [12:08<1:13:45, 2.86s/it]g-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 237/1784 [12:08<1:13:45, 2.86s/it]g-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:57:32,914 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:57:32,914 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:57:20,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.3229, 'learning_rate': 0.000472, 'epoch': 0.13} 13%|██████████▍ | 239/1784 [12:13<1:10:28, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:36,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 239/1784 [12:13<1:10:28, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:36,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 240/1784 [12:16<1:08:26, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:39,171 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 240/1784 [12:16<1:08:26, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:39,171 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 241/1784 [12:18<1:05:12, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:41,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 241/1784 [12:18<1:05:12, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:41,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 242/1784 [12:20<1:01:45, 2.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:43,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 242/1784 [12:20<1:01:45, 2.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:43,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 243/1784 [12:22<58:02, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:45,190 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 243/1784 [12:22<58:02, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:45,190 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 244/1784 [12:24<54:19, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:46,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 244/1784 [12:24<54:19, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:46,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 246/1784 [12:27<47:00, 1.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:48,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 246/1784 [12:27<47:00, 1.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:48,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3271, 'learning_rate': 0.000486, 'epoch': 0.14} 14%|███████████ | 247/1784 [12:28<43:34, 1.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:51,248 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 247/1784 [12:28<43:34, 1.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:51,248 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 249/1784 [12:31<37:12, 1.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:53,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 249/1784 [12:31<37:12, 1.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:53,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3764, 'learning_rate': 0.000492, 'epoch': 0.14} 14%|███████████▏ | 250/1784 [12:33<38:30, 1.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:53,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 250/1784 [12:33<38:30, 1.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:53,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 250/1784 [12:33<38:30, 1.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:56,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 251/1784 [12:36<56:55, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:56,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 251/1784 [12:36<56:55, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:57:56,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 251/1784 [12:36<56:55, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:00,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 252/1784 [12:40<1:08:40, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:00,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 252/1784 [12:40<1:08:40, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:00,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 7.5569, 'learning_rate': 0.0005, 'epoch': 0.14} 14%|███████████ | 253/1784 [12:44<1:16:22, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:00,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 253/1784 [12:44<1:16:22, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:00,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.1258, 'learning_rate': 0.0005020000000000001, 'epoch': 0.14} 14%|███████████ | 253/1784 [12:44<1:16:22, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:00,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 254/1784 [12:48<1:21:58, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 255/1784 [12:51<1:25:30, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 255/1784 [12:51<1:25:30, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2723, 'learning_rate': 0.000506, 'epoch': 0.14} 14%|███████████▏ | 256/1784 [12:55<1:27:03, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 256/1784 [12:55<1:27:03, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2628, 'learning_rate': 0.000508, 'epoch': 0.14} 14%|███████████▏ | 257/1784 [12:59<1:28:22, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 257/1784 [12:59<1:28:22, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2784, 'learning_rate': 0.00051, 'epoch': 0.14} 14%|███████████▏ | 257/1784 [12:59<1:28:22, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 258/1784 [13:02<1:28:57, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:58:27,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:58:27,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4261, 'learning_rate': 0.000514, 'epoch': 0.15} 15%|███████████▎ | 260/1784 [13:09<1:29:46, 3.53s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▎ | 260/1784 [13:09<1:29:46, 3.53s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9251, 'learning_rate': 0.0005160000000000001, 'epoch': 0.15} 15%|███████████▍ | 261/1784 [13:13<1:29:29, 3.53s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 261/1784 [13:13<1:29:29, 3.53s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:58:38,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:58:38,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8142, 'learning_rate': 0.0005200000000000001, 'epoch': 0.15} 15%|███████████▍ | 263/1784 [13:20<1:28:29, 3.49s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 263/1784 [13:20<1:28:29, 3.49s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0686, 'learning_rate': 0.000522, 'epoch': 0.15} 15%|███████████▌ | 264/1784 [13:23<1:28:22, 3.49s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 264/1784 [13:23<1:28:22, 3.49s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6381, 'learning_rate': 0.000524, 'epoch': 0.15} 15%|███████████▌ | 264/1784 [13:23<1:28:22, 3.49s/it]g-point operations will not be computed-03 00:58:11,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 265/1784 [13:26<1:27:38, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 266/1784 [13:30<1:27:01, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 266/1784 [13:30<1:27:01, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8176, 'learning_rate': 0.000528, 'epoch': 0.15} 15%|███████████▋ | 267/1784 [13:33<1:26:42, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 267/1784 [13:33<1:26:42, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:58:58,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:58:58,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9445, 'learning_rate': 0.000532, 'epoch': 0.15} 15%|███████████▊ | 269/1784 [13:40<1:25:39, 3.39s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▊ | 269/1784 [13:40<1:25:39, 3.39s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2645, 'learning_rate': 0.0005340000000000001, 'epoch': 0.15} 15%|███████████▊ | 270/1784 [13:43<1:25:41, 3.40s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▊ | 270/1784 [13:43<1:25:41, 3.40s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:08,861 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:08,861 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3492, 'learning_rate': 0.0005380000000000001, 'epoch': 0.15} 15%|███████████▉ | 272/1784 [13:50<1:24:34, 3.36s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▉ | 272/1784 [13:50<1:24:34, 3.36s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3108, 'learning_rate': 0.00054, 'epoch': 0.15} 15%|███████████▉ | 272/1784 [13:50<1:24:34, 3.36s/it]g-point operations will not be computed-03 00:58:50,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▉ | 273/1784 [13:53<1:24:05, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▉ | 274/1784 [13:57<1:23:22, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▉ | 274/1784 [13:57<1:23:22, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.3335, 'learning_rate': 0.0005440000000000001, 'epoch': 0.15} 15%|████████████ | 275/1784 [14:00<1:22:27, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 275/1784 [14:00<1:22:27, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:25,124 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:25,124 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.1695, 'learning_rate': 0.0005480000000000001, 'epoch': 0.15} 16%|████████████ | 277/1784 [14:06<1:21:56, 3.26s/it]g-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████ | 277/1784 [14:06<1:21:56, 3.26s/it]g-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.2355, 'learning_rate': 0.00055, 'epoch': 0.16} [WARNING|modeling_utils.py:388] 2022-03-03 00:59:31,561 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:31,561 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:31,561 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 279/1784 [14:13<1:20:28, 3.21s/it]g-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:37,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:37,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:37,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 281/1784 [14:19<1:19:29, 3.17s/it]g-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 281/1784 [14:19<1:19:29, 3.17s/it]g-point operations will not be computed-03 00:59:17,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8305, 'learning_rate': 0.000558, 'epoch': 0.16} 16%|████████████▎ | 282/1784 [14:22<1:19:02, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:45,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 282/1784 [14:22<1:19:02, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:45,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 283/1784 [14:25<1:18:10, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:45,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 283/1784 [14:25<1:18:10, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:45,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.5372, 'learning_rate': 0.0005620000000000001, 'epoch': 0.16} 16%|████████████▍ | 284/1784 [14:28<1:17:08, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 284/1784 [14:28<1:17:08, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 285/1784 [14:31<1:15:56, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 285/1784 [14:31<1:15:56, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:55,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 00:59:55,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.7623, 'learning_rate': 0.0005679999999999999, 'epoch': 0.16} 16%|████████████▌ | 287/1784 [14:37<1:13:43, 2.95s/it]g-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▌ | 287/1784 [14:37<1:13:43, 2.95s/it]g-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:01,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:01,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:04,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:04,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 00:59:51,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0644, 'learning_rate': 0.000574, 'epoch': 0.16} 16%|████████████▋ | 290/1784 [14:45<1:07:51, 2.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:00:08,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▋ | 290/1784 [14:45<1:07:51, 2.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:00:08,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▋ | 291/1784 [14:47<1:05:28, 2.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▋ | 291/1784 [14:47<1:05:28, 2.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▊ | 292/1784 [14:49<1:03:20, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▊ | 292/1784 [14:49<1:03:20, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.9815, 'learning_rate': 0.00058, 'epoch': 0.16} [WARNING|modeling_utils.py:388] 2022-03-03 01:00:13,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:15,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:15,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:17,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:17,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4079, 'learning_rate': 0.0005859999999999999, 'epoch': 0.17} [WARNING|modeling_utils.py:388] 2022-03-03 01:00:19,312 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:19,312 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.8535, 'learning_rate': 0.00059, 'epoch': 0.17} [WARNING|modeling_utils.py:388] 2022-03-03 01:00:22,365 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:22,365 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:23,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:23,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:25,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:25,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:25,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:29,216 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:32,971 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:32,971 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.825, 'learning_rate': 0.0006, 'epoch': 0.17} [WARNING|modeling_utils.py:388] 2022-03-03 01:00:32,971 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▏ | 303/1784 [15:15<1:14:55, 3.04s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▏ | 303/1784 [15:15<1:14:55, 3.04s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▏ | 303/1784 [15:15<1:14:55, 3.04s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 304/1784 [15:18<1:20:04, 3.25s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 304/1784 [15:18<1:20:04, 3.25s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 304/1784 [15:18<1:20:04, 3.25s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 305/1784 [15:22<1:23:41, 3.40s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 305/1784 [15:22<1:23:41, 3.40s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 305/1784 [15:22<1:23:41, 3.40s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 306/1784 [15:26<1:25:40, 3.48s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:51,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:00:51,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5677, 'learning_rate': 0.00061, 'epoch': 0.17} [WARNING|modeling_utils.py:388] 2022-03-03 01:00:51,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 308/1784 [15:33<1:27:19, 3.55s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 308/1784 [15:33<1:27:19, 3.55s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 308/1784 [15:33<1:27:19, 3.55s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 309/1784 [15:37<1:27:37, 3.56s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 309/1784 [15:37<1:27:37, 3.56s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 309/1784 [15:37<1:27:37, 3.56s/it]g-point operations will not be computed-03 01:00:10,367 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 310/1784 [15:40<1:27:18, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 311/1784 [15:44<1:26:49, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 311/1784 [15:44<1:26:49, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3806, 'learning_rate': 0.0006180000000000001, 'epoch': 0.17} 17%|█████████████▌ | 311/1784 [15:44<1:26:49, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 312/1784 [15:47<1:26:41, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 312/1784 [15:47<1:26:41, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 312/1784 [15:47<1:26:41, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▋ | 313/1784 [15:51<1:26:07, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▋ | 313/1784 [15:51<1:26:07, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▋ | 313/1784 [15:51<1:26:07, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:03,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▋ | 314/1784 [15:54<1:25:38, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▋ | 314/1784 [15:54<1:25:38, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 315/1784 [15:58<1:25:45, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 315/1784 [15:58<1:25:45, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 315/1784 [15:58<1:25:45, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 316/1784 [16:01<1:25:02, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 316/1784 [16:01<1:25:02, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 316/1784 [16:01<1:25:02, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:17,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 317/1784 [16:04<1:25:03, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 317/1784 [16:04<1:25:03, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 318/1784 [16:08<1:24:47, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 318/1784 [16:08<1:24:47, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 318/1784 [16:08<1:24:47, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 319/1784 [16:11<1:24:05, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 319/1784 [16:11<1:24:05, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 319/1784 [16:11<1:24:05, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 320/1784 [16:15<1:23:51, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 320/1784 [16:15<1:23:51, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:01:40,140 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:01:40,140 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:01:40,140 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 322/1784 [16:21<1:22:46, 3.40s/it]g-point operations will not be computed-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 322/1784 [16:21<1:22:46, 3.40s/it]g-point operations will not be computed-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 322/1784 [16:21<1:22:46, 3.40s/it]g-point operations will not be computed-03 01:01:28,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 323/1784 [16:25<1:22:06, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 323/1784 [16:25<1:22:06, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 324/1784 [16:28<1:20:57, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 324/1784 [16:28<1:20:57, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 325/1784 [16:31<1:20:06, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 325/1784 [16:31<1:20:06, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:01:56,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:01:56,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.7701, 'learning_rate': 0.000648, 'epoch': 0.18} 18%|██████████████▎ | 327/1784 [16:38<1:19:36, 3.28s/it]g-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 327/1784 [16:38<1:19:36, 3.28s/it]g-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:02,998 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:02,998 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.1997, 'learning_rate': 0.000652, 'epoch': 0.18} 18%|██████████████▍ | 329/1784 [16:44<1:18:29, 3.24s/it]g-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▍ | 329/1784 [16:44<1:18:29, 3.24s/it]g-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2808, 'learning_rate': 0.0006540000000000001, 'epoch': 0.18} 18%|██████████████▍ | 329/1784 [16:44<1:18:29, 3.24s/it]g-point operations will not be computed-03 01:01:48,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▍ | 330/1784 [16:47<1:18:20, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 331/1784 [16:50<1:17:12, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 331/1784 [16:50<1:17:12, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:15,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:15,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:15,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▌ | 333/1784 [16:57<1:15:35, 3.13s/it]g-point operations will not be computed-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▌ | 333/1784 [16:57<1:15:35, 3.13s/it]g-point operations will not be computed-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.6766, 'learning_rate': 0.000662, 'epoch': 0.19} 19%|██████████████▌ | 333/1784 [16:57<1:15:35, 3.13s/it]g-point operations will not be computed-03 01:02:11,017 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▌ | 334/1784 [17:00<1:14:37, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 335/1784 [17:02<1:13:21, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 335/1784 [17:02<1:13:21, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:27,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:27,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0338, 'learning_rate': 0.0006680000000000001, 'epoch': 0.19} 19%|██████████████▋ | 337/1784 [17:08<1:11:11, 2.95s/it]g-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 337/1784 [17:08<1:11:11, 2.95s/it]g-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:33,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:33,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4539, 'learning_rate': 0.0006720000000000001, 'epoch': 0.19} [WARNING|modeling_utils.py:388] 2022-03-03 01:02:33,116 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:23,170 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 339/1784 [17:14<1:08:56, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:37,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 340/1784 [17:16<1:07:38, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 340/1784 [17:16<1:07:38, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 341/1784 [17:19<1:06:07, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 341/1784 [17:19<1:06:07, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:43,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:43,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:45,894 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:45,894 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:48,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:48,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:50,055 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:50,055 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:51,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:51,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.198, 'learning_rate': 0.0006879999999999999, 'epoch': 0.19} [WARNING|modeling_utils.py:388] 2022-03-03 01:02:53,571 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:56,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:56,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5543, 'learning_rate': 0.000692, 'epoch': 0.2} {'loss': 5.9238, 'learning_rate': 0.000694, 'epoch': 0.2} [WARNING|modeling_utils.py:388] 2022-03-03 01:02:58,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:58,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:02:58,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:02,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:02,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:02,110 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 352/1784 [17:44<1:06:50, 2.80s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 352/1784 [17:44<1:06:50, 2.80s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 352/1784 [17:44<1:06:50, 2.80s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 353/1784 [17:48<1:13:24, 3.08s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 353/1784 [17:48<1:13:24, 3.08s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 353/1784 [17:48<1:13:24, 3.08s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 354/1784 [17:51<1:17:55, 3.27s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 354/1784 [17:51<1:17:55, 3.27s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 354/1784 [17:51<1:17:55, 3.27s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 355/1784 [17:55<1:21:01, 3.40s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 355/1784 [17:55<1:21:01, 3.40s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:20,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:20,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:20,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 357/1784 [18:02<1:23:36, 3.52s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 357/1784 [18:02<1:23:36, 3.52s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 357/1784 [18:02<1:23:36, 3.52s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 358/1784 [18:06<1:24:16, 3.55s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 358/1784 [18:06<1:24:16, 3.55s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 358/1784 [18:06<1:24:16, 3.55s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 359/1784 [18:09<1:24:43, 3.57s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 359/1784 [18:09<1:24:43, 3.57s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:35,101 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:35,101 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:35,101 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 361/1784 [18:17<1:25:03, 3.59s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 361/1784 [18:17<1:25:03, 3.59s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 361/1784 [18:17<1:25:03, 3.59s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 362/1784 [18:20<1:24:29, 3.56s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 362/1784 [18:20<1:24:29, 3.56s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 362/1784 [18:20<1:24:29, 3.56s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▊ | 363/1784 [18:24<1:23:47, 3.54s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:49,180 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:49,180 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9611, 'learning_rate': 0.000724, 'epoch': 0.2} [WARNING|modeling_utils.py:388] 2022-03-03 01:03:49,180 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▉ | 365/1784 [18:31<1:23:02, 3.51s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▉ | 365/1784 [18:31<1:23:02, 3.51s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▉ | 365/1784 [18:31<1:23:02, 3.51s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████ | 366/1784 [18:34<1:22:24, 3.49s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████ | 366/1784 [18:34<1:22:24, 3.49s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:59,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:59,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:03:59,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████ | 368/1784 [18:41<1:21:27, 3.45s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████ | 368/1784 [18:41<1:21:27, 3.45s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████ | 368/1784 [18:41<1:21:27, 3.45s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▏ | 369/1784 [18:44<1:21:14, 3.44s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:09,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:09,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.649, 'learning_rate': 0.000736, 'epoch': 0.21} [WARNING|modeling_utils.py:388] 2022-03-03 01:04:09,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▏ | 371/1784 [18:51<1:20:10, 3.40s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:16,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:16,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9999, 'learning_rate': 0.00074, 'epoch': 0.21} [WARNING|modeling_utils.py:388] 2022-03-03 01:04:16,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▎ | 373/1784 [18:58<1:18:52, 3.35s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▎ | 373/1784 [18:58<1:18:52, 3.35s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▎ | 373/1784 [18:58<1:18:52, 3.35s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▎ | 374/1784 [19:01<1:17:59, 3.32s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:26,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:26,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.1289, 'learning_rate': 0.000746, 'epoch': 0.21} [WARNING|modeling_utils.py:388] 2022-03-03 01:04:26,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▍ | 376/1784 [19:07<1:16:51, 3.28s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:32,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:32,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5028, 'learning_rate': 0.00075, 'epoch': 0.21} [WARNING|modeling_utils.py:388] 2022-03-03 01:04:32,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 378/1784 [19:14<1:15:33, 3.22s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 378/1784 [19:14<1:15:33, 3.22s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 378/1784 [19:14<1:15:33, 3.22s/it]g-point operations will not be computed-03 01:02:39,909 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 379/1784 [19:17<1:15:03, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:40,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 380/1784 [19:20<1:14:26, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:40,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 380/1784 [19:20<1:14:26, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:40,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.76, 'learning_rate': 0.000756, 'epoch': 0.21} 21%|████████████████▌ | 380/1784 [19:20<1:14:26, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:40,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 381/1784 [19:23<1:14:08, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:46,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 382/1784 [19:26<1:13:39, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:46,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 382/1784 [19:26<1:13:39, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:46,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3031, 'learning_rate': 0.00076, 'epoch': 0.21} 21%|████████████████▋ | 382/1784 [19:26<1:13:39, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:46,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 383/1784 [19:29<1:12:37, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 383/1784 [19:29<1:12:37, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 384/1784 [19:32<1:11:13, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:57,183 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:04:57,183 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8042, 'learning_rate': 0.0007660000000000001, 'epoch': 0.22} [WARNING|modeling_utils.py:388] 2022-03-03 01:04:57,183 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 386/1784 [19:38<1:09:43, 2.99s/it]g-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:02,915 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:02,915 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:05,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:05,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0925, 'learning_rate': 0.000772, 'epoch': 0.22} [WARNING|modeling_utils.py:388] 2022-03-03 01:05:05,619 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:04:52,853 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 389/1784 [19:46<1:05:08, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 389/1784 [19:46<1:05:08, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 390/1784 [19:49<1:03:30, 2.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:13,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:13,398 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:15,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:15,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:17,865 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:17,865 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:19,856 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:19,856 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:21,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:21,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:23,311 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:23,311 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.1241, 'learning_rate': 0.0007880000000000001, 'epoch': 0.22} [WARNING|modeling_utils.py:388] 2022-03-03 01:05:26,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:26,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:27,249 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:27,249 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 10.8678, 'learning_rate': 0.0007940000000000001, 'epoch': 0.22} [WARNING|modeling_utils.py:388] 2022-03-03 01:05:28,930 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:28,930 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:28,930 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:32,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:32,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:05:32,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▌ | 402/1784 [20:15<1:02:49, 2.73s/it]g-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▌ | 402/1784 [20:15<1:02:49, 2.73s/it]g-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▌ | 402/1784 [20:15<1:02:49, 2.73s/it]g-point operations will not be computed-03 01:05:09,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▌ | 403/1784 [20:18<1:09:56, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 404/1784 [20:22<1:14:11, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 404/1784 [20:22<1:14:11, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8218, 'learning_rate': 0.000804, 'epoch': 0.23} 23%|█████████████████▋ | 405/1784 [20:26<1:17:35, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 405/1784 [20:26<1:17:35, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3772, 'learning_rate': 0.0008060000000000001, 'epoch': 0.23} 23%|█████████████████▋ | 405/1784 [20:26<1:17:35, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 406/1784 [20:29<1:19:35, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 406/1784 [20:29<1:19:35, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 406/1784 [20:29<1:19:35, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 407/1784 [20:33<1:20:36, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 407/1784 [20:33<1:20:36, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 407/1784 [20:33<1:20:36, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:05:42,252 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 408/1784 [20:37<1:20:50, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 409/1784 [20:40<1:20:55, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 409/1784 [20:40<1:20:55, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9483, 'learning_rate': 0.0008139999999999999, 'epoch': 0.23} 23%|█████████████████▉ | 409/1784 [20:40<1:20:55, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 410/1784 [20:44<1:21:04, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 410/1784 [20:44<1:21:04, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 410/1784 [20:44<1:21:04, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 411/1784 [20:47<1:20:44, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:06:12,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:06:12,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5031, 'learning_rate': 0.00082, 'epoch': 0.23} 23%|██████████████████ | 413/1784 [20:54<1:20:44, 3.53s/it]g-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 413/1784 [20:54<1:20:44, 3.53s/it]g-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.3287, 'learning_rate': 0.0008219999999999999, 'epoch': 0.23} 23%|██████████████████ | 413/1784 [20:54<1:20:44, 3.53s/it]g-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 414/1784 [20:58<1:20:25, 3.52s/it]g-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 414/1784 [20:58<1:20:25, 3.52s/it]g-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 414/1784 [20:58<1:20:25, 3.52s/it]g-point operations will not be computed-03 01:06:00,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 415/1784 [21:01<1:20:23, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 416/1784 [21:05<1:19:49, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 416/1784 [21:05<1:19:49, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4594, 'learning_rate': 0.000828, 'epoch': 0.23} 23%|██████████████████▏ | 416/1784 [21:05<1:19:49, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 417/1784 [21:08<1:19:10, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 417/1784 [21:08<1:19:10, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 417/1784 [21:08<1:19:10, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:25,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 418/1784 [21:12<1:19:07, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 419/1784 [21:15<1:18:29, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 419/1784 [21:15<1:18:29, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.57, 'learning_rate': 0.000834, 'epoch': 0.23} 23%|██████████████████▎ | 419/1784 [21:15<1:18:29, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 420/1784 [21:18<1:18:54, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 420/1784 [21:18<1:18:54, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 420/1784 [21:18<1:18:54, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 421/1784 [21:22<1:18:23, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:06:47,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:06:47,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8436, 'learning_rate': 0.00084, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-03 01:06:47,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 423/1784 [21:29<1:16:58, 3.39s/it]g-point operations will not be computed-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 423/1784 [21:29<1:16:58, 3.39s/it]g-point operations will not be computed-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 423/1784 [21:29<1:16:58, 3.39s/it]g-point operations will not be computed-03 01:06:35,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 424/1784 [21:32<1:16:29, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 425/1784 [21:35<1:16:01, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 425/1784 [21:35<1:16:01, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5169, 'learning_rate': 0.000846, 'epoch': 0.24} 24%|██████████████████▌ | 425/1784 [21:35<1:16:01, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 426/1784 [21:38<1:14:58, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:03,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:03,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.98, 'learning_rate': 0.00085, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-03 01:07:03,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 428/1784 [21:45<1:13:19, 3.24s/it]g-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:10,019 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:10,019 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.7028, 'learning_rate': 0.000854, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-03 01:07:10,019 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▊ | 430/1784 [21:51<1:12:13, 3.20s/it]g-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:16,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:16,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0355, 'learning_rate': 0.000858, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-03 01:07:16,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▉ | 432/1784 [21:57<1:11:09, 3.16s/it]g-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:22,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:22,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6191, 'learning_rate': 0.000862, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-03 01:07:22,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:06:55,685 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▉ | 434/1784 [22:03<1:09:13, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:26,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████ | 435/1784 [22:06<1:07:59, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:26,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████ | 435/1784 [22:06<1:07:59, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:26,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:31,140 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:07:26,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:31,140 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:07:26,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.7428, 'learning_rate': 0.0008680000000000001, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-03 01:07:31,140 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:07:26,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████ | 437/1784 [22:12<1:05:15, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:35,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▏ | 438/1784 [22:15<1:04:27, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:35,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▏ | 438/1784 [22:15<1:04:27, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:35,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:39,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:07:35,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:07:39,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:07:35,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2282, 'learning_rate': 0.000874, 'epoch': 0.25} [WARNING|modeling_utils.py:388] 2022-03-03 01:07:39,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:07:35,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▏ | 440/1784 [22:20<1:01:31, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:43,278 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 441/1784 [22:22<59:35, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:45,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 441/1784 [22:22<59:35, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:45,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 442/1784 [22:25<56:43, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:47,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 442/1784 [22:25<56:43, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:47,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 443/1784 [22:27<53:22, 2.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:49,761 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 443/1784 [22:27<53:22, 2.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:49,761 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▉ | 444/1784 [22:29<50:16, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:51,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▉ | 444/1784 [22:29<50:16, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:51,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▉ | 445/1784 [22:30<47:23, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:53,394 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▉ | 445/1784 [22:30<47:23, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:53,394 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5112, 'learning_rate': 0.0008860000000000001, 'epoch': 0.25} 25%|████████████████████ | 447/1784 [22:34<41:04, 1.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:54,970 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████ | 447/1784 [22:34<41:04, 1.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:54,970 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████ | 448/1784 [22:35<37:41, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:57,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████ | 448/1784 [22:35<37:41, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:57,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0517, 'learning_rate': 0.000892, 'epoch': 0.25} 25%|████████████████████▏ | 449/1784 [22:36<34:45, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:58,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▏ | 449/1784 [22:36<34:45, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:58,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▏ | 450/1784 [22:38<36:02, 1.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:07:58,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▏ | 451/1784 [22:42<51:28, 2.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:02,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▏ | 451/1784 [22:42<51:28, 2.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:02,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▏ | 451/1784 [22:42<51:28, 2.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 452/1784 [22:46<1:01:32, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 452/1784 [22:46<1:01:32, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8886, 'learning_rate': 0.0009000000000000001, 'epoch': 0.25} 25%|███████████████████▊ | 453/1784 [22:49<1:07:44, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 453/1784 [22:49<1:07:44, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.934, 'learning_rate': 0.000902, 'epoch': 0.25} 25%|███████████████████▊ | 454/1784 [22:53<1:12:34, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▊ | 454/1784 [22:53<1:12:34, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5421, 'learning_rate': 0.0009040000000000001, 'epoch': 0.25} 26%|███████████████████▉ | 455/1784 [22:57<1:15:24, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|███████████████████▉ | 455/1784 [22:57<1:15:24, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5831, 'learning_rate': 0.000906, 'epoch': 0.26} 26%|███████████████████▉ | 455/1784 [22:57<1:15:24, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|███████████████████▉ | 456/1784 [23:01<1:17:28, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:08:26,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:08:26,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0166, 'learning_rate': 0.00091, 'epoch': 0.26} 26%|████████████████████ | 458/1784 [23:08<1:19:26, 3.59s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 458/1784 [23:08<1:19:26, 3.59s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5779, 'learning_rate': 0.000912, 'epoch': 0.26} 26%|████████████████████ | 459/1784 [23:12<1:19:33, 3.60s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 459/1784 [23:12<1:19:33, 3.60s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4935, 'learning_rate': 0.0009140000000000001, 'epoch': 0.26} 26%|████████████████████ | 460/1784 [23:15<1:19:27, 3.60s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 460/1784 [23:15<1:19:27, 3.60s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:08:40,881 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:08:40,881 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 7.7115, 'learning_rate': 0.0009180000000000001, 'epoch': 0.26} 26%|████████████████████▏ | 462/1784 [23:22<1:19:14, 3.60s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 462/1784 [23:22<1:19:14, 3.60s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3225, 'learning_rate': 0.00092, 'epoch': 0.26} 26%|████████████████████▏ | 463/1784 [23:26<1:18:35, 3.57s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 463/1784 [23:26<1:18:35, 3.57s/it]g-point operations will not be computed-03 01:08:05,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.9773, 'learning_rate': 0.0009220000000000001, 'epoch': 0.26} 26%|████████████████████▎ | 464/1784 [23:29<1:17:58, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 464/1784 [23:29<1:17:58, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 465/1784 [23:33<1:17:34, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 465/1784 [23:33<1:17:34, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.67, 'learning_rate': 0.0009260000000000001, 'epoch': 0.26} 26%|████████████████████▎ | 466/1784 [23:36<1:17:01, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 466/1784 [23:36<1:17:01, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.6142, 'learning_rate': 0.0009280000000000001, 'epoch': 0.26} 26%|████████████████████▍ | 467/1784 [23:40<1:16:45, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 467/1784 [23:40<1:16:45, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:09:05,324 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:09:05,324 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.3521, 'learning_rate': 0.0009320000000000001, 'epoch': 0.26} 26%|████████████████████▌ | 469/1784 [23:47<1:16:11, 3.48s/it]g-point operations will not be computed-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 469/1784 [23:47<1:16:11, 3.48s/it]g-point operations will not be computed-03 01:08:53,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.3542, 'learning_rate': 0.000934, 'epoch': 0.26} 26%|████████████████████▌ | 470/1784 [23:50<1:15:33, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:13,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 470/1784 [23:50<1:15:33, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:13,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 471/1784 [23:54<1:15:13, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:13,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 471/1784 [23:54<1:15:13, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:13,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0444, 'learning_rate': 0.0009379999999999999, 'epoch': 0.26} 26%|████████████████████▋ | 472/1784 [23:57<1:14:44, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:13,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▋ | 472/1784 [23:57<1:14:44, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:13,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.4191, 'learning_rate': 0.00094, 'epoch': 0.26} 27%|████████████████████▋ | 473/1784 [24:00<1:14:08, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▋ | 473/1784 [24:00<1:14:08, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▋ | 474/1784 [24:04<1:13:45, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▋ | 474/1784 [24:04<1:13:45, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.6918, 'learning_rate': 0.000944, 'epoch': 0.27} 27%|████████████████████▊ | 475/1784 [24:07<1:13:29, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 475/1784 [24:07<1:13:29, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6161, 'learning_rate': 0.000946, 'epoch': 0.27} 27%|████████████████████▊ | 475/1784 [24:07<1:13:29, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:24,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 476/1784 [24:10<1:12:40, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:33,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 477/1784 [24:13<1:12:11, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:33,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 477/1784 [24:13<1:12:11, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:33,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.776, 'learning_rate': 0.00095, 'epoch': 0.27} 27%|████████████████████▉ | 478/1784 [24:17<1:11:26, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 478/1784 [24:17<1:11:26, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 479/1784 [24:20<1:10:54, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 479/1784 [24:20<1:10:54, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.8037, 'learning_rate': 0.000954, 'epoch': 0.27} 27%|████████████████████▉ | 480/1784 [24:23<1:10:45, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 480/1784 [24:23<1:10:45, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:09:48,332 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:09:48,332 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6293, 'learning_rate': 0.000958, 'epoch': 0.27} 27%|█████████████████████ | 482/1784 [24:29<1:09:42, 3.21s/it]g-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████ | 482/1784 [24:29<1:09:42, 3.21s/it]g-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:09:54,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:09:54,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 6.0316, 'learning_rate': 0.000962, 'epoch': 0.27} [WARNING|modeling_utils.py:388] 2022-03-03 01:09:54,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▏ | 484/1784 [24:36<1:08:13, 3.15s/it]g-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▏ | 484/1784 [24:36<1:08:13, 3.15s/it]g-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:10:00,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:10:00,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:10:00,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:09:40,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▏ | 486/1784 [24:42<1:06:10, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:05,144 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 487/1784 [24:44<1:04:58, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:05,144 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 487/1784 [24:44<1:04:58, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:05,144 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.478, 'learning_rate': 0.0009699999999999999, 'epoch': 0.27} 27%|█████████████████████▎ | 487/1784 [24:44<1:04:58, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:05,144 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 488/1784 [24:47<1:03:39, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:10,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 488/1784 [24:47<1:03:39, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:10,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▍ | 489/1784 [24:50<1:02:18, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:10,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:10:14,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:10:10,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-03 01:10:14,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:10:10,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5472, 'learning_rate': 0.000976, 'epoch': 0.27} {'loss': 5.2288, 'learning_rate': 0.000978, 'epoch': 0.28} 28%|██████████████████████ | 491/1784 [24:55<59:14, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:18,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████ | 491/1784 [24:55<59:14, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:18,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████ | 492/1784 [24:58<57:00, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:20,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████ | 492/1784 [24:58<57:00, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:20,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████ | 493/1784 [25:00<54:32, 2.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:23,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████ | 493/1784 [25:00<54:32, 2.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:23,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▏ | 494/1784 [25:02<51:28, 2.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:25,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▏ | 494/1784 [25:02<51:28, 2.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:25,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▏ | 495/1784 [25:04<48:37, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:26,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▏ | 495/1784 [25:04<48:37, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:26,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.5781, 'learning_rate': 0.000988, 'epoch': 0.28} 28%|██████████████████████▎ | 497/1784 [25:07<42:10, 1.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:28,693 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▎ | 497/1784 [25:07<42:10, 1.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:28,693 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▎ | 498/1784 [25:09<38:42, 1.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:31,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▎ | 498/1784 [25:09<38:42, 1.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:31,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▍ | 499/1784 [25:10<35:21, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:32,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▍ | 499/1784 [25:10<35:21, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:10:32,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [INFO|trainer.py:2366] 2022-03-03 01:10:34,079 >> Num examples = 2642 | 500/1784 [25:12<35:59, 1.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:10:34,079 >> Num examples = 2642 | 500/1784 [25:12<35:59, 1.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:10:34,079 >> Num examples = 2642 | 500/1784 [25:12<35:59, 1.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:10:34,079 >> Num examples = 2642 | 500/1784 [25:12<35:59, 1.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 1%|█ | 4/331 [00:06<10:17, 1.89s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▎ | 5/331 [00:09<11:51, 2.18s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▌ | 6/331 [00:12<12:52, 2.38s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▊ | 7/331 [00:15<13:05, 2.42s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██ | 8/331 [00:17<13:30, 2.51s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▎ | 9/331 [00:20<14:07, 2.63s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▍ | 10/331 [00:23<15:01, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▋ | 11/331 [00:26<14:30, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▉ | 12/331 [00:29<14:23, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▏ | 13/331 [00:31<14:11, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▍ | 14/331 [00:34<13:58, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▋ | 15/331 [00:37<15:10, 2.88s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▉ | 16/331 [00:41<16:03, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▏ | 17/331 [00:44<16:13, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▍ | 18/331 [00:46<14:47, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▋ | 19/331 [00:49<14:36, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▉ | 20/331 [00:51<13:36, 2.63s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▏ | 21/331 [00:54<14:07, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▍ | 22/331 [00:57<15:14, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▋ | 23/331 [01:01<16:45, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▉ | 24/331 [01:05<17:42, 3.46s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▏ | 25/331 [01:08<17:03, 3.35s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▍ | 26/331 [01:11<15:49, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▋ | 27/331 [01:14<15:52, 3.13s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▉ | 28/331 [01:17<15:20, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▏ | 29/331 [01:20<14:57, 2.97s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▍ | 30/331 [01:22<14:22, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▋ | 31/331 [01:25<13:48, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▉ | 32/331 [01:28<13:34, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▏ | 33/331 [01:30<13:37, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▍ | 34/331 [01:33<13:33, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▋ | 35/331 [01:36<13:43, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▉ | 36/331 [01:39<14:18, 2.91s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▏ | 37/331 [01:43<14:59, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▍ | 38/331 [01:46<15:14, 3.12s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▋ | 39/331 [01:49<15:17, 3.14s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▉ | 40/331 [01:51<13:55, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▏ | 41/331 [01:54<13:13, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▍ | 42/331 [01:57<14:11, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▋ | 43/331 [02:01<14:49, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▉ | 44/331 [02:04<15:18, 3.20s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▏ | 45/331 [02:07<14:29, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▍ | 46/331 [02:09<13:27, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▋ | 47/331 [02:11<12:33, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▉ | 48/331 [02:14<12:57, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▏ | 49/331 [02:17<13:35, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▍ | 50/331 [02:20<13:25, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▋ | 51/331 [02:23<13:45, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▉ | 52/331 [02:26<13:07, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▏ | 53/331 [02:29<13:02, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▍ | 54/331 [02:31<12:28, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▋ | 55/331 [02:35<13:36, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▊ | 56/331 [02:38<13:24, 2.93s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████ | 57/331 [02:40<12:59, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▎ | 58/331 [02:43<13:31, 2.97s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▌ | 59/331 [02:46<12:46, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▊ | 60/331 [02:49<12:23, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████ | 61/331 [02:52<12:51, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▎ | 62/331 [02:54<12:42, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▌ | 63/331 [02:58<13:50, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▊ | 64/331 [03:01<13:17, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████ | 65/331 [03:04<13:06, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▎ | 66/331 [03:08<14:16, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▌ | 67/331 [03:11<14:55, 3.39s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▊ | 68/331 [03:15<15:07, 3.45s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████ | 69/331 [03:18<14:45, 3.38s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▎ | 70/331 [03:21<14:23, 3.31s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▌ | 71/331 [03:25<14:29, 3.34s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▊ | 72/331 [03:28<14:23, 3.34s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████ | 73/331 [03:31<13:56, 3.24s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▎ | 74/331 [03:34<13:35, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▌ | 75/331 [03:37<13:44, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▊ | 76/331 [03:40<13:02, 3.07s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████ | 77/331 [03:43<12:41, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▎ | 78/331 [03:46<12:05, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▌ | 79/331 [03:48<11:44, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▊ | 80/331 [03:51<11:33, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████ | 81/331 [03:54<12:01, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▎ | 82/331 [03:57<11:49, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▌ | 83/331 [04:00<12:08, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▊ | 84/331 [04:04<12:54, 3.13s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████ | 85/331 [04:06<12:00, 2.93s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▎ | 86/331 [04:09<12:39, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▌ | 87/331 [04:12<12:15, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 88/331 [04:15<11:54, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████ | 89/331 [04:17<11:09, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 90/331 [04:20<10:36, 2.64s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 91/331 [04:23<11:03, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 92/331 [04:25<10:20, 2.60s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████ | 93/331 [04:28<10:31, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▎ | 94/331 [04:31<10:45, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▌ | 95/331 [04:34<10:54, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▊ | 96/331 [04:37<11:02, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████ | 97/331 [04:39<10:33, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▎ | 98/331 [04:42<10:52, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▌ | 99/331 [04:45<10:51, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▍ | 100/331 [04:47<10:19, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▋ | 101/331 [04:50<10:16, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▉ | 102/331 [04:53<11:01, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▏ | 103/331 [04:56<10:33, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▍ | 104/331 [04:59<10:35, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▋ | 105/331 [05:02<10:41, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▉ | 106/331 [05:04<10:38, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▏ | 107/331 [05:07<09:55, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▍ | 108/331 [05:09<09:42, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▋ | 109/331 [05:12<09:39, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▉ | 110/331 [05:15<10:09, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▏ | 111/331 [05:18<10:15, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▍ | 112/331 [05:21<10:14, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▋ | 113/331 [05:23<09:39, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▉ | 114/331 [05:26<09:41, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▏ | 115/331 [05:28<09:38, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▍ | 116/331 [05:31<09:58, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▋ | 117/331 [05:34<09:56, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▉ | 118/331 [05:37<09:45, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████ | 119/331 [05:40<09:45, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▎ | 120/331 [05:42<09:40, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▌ | 121/331 [05:46<10:10, 2.91s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▊ | 122/331 [05:48<09:52, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████ | 123/331 [05:52<10:27, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▎ | 124/331 [05:55<10:16, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▌ | 125/331 [05:58<10:49, 3.15s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▊ | 126/331 [06:01<10:55, 3.20s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████ | 127/331 [06:05<11:21, 3.34s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▎ | 128/331 [06:08<11:22, 3.36s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▌ | 129/331 [06:12<11:07, 3.30s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▊ | 130/331 [06:15<11:13, 3.35s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████ | 131/331 [06:19<11:28, 3.44s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▎ | 132/331 [06:22<10:50, 3.27s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▌ | 133/331 [06:24<10:08, 3.08s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▊ | 134/331 [06:27<09:48, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████ | 135/331 [06:30<09:53, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▎ | 136/331 [06:33<10:06, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▌ | 137/331 [06:37<10:27, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▊ | 138/331 [06:41<10:46, 3.35s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████ | 139/331 [06:43<09:38, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▎ | 140/331 [06:47<10:19, 3.25s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▌ | 141/331 [06:49<09:49, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▋ | 142/331 [06:52<09:28, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▉ | 143/331 [06:56<09:52, 3.15s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▏ | 144/331 [06:58<09:27, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▍ | 145/331 [07:01<09:16, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▋ | 146/331 [07:05<09:43, 3.16s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▉ | 147/331 [07:08<09:22, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▏ | 148/331 [07:10<08:45, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▍ | 149/331 [07:13<08:16, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▋ | 150/331 [07:16<08:36, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▉ | 151/331 [07:18<08:26, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▏ | 152/331 [07:21<08:03, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▍ | 153/331 [07:23<07:57, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▋ | 154/331 [07:27<08:22, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▉ | 155/331 [07:30<08:47, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▏ | 156/331 [07:33<08:57, 3.07s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▍ | 157/331 [07:37<09:14, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▋ | 158/331 [07:40<09:17, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▉ | 159/331 [07:43<09:23, 3.28s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▏ | 160/331 [07:46<08:51, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▍ | 161/331 [07:49<08:39, 3.05s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▋ | 162/331 [07:53<09:05, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▉ | 163/331 [07:56<09:06, 3.25s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▏ | 164/331 [07:59<08:38, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▍ | 165/331 [08:02<08:25, 3.05s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▌ | 166/331 [08:04<08:09, 2.97s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▊ | 167/331 [08:08<08:16, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 168/331 [08:10<07:49, 2.88s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▎ | 169/331 [08:13<07:56, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▌ | 170/331 [08:16<07:30, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▊ | 171/331 [08:19<07:27, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████ | 172/331 [08:21<07:10, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▎ | 173/331 [08:24<07:23, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▌ | 174/331 [08:27<07:04, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▊ | 175/331 [08:29<07:08, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████ | 176/331 [08:32<06:52, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▎ | 177/331 [08:35<07:14, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▌ | 178/331 [08:39<07:41, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▊ | 179/331 [08:42<08:01, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████ | 180/331 [08:45<07:53, 3.13s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▎ | 181/331 [08:48<07:46, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▌ | 182/331 [08:50<07:09, 2.88s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▊ | 183/331 [08:53<06:37, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████ | 184/331 [08:55<06:11, 2.53s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▎ | 185/331 [08:57<05:46, 2.38s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▌ | 186/331 [09:00<05:57, 2.46s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▊ | 187/331 [09:03<06:26, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████ | 188/331 [09:06<06:26, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▎ | 189/331 [09:08<06:07, 2.59s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▍ | 190/331 [09:10<05:52, 2.50s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▋ | 191/331 [09:13<05:51, 2.51s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▉ | 192/331 [09:15<05:41, 2.46s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▏ | 193/331 [09:18<06:10, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▍ | 194/331 [09:20<05:49, 2.55s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▋ | 195/331 [09:23<05:43, 2.52s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▉ | 196/331 [09:26<05:48, 2.58s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▏ | 197/331 [09:29<06:06, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▍ | 198/331 [09:31<05:48, 2.62s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▋ | 199/331 [09:34<05:54, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▉ | 200/331 [09:36<05:36, 2.57s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▏ | 201/331 [09:39<05:32, 2.56s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▍ | 202/331 [09:42<05:41, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▋ | 203/331 [09:44<05:41, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▉ | 204/331 [09:48<06:01, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▏ | 205/331 [09:51<06:01, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▍ | 206/331 [09:53<05:52, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▋ | 207/331 [09:57<06:07, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▉ | 208/331 [10:00<06:12, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▏ | 209/331 [10:02<05:43, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▍ | 210/331 [10:04<05:20, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▋ | 211/331 [10:07<05:25, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▉ | 212/331 [10:09<05:09, 2.60s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████ | 213/331 [10:12<05:07, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▎ | 214/331 [10:14<04:49, 2.48s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▌ | 215/331 [10:16<04:37, 2.39s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▊ | 216/331 [10:20<05:06, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████ | 217/331 [10:22<05:05, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▎ | 218/331 [10:26<05:19, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▌ | 219/331 [10:28<05:15, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▊ | 220/331 [10:31<05:01, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████ | 221/331 [10:34<05:03, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▎ | 222/331 [10:36<04:50, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▌ | 223/331 [10:39<04:52, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▊ | 224/331 [10:42<04:52, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████ | 225/331 [10:45<04:47, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▎ | 226/331 [10:48<04:59, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▌ | 227/331 [10:50<04:53, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▊ | 228/331 [10:53<04:46, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████ | 229/331 [10:56<04:41, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▎ | 230/331 [10:58<04:32, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▌ | 231/331 [11:01<04:38, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▊ | 232/331 [11:04<04:31, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████ | 233/331 [11:07<04:39, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▎ | 234/331 [11:10<04:25, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▌ | 235/331 [11:12<04:15, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▊ | 236/331 [11:16<04:42, 2.97s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▉ | 237/331 [11:19<04:51, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▏ | 238/331 [11:22<04:49, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▍ | 239/331 [11:26<04:49, 3.15s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▋ | 240/331 [11:29<04:52, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▉ | 241/331 [11:32<04:57, 3.30s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▏ | 242/331 [11:36<04:55, 3.32s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▍ | 243/331 [11:39<04:52, 3.33s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▋ | 244/331 [11:43<04:58, 3.43s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▉ | 245/331 [11:46<04:46, 3.34s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▏ | 246/331 [11:50<04:55, 3.48s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▍ | 247/331 [11:53<04:42, 3.36s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▋ | 248/331 [11:55<04:21, 3.15s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▉ | 249/331 [11:58<04:00, 2.93s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▏ | 250/331 [12:00<03:48, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 251/331 [12:03<03:51, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▋ | 252/331 [12:06<03:38, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▉ | 253/331 [12:09<03:49, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▏ | 254/331 [12:12<03:40, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 255/331 [12:15<03:46, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▋ | 256/331 [12:18<03:38, 2.91s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▉ | 257/331 [12:21<03:41, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▏ | 258/331 [12:24<03:27, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 259/331 [12:26<03:21, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▋ | 260/331 [12:29<03:23, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▊ | 261/331 [12:32<03:09, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 262/331 [12:34<03:07, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▎ | 263/331 [12:38<03:14, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▌ | 264/331 [12:40<03:07, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▊ | 265/331 [12:43<03:01, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████ | 266/331 [12:46<02:54, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 267/331 [12:49<03:03, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 268/331 [12:52<03:00, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 269/331 [12:55<03:07, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████ | 270/331 [12:58<03:02, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▎ | 271/331 [13:01<03:05, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 272/331 [13:04<02:56, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▊ | 273/331 [13:07<02:55, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████ | 274/331 [13:11<03:01, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▎ | 275/331 [13:14<03:01, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▌ | 276/331 [13:17<02:47, 3.05s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 277/331 [13:19<02:39, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████ | 278/331 [13:22<02:35, 2.93s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 279/331 [13:26<02:45, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▌ | 280/331 [13:29<02:37, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▊ | 281/331 [13:32<02:39, 3.18s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████ | 282/331 [13:35<02:35, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▎ | 283/331 [13:39<02:35, 3.24s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 284/331 [13:42<02:37, 3.35s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▋ | 285/331 [13:46<02:36, 3.40s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▉ | 286/331 [13:50<02:34, 3.44s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▏ | 287/331 [13:53<02:35, 3.54s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▍ | 288/331 [13:57<02:30, 3.50s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▋ | 289/331 [14:00<02:18, 3.29s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▉ | 290/331 [14:02<02:07, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▏ | 291/331 [14:05<01:58, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▍ | 292/331 [14:08<01:52, 2.88s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▋ | 293/331 [14:10<01:48, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▉ | 294/331 [14:13<01:42, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▏ | 295/331 [14:15<01:36, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▍ | 296/331 [14:18<01:31, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▋ | 297/331 [14:21<01:39, 2.92s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▉ | 298/331 [14:25<01:44, 3.16s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▏ | 299/331 [14:28<01:37, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▍ | 300/331 [14:31<01:33, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▋ | 301/331 [14:34<01:28, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▉ | 302/331 [14:36<01:23, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▏ | 303/331 [14:39<01:18, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▍ | 304/331 [14:42<01:18, 2.90s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▋ | 305/331 [14:45<01:18, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▉ | 306/331 [14:49<01:19, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▏ | 307/331 [14:53<01:19, 3.32s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▎ | 308/331 [14:57<01:20, 3.51s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▌ | 309/331 [15:00<01:17, 3.54s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▊ | 310/331 [15:03<01:09, 3.32s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████ | 311/331 [15:06<01:06, 3.31s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▎ | 312/331 [15:09<00:58, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▌ | 313/331 [15:12<00:54, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▊ | 314/331 [15:15<00:52, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████ | 315/331 [15:18<00:51, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▎ | 316/331 [15:22<00:48, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▌ | 317/331 [15:25<00:47, 3.36s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▊ | 318/331 [15:28<00:41, 3.18s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████ | 319/331 [15:31<00:36, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▎ | 320/331 [15:34<00:33, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▌ | 321/331 [15:37<00:30, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▊ | 322/331 [15:40<00:28, 3.16s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████ | 323/331 [15:43<00:24, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████ | 323/331 [15:43<00:24, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████ | 323/331 [15:43<00:24, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▌ | 325/331 [15:50<00:19, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▊ | 326/331 [15:53<00:16, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████ | 327/331 [15:57<00:12, 3.25s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▎| 328/331 [16:00<00:09, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▎| 328/331 [16:00<00:09, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▎| 328/331 [16:00<00:09, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▊| 330/331 [16:07<00:03, 3.35s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████████| 331/331 [16:08<00:00, 2.92s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████████| 331/331 [16:08<00:00, 2.92s/it][INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 01:26:46 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|configuration_utils.py:438] 2022-03-03 01:26:46,475 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:27:02,906 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:27:02,906 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:27:02,906 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 01:28:45 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20220302_214437-2u4nhnsf/run-2u4nhnsf.wandb', 'wandb/run-20220302_222605-10glutwr/run-10glutwr.wandb', 'wandb/run-20220302_233655-33dtvgaa/run-33dtvgaa.wandb', 'wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb']. This may take a bit of time if the files are large. [INFO|feature_extraction_utils.py:324] 2022-03-03 01:27:02,906 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:27:02,906 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████ | 501/1784 [43:58<120:46:32, 338.89s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████ | 501/1784 [43:58<120:46:32, 338.89s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████ | 501/1784 [43:58<120:46:32, 338.89s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 502/1784 [44:02<84:55:39, 238.49s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 502/1784 [44:02<84:55:39, 238.49s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 502/1784 [44:02<84:55:39, 238.49s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 503/1784 [44:06<59:49:14, 168.11s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 503/1784 [44:06<59:49:14, 168.11s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 503/1784 [44:06<59:49:14, 168.11s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 504/1784 [44:10<42:15:07, 118.83s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 504/1784 [44:10<42:15:07, 118.83s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▍ | 504/1784 [44:10<42:15:07, 118.83s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 505/1784 [44:13<29:57:42, 84.33s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 505/1784 [44:13<29:57:42, 84.33s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 505/1784 [44:13<29:57:42, 84.33s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 506/1784 [44:17<21:21:28, 60.16s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 506/1784 [44:17<21:21:28, 60.16s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 506/1784 [44:17<21:21:28, 60.16s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▉ | 507/1784 [44:21<15:20:32, 43.25s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▉ | 507/1784 [44:21<15:20:32, 43.25s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▉ | 507/1784 [44:21<15:20:32, 43.25s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▉ | 508/1784 [44:25<11:07:48, 31.40s/it]onfig.jsonner.py:560] 2022-03-03 01:10:34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:29:50,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:29:50,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.22, 'learning_rate': 0.0009945482866043614, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-03-03 01:29:50,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 510/1784 [44:32<6:07:13, 17.30s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 510/1784 [44:32<6:07:13, 17.30s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 510/1784 [44:32<6:07:13, 17.30s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 511/1784 [44:36<4:40:40, 13.23s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 511/1784 [44:36<4:40:40, 13.23s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 511/1784 [44:36<4:40:40, 13.23s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▍ | 512/1784 [44:40<3:39:51, 10.37s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▍ | 512/1784 [44:40<3:39:51, 10.37s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▍ | 512/1784 [44:40<3:39:51, 10.37s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▍ | 513/1784 [44:43<2:57:00, 8.36s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:08,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:08,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.304, 'learning_rate': 0.0009906542056074767, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-03-03 01:30:08,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 515/1784 [44:50<2:05:41, 5.94s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 515/1784 [44:50<2:05:41, 5.94s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 515/1784 [44:50<2:05:41, 5.94s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 516/1784 [44:54<1:51:31, 5.28s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 516/1784 [44:54<1:51:31, 5.28s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 516/1784 [44:54<1:51:31, 5.28s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 517/1784 [44:58<1:40:30, 4.76s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:23,415 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:23,415 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6919, 'learning_rate': 0.0009875389408099688, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-03-03 01:30:23,415 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▋ | 519/1784 [45:05<1:27:31, 4.15s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▋ | 519/1784 [45:05<1:27:31, 4.15s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▋ | 519/1784 [45:05<1:27:31, 4.15s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▋ | 520/1784 [45:08<1:23:45, 3.98s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▋ | 520/1784 [45:08<1:23:45, 3.98s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▋ | 520/1784 [45:08<1:23:45, 3.98s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 521/1784 [45:12<1:22:58, 3.94s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 521/1784 [45:12<1:22:58, 3.94s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 521/1784 [45:12<1:22:58, 3.94s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 522/1784 [45:16<1:20:12, 3.81s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:41,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:41,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.2262, 'learning_rate': 0.0009836448598130841, 'epoch': 0.29} 29%|██████████████████████▉ | 524/1784 [45:23<1:16:39, 3.65s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▉ | 524/1784 [45:23<1:16:39, 3.65s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.9193, 'learning_rate': 0.0009828660436137073, 'epoch': 0.29} 29%|██████████████████████▉ | 524/1784 [45:23<1:16:39, 3.65s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▉ | 525/1784 [45:26<1:15:06, 3.58s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:51,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:30:51,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.493, 'learning_rate': 0.0009813084112149533, 'epoch': 0.29} 30%|███████████████████████ | 527/1784 [45:33<1:13:20, 3.50s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████ | 527/1784 [45:33<1:13:20, 3.50s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.264, 'learning_rate': 0.0009805295950155765, 'epoch': 0.3} 30%|███████████████████████ | 528/1784 [45:37<1:12:59, 3.49s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████ | 528/1784 [45:37<1:12:59, 3.49s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:02,019 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:02,019 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.0991, 'learning_rate': 0.0009789719626168223, 'epoch': 0.3} 30%|███████████████████████▏ | 530/1784 [45:43<1:11:42, 3.43s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▏ | 530/1784 [45:43<1:11:42, 3.43s/it]g-point operations will not be computed34,077 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.0431, 'learning_rate': 0.0009781931464174455, 'epoch': 0.3} 30%|███████████████████████▏ | 531/1784 [45:47<1:12:23, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▏ | 531/1784 [45:47<1:12:23, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▎ | 532/1784 [45:50<1:11:03, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▎ | 532/1784 [45:50<1:11:03, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.402, 'learning_rate': 0.0009766355140186918, 'epoch': 0.3} 30%|███████████████████████▎ | 533/1784 [45:53<1:09:31, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▎ | 533/1784 [45:53<1:09:31, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:18,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:18,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.372, 'learning_rate': 0.0009750778816199377, 'epoch': 0.3} 30%|███████████████████████▍ | 535/1784 [46:00<1:07:05, 3.22s/it]g-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▍ | 535/1784 [46:00<1:07:05, 3.22s/it]g-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:24,659 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:24,659 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6769, 'learning_rate': 0.0009735202492211839, 'epoch': 0.3} 30%|███████████████████████▍ | 537/1784 [46:06<1:04:57, 3.13s/it]g-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▍ | 537/1784 [46:06<1:04:57, 3.13s/it]g-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:30,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:30,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:10,640 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.3551, 'learning_rate': 0.0009719626168224299, 'epoch': 0.3} 30%|███████████████████████▌ | 539/1784 [46:11<1:01:35, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:34,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|███████████████████████▌ | 539/1784 [46:11<1:01:35, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:34,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▏ | 540/1784 [46:14<59:42, 2.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▏ | 540/1784 [46:14<59:42, 2.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▎ | 541/1784 [46:16<57:32, 2.78s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▎ | 541/1784 [46:16<57:32, 2.78s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:41,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:41,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:43,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:31:43,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.7628, 'learning_rate': 0.0009680685358255452, 'epoch': 0.3} [WARNING|modeling_utils.py:388] 2022-03-03 01:31:43,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:31:37,354 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7015, 'learning_rate': 0.0009672897196261683, 'epoch': 0.3} 30%|████████████████████████▍ | 544/1784 [46:23<50:42, 2.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:46,626 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▍ | 544/1784 [46:23<50:42, 2.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:46,626 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 546/1784 [46:27<44:33, 2.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:48,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 546/1784 [46:27<44:33, 2.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:48,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 547/1784 [46:29<41:26, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:50,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 547/1784 [46:29<41:26, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:50,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 548/1784 [46:30<38:27, 1.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:53,289 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 548/1784 [46:30<38:27, 1.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:53,289 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 549/1784 [46:32<35:14, 1.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:54,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 549/1784 [46:32<35:14, 1.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:54,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▋ | 550/1784 [46:34<36:20, 1.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:54,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▋ | 551/1784 [46:38<51:06, 2.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:58,012 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▋ | 551/1784 [46:38<51:06, 2.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:31:58,012 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▋ | 551/1784 [46:38<51:06, 2.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▋ | 551/1784 [46:38<51:06, 2.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▊ | 552/1784 [46:42<59:33, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▊ | 552/1784 [46:42<59:33, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▊ | 552/1784 [46:42<59:33, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▏ | 553/1784 [46:46<1:04:54, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▏ | 553/1784 [46:46<1:04:54, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▏ | 553/1784 [46:46<1:04:54, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▏ | 554/1784 [46:49<1:08:32, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▏ | 554/1784 [46:49<1:08:32, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▏ | 554/1784 [46:49<1:08:32, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 555/1784 [46:53<1:12:02, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 555/1784 [46:53<1:12:02, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 555/1784 [46:53<1:12:02, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 556/1784 [46:57<1:13:15, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 556/1784 [46:57<1:13:15, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 556/1784 [46:57<1:13:15, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:01,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 557/1784 [47:01<1:14:01, 3.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▎ | 557/1784 [47:01<1:14:01, 3.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 558/1784 [47:04<1:14:44, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 558/1784 [47:04<1:14:44, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 558/1784 [47:04<1:14:44, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 559/1784 [47:08<1:14:50, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 559/1784 [47:08<1:14:50, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 559/1784 [47:08<1:14:50, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 560/1784 [47:12<1:14:54, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 560/1784 [47:12<1:14:54, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▍ | 560/1784 [47:12<1:14:54, 3.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 561/1784 [47:15<1:14:55, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 561/1784 [47:15<1:14:55, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|████████████████████████▌ | 561/1784 [47:15<1:14:55, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:24,665 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▌ | 562/1784 [47:19<1:14:22, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▌ | 562/1784 [47:19<1:14:22, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▌ | 563/1784 [47:23<1:14:01, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▌ | 563/1784 [47:23<1:14:01, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▌ | 563/1784 [47:23<1:14:01, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 564/1784 [47:26<1:14:19, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 564/1784 [47:26<1:14:19, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 564/1784 [47:26<1:14:19, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 565/1784 [47:30<1:14:44, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 565/1784 [47:30<1:14:44, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 565/1784 [47:30<1:14:44, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 566/1784 [47:34<1:13:57, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▋ | 566/1784 [47:34<1:13:57, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:32:59,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:32:59,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:32:59,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▊ | 568/1784 [47:41<1:12:51, 3.59s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▊ | 568/1784 [47:41<1:12:51, 3.59s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▊ | 568/1784 [47:41<1:12:51, 3.59s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▉ | 569/1784 [47:44<1:11:55, 3.55s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:33:09,724 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:33:09,724 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6237, 'learning_rate': 0.0009470404984423676, 'epoch': 0.32} [WARNING|modeling_utils.py:388] 2022-03-03 01:33:09,724 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▉ | 571/1784 [47:51<1:10:56, 3.51s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▉ | 571/1784 [47:51<1:10:56, 3.51s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|████████████████████████▉ | 571/1784 [47:51<1:10:56, 3.51s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 572/1784 [47:55<1:11:04, 3.52s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 572/1784 [47:55<1:11:04, 3.52s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 572/1784 [47:55<1:11:04, 3.52s/it]g-point operations will not be computed-03 01:32:43,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 573/1784 [47:58<1:10:01, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 573/1784 [47:58<1:10:01, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 574/1784 [48:01<1:09:22, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 574/1784 [48:01<1:09:22, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████ | 574/1784 [48:01<1:09:22, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▏ | 575/1784 [48:05<1:09:04, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:33:30,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:33:30,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3686, 'learning_rate': 0.000942367601246106, 'epoch': 0.32} [WARNING|modeling_utils.py:388] 2022-03-03 01:33:30,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▏ | 577/1784 [48:11<1:07:28, 3.35s/it]g-point operations will not be computed-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▏ | 577/1784 [48:11<1:07:28, 3.35s/it]g-point operations will not be computed-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▏ | 577/1784 [48:11<1:07:28, 3.35s/it]g-point operations will not be computed-03 01:33:21,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▎ | 578/1784 [48:15<1:06:53, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▎ | 578/1784 [48:15<1:06:53, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▎ | 579/1784 [48:18<1:06:17, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▎ | 579/1784 [48:18<1:06:17, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▎ | 579/1784 [48:18<1:06:17, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▎ | 580/1784 [48:21<1:05:57, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▎ | 580/1784 [48:21<1:05:57, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:38,356 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4733, 'learning_rate': 0.0009384735202492212, 'epoch': 0.33} 33%|█████████████████████████▍ | 581/1784 [48:24<1:05:22, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:48,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▍ | 581/1784 [48:24<1:05:22, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:48,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▍ | 582/1784 [48:27<1:04:37, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:48,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▍ | 582/1784 [48:27<1:04:37, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:48,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▍ | 582/1784 [48:27<1:04:37, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:48,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▍ | 583/1784 [48:30<1:03:18, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▍ | 583/1784 [48:30<1:03:18, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▌ | 584/1784 [48:33<1:02:12, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:33:58,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:33:58,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.7359, 'learning_rate': 0.0009353582554517133, 'epoch': 0.33} [WARNING|modeling_utils.py:388] 2022-03-03 01:33:58,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▌ | 586/1784 [48:39<1:00:34, 3.03s/it]g-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|█████████████████████████▌ | 586/1784 [48:39<1:00:34, 3.03s/it]g-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:04,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:07,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:07,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5215, 'learning_rate': 0.0009330218068535827, 'epoch': 0.33} [WARNING|modeling_utils.py:388] 2022-03-03 01:34:07,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:33:54,130 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|██████████████████████████▍ | 589/1784 [48:48<56:12, 2.82s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|██████████████████████████▍ | 589/1784 [48:48<56:12, 2.82s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|██████████████████████████▍ | 590/1784 [48:50<54:33, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:14,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:14,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:16,953 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:16,953 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:19,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:19,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:21,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:21,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:22,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:22,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4131, 'learning_rate': 0.0009275700934579439, 'epoch': 0.33} [WARNING|modeling_utils.py:388] 2022-03-03 01:34:24,617 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:24,617 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:27,483 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:27,483 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.6016, 'learning_rate': 0.0009252336448598131, 'epoch': 0.34} [WARNING|modeling_utils.py:388] 2022-03-03 01:34:28,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:30,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:30,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8385, 'learning_rate': 0.0009236760124610592, 'epoch': 0.34} [WARNING|modeling_utils.py:388] 2022-03-03 01:34:30,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:34,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:34,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:34,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▉ | 602/1784 [49:16<55:12, 2.80s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▉ | 602/1784 [49:16<55:12, 2.80s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▉ | 602/1784 [49:16<55:12, 2.80s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▎ | 603/1784 [49:20<1:01:31, 3.13s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▎ | 603/1784 [49:20<1:01:31, 3.13s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▎ | 603/1784 [49:20<1:01:31, 3.13s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▍ | 604/1784 [49:24<1:05:33, 3.33s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▍ | 604/1784 [49:24<1:05:33, 3.33s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▍ | 604/1784 [49:24<1:05:33, 3.33s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▍ | 605/1784 [49:28<1:08:11, 3.47s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:53,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:34:53,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3185, 'learning_rate': 0.0009190031152647975, 'epoch': 0.34} 34%|██████████████████████████▌ | 607/1784 [49:35<1:10:44, 3.61s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▌ | 607/1784 [49:35<1:10:44, 3.61s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1185, 'learning_rate': 0.0009182242990654206, 'epoch': 0.34} 34%|██████████████████████████▌ | 607/1784 [49:35<1:10:44, 3.61s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▌ | 608/1784 [49:39<1:11:25, 3.64s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▌ | 608/1784 [49:39<1:11:25, 3.64s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▌ | 608/1784 [49:39<1:11:25, 3.64s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 609/1784 [49:43<1:11:30, 3.65s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 609/1784 [49:43<1:11:30, 3.65s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 609/1784 [49:43<1:11:30, 3.65s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 610/1784 [49:46<1:11:22, 3.65s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 610/1784 [49:46<1:11:22, 3.65s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 610/1784 [49:46<1:11:22, 3.65s/it]g-point operations will not be computed-03 01:34:11,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▋ | 611/1784 [49:50<1:11:37, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▊ | 612/1784 [49:54<1:10:55, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▊ | 612/1784 [49:54<1:10:55, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4691, 'learning_rate': 0.0009143302180685359, 'epoch': 0.34} 34%|██████████████████████████▊ | 612/1784 [49:54<1:10:55, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▊ | 613/1784 [49:57<1:10:25, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▊ | 613/1784 [49:57<1:10:25, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▊ | 613/1784 [49:57<1:10:25, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:13,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▊ | 614/1784 [50:01<1:09:49, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▉ | 615/1784 [50:04<1:09:29, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|██████████████████████████▉ | 615/1784 [50:04<1:09:29, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1429, 'learning_rate': 0.000911993769470405, 'epoch': 0.34} 34%|██████████████████████████▉ | 615/1784 [50:04<1:09:29, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|██████████████████████████▉ | 616/1784 [50:08<1:08:52, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|██████████████████████████▉ | 616/1784 [50:08<1:08:52, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|██████████████████████████▉ | 616/1784 [50:08<1:08:52, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|██████████████████████████▉ | 617/1784 [50:11<1:08:51, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:35:36,761 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:35:36,761 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2208, 'learning_rate': 0.0009096573208722742, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-03-03 01:35:36,761 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████ | 619/1784 [50:18<1:08:00, 3.50s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████ | 619/1784 [50:18<1:08:00, 3.50s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████ | 619/1784 [50:18<1:08:00, 3.50s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████ | 620/1784 [50:22<1:07:18, 3.47s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:35:47,120 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:35:47,120 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6269, 'learning_rate': 0.0009073208722741433, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-03-03 01:35:47,120 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▏ | 622/1784 [50:28<1:07:06, 3.47s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▏ | 622/1784 [50:28<1:07:06, 3.47s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▏ | 622/1784 [50:28<1:07:06, 3.47s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▏ | 623/1784 [50:32<1:06:29, 3.44s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:35:57,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:35:57,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.9756, 'learning_rate': 0.0009049844236760125, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-03-03 01:35:57,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▎ | 625/1784 [50:39<1:05:31, 3.39s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▎ | 625/1784 [50:39<1:05:31, 3.39s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▎ | 625/1784 [50:39<1:05:31, 3.39s/it]g-point operations will not be computed-03 01:35:24,560 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▎ | 626/1784 [50:42<1:05:04, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▍ | 627/1784 [50:45<1:04:20, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▍ | 627/1784 [50:45<1:04:20, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6423, 'learning_rate': 0.0009026479750778816, 'epoch': 0.35} 35%|███████████████████████████▍ | 627/1784 [50:45<1:04:20, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▍ | 628/1784 [50:48<1:03:56, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:13,723 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:13,723 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.2212, 'learning_rate': 0.0009010903426791277, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-03-03 01:36:13,723 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▌ | 630/1784 [50:55<1:03:10, 3.28s/it]g-point operations will not be computed-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▌ | 630/1784 [50:55<1:03:10, 3.28s/it]g-point operations will not be computed-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▌ | 630/1784 [50:55<1:03:10, 3.28s/it]g-point operations will not be computed-03 01:36:05,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▌ | 631/1784 [50:58<1:02:39, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:21,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▋ | 632/1784 [51:01<1:01:43, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:21,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▋ | 632/1784 [51:01<1:01:43, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:21,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6349, 'learning_rate': 0.0008987538940809969, 'epoch': 0.35} 35%|███████████████████████████▋ | 632/1784 [51:01<1:01:43, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:21,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|███████████████████████████▋ | 633/1784 [51:04<1:01:05, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:28,011 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|███████████████████████████▋ | 634/1784 [51:07<1:00:20, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:28,011 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|███████████████████████████▋ | 634/1784 [51:07<1:00:20, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:28,011 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7571, 'learning_rate': 0.000897196261682243, 'epoch': 0.36} 36%|███████████████████████████▋ | 634/1784 [51:07<1:00:20, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:28,011 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▍ | 635/1784 [51:10<59:56, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▌ | 636/1784 [51:13<59:01, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▌ | 636/1784 [51:13<59:01, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:38,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:38,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4477, 'learning_rate': 0.0008948598130841121, 'epoch': 0.36} [WARNING|modeling_utils.py:388] 2022-03-03 01:36:38,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▌ | 638/1784 [51:19<56:37, 2.96s/it]g-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▌ | 638/1784 [51:19<56:37, 2.96s/it]g-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:43,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:46,511 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:36:46,511 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.0817, 'learning_rate': 0.0008925233644859813, 'epoch': 0.36} [WARNING|modeling_utils.py:388] 2022-03-03 01:36:46,511 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:36:34,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▋ | 641/1784 [51:27<51:24, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:50,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▋ | 641/1784 [51:27<51:24, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:50,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▊ | 642/1784 [51:29<49:32, 2.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:52,538 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▊ | 642/1784 [51:29<49:32, 2.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:52,538 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▊ | 643/1784 [51:32<47:26, 2.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:54,719 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▊ | 643/1784 [51:32<47:26, 2.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:54,719 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▉ | 644/1784 [51:34<44:58, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:56,700 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▉ | 644/1784 [51:34<44:58, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:56,700 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▉ | 645/1784 [51:36<42:20, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:58,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▉ | 645/1784 [51:36<42:20, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:36:58,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▉ | 646/1784 [51:37<39:24, 2.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:00,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|████████████████████████████▉ | 646/1784 [51:37<39:24, 2.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:00,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████ | 648/1784 [51:40<34:13, 1.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:01,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████ | 648/1784 [51:40<34:13, 1.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:01,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 8.5368, 'learning_rate': 0.0008862928348909658, 'epoch': 0.36} 36%|█████████████████████████████ | 649/1784 [51:42<31:39, 1.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:04,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████ | 649/1784 [51:42<31:39, 1.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:04,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▏ | 650/1784 [51:44<32:34, 1.72s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:04,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▏ | 650/1784 [51:44<32:34, 1.72s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▏ | 650/1784 [51:44<32:34, 1.72s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▏ | 651/1784 [51:48<45:37, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▏ | 651/1784 [51:48<45:37, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▏ | 651/1784 [51:48<45:37, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████▏ | 652/1784 [51:51<53:42, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:37:17,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:37:17,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5281, 'learning_rate': 0.000882398753894081, 'epoch': 0.37} 37%|████████████████████████████▌ | 654/1784 [51:59<1:02:43, 3.33s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▌ | 654/1784 [51:59<1:02:43, 3.33s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5034, 'learning_rate': 0.000881619937694704, 'epoch': 0.37} 37%|████████████████████████████▋ | 655/1784 [52:03<1:04:56, 3.45s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▋ | 655/1784 [52:03<1:04:56, 3.45s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4803, 'learning_rate': 0.0008808411214953271, 'epoch': 0.37} 37%|████████████████████████████▋ | 656/1784 [52:06<1:06:20, 3.53s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▋ | 656/1784 [52:06<1:06:20, 3.53s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3844, 'learning_rate': 0.0008800623052959502, 'epoch': 0.37} 37%|████████████████████████████▋ | 656/1784 [52:06<1:06:20, 3.53s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▋ | 657/1784 [52:10<1:07:01, 3.57s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▋ | 657/1784 [52:10<1:07:01, 3.57s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▋ | 657/1784 [52:10<1:07:01, 3.57s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▊ | 658/1784 [52:14<1:07:34, 3.60s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:37:39,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:37:39,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7949, 'learning_rate': 0.0008777258566978193, 'epoch': 0.37} 37%|████████████████████████████▊ | 660/1784 [52:21<1:07:51, 3.62s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▊ | 660/1784 [52:21<1:07:51, 3.62s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5483, 'learning_rate': 0.0008769470404984425, 'epoch': 0.37} 37%|████████████████████████████▊ | 660/1784 [52:21<1:07:51, 3.62s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▉ | 661/1784 [52:25<1:07:34, 3.61s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▉ | 661/1784 [52:25<1:07:34, 3.61s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▉ | 661/1784 [52:25<1:07:34, 3.61s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|████████████████████████████▉ | 662/1784 [52:28<1:07:16, 3.60s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:37:53,878 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:37:53,878 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5422, 'learning_rate': 0.0008746105919003116, 'epoch': 0.37} 37%|█████████████████████████████ | 664/1784 [52:35<1:06:54, 3.58s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████ | 664/1784 [52:35<1:06:54, 3.58s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7667, 'learning_rate': 0.0008738317757009346, 'epoch': 0.37} 37%|█████████████████████████████ | 665/1784 [52:39<1:06:52, 3.59s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████ | 665/1784 [52:39<1:06:52, 3.59s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3402, 'learning_rate': 0.0008730529595015576, 'epoch': 0.37} 37%|█████████████████████████████ | 665/1784 [52:39<1:06:52, 3.59s/it]g-point operations will not be computed-03 01:37:07,740 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████ | 666/1784 [52:43<1:06:36, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████▏ | 667/1784 [52:46<1:06:13, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████▏ | 667/1784 [52:46<1:06:13, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6818, 'learning_rate': 0.0008714953271028037, 'epoch': 0.37} 37%|█████████████████████████████▏ | 668/1784 [52:50<1:06:05, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|█████████████████████████████▏ | 668/1784 [52:50<1:06:05, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.969, 'learning_rate': 0.0008707165109034269, 'epoch': 0.37} 37%|█████████████████████████████▏ | 668/1784 [52:50<1:06:05, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▎ | 669/1784 [52:53<1:05:29, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▎ | 669/1784 [52:53<1:05:29, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▎ | 669/1784 [52:53<1:05:29, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:06,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▎ | 670/1784 [52:57<1:05:05, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▎ | 671/1784 [53:00<1:04:46, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▎ | 671/1784 [53:00<1:04:46, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6812, 'learning_rate': 0.000868380062305296, 'epoch': 0.38} 38%|█████████████████████████████▎ | 671/1784 [53:00<1:04:46, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▍ | 672/1784 [53:03<1:04:22, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:38:28,940 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:38:28,940 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.357, 'learning_rate': 0.0008668224299065421, 'epoch': 0.38} 38%|█████████████████████████████▍ | 674/1784 [53:10<1:03:46, 3.45s/it]g-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▍ | 674/1784 [53:10<1:03:46, 3.45s/it]g-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2617, 'learning_rate': 0.0008660436137071651, 'epoch': 0.38} 38%|█████████████████████████████▌ | 675/1784 [53:14<1:03:30, 3.44s/it]g-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▌ | 675/1784 [53:14<1:03:30, 3.44s/it]g-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.0633, 'learning_rate': 0.0008652647975077882, 'epoch': 0.38} 38%|█████████████████████████████▌ | 675/1784 [53:14<1:03:30, 3.44s/it]g-point operations will not be computed-03 01:38:20,407 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▌ | 676/1784 [53:17<1:02:55, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▌ | 677/1784 [53:20<1:02:40, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▌ | 677/1784 [53:20<1:02:40, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2393, 'learning_rate': 0.0008637071651090342, 'epoch': 0.38} 38%|█████████████████████████████▌ | 677/1784 [53:20<1:02:40, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▋ | 678/1784 [53:24<1:02:07, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:38:49,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:38:49,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.9874, 'learning_rate': 0.0008621495327102804, 'epoch': 0.38} [WARNING|modeling_utils.py:388] 2022-03-03 01:38:49,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|█████████████████████████████▋ | 680/1784 [53:30<1:00:55, 3.31s/it]g-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:38:55,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:38:55,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5351, 'learning_rate': 0.0008605919003115265, 'epoch': 0.38} 38%|██████████████████████████████▌ | 682/1784 [53:37<59:36, 3.25s/it]g-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▌ | 682/1784 [53:37<59:36, 3.25s/it]g-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:01,840 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:01,840 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6922, 'learning_rate': 0.0008590342679127726, 'epoch': 0.38} [WARNING|modeling_utils.py:388] 2022-03-03 01:39:04,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:04,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6893, 'learning_rate': 0.0008582554517133957, 'epoch': 0.38} [WARNING|modeling_utils.py:388] 2022-03-03 01:39:04,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:38:40,830 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▋ | 685/1784 [53:46<57:16, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▊ | 686/1784 [53:49<56:19, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▊ | 686/1784 [53:49<56:19, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:13,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:13,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.3004, 'learning_rate': 0.0008559190031152648, 'epoch': 0.39} 39%|██████████████████████████████▊ | 688/1784 [53:55<54:22, 2.98s/it]g-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|██████████████████████████████▊ | 688/1784 [53:55<54:22, 2.98s/it]g-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:19,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:19,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:22,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:22,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4185, 'learning_rate': 0.000853582554517134, 'epoch': 0.39} [WARNING|modeling_utils.py:388] 2022-03-03 01:39:22,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:09,450 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|██████████████████████████████▉ | 691/1784 [54:02<49:59, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████ | 692/1784 [54:05<48:23, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████ | 692/1784 [54:05<48:23, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:29,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:29,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:31,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:31,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:33,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:33,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4339, 'learning_rate': 0.0008496884735202493, 'epoch': 0.39} [WARNING|modeling_utils.py:388] 2022-03-03 01:39:34,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:34,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:37,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:37,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3447, 'learning_rate': 0.0008473520249221184, 'epoch': 0.39} [WARNING|modeling_utils.py:388] 2022-03-03 01:39:38,981 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:38,981 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:40,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:40,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:40,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:44,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:48,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:39:48,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.43, 'learning_rate': 0.0008442367601246106, 'epoch': 0.39} 39%|███████████████████████████████▌ | 703/1784 [54:30<55:25, 3.08s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████▌ | 703/1784 [54:30<55:25, 3.08s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.3139, 'learning_rate': 0.0008434579439252337, 'epoch': 0.39} 39%|███████████████████████████████▌ | 704/1784 [54:34<58:56, 3.27s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████▌ | 704/1784 [54:34<58:56, 3.27s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.924, 'learning_rate': 0.0008426791277258567, 'epoch': 0.39} 40%|██████████████████████████████▊ | 705/1784 [54:38<1:01:25, 3.42s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|██████████████████████████████▊ | 705/1784 [54:38<1:01:25, 3.42s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.0024, 'learning_rate': 0.0008419003115264798, 'epoch': 0.4} 40%|██████████████████████████████▊ | 706/1784 [54:41<1:02:34, 3.48s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|██████████████████████████████▊ | 706/1784 [54:41<1:02:34, 3.48s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.9137, 'learning_rate': 0.0008411214953271028, 'epoch': 0.4} 40%|██████████████████████████████▊ | 706/1784 [54:41<1:02:34, 3.48s/it]g-point operations will not be computed-03 01:39:25,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|██████████████████████████████▉ | 707/1784 [54:45<1:03:10, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|██████████████████████████████▉ | 708/1784 [54:49<1:03:22, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|██████████████████████████████▉ | 708/1784 [54:49<1:03:22, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.769, 'learning_rate': 0.000839563862928349, 'epoch': 0.4} 40%|██████████████████████████████▉ | 709/1784 [54:52<1:03:49, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|██████████████████████████████▉ | 709/1784 [54:52<1:03:49, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.0759, 'learning_rate': 0.0008387850467289719, 'epoch': 0.4} 40%|███████████████████████████████ | 710/1784 [54:56<1:03:24, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████ | 710/1784 [54:56<1:03:24, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:21,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:21,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.0019, 'learning_rate': 0.0008372274143302181, 'epoch': 0.4} 40%|███████████████████████████████▏ | 712/1784 [55:03<1:03:07, 3.53s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▏ | 712/1784 [55:03<1:03:07, 3.53s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7339, 'learning_rate': 0.0008364485981308411, 'epoch': 0.4} 40%|███████████████████████████████▏ | 713/1784 [55:06<1:03:05, 3.53s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▏ | 713/1784 [55:06<1:03:05, 3.53s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.09, 'learning_rate': 0.0008348909657320872, 'epoch': 0.4} [WARNING|modeling_utils.py:388] 2022-03-03 01:40:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 715/1784 [55:13<1:02:42, 3.52s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 715/1784 [55:13<1:02:42, 3.52s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 715/1784 [55:13<1:02:42, 3.52s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 716/1784 [55:17<1:02:19, 3.50s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 716/1784 [55:17<1:02:19, 3.50s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 717/1784 [55:20<1:02:12, 3.50s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▎ | 717/1784 [55:20<1:02:12, 3.50s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:45,828 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:45,828 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.4586, 'learning_rate': 0.0008317757009345795, 'epoch': 0.4} 40%|███████████████████████████████▍ | 719/1784 [55:27<1:01:49, 3.48s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▍ | 719/1784 [55:27<1:01:49, 3.48s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 127.5589, 'learning_rate': 0.0008317757009345795, 'epoch': 0.4} 40%|███████████████████████████████▍ | 720/1784 [55:31<1:01:06, 3.45s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▍ | 720/1784 [55:31<1:01:06, 3.45s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:56,064 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:56,064 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:40:56,064 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▌ | 722/1784 [55:37<1:01:22, 3.47s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|███████████████████████████████▌ | 722/1784 [55:37<1:01:22, 3.47s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.304, 'learning_rate': 0.0008302180685358256, 'epoch': 0.4} 41%|███████████████████████████████▌ | 723/1784 [55:41<1:00:27, 3.42s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|███████████████████████████████▌ | 723/1784 [55:41<1:00:27, 3.42s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:06,259 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:06,259 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 8.2908, 'learning_rate': 0.0008286604361370716, 'epoch': 0.41} 41%|████████████████████████████████▌ | 725/1784 [55:47<59:00, 3.34s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▌ | 725/1784 [55:47<59:00, 3.34s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:12,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:12,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 362.119, 'learning_rate': 0.0008286604361370716, 'epoch': 0.41} [WARNING|modeling_utils.py:388] 2022-03-03 01:41:12,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▌ | 727/1784 [55:54<57:48, 3.28s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▌ | 727/1784 [55:54<57:48, 3.28s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▌ | 727/1784 [55:54<57:48, 3.28s/it]g-point operations will not be computed-03 01:40:08,866 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 728/1784 [55:57<57:32, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 728/1784 [55:57<57:32, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 729/1784 [56:00<57:23, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 729/1784 [56:00<57:23, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 729/1784 [56:00<57:23, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 730/1784 [56:03<56:58, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▋ | 730/1784 [56:03<56:58, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:28,783 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:28,783 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:28,783 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▊ | 732/1784 [56:10<56:12, 3.21s/it]g-point operations will not be computed-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▊ | 732/1784 [56:10<56:12, 3.21s/it]g-point operations will not be computed-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▊ | 732/1784 [56:10<56:12, 3.21s/it]g-point operations will not be computed-03 01:41:20,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▊ | 733/1784 [56:13<55:31, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▊ | 733/1784 [56:13<55:31, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▉ | 734/1784 [56:16<54:49, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|████████████████████████████████▉ | 734/1784 [56:16<54:49, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:41,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:41,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:41,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████ | 736/1784 [56:22<53:15, 3.05s/it]g-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████ | 736/1784 [56:22<53:15, 3.05s/it]g-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:46,891 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:46,891 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:46,891 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:36,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████ | 738/1784 [56:28<51:11, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:51,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████ | 738/1784 [56:28<51:11, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:51,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▏ | 739/1784 [56:30<50:01, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:51,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:55,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:51,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:41:55,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:51,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.8709, 'learning_rate': 0.0008177570093457944, 'epoch': 0.41} [WARNING|modeling_utils.py:388] 2022-03-03 01:41:55,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:41:51,083 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▏ | 741/1784 [56:36<47:42, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:58,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▏ | 741/1784 [56:36<47:42, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:41:58,962 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▎ | 742/1784 [56:38<46:12, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▎ | 742/1784 [56:38<46:12, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▎ | 743/1784 [56:40<44:10, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▎ | 743/1784 [56:40<44:10, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:04,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:04,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:06,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:06,607 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:08,414 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:08,414 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 68.4556, 'learning_rate': 0.0008146417445482867, 'epoch': 0.42} [WARNING|modeling_utils.py:388] 2022-03-03 01:42:11,299 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:11,299 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:12,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:12,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:14,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:14,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:14,541 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:18,563 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:18,563 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:18,563 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▋ | 752/1784 [57:00<48:29, 2.82s/it]g-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▋ | 752/1784 [57:00<48:29, 2.82s/it]g-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▋ | 752/1784 [57:00<48:29, 2.82s/it]g-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 753/1784 [57:04<53:27, 3.11s/it]g-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 753/1784 [57:04<53:27, 3.11s/it]g-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 753/1784 [57:04<53:27, 3.11s/it]g-point operations will not be computed-03 01:42:01,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 754/1784 [57:08<56:56, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 754/1784 [57:08<56:56, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 755/1784 [57:12<59:13, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 755/1784 [57:12<59:13, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▊ | 755/1784 [57:12<59:13, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████ | 756/1784 [57:15<1:00:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████ | 756/1784 [57:15<1:00:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████ | 756/1784 [57:15<1:00:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████ | 757/1784 [57:19<1:01:23, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████ | 757/1784 [57:19<1:01:23, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████ | 757/1784 [57:19<1:01:23, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▏ | 758/1784 [57:23<1:01:35, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▏ | 758/1784 [57:23<1:01:35, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|█████████████████████████████████▏ | 758/1784 [57:23<1:01:35, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▏ | 759/1784 [57:26<1:02:05, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:52,161 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:42:52,161 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.2027, 'learning_rate': 0.0008052959501557632, 'epoch': 0.43} 43%|█████████████████████████████████▎ | 761/1784 [57:34<1:02:11, 3.65s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 761/1784 [57:34<1:02:11, 3.65s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 96.2049, 'learning_rate': 0.0008045171339563863, 'epoch': 0.43} 43%|█████████████████████████████████▎ | 761/1784 [57:34<1:02:11, 3.65s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 762/1784 [57:37<1:02:10, 3.65s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 762/1784 [57:37<1:02:10, 3.65s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 762/1784 [57:37<1:02:10, 3.65s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 763/1784 [57:41<1:01:52, 3.64s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 763/1784 [57:41<1:01:52, 3.64s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 763/1784 [57:41<1:01:52, 3.64s/it]g-point operations will not be computed-03 01:42:31,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 764/1784 [57:45<1:01:36, 3.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 764/1784 [57:45<1:01:36, 3.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 765/1784 [57:48<1:01:11, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 765/1784 [57:48<1:01:11, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 765/1784 [57:48<1:01:11, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 766/1784 [57:52<1:00:26, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 766/1784 [57:52<1:00:26, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 766/1784 [57:52<1:00:26, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▍ | 767/1784 [57:55<59:44, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:20,609 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:20,609 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.8516, 'learning_rate': 0.0007990654205607477, 'epoch': 0.43} [WARNING|modeling_utils.py:388] 2022-03-03 01:43:20,609 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▍ | 769/1784 [58:02<59:30, 3.52s/it]g-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▍ | 769/1784 [58:02<59:30, 3.52s/it]g-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▍ | 769/1784 [58:02<59:30, 3.52s/it]g-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 770/1784 [58:06<59:06, 3.50s/it]g-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 770/1784 [58:06<59:06, 3.50s/it]g-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 770/1784 [58:06<59:06, 3.50s/it]g-point operations will not be computed-03 01:43:08,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 771/1784 [58:09<58:40, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 771/1784 [58:09<58:40, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 772/1784 [58:12<58:33, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 772/1784 [58:12<58:33, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▌ | 772/1784 [58:12<58:33, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▋ | 773/1784 [58:16<58:16, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:41,301 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:41,301 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.7233, 'learning_rate': 0.000794392523364486, 'epoch': 0.43} 43%|██████████████████████████████████▊ | 775/1784 [58:23<57:48, 3.44s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▊ | 775/1784 [58:23<57:48, 3.44s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.9973, 'learning_rate': 0.000793613707165109, 'epoch': 0.43} 43%|██████████████████████████████████▊ | 775/1784 [58:23<57:48, 3.44s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▊ | 776/1784 [58:26<57:13, 3.41s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:51,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:51,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.405, 'learning_rate': 0.0007920560747663551, 'epoch': 0.44} [WARNING|modeling_utils.py:388] 2022-03-03 01:43:51,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 778/1784 [58:33<55:50, 3.33s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:57,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:43:57,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.3522, 'learning_rate': 0.0007904984423676013, 'epoch': 0.44} 44%|██████████████████████████████████▉ | 780/1784 [58:39<55:02, 3.29s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 780/1784 [58:39<55:02, 3.29s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.1215, 'learning_rate': 0.0007897196261682244, 'epoch': 0.44} 44%|██████████████████████████████████▉ | 780/1784 [58:39<55:02, 3.29s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 781/1784 [58:42<54:28, 3.26s/it]g-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:07,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:07,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.6109, 'learning_rate': 0.0007881619937694704, 'epoch': 0.44} [WARNING|modeling_utils.py:388] 2022-03-03 01:44:07,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:43:32,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 783/1784 [58:48<53:18, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:12,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 784/1784 [58:51<52:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:12,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 784/1784 [58:51<52:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:12,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.2217, 'learning_rate': 0.0007866043613707165, 'epoch': 0.44} 44%|███████████████████████████████████▏ | 784/1784 [58:51<52:08, 3.13s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:12,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 785/1784 [58:54<51:12, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:18,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 786/1784 [58:57<50:19, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:18,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 786/1784 [58:57<50:19, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:18,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:22,235 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:18,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:22,235 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:18,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.2222, 'learning_rate': 0.0007842679127725857, 'epoch': 0.44} [WARNING|modeling_utils.py:388] 2022-03-03 01:44:22,235 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:18,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 788/1784 [59:03<48:23, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:26,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 789/1784 [59:06<46:54, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:26,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 789/1784 [59:06<46:54, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:26,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:30,278 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:26,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:30,278 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:26,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.2519, 'learning_rate': 0.0007819314641744549, 'epoch': 0.44} [WARNING|modeling_utils.py:388] 2022-03-03 01:44:30,278 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:26,383 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 791/1784 [59:11<44:37, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:34,066 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 791/1784 [59:11<44:37, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:34,066 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 792/1784 [59:13<42:59, 2.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 792/1784 [59:13<42:59, 2.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 793/1784 [59:15<41:12, 2.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 793/1784 [59:15<41:12, 2.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:39,561 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:39,561 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:41,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:41,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:43,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:43,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:46,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:46,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:47,654 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:47,654 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:49,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:49,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8895, 'learning_rate': 0.0007741433021806855, 'epoch': 0.45} [WARNING|modeling_utils.py:388] 2022-03-03 01:44:49,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:53,601 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:53,601 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:44:53,601 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 802/1784 [59:35<46:56, 2.87s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 802/1784 [59:35<46:56, 2.87s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 802/1784 [59:35<46:56, 2.87s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████ | 803/1784 [59:39<51:42, 3.16s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████ | 803/1784 [59:39<51:42, 3.16s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████ | 803/1784 [59:39<51:42, 3.16s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████ | 804/1784 [59:43<54:42, 3.35s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:08,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:08,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:12,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:12,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.9224, 'learning_rate': 0.0007694704049844237, 'epoch': 0.45} [WARNING|modeling_utils.py:388] 2022-03-03 01:45:12,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 807/1784 [59:54<58:29, 3.59s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 807/1784 [59:54<58:29, 3.59s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 807/1784 [59:54<58:29, 3.59s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 808/1784 [59:58<58:40, 3.61s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 808/1784 [59:58<58:40, 3.61s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 808/1784 [59:58<58:40, 3.61s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▎ | 809/1784 [1:00:02<58:41, 3.61s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:27,261 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:27,261 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8922, 'learning_rate': 0.0007663551401869159, 'epoch': 0.45} 45%|███████████████████████████████████▍ | 811/1784 [1:00:09<58:20, 3.60s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▍ | 811/1784 [1:00:09<58:20, 3.60s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4932, 'learning_rate': 0.000765576323987539, 'epoch': 0.45} 45%|███████████████████████████████████▍ | 811/1784 [1:00:09<58:20, 3.60s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▌ | 812/1784 [1:00:12<58:02, 3.58s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▌ | 812/1784 [1:00:12<58:02, 3.58s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▌ | 812/1784 [1:00:12<58:02, 3.58s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▌ | 813/1784 [1:00:16<57:47, 3.57s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:41,436 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:41,436 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3238, 'learning_rate': 0.0007632398753894081, 'epoch': 0.46} 46%|███████████████████████████████████▋ | 815/1784 [1:00:23<57:10, 3.54s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▋ | 815/1784 [1:00:23<57:10, 3.54s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6348, 'learning_rate': 0.0007624610591900312, 'epoch': 0.46} 46%|███████████████████████████████████▋ | 815/1784 [1:00:23<57:10, 3.54s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▋ | 816/1784 [1:00:26<56:46, 3.52s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:51,901 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:45:51,901 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8736, 'learning_rate': 0.0007609034267912772, 'epoch': 0.46} 46%|███████████████████████████████████▊ | 818/1784 [1:00:33<57:13, 3.55s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▊ | 818/1784 [1:00:33<57:13, 3.55s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.684, 'learning_rate': 0.0007601246105919003, 'epoch': 0.46} 46%|███████████████████████████████████▊ | 819/1784 [1:00:37<56:39, 3.52s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▊ | 819/1784 [1:00:37<56:39, 3.52s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:02,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:02,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5375, 'learning_rate': 0.0007585669781931465, 'epoch': 0.46} 46%|███████████████████████████████████▉ | 821/1784 [1:00:44<55:51, 3.48s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▉ | 821/1784 [1:00:44<55:51, 3.48s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5663, 'learning_rate': 0.0007577881619937694, 'epoch': 0.46} 46%|███████████████████████████████████▉ | 822/1784 [1:00:47<55:26, 3.46s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▉ | 822/1784 [1:00:47<55:26, 3.46s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 28.2445, 'learning_rate': 0.0007570093457943925, 'epoch': 0.46} 46%|███████████████████████████████████▉ | 822/1784 [1:00:47<55:26, 3.46s/it]g-point operations will not be computed-03 01:44:36,385 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|███████████████████████████████████▉ | 823/1784 [1:00:51<54:50, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████ | 824/1784 [1:00:54<54:21, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████ | 824/1784 [1:00:54<54:21, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7559, 'learning_rate': 0.0007554517133956387, 'epoch': 0.46} 46%|████████████████████████████████████ | 824/1784 [1:00:54<54:21, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████ | 825/1784 [1:00:57<53:54, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:22,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:22,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5401, 'learning_rate': 0.0007538940809968847, 'epoch': 0.46} 46%|████████████████████████████████████▏ | 827/1784 [1:01:04<53:18, 3.34s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▏ | 827/1784 [1:01:04<53:18, 3.34s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8127, 'learning_rate': 0.0007531152647975078, 'epoch': 0.46} 46%|████████████████████████████████████▏ | 827/1784 [1:01:04<53:18, 3.34s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▏ | 828/1784 [1:01:07<52:57, 3.32s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:32,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:32,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7264, 'learning_rate': 0.0007515576323987538, 'epoch': 0.46} 47%|████████████████████████████████████▎ | 830/1784 [1:01:14<52:20, 3.29s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▎ | 830/1784 [1:01:14<52:20, 3.29s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:38,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:38,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8572, 'learning_rate': 0.00075, 'epoch': 0.47} 47%|████████████████████████████████████▍ | 832/1784 [1:01:20<51:28, 3.24s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▍ | 832/1784 [1:01:20<51:28, 3.24s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:45,264 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:45,264 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6782, 'learning_rate': 0.0007484423676012462, 'epoch': 0.47} 47%|████████████████████████████████████▍ | 834/1784 [1:01:26<50:58, 3.22s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▍ | 834/1784 [1:01:26<50:58, 3.22s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:51,621 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:51,621 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3408, 'learning_rate': 0.0007468847352024923, 'epoch': 0.47} 47%|████████████████████████████████████▌ | 836/1784 [1:01:33<49:21, 3.12s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▌ | 836/1784 [1:01:33<49:21, 3.12s/it]g-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:57,535 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:46:57,535 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:46:14,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5262, 'learning_rate': 0.0007453271028037383, 'epoch': 0.47} 47%|████████████████████████████████████▋ | 838/1784 [1:01:38<47:50, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:01,986 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▋ | 838/1784 [1:01:38<47:50, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:01,986 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▋ | 839/1784 [1:01:41<46:50, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:01,986 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▋ | 839/1784 [1:01:41<46:50, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:01,986 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:06,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:01,986 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:06,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:01,986 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8701, 'learning_rate': 0.0007429906542056076, 'epoch': 0.47} 47%|████████████████████████████████████▊ | 841/1784 [1:01:47<44:26, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▊ | 841/1784 [1:01:47<44:26, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▊ | 842/1784 [1:01:49<43:01, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|████████████████████████████████████▊ | 842/1784 [1:01:49<43:01, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:13,536 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:13,536 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:15,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:15,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:17,783 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:17,783 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:19,655 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:19,655 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:21,389 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:21,389 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3203, 'learning_rate': 0.0007375389408099688, 'epoch': 0.47} [WARNING|modeling_utils.py:388] 2022-03-03 01:47:24,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:24,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:25,880 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:25,880 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.4499, 'learning_rate': 0.000735202492211838, 'epoch': 0.48} [WARNING|modeling_utils.py:388] 2022-03-03 01:47:29,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:47:29,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.6898, 'learning_rate': 0.0007344236760124611, 'epoch': 0.48} 48%|█████████████████████████████████████▎ | 852/1784 [1:02:12<44:17, 2.85s/it]g-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▎ | 852/1784 [1:02:12<44:17, 2.85s/it]g-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1893, 'learning_rate': 0.0007336448598130841, 'epoch': 0.48} 48%|█████████████████████████████████████▎ | 853/1784 [1:02:15<48:34, 3.13s/it]g-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▎ | 853/1784 [1:02:15<48:34, 3.13s/it]g-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7563, 'learning_rate': 0.0007328660436137072, 'epoch': 0.48} 48%|█████████████████████████████████████▎ | 854/1784 [1:02:19<51:29, 3.32s/it]g-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▎ | 854/1784 [1:02:19<51:29, 3.32s/it]g-point operations will not be computed-03 01:47:10,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6705, 'learning_rate': 0.0007320872274143302, 'epoch': 0.48} 48%|█████████████████████████████████████▍ | 855/1784 [1:02:23<52:58, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▍ | 855/1784 [1:02:23<52:58, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▍ | 856/1784 [1:02:27<54:17, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▍ | 856/1784 [1:02:27<54:17, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7006, 'learning_rate': 0.0007305295950155764, 'epoch': 0.48} 48%|█████████████████████████████████████▍ | 857/1784 [1:02:30<55:12, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▍ | 857/1784 [1:02:30<55:12, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4542, 'learning_rate': 0.0007297507788161994, 'epoch': 0.48} 48%|█████████████████████████████████████▌ | 858/1784 [1:02:34<55:25, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▌ | 858/1784 [1:02:34<55:25, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6944, 'learning_rate': 0.0007289719626168224, 'epoch': 0.48} 48%|█████████████████████████████████████▌ | 859/1784 [1:02:38<55:26, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▌ | 859/1784 [1:02:38<55:26, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5975, 'learning_rate': 0.0007281931464174455, 'epoch': 0.48} 48%|█████████████████████████████████████▌ | 859/1784 [1:02:38<55:26, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:47:46,906 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▌ | 860/1784 [1:02:41<55:27, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▋ | 861/1784 [1:02:45<55:32, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▋ | 861/1784 [1:02:45<55:32, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.172, 'learning_rate': 0.0007266355140186916, 'epoch': 0.48} 48%|█████████████████████████████████████▋ | 862/1784 [1:02:48<55:13, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▋ | 862/1784 [1:02:48<55:13, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.32, 'learning_rate': 0.0007258566978193146, 'epoch': 0.48} 48%|█████████████████████████████████████▋ | 863/1784 [1:02:52<55:03, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▋ | 863/1784 [1:02:52<55:03, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:17,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:17,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2023, 'learning_rate': 0.0007242990654205608, 'epoch': 0.48} 48%|█████████████████████████████████████▊ | 865/1784 [1:02:59<54:29, 3.56s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|█████████████████████████████████████▊ | 865/1784 [1:02:59<54:29, 3.56s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.2759, 'learning_rate': 0.0007235202492211839, 'epoch': 0.48} 49%|█████████████████████████████████████▊ | 866/1784 [1:03:03<54:16, 3.55s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|█████████████████████████████████████▊ | 866/1784 [1:03:03<54:16, 3.55s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6983, 'learning_rate': 0.0007227414330218068, 'epoch': 0.49} 49%|█████████████████████████████████████▊ | 866/1784 [1:03:03<54:16, 3.55s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|█████████████████████████████████████▉ | 867/1784 [1:03:06<53:54, 3.53s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:31,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:31,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6701, 'learning_rate': 0.000721183800623053, 'epoch': 0.49} 49%|█████████████████████████████████████▉ | 869/1784 [1:03:13<52:59, 3.48s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|█████████████████████████████████████▉ | 869/1784 [1:03:13<52:59, 3.48s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5527, 'learning_rate': 0.000720404984423676, 'epoch': 0.49} 49%|██████████████████████████████████████ | 870/1784 [1:03:16<52:38, 3.46s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████ | 870/1784 [1:03:16<52:38, 3.46s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:41,737 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:41,737 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5059, 'learning_rate': 0.0007188473520249221, 'epoch': 0.49} 49%|██████████████████████████████████████▏ | 872/1784 [1:03:23<51:55, 3.42s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▏ | 872/1784 [1:03:23<51:55, 3.42s/it]g-point operations will not be computed-03 01:48:05,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5104, 'learning_rate': 0.0007180685358255452, 'epoch': 0.49} 49%|██████████████████████████████████████▏ | 873/1784 [1:03:26<51:33, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▏ | 873/1784 [1:03:26<51:33, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▏ | 874/1784 [1:03:30<51:02, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▏ | 874/1784 [1:03:30<51:02, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3712, 'learning_rate': 0.0007165109034267912, 'epoch': 0.49} 49%|██████████████████████████████████████▎ | 875/1784 [1:03:33<50:26, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▎ | 875/1784 [1:03:33<50:26, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:58,266 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:48:58,266 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.617, 'learning_rate': 0.0007149532710280374, 'epoch': 0.49} 49%|██████████████████████████████████████▎ | 877/1784 [1:03:39<49:34, 3.28s/it]g-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▎ | 877/1784 [1:03:39<49:34, 3.28s/it]g-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:04,681 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:04,681 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:04,681 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▍ | 879/1784 [1:03:46<48:45, 3.23s/it]g-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▍ | 879/1784 [1:03:46<48:45, 3.23s/it]g-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3048, 'learning_rate': 0.0007126168224299065, 'epoch': 0.49} 49%|██████████████████████████████████████▍ | 879/1784 [1:03:46<48:45, 3.23s/it]g-point operations will not be computed-03 01:48:50,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▍ | 880/1784 [1:03:49<48:37, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▍ | 880/1784 [1:03:49<48:37, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▌ | 881/1784 [1:03:52<48:08, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▌ | 881/1784 [1:03:52<48:08, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:12,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▌ | 882/1784 [1:03:55<47:51, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:18,952 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▌ | 882/1784 [1:03:55<47:51, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:18,952 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▌ | 883/1784 [1:03:58<47:25, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:18,952 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|██████████████████████████████████████▌ | 883/1784 [1:03:58<47:25, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:18,952 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7107, 'learning_rate': 0.0007095015576323988, 'epoch': 0.49} 49%|██████████████████████████████████████▌ | 883/1784 [1:03:58<47:25, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:18,952 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▋ | 884/1784 [1:04:01<46:29, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▋ | 884/1784 [1:04:01<46:29, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▋ | 885/1784 [1:04:04<45:57, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▋ | 885/1784 [1:04:04<45:57, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:29,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:29,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:29,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▊ | 887/1784 [1:04:10<44:29, 2.98s/it]g-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▊ | 887/1784 [1:04:10<44:29, 2.98s/it]g-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:35,036 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:37,720 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:37,720 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6177, 'learning_rate': 0.0007048286604361371, 'epoch': 0.5} [WARNING|modeling_utils.py:388] 2022-03-03 01:49:37,720 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:24,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▉ | 890/1784 [1:04:18<41:33, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▉ | 890/1784 [1:04:18<41:33, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▉ | 891/1784 [1:04:21<40:14, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|██████████████████████████████████████▉ | 891/1784 [1:04:21<40:14, 2.70s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:45,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:45,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:47,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:47,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:49,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:49,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:51,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:51,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:53,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:53,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:56,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:56,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 9.6362, 'learning_rate': 0.0006978193146417445, 'epoch': 0.5} [WARNING|modeling_utils.py:388] 2022-03-03 01:49:57,351 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:57,351 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:59,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:59,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:49:59,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:03,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:03,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:03,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▍ | 902/1784 [1:04:45<41:49, 2.85s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▍ | 902/1784 [1:04:45<41:49, 2.85s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▍ | 902/1784 [1:04:45<41:49, 2.85s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▍ | 903/1784 [1:04:49<45:43, 3.11s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▍ | 903/1784 [1:04:49<45:43, 3.11s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▍ | 903/1784 [1:04:49<45:43, 3.11s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 904/1784 [1:04:53<48:31, 3.31s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 904/1784 [1:04:53<48:31, 3.31s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 904/1784 [1:04:53<48:31, 3.31s/it]g-point operations will not be computed-03 01:49:41,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 905/1784 [1:04:56<49:58, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 905/1784 [1:04:56<49:58, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 906/1784 [1:05:00<51:18, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 906/1784 [1:05:00<51:18, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▌ | 906/1784 [1:05:00<51:18, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 907/1784 [1:05:04<52:07, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 907/1784 [1:05:04<52:07, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 907/1784 [1:05:04<52:07, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 908/1784 [1:05:07<52:26, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 908/1784 [1:05:07<52:26, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 908/1784 [1:05:07<52:26, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 909/1784 [1:05:11<52:41, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 909/1784 [1:05:11<52:41, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▋ | 909/1784 [1:05:11<52:41, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▊ | 910/1784 [1:05:15<52:46, 3.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▊ | 910/1784 [1:05:15<52:46, 3.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:40,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:40,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:40,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▊ | 912/1784 [1:05:22<52:12, 3.59s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▊ | 912/1784 [1:05:22<52:12, 3.59s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▊ | 912/1784 [1:05:22<52:12, 3.59s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▉ | 913/1784 [1:05:25<51:51, 3.57s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|███████████████████████████████████████▉ | 913/1784 [1:05:25<51:51, 3.57s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:50,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:50:50,795 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████ | 915/1784 [1:05:32<50:51, 3.51s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████ | 915/1784 [1:05:32<50:51, 3.51s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8981, 'learning_rate': 0.0006845794392523365, 'epoch': 0.51} 51%|████████████████████████████████████████ | 915/1784 [1:05:32<50:51, 3.51s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████ | 916/1784 [1:05:36<50:40, 3.50s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████ | 916/1784 [1:05:36<50:40, 3.50s/it]g-point operations will not be computed-03 01:50:20,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████ | 917/1784 [1:05:39<50:35, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████ | 917/1784 [1:05:39<50:35, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████▏ | 918/1784 [1:05:43<50:12, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|████████████████████████████████████████▏ | 918/1784 [1:05:43<50:12, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.4503, 'learning_rate': 0.0006822429906542056, 'epoch': 0.51} 52%|████████████████████████████████████████▏ | 919/1784 [1:05:46<50:01, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▏ | 919/1784 [1:05:46<50:01, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:11,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:11,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:11,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:14,937 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:14,937 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3855, 'learning_rate': 0.0006799065420560748, 'epoch': 0.52} 52%|████████████████████████████████████████▎ | 922/1784 [1:05:56<49:13, 3.43s/it]g-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▎ | 922/1784 [1:05:56<49:13, 3.43s/it]g-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7024, 'learning_rate': 0.0006791277258566978, 'epoch': 0.52} 52%|████████████████████████████████████████▎ | 922/1784 [1:05:56<49:13, 3.43s/it]g-point operations will not be computed-03 01:51:03,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▎ | 923/1784 [1:06:00<48:43, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▎ | 923/1784 [1:06:00<48:43, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▍ | 924/1784 [1:06:03<48:25, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▍ | 924/1784 [1:06:03<48:25, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▍ | 924/1784 [1:06:03<48:25, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▍ | 925/1784 [1:06:06<47:55, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:31,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:31,516 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8137, 'learning_rate': 0.00067601246105919, 'epoch': 0.52} 52%|████████████████████████████████████████▌ | 927/1784 [1:06:13<46:53, 3.28s/it]g-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▌ | 927/1784 [1:06:13<46:53, 3.28s/it]g-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:37,924 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:51:37,924 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.343, 'learning_rate': 0.0006744548286604362, 'epoch': 0.52} 52%|████████████████████████████████████████▌ | 929/1784 [1:06:19<46:10, 3.24s/it]g-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▌ | 929/1784 [1:06:19<46:10, 3.24s/it]g-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2121, 'learning_rate': 0.0006736760124610592, 'epoch': 0.52} 52%|████████████████████████████████████████▌ | 929/1784 [1:06:19<46:10, 3.24s/it]g-point operations will not be computed-03 01:51:23,395 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 930/1784 [1:06:22<45:52, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:45,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 930/1784 [1:06:22<45:52, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:45,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 931/1784 [1:06:25<45:27, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:45,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 931/1784 [1:06:25<45:27, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:45,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 931/1784 [1:06:25<45:27, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:45,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 932/1784 [1:06:29<45:14, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:52,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▋ | 932/1784 [1:06:29<45:14, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:52,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▊ | 933/1784 [1:06:32<44:40, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:52,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▊ | 933/1784 [1:06:32<44:40, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:52,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▊ | 933/1784 [1:06:32<44:40, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:52,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▊ | 934/1784 [1:06:35<43:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▊ | 934/1784 [1:06:35<43:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|████████████████████████████████████████▉ | 935/1784 [1:06:38<43:23, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:02,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:02,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5249, 'learning_rate': 0.0006682242990654206, 'epoch': 0.52} [WARNING|modeling_utils.py:388] 2022-03-03 01:52:02,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|████████████████████████████████████████▉ | 937/1784 [1:06:43<42:22, 3.00s/it]g-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|████████████████████████████████████████▉ | 937/1784 [1:06:43<42:22, 3.00s/it]g-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:08,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:08,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:08,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:51:58,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████ | 939/1784 [1:06:49<41:01, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████ | 939/1784 [1:06:49<41:01, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████ | 940/1784 [1:06:52<40:08, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████ | 940/1784 [1:06:52<40:08, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:16,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:16,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:16,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:12,605 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▏ | 943/1784 [1:06:59<35:33, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:20,134 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▏ | 943/1784 [1:06:59<35:33, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:20,134 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▎ | 944/1784 [1:07:01<33:28, 2.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:22,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▎ | 944/1784 [1:07:01<33:28, 2.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:22,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▎ | 945/1784 [1:07:03<31:14, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:24,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▎ | 945/1784 [1:07:03<31:14, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:24,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6919, 'learning_rate': 0.0006612149532710281, 'epoch': 0.53} 53%|█████████████████████████████████████████▎ | 946/1784 [1:07:05<28:56, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:25,980 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▎ | 946/1784 [1:07:05<28:56, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:25,980 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▍ | 947/1784 [1:07:06<26:48, 1.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:29,080 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▍ | 947/1784 [1:07:06<26:48, 1.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:29,080 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▍ | 949/1784 [1:07:09<22:21, 1.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:30,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▍ | 949/1784 [1:07:09<22:21, 1.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:30,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.5744, 'learning_rate': 0.0006580996884735203, 'epoch': 0.53} 53%|█████████████████████████████████████████▌ | 950/1784 [1:07:11<23:08, 1.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:31,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 950/1784 [1:07:11<23:08, 1.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:34,865 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 950/1784 [1:07:11<23:08, 1.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:34,865 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 951/1784 [1:07:15<32:46, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:34,865 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 951/1784 [1:07:15<32:46, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 951/1784 [1:07:15<32:46, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 952/1784 [1:07:19<38:59, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 952/1784 [1:07:19<38:59, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▌ | 952/1784 [1:07:19<38:59, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▋ | 953/1784 [1:07:22<42:54, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▋ | 953/1784 [1:07:22<42:54, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▋ | 953/1784 [1:07:22<42:54, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▋ | 954/1784 [1:07:26<45:35, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▋ | 954/1784 [1:07:26<45:35, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|█████████████████████████████████████████▋ | 954/1784 [1:07:26<45:35, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▊ | 955/1784 [1:07:30<47:25, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▊ | 955/1784 [1:07:30<47:25, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▊ | 955/1784 [1:07:30<47:25, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▊ | 956/1784 [1:07:34<48:39, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▊ | 956/1784 [1:07:34<48:39, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:59,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:59,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:52:59,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 958/1784 [1:07:41<49:57, 3.63s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 958/1784 [1:07:41<49:57, 3.63s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 958/1784 [1:07:41<49:57, 3.63s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 959/1784 [1:07:45<49:51, 3.63s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 959/1784 [1:07:45<49:51, 3.63s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 959/1784 [1:07:45<49:51, 3.63s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|█████████████████████████████████████████▉ | 960/1784 [1:07:48<50:07, 3.65s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:53:13,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:53:13,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2214, 'learning_rate': 0.0006487538940809969, 'epoch': 0.54} [WARNING|modeling_utils.py:388] 2022-03-03 01:53:13,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████ | 962/1784 [1:07:55<49:21, 3.60s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████ | 962/1784 [1:07:55<49:21, 3.60s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████ | 962/1784 [1:07:55<49:21, 3.60s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████ | 963/1784 [1:07:59<49:06, 3.59s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████ | 963/1784 [1:07:59<49:06, 3.59s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████ | 963/1784 [1:07:59<49:06, 3.59s/it]g-point operations will not be computed-03 01:52:38,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 964/1784 [1:08:03<48:41, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 964/1784 [1:08:03<48:41, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 965/1784 [1:08:06<48:23, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 965/1784 [1:08:06<48:23, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 965/1784 [1:08:06<48:23, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 966/1784 [1:08:10<48:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 966/1784 [1:08:10<48:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▏ | 966/1784 [1:08:10<48:06, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▎ | 967/1784 [1:08:13<47:56, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:53:38,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:53:38,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4088, 'learning_rate': 0.0006433021806853583, 'epoch': 0.54} [WARNING|modeling_utils.py:388] 2022-03-03 01:53:38,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▎ | 969/1784 [1:08:20<47:25, 3.49s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▎ | 969/1784 [1:08:20<47:25, 3.49s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▎ | 969/1784 [1:08:20<47:25, 3.49s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▍ | 970/1784 [1:08:23<47:14, 3.48s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:53:48,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:53:48,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3821, 'learning_rate': 0.0006409657320872274, 'epoch': 0.54} [WARNING|modeling_utils.py:388] 2022-03-03 01:53:48,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▍ | 972/1784 [1:08:30<46:20, 3.42s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▍ | 972/1784 [1:08:30<46:20, 3.42s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|██████████████████████████████████████████▍ | 972/1784 [1:08:30<46:20, 3.42s/it]g-point operations will not be computed-03 01:53:26,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▌ | 973/1784 [1:08:34<46:06, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▌ | 974/1784 [1:08:37<45:50, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▌ | 974/1784 [1:08:37<45:50, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.7089, 'learning_rate': 0.0006386292834890965, 'epoch': 0.55} 55%|██████████████████████████████████████████▌ | 974/1784 [1:08:37<45:50, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▋ | 975/1784 [1:08:40<45:28, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:05,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:05,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1485, 'learning_rate': 0.0006370716510903427, 'epoch': 0.55} 55%|██████████████████████████████████████████▋ | 977/1784 [1:08:47<44:35, 3.32s/it]g-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▋ | 977/1784 [1:08:47<44:35, 3.32s/it]g-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1073, 'learning_rate': 0.0006362928348909658, 'epoch': 0.55} 55%|██████████████████████████████████████████▋ | 977/1784 [1:08:47<44:35, 3.32s/it]g-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▊ | 978/1784 [1:08:50<44:13, 3.29s/it]g-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:15,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:15,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8938, 'learning_rate': 0.0006347352024922118, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-03-03 01:54:15,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▊ | 980/1784 [1:08:56<43:27, 3.24s/it]g-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:21,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:21,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0848, 'learning_rate': 0.000633177570093458, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-03-03 01:54:21,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|██████████████████████████████████████████▉ | 982/1784 [1:09:03<42:42, 3.19s/it]g-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:27,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:27,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6771, 'learning_rate': 0.000631619937694704, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-03-03 01:54:27,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:53:57,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████ | 984/1784 [1:09:09<41:13, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:32,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████ | 985/1784 [1:09:12<40:31, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:32,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████ | 985/1784 [1:09:12<40:31, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:32,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1484, 'learning_rate': 0.0006300623052959502, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 985/1784 [1:09:12<40:31, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:32,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████ | 986/1784 [1:09:14<39:59, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:38,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████▏ | 987/1784 [1:09:17<39:22, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:38,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████▏ | 987/1784 [1:09:17<39:22, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:38,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:42,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:54:38,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 01:54:42,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:54:38,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3653, 'learning_rate': 0.0006277258566978193, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-03-03 01:54:42,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 01:54:38,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████▏ | 989/1784 [1:09:23<36:58, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:46,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████▏ | 989/1784 [1:09:23<36:58, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:46,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|███████████████████████████████████████████▎ | 990/1784 [1:09:25<35:38, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:48,408 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▎ | 991/1784 [1:09:27<34:10, 2.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:50,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▎ | 991/1784 [1:09:27<34:10, 2.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:50,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▎ | 992/1784 [1:09:30<32:34, 2.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:52,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▎ | 992/1784 [1:09:30<32:34, 2.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:52,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▍ | 993/1784 [1:09:32<30:45, 2.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:54,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▍ | 993/1784 [1:09:32<30:45, 2.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:54,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▍ | 994/1784 [1:09:34<29:00, 2.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:56,575 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▍ | 994/1784 [1:09:34<29:00, 2.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:56,575 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8827, 'learning_rate': 0.0006230529595015575, 'epoch': 0.56} 56%|███████████████████████████████████████████▌ | 995/1784 [1:09:35<27:12, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:58,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▌ | 995/1784 [1:09:35<27:12, 2.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:58,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▌ | 997/1784 [1:09:38<23:26, 1.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:59,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▌ | 997/1784 [1:09:38<23:26, 1.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:54:59,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▋ | 998/1784 [1:09:40<21:33, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:55:02,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|███████████████████████████████████████████▋ | 998/1784 [1:09:40<21:33, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 01:55:02,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1309, 'learning_rate': 0.0006199376947040498, 'epoch': 0.56} [INFO|trainer.py:2366] 2022-03-03 01:55:04,984 >> Num examples = 2642 | 1000/1784 [1:09:43<21:06, 1.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:55:04,984 >> Num examples = 2642 | 1000/1784 [1:09:43<21:06, 1.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2015, 'learning_rate': 0.000618380062305296, 'epoch': 0.56} [INFO|trainer.py:2366] 2022-03-03 01:55:04,984 >> Num examples = 2642 | 1000/1784 [1:09:43<21:06, 1.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:55:04,984 >> Num examples = 2642 | 1000/1784 [1:09:43<21:06, 1.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 01:55:04,984 >> Num examples = 2642 | 1000/1784 [1:09:43<21:06, 1.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▎ | 5/331 [00:09<11:39, 2.15s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▌ | 6/331 [00:12<12:40, 2.34s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▊ | 7/331 [00:14<12:49, 2.37s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██ | 8/331 [00:17<13:17, 2.47s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▎ | 9/331 [00:20<13:46, 2.57s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▍ | 10/331 [00:23<14:38, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▋ | 11/331 [00:25<14:12, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▉ | 12/331 [00:28<14:08, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▏ | 13/331 [00:31<14:01, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▍ | 14/331 [00:33<13:55, 2.64s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▋ | 15/331 [00:37<15:08, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▉ | 16/331 [00:40<16:05, 3.07s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▏ | 17/331 [00:43<16:08, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▍ | 18/331 [00:46<14:49, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▋ | 19/331 [00:48<14:30, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▉ | 20/331 [00:50<13:38, 2.63s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▏ | 21/331 [00:53<14:08, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▍ | 22/331 [00:57<15:20, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▋ | 23/331 [01:01<16:38, 3.24s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▉ | 24/331 [01:05<17:40, 3.45s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▏ | 25/331 [01:08<17:03, 3.34s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▍ | 26/331 [01:10<15:48, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▋ | 27/331 [01:14<15:46, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▉ | 28/331 [01:16<15:21, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▏ | 29/331 [01:19<14:59, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▍ | 30/331 [01:22<14:19, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▋ | 31/331 [01:24<13:39, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▉ | 32/331 [01:27<13:27, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▏ | 33/331 [01:30<13:24, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▍ | 34/331 [01:32<13:14, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▋ | 35/331 [01:35<13:25, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▉ | 36/331 [01:38<14:04, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▏ | 37/331 [01:42<14:44, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▍ | 38/331 [01:45<15:05, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▋ | 39/331 [01:48<15:09, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▉ | 40/331 [01:50<14:01, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▏ | 41/331 [01:53<13:23, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▍ | 42/331 [01:56<14:18, 2.97s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▋ | 43/331 [02:00<14:57, 3.12s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▉ | 44/331 [02:03<15:24, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▏ | 45/331 [02:06<14:33, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▍ | 46/331 [02:08<13:29, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▋ | 47/331 [02:11<12:36, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▉ | 48/331 [02:13<12:46, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▏ | 49/331 [02:16<13:19, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▍ | 50/331 [02:19<13:11, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▋ | 51/331 [02:22<13:29, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▉ | 52/331 [02:25<12:53, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▏ | 53/331 [02:28<12:50, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▍ | 54/331 [02:30<12:10, 2.64s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▋ | 55/331 [02:33<13:09, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▊ | 56/331 [02:36<13:05, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████ | 57/331 [02:39<12:36, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▎ | 58/331 [02:42<13:08, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▌ | 59/331 [02:44<12:28, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▊ | 60/331 [02:47<12:14, 2.71s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████ | 61/331 [02:50<12:42, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▎ | 62/331 [02:53<12:36, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▌ | 63/331 [02:57<13:46, 3.08s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▊ | 64/331 [02:59<13:21, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████ | 65/331 [03:02<12:56, 2.92s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▎ | 66/331 [03:06<14:06, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▎ | 66/331 [03:06<14:06, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▎ | 66/331 [03:06<14:06, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▊ | 68/331 [03:13<14:53, 3.40s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████ | 69/331 [03:16<14:30, 3.32s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▎ | 70/331 [03:19<14:11, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▌ | 71/331 [03:23<14:13, 3.28s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▊ | 72/331 [03:26<14:07, 3.27s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████ | 73/331 [03:29<13:37, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▎ | 74/331 [03:32<13:22, 3.12s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▌ | 75/331 [03:35<13:37, 3.20s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▌ | 75/331 [03:35<13:37, 3.20s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▌ | 75/331 [03:35<13:37, 3.20s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████ | 77/331 [03:41<12:37, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▎ | 78/331 [03:43<12:04, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▌ | 79/331 [03:46<11:44, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▊ | 80/331 [03:49<11:27, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████ | 81/331 [03:52<11:51, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▎ | 82/331 [03:54<11:37, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▌ | 83/331 [03:58<12:01, 2.91s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▊ | 84/331 [04:01<12:51, 3.12s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████ | 85/331 [04:04<11:58, 2.92s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▎ | 86/331 [04:07<12:41, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▌ | 87/331 [04:10<12:17, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 88/331 [04:13<11:55, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████ | 89/331 [04:15<11:02, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 90/331 [04:17<10:37, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 91/331 [04:21<11:09, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 92/331 [04:23<10:27, 2.63s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████ | 93/331 [04:26<10:31, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▎ | 94/331 [04:28<10:46, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▌ | 95/331 [04:31<10:55, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▊ | 96/331 [04:34<10:55, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████ | 97/331 [04:37<10:27, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▎ | 98/331 [04:40<10:54, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▌ | 99/331 [04:42<10:45, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▍ | 100/331 [04:45<10:21, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▋ | 101/331 [04:48<10:14, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▉ | 102/331 [04:51<11:02, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▏ | 103/331 [04:53<10:28, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▍ | 104/331 [04:56<10:21, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▋ | 105/331 [04:59<10:20, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▉ | 106/331 [05:02<10:16, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▏ | 107/331 [05:04<09:36, 2.57s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▍ | 108/331 [05:06<09:23, 2.53s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▋ | 109/331 [05:09<09:24, 2.54s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▉ | 110/331 [05:12<09:50, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▏ | 111/331 [05:15<09:59, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▍ | 112/331 [05:17<09:59, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▋ | 113/331 [05:20<09:29, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▉ | 114/331 [05:22<09:35, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▏ | 115/331 [05:25<09:38, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▍ | 116/331 [05:28<09:52, 2.76s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▋ | 117/331 [05:31<09:48, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▉ | 118/331 [05:33<09:34, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████ | 119/331 [05:36<09:32, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▎ | 120/331 [05:39<09:28, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▌ | 121/331 [05:42<09:58, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▊ | 122/331 [05:45<09:46, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████ | 123/331 [05:48<10:27, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▎ | 124/331 [05:51<10:21, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▌ | 125/331 [05:55<10:53, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▊ | 126/331 [05:58<10:55, 3.20s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████ | 127/331 [06:02<11:16, 3.32s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▎ | 128/331 [06:05<11:12, 3.31s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▌ | 129/331 [06:08<10:57, 3.26s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▊ | 130/331 [06:11<11:03, 3.30s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████ | 131/331 [06:15<11:17, 3.39s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▎ | 132/331 [06:18<10:41, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▌ | 133/331 [06:20<10:00, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▊ | 134/331 [06:23<09:40, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████ | 135/331 [06:26<09:44, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▎ | 136/331 [06:29<09:58, 3.07s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▌ | 137/331 [06:33<10:22, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▊ | 138/331 [06:37<10:35, 3.29s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████ | 139/331 [06:39<09:26, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▎ | 140/331 [06:42<10:05, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▌ | 141/331 [06:45<09:37, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▋ | 142/331 [06:48<09:19, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▉ | 143/331 [06:51<09:41, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▏ | 144/331 [06:54<09:17, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▍ | 145/331 [06:57<09:09, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▋ | 146/331 [07:00<09:37, 3.12s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▉ | 147/331 [07:03<09:15, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▏ | 148/331 [07:06<08:39, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▍ | 149/331 [07:08<08:11, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▋ | 150/331 [07:11<08:33, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▉ | 151/331 [07:14<08:24, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▏ | 152/331 [07:16<08:00, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▍ | 153/331 [07:19<07:52, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▋ | 154/331 [07:22<08:13, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▉ | 155/331 [07:25<08:37, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▉ | 155/331 [07:25<08:37, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▉ | 155/331 [07:25<08:37, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▍ | 157/331 [07:32<09:11, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▋ | 158/331 [07:35<09:19, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▋ | 158/331 [07:35<09:19, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▋ | 158/331 [07:35<09:19, 3.23s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▏ | 160/331 [07:41<08:46, 3.08s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▍ | 161/331 [07:44<08:29, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▋ | 162/331 [07:48<08:56, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▉ | 163/331 [07:51<09:04, 3.24s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▏ | 164/331 [07:54<08:38, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▍ | 165/331 [07:57<08:28, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▌ | 166/331 [08:00<08:14, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▊ | 167/331 [08:03<08:23, 3.07s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 168/331 [08:05<07:51, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▎ | 169/331 [08:09<08:00, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▌ | 170/331 [08:11<07:37, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▊ | 171/331 [08:14<07:34, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████ | 172/331 [08:16<07:09, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▎ | 173/331 [08:19<07:14, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▌ | 174/331 [08:22<06:55, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▊ | 175/331 [08:24<06:57, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████ | 176/331 [08:27<06:40, 2.58s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▎ | 177/331 [08:30<07:01, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▌ | 178/331 [08:33<07:25, 2.91s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▊ | 179/331 [08:37<07:46, 3.07s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████ | 180/331 [08:40<07:39, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▎ | 181/331 [08:43<07:34, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▌ | 182/331 [08:45<07:00, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▊ | 183/331 [08:47<06:27, 2.62s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████ | 184/331 [08:49<06:04, 2.48s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▎ | 185/331 [08:51<05:42, 2.35s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▌ | 186/331 [08:54<05:52, 2.43s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▊ | 187/331 [08:57<06:23, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████ | 188/331 [09:00<06:21, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▎ | 189/331 [09:02<06:02, 2.55s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▍ | 190/331 [09:04<05:44, 2.44s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▋ | 191/331 [09:07<05:41, 2.44s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▉ | 192/331 [09:09<05:31, 2.39s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▏ | 193/331 [09:12<05:57, 2.59s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▍ | 194/331 [09:14<05:35, 2.45s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▋ | 195/331 [09:16<05:27, 2.41s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▉ | 196/331 [09:19<05:33, 2.47s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▏ | 197/331 [09:22<05:47, 2.60s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▍ | 198/331 [09:24<05:29, 2.48s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▋ | 199/331 [09:27<05:37, 2.56s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▉ | 200/331 [09:29<05:21, 2.45s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▏ | 201/331 [09:31<05:17, 2.44s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▍ | 202/331 [09:34<05:23, 2.51s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▋ | 203/331 [09:37<05:23, 2.53s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▉ | 204/331 [09:40<05:42, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▏ | 205/331 [09:43<05:45, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▍ | 206/331 [09:45<05:41, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▋ | 207/331 [09:49<05:55, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▉ | 208/331 [09:52<05:59, 2.92s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▏ | 209/331 [09:54<05:28, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▍ | 210/331 [09:56<05:04, 2.52s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▋ | 211/331 [09:59<05:08, 2.57s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▉ | 212/331 [10:01<04:55, 2.48s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████ | 213/331 [10:03<04:56, 2.51s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▎ | 214/331 [10:06<04:39, 2.39s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▌ | 215/331 [10:08<04:29, 2.32s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▊ | 216/331 [10:11<04:58, 2.60s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████ | 217/331 [10:14<04:58, 2.62s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▎ | 218/331 [10:17<05:11, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▌ | 219/331 [10:19<05:05, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▊ | 220/331 [10:22<04:50, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████ | 221/331 [10:24<04:53, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▎ | 222/331 [10:27<04:40, 2.57s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▌ | 223/331 [10:30<04:42, 2.62s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▊ | 224/331 [10:32<04:43, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████ | 225/331 [10:35<04:41, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▎ | 226/331 [10:38<04:52, 2.79s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▌ | 227/331 [10:41<04:44, 2.74s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▊ | 228/331 [10:43<04:38, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████ | 229/331 [10:46<04:35, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▎ | 230/331 [10:48<04:27, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▌ | 231/331 [10:51<04:32, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▊ | 232/331 [10:54<04:25, 2.69s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████ | 233/331 [10:57<04:31, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▎ | 234/331 [10:59<04:14, 2.62s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▌ | 235/331 [11:02<04:02, 2.52s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▊ | 236/331 [11:05<04:28, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▉ | 237/331 [11:08<04:39, 2.98s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▏ | 238/331 [11:11<04:36, 2.97s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▍ | 239/331 [11:14<04:38, 3.03s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▋ | 240/331 [11:18<04:43, 3.12s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▉ | 241/331 [11:21<04:48, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▏ | 242/331 [11:24<04:45, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▍ | 243/331 [11:28<04:42, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▋ | 244/331 [11:31<04:46, 3.30s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▉ | 245/331 [11:34<04:35, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▏ | 246/331 [11:38<04:46, 3.37s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▍ | 247/331 [11:41<04:36, 3.30s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▋ | 248/331 [11:44<04:16, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▉ | 249/331 [11:46<03:54, 2.86s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▏ | 250/331 [11:48<03:41, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 251/331 [11:51<03:44, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▋ | 252/331 [11:54<03:31, 2.68s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▉ | 253/331 [11:57<03:39, 2.81s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▏ | 254/331 [12:00<03:32, 2.75s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 255/331 [12:03<03:37, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▋ | 256/331 [12:05<03:28, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▉ | 257/331 [12:08<03:32, 2.87s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▏ | 258/331 [12:11<03:18, 2.73s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 259/331 [12:13<03:15, 2.72s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▋ | 260/331 [12:16<03:18, 2.80s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▊ | 261/331 [12:19<03:05, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 262/331 [12:21<03:02, 2.65s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▎ | 263/331 [12:24<03:09, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▌ | 264/331 [12:27<03:00, 2.70s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▊ | 265/331 [12:29<02:54, 2.64s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████ | 266/331 [12:32<02:48, 2.60s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 267/331 [12:35<02:57, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 268/331 [12:38<02:55, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 269/331 [12:41<03:03, 2.96s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████ | 270/331 [12:44<02:58, 2.93s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▎ | 271/331 [12:47<03:02, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 272/331 [12:50<02:52, 2.93s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▊ | 273/331 [12:53<02:50, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████ | 274/331 [12:57<02:57, 3.11s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▎ | 275/331 [13:00<02:55, 3.14s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▌ | 276/331 [13:02<02:41, 2.94s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 277/331 [13:05<02:34, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████ | 278/331 [13:08<02:29, 2.82s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 279/331 [13:11<02:39, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▌ | 280/331 [13:14<02:33, 3.00s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▊ | 281/331 [13:17<02:34, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████ | 282/331 [13:21<02:31, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▎ | 283/331 [13:24<02:31, 3.16s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 284/331 [13:27<02:32, 3.25s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▋ | 285/331 [13:31<02:31, 3.29s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▉ | 286/331 [13:34<02:28, 3.31s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▏ | 287/331 [13:38<02:30, 3.41s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▍ | 288/331 [13:41<02:26, 3.40s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▋ | 289/331 [13:44<02:13, 3.19s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▉ | 290/331 [13:46<02:03, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▏ | 291/331 [13:49<01:53, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▍ | 292/331 [13:51<01:48, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▋ | 293/331 [13:54<01:45, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▉ | 294/331 [13:57<01:38, 2.66s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▏ | 295/331 [13:59<01:33, 2.61s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▍ | 296/331 [14:01<01:28, 2.54s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▋ | 297/331 [14:05<01:36, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▋ | 297/331 [14:05<01:36, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▋ | 297/331 [14:05<01:36, 2.83s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▏ | 299/331 [14:11<01:32, 2.90s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▍ | 300/331 [14:14<01:29, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▋ | 301/331 [14:17<01:25, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▉ | 302/331 [14:19<01:20, 2.77s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▏ | 303/331 [14:22<01:14, 2.67s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▍ | 304/331 [14:25<01:14, 2.78s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▋ | 305/331 [14:28<01:15, 2.89s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▉ | 306/331 [14:31<01:16, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▏ | 307/331 [14:35<01:17, 3.22s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▎ | 308/331 [14:39<01:18, 3.41s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▌ | 309/331 [14:42<01:15, 3.45s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▊ | 310/331 [14:45<01:07, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████ | 311/331 [14:48<01:03, 3.17s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▎ | 312/331 [14:51<00:56, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▌ | 313/331 [14:53<00:52, 2.90s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▊ | 314/331 [14:56<00:50, 2.95s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████ | 315/331 [15:00<00:48, 3.06s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▎ | 316/331 [15:03<00:46, 3.08s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▌ | 317/331 [15:06<00:44, 3.21s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▊ | 318/331 [15:09<00:39, 3.01s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████ | 319/331 [15:11<00:34, 2.85s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▎ | 320/331 [15:14<00:31, 2.88s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▌ | 321/331 [15:17<00:28, 2.84s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▊ | 322/331 [15:20<00:26, 2.99s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████ | 323/331 [15:23<00:23, 2.91s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▎ | 324/331 [15:26<00:21, 3.02s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▌ | 325/331 [15:29<00:18, 3.04s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▊ | 326/331 [15:33<00:15, 3.09s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████ | 327/331 [15:36<00:12, 3.10s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▎| 328/331 [15:39<00:09, 3.13s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▌| 329/331 [15:42<00:06, 3.08s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▊| 330/331 [15:46<00:03, 3.25s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▊| 330/331 [15:46<00:03, 3.25s/it][INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 02:10:55 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|configuration_utils.py:438] 2022-03-03 02:10:55,625 >> Configuration saved in ./checkpoint-1000/config.json [INFO|trainer.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:11:00,720 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:11:00,720 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:11:00,720 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:11:00,720 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:11:00,720 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▉ | 1001/1784 [1:27:45<70:53:08, 325.91s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▉ | 1001/1784 [1:27:45<70:53:08, 325.91s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▉ | 1001/1784 [1:27:45<70:53:08, 325.91s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1002/1784 [1:27:50<49:50:10, 229.43s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1002/1784 [1:27:50<49:50:10, 229.43s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1002/1784 [1:27:50<49:50:10, 229.43s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1003/1784 [1:27:54<35:06:19, 161.82s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1003/1784 [1:27:54<35:06:19, 161.82s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1003/1784 [1:27:54<35:06:19, 161.82s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1004/1784 [1:27:57<24:47:19, 114.41s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1004/1784 [1:27:57<24:47:19, 114.41s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 1004/1784 [1:27:57<24:47:19, 114.41s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▋ | 1005/1784 [1:28:01<17:34:20, 81.21s/it]config.jsoner.py:560] 2022-03-03 01:55:04,981 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:13:27,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:13:27,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5111, 'learning_rate': 0.0006137071651090342, 'epoch': 0.56} 56%|██████████████████████████████████████████▎ | 1007/1784 [1:28:09<9:00:34, 41.74s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▎ | 1007/1784 [1:28:09<9:00:34, 41.74s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8861, 'learning_rate': 0.0006129283489096573, 'epoch': 0.56} 56%|██████████████████████████████████████████▎ | 1007/1784 [1:28:09<9:00:34, 41.74s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1008/1784 [1:28:13<6:32:21, 30.34s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1008/1784 [1:28:13<6:32:21, 30.34s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1008/1784 [1:28:13<6:32:21, 30.34s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1009/1784 [1:28:16<4:48:30, 22.34s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1009/1784 [1:28:16<4:48:30, 22.34s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1009/1784 [1:28:16<4:48:30, 22.34s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1010/1784 [1:28:20<3:35:59, 16.74s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1010/1784 [1:28:20<3:35:59, 16.74s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▍ | 1010/1784 [1:28:20<3:35:59, 16.74s/it]g-point operations will not be computed04,981 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▌ | 1011/1784 [1:28:24<2:44:52, 12.80s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▌ | 1012/1784 [1:28:27<2:08:56, 10.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▌ | 1012/1784 [1:28:27<2:08:56, 10.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5457, 'learning_rate': 0.0006090342679127726, 'epoch': 0.57} 57%|██████████████████████████████████████████▌ | 1012/1784 [1:28:27<2:08:56, 10.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▌ | 1013/1784 [1:28:31<1:43:56, 8.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▌ | 1013/1784 [1:28:31<1:43:56, 8.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▌ | 1013/1784 [1:28:31<1:43:56, 8.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▋ | 1014/1784 [1:28:34<1:26:19, 6.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:13:59,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:13:59,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7337, 'learning_rate': 0.0006066978193146417, 'epoch': 0.57} 57%|██████████████████████████████████████████▋ | 1016/1784 [1:28:41<1:05:36, 5.13s/it]g-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████▋ | 1016/1784 [1:28:41<1:05:36, 5.13s/it]g-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.176, 'learning_rate': 0.0006059190031152648, 'epoch': 0.57} 57%|██████████████████████████████████████████▋ | 1016/1784 [1:28:41<1:05:36, 5.13s/it]g-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|███████████████████████████████████████████▉ | 1017/1784 [1:28:45<59:16, 4.64s/it]g-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|███████████████████████████████████████████▉ | 1017/1784 [1:28:45<59:16, 4.64s/it]g-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|███████████████████████████████████████████▉ | 1017/1784 [1:28:45<59:16, 4.64s/it]g-point operations will not be computed-03 02:13:47,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|███████████████████████████████████████████▉ | 1018/1784 [1:28:48<54:36, 4.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|███████████████████████████████████████████▉ | 1019/1784 [1:28:52<51:22, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|███████████████████████████████████████████▉ | 1019/1784 [1:28:52<51:22, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.7956, 'learning_rate': 0.000603582554517134, 'epoch': 0.57} 57%|███████████████████████████████████████████▉ | 1019/1784 [1:28:52<51:22, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|████████████████████████████████████████████ | 1020/1784 [1:28:55<49:03, 3.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|████████████████████████████████████████████ | 1020/1784 [1:28:55<49:03, 3.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|████████████████████████████████████████████ | 1020/1784 [1:28:55<49:03, 3.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|████████████████████████████████████████████ | 1021/1784 [1:28:59<47:26, 3.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:14:24,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:14:24,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4171, 'learning_rate': 0.0006012461059190031, 'epoch': 0.57} [WARNING|modeling_utils.py:388] 2022-03-03 02:14:24,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|████████████████████████████████████████████▏ | 1023/1784 [1:29:05<44:54, 3.54s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:14:30,869 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:14:30,869 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5185, 'learning_rate': 0.0005996884735202493, 'epoch': 0.57} 57%|████████████████████████████████████████████▏ | 1025/1784 [1:29:12<43:33, 3.44s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|████████████████████████████████████████████▏ | 1025/1784 [1:29:12<43:33, 3.44s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.033, 'learning_rate': 0.0005989096573208723, 'epoch': 0.57} 57%|████████████████████████████████████████████▏ | 1025/1784 [1:29:12<43:33, 3.44s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▎ | 1026/1784 [1:29:15<43:01, 3.41s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▎ | 1026/1784 [1:29:15<43:01, 3.41s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▎ | 1026/1784 [1:29:15<43:01, 3.41s/it]g-point operations will not be computed-03 02:14:12,246 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▎ | 1027/1784 [1:29:19<42:26, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:42,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▎ | 1028/1784 [1:29:22<41:54, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:42,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▎ | 1028/1784 [1:29:22<41:54, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:42,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7042, 'learning_rate': 0.0005965732087227414, 'epoch': 0.58} 58%|████████████████████████████████████████████▎ | 1028/1784 [1:29:22<41:54, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:42,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▍ | 1029/1784 [1:29:25<41:29, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▍ | 1030/1784 [1:29:28<41:11, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▍ | 1030/1784 [1:29:28<41:11, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.45, 'learning_rate': 0.0005950155763239875, 'epoch': 0.58} 58%|████████████████████████████████████████████▍ | 1030/1784 [1:29:28<41:11, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▍ | 1031/1784 [1:29:32<41:19, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:14:57,046 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:14:57,046 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6557, 'learning_rate': 0.0005934579439252337, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-03-03 02:14:57,046 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▌ | 1033/1784 [1:29:38<40:09, 3.21s/it]g-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:03,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:03,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0558, 'learning_rate': 0.0005919003115264798, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:03,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▋ | 1035/1784 [1:29:44<38:44, 3.10s/it]g-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:09,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:09,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.651, 'learning_rate': 0.0005903426791277258, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:09,077 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▊ | 1037/1784 [1:29:50<37:33, 3.02s/it]g-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:14,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:14,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4711, 'learning_rate': 0.0005887850467289719, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:14,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:14:48,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▊ | 1039/1784 [1:29:55<35:43, 2.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:15:18,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▊ | 1039/1784 [1:29:55<35:43, 2.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:15:18,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▉ | 1040/1784 [1:29:58<34:14, 2.76s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▉ | 1040/1784 [1:29:58<34:14, 2.76s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▉ | 1041/1784 [1:30:00<32:52, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|████████████████████████████████████████████▉ | 1041/1784 [1:30:00<32:52, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:24,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:24,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:26,788 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:26,788 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:28,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:28,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:30,306 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:30,306 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:33,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:33,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5014, 'learning_rate': 0.0005817757009345795, 'epoch': 0.59} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:34,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:34,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:37,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:37,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.4257, 'learning_rate': 0.0005794392523364486, 'epoch': 0.59} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:41,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:41,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.7644, 'learning_rate': 0.0005786604361370716, 'epoch': 0.59} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:45,299 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:15:45,299 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5467, 'learning_rate': 0.0005778816199376947, 'epoch': 0.59} [WARNING|modeling_utils.py:388] 2022-03-03 02:15:45,299 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▍ | 1053/1784 [1:30:27<37:01, 3.04s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▍ | 1053/1784 [1:30:27<37:01, 3.04s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▍ | 1054/1784 [1:30:31<39:28, 3.25s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▍ | 1054/1784 [1:30:31<39:28, 3.25s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1816, 'learning_rate': 0.0005763239875389408, 'epoch': 0.59} 59%|█████████████████████████████████████████████▍ | 1054/1784 [1:30:31<39:28, 3.25s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▌ | 1055/1784 [1:30:34<40:52, 3.36s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:16:00,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:16:00,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2733, 'learning_rate': 0.0005747663551401869, 'epoch': 0.59} 59%|█████████████████████████████████████████████▌ | 1057/1784 [1:30:42<42:52, 3.54s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▌ | 1057/1784 [1:30:42<42:52, 3.54s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.0753, 'learning_rate': 0.00057398753894081, 'epoch': 0.59} 59%|█████████████████████████████████████████████▋ | 1058/1784 [1:30:45<42:59, 3.55s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▋ | 1058/1784 [1:30:45<42:59, 3.55s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2696, 'learning_rate': 0.000573208722741433, 'epoch': 0.59} 59%|█████████████████████████████████████████████▋ | 1058/1784 [1:30:45<42:59, 3.55s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▋ | 1059/1784 [1:30:49<43:14, 3.58s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▋ | 1059/1784 [1:30:49<43:14, 3.58s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▋ | 1059/1784 [1:30:49<43:14, 3.58s/it]g-point operations will not be computed-03 02:15:21,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▊ | 1060/1784 [1:30:53<43:25, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:16,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▊ | 1061/1784 [1:30:56<43:15, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:16,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▊ | 1061/1784 [1:30:56<43:15, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:16,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5776, 'learning_rate': 0.0005708722741433022, 'epoch': 0.59} 60%|█████████████████████████████████████████████▊ | 1062/1784 [1:31:00<42:52, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:16,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|█████████████████████████████████████████████▊ | 1062/1784 [1:31:00<42:52, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:16,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3782, 'learning_rate': 0.0005700934579439252, 'epoch': 0.6} 60%|█████████████████████████████████████████████▊ | 1062/1784 [1:31:00<42:52, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:16,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|█████████████████████████████████████████████▉ | 1063/1784 [1:31:03<42:34, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|█████████████████████████████████████████████▉ | 1064/1784 [1:31:07<42:10, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|█████████████████████████████████████████████▉ | 1064/1784 [1:31:07<42:10, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.036, 'learning_rate': 0.0005685358255451714, 'epoch': 0.6} 60%|█████████████████████████████████████████████▉ | 1065/1784 [1:31:10<42:02, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|█████████████████████████████████████████████▉ | 1065/1784 [1:31:10<42:02, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.0397, 'learning_rate': 0.0005677570093457944, 'epoch': 0.6} 60%|█████████████████████████████████████████████▉ | 1065/1784 [1:31:10<42:02, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████ | 1066/1784 [1:31:14<41:30, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:16:39,015 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:16:39,015 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4592, 'learning_rate': 0.0005661993769470405, 'epoch': 0.6} 60%|██████████████████████████████████████████████ | 1068/1784 [1:31:20<41:18, 3.46s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████ | 1068/1784 [1:31:20<41:18, 3.46s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2184, 'learning_rate': 0.0005654205607476635, 'epoch': 0.6} 60%|██████████████████████████████████████████████ | 1068/1784 [1:31:20<41:18, 3.46s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▏ | 1069/1784 [1:31:24<41:00, 3.44s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:16:49,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:16:49,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2781, 'learning_rate': 0.0005638629283489096, 'epoch': 0.6} 60%|██████████████████████████████████████████████▏ | 1071/1784 [1:31:31<40:27, 3.40s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▏ | 1071/1784 [1:31:31<40:27, 3.40s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2661, 'learning_rate': 0.0005630841121495327, 'epoch': 0.6} 60%|██████████████████████████████████████████████▏ | 1071/1784 [1:31:31<40:27, 3.40s/it]g-point operations will not be computed-03 02:16:27,072 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▎ | 1072/1784 [1:31:34<40:01, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:57,624 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▎ | 1073/1784 [1:31:37<39:42, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:57,624 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▎ | 1073/1784 [1:31:37<39:42, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:57,624 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2231, 'learning_rate': 0.0005615264797507788, 'epoch': 0.6} 60%|██████████████████████████████████████████████▎ | 1074/1784 [1:31:41<39:53, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:57,624 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▎ | 1074/1784 [1:31:41<39:53, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:57,624 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7709, 'learning_rate': 0.0005607476635514019, 'epoch': 0.6} 60%|██████████████████████████████████████████████▎ | 1074/1784 [1:31:41<39:53, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:16:57,624 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 1075/1784 [1:31:44<39:25, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:07,539 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 1076/1784 [1:31:47<38:44, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:07,539 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 1076/1784 [1:31:47<38:44, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:07,539 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.7439, 'learning_rate': 0.0005591900311526479, 'epoch': 0.6} 60%|██████████████████████████████████████████████▍ | 1076/1784 [1:31:47<38:44, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:07,539 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 1077/1784 [1:31:50<38:21, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:13,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 1078/1784 [1:31:53<38:00, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:13,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 1078/1784 [1:31:53<38:00, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:13,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1565, 'learning_rate': 0.000557632398753894, 'epoch': 0.6} 60%|██████████████████████████████████████████████▌ | 1079/1784 [1:31:57<37:53, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:20,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 1079/1784 [1:31:57<37:53, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:20,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▌ | 1080/1784 [1:32:00<37:31, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:20,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▌ | 1080/1784 [1:32:00<37:31, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:20,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6181, 'learning_rate': 0.0005560747663551402, 'epoch': 0.61} 61%|██████████████████████████████████████████████▋ | 1081/1784 [1:32:03<37:06, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:26,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▋ | 1081/1784 [1:32:03<37:06, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:26,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▋ | 1082/1784 [1:32:06<36:53, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:26,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▋ | 1082/1784 [1:32:06<36:53, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:26,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5936, 'learning_rate': 0.0005545171339563863, 'epoch': 0.61} 61%|██████████████████████████████████████████████▋ | 1083/1784 [1:32:09<36:20, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▋ | 1083/1784 [1:32:09<36:20, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▊ | 1084/1784 [1:32:12<35:35, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▊ | 1084/1784 [1:32:12<35:35, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:36,810 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:36,810 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1309, 'learning_rate': 0.0005521806853582555, 'epoch': 0.61} 61%|██████████████████████████████████████████████▊ | 1086/1784 [1:32:18<34:36, 2.98s/it]g-point operations will not be computed-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▊ | 1086/1784 [1:32:18<34:36, 2.98s/it]g-point operations will not be computed-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:42,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:42,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:32,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5907, 'learning_rate': 0.0005506230529595016, 'epoch': 0.61} 61%|██████████████████████████████████████████████▉ | 1088/1784 [1:32:23<33:43, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|██████████████████████████████████████████████▉ | 1088/1784 [1:32:23<33:43, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████ | 1089/1784 [1:32:26<32:58, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████ | 1089/1784 [1:32:26<32:58, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:50,656 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:50,656 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:52,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:17:52,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2926, 'learning_rate': 0.0005475077881619937, 'epoch': 0.61} [WARNING|modeling_utils.py:388] 2022-03-03 02:17:52,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:17:46,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▏ | 1093/1784 [1:32:35<27:19, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:56,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▏ | 1093/1784 [1:32:35<27:19, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:56,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▏ | 1094/1784 [1:32:37<25:45, 2.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:58,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▏ | 1094/1784 [1:32:37<25:45, 2.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:17:58,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 1095/1784 [1:32:39<23:54, 2.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:00,113 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 1095/1784 [1:32:39<23:54, 2.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:00,113 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 1096/1784 [1:32:40<22:11, 1.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:03,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 1096/1784 [1:32:40<22:11, 1.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:03,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 1097/1784 [1:32:42<20:31, 1.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:04,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 1097/1784 [1:32:42<20:31, 1.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:04,708 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 7.1915, 'learning_rate': 0.0005428348909657321, 'epoch': 0.61} 62%|███████████████████████████████████████████████▍ | 1099/1784 [1:32:45<17:48, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:06,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▍ | 1099/1784 [1:32:45<17:48, 1.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:06,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▍ | 1100/1784 [1:32:46<18:15, 1.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:07,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▍ | 1100/1784 [1:32:46<18:15, 1.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:07,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▍ | 1100/1784 [1:32:46<18:15, 1.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:10,447 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▌ | 1101/1784 [1:32:50<26:18, 2.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:10,447 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▌ | 1101/1784 [1:32:50<26:18, 2.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:10,447 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▌ | 1101/1784 [1:32:50<26:18, 2.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:14,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▌ | 1102/1784 [1:32:54<31:15, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:14,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▌ | 1102/1784 [1:32:54<31:15, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:14,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4949, 'learning_rate': 0.0005389408099688473, 'epoch': 0.62} 62%|███████████████████████████████████████████████▌ | 1103/1784 [1:32:58<34:34, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▌ | 1103/1784 [1:32:58<34:34, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▋ | 1104/1784 [1:33:01<36:20, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▋ | 1104/1784 [1:33:01<36:20, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▋ | 1104/1784 [1:33:01<36:20, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▋ | 1105/1784 [1:33:05<37:48, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▋ | 1105/1784 [1:33:05<37:48, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2455, 'learning_rate': 0.0005366043613707165, 'epoch': 0.62} 62%|███████████████████████████████████████████████▋ | 1106/1784 [1:33:09<38:47, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▋ | 1106/1784 [1:33:09<38:47, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.004, 'learning_rate': 0.0005358255451713396, 'epoch': 0.62} 62%|███████████████████████████████████████████████▊ | 1107/1784 [1:33:12<39:08, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▊ | 1107/1784 [1:33:12<39:08, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:18:37,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:18:37,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2132, 'learning_rate': 0.0005342679127725857, 'epoch': 0.62} [WARNING|modeling_utils.py:388] 2022-03-03 02:18:37,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▊ | 1109/1784 [1:33:19<39:30, 3.51s/it]g-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▊ | 1109/1784 [1:33:19<39:30, 3.51s/it]g-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▊ | 1109/1784 [1:33:19<39:30, 3.51s/it]g-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▉ | 1110/1784 [1:33:23<39:39, 3.53s/it]g-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▉ | 1110/1784 [1:33:23<39:39, 3.53s/it]g-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▉ | 1110/1784 [1:33:23<39:39, 3.53s/it]g-point operations will not be computed-03 02:18:21,628 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▉ | 1111/1784 [1:33:26<39:25, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▉ | 1112/1784 [1:33:30<39:16, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|███████████████████████████████████████████████▉ | 1112/1784 [1:33:30<39:16, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4272, 'learning_rate': 0.0005311526479750779, 'epoch': 0.62} 62%|███████████████████████████████████████████████▉ | 1112/1784 [1:33:30<39:16, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 1113/1784 [1:33:33<39:16, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 1113/1784 [1:33:33<39:16, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 1113/1784 [1:33:33<39:16, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 1114/1784 [1:33:37<39:27, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:02,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:02,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8371, 'learning_rate': 0.000528816199376947, 'epoch': 0.62} 63%|████████████████████████████████████████████████▏ | 1116/1784 [1:33:44<39:13, 3.52s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▏ | 1116/1784 [1:33:44<39:13, 3.52s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0897, 'learning_rate': 0.0005280373831775702, 'epoch': 0.63} 63%|████████████████████████████████████████████████▏ | 1116/1784 [1:33:44<39:13, 3.52s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▏ | 1117/1784 [1:33:47<38:54, 3.50s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:12,884 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:12,884 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.542, 'learning_rate': 0.0005264797507788161, 'epoch': 0.63} 63%|████████████████████████████████████████████████▎ | 1119/1784 [1:33:54<38:13, 3.45s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▎ | 1119/1784 [1:33:54<38:13, 3.45s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3313, 'learning_rate': 0.0005257009345794393, 'epoch': 0.63} 63%|████████████████████████████████████████████████▎ | 1119/1784 [1:33:54<38:13, 3.45s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▎ | 1120/1784 [1:33:58<38:01, 3.44s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▎ | 1120/1784 [1:33:58<38:01, 3.44s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▎ | 1120/1784 [1:33:58<38:01, 3.44s/it]g-point operations will not be computed-03 02:18:50,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▍ | 1121/1784 [1:34:01<37:45, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▍ | 1121/1784 [1:34:01<37:45, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▍ | 1122/1784 [1:34:04<37:21, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▍ | 1122/1784 [1:34:04<37:21, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▍ | 1122/1784 [1:34:04<37:21, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▍ | 1123/1784 [1:34:08<37:07, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:33,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:33,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9823, 'learning_rate': 0.0005218068535825546, 'epoch': 0.63} [WARNING|modeling_utils.py:388] 2022-03-03 02:19:33,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▌ | 1125/1784 [1:34:14<36:28, 3.32s/it]g-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:39,496 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:19:39,496 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2799, 'learning_rate': 0.0005202492211838006, 'epoch': 0.63} [WARNING|modeling_utils.py:388] 2022-03-03 02:19:39,496 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▋ | 1127/1784 [1:34:21<35:52, 3.28s/it]g-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▋ | 1127/1784 [1:34:21<35:52, 3.28s/it]g-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▋ | 1127/1784 [1:34:21<35:52, 3.28s/it]g-point operations will not be computed-03 02:19:24,771 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▋ | 1128/1784 [1:34:24<35:35, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:47,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▋ | 1129/1784 [1:34:27<35:19, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:47,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▋ | 1129/1784 [1:34:27<35:19, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:47,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9513, 'learning_rate': 0.0005179127725856698, 'epoch': 0.63} 63%|████████████████████████████████████████████████▋ | 1129/1784 [1:34:27<35:19, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:47,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▊ | 1130/1784 [1:34:30<35:04, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▊ | 1131/1784 [1:34:33<34:35, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▊ | 1131/1784 [1:34:33<34:35, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4049, 'learning_rate': 0.0005163551401869159, 'epoch': 0.63} 63%|████████████████████████████████████████████████▊ | 1131/1784 [1:34:33<34:35, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|████████████████████████████████████████████████▊ | 1132/1784 [1:34:36<34:16, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:01,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:01,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4968, 'learning_rate': 0.000514797507788162, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-03-03 02:20:01,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|████████████████████████████████████████████████▉ | 1134/1784 [1:34:43<33:31, 3.09s/it]g-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:07,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:07,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6117, 'learning_rate': 0.0005132398753894081, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-03-03 02:20:07,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:19:53,900 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████ | 1136/1784 [1:34:48<32:38, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:12,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████ | 1137/1784 [1:34:51<32:05, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:12,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████ | 1137/1784 [1:34:51<32:05, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:12,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:16,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:12,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:16,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:12,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3672, 'learning_rate': 0.0005109034267912772, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-03-03 02:20:16,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:12,024 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▏ | 1139/1784 [1:34:57<30:43, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▏ | 1140/1784 [1:34:59<30:08, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▏ | 1140/1784 [1:34:59<30:08, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:24,207 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:24,207 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:26,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:20:26,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.9577, 'learning_rate': 0.0005077881619937694, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-03-03 02:20:26,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:20,280 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▎ | 1143/1784 [1:35:07<27:31, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:30,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▎ | 1143/1784 [1:35:07<27:31, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:30,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▍ | 1144/1784 [1:35:09<26:24, 2.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:32,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▍ | 1144/1784 [1:35:09<26:24, 2.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:32,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▍ | 1145/1784 [1:35:11<24:59, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:34,330 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▍ | 1145/1784 [1:35:11<24:59, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:34,330 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▌ | 1147/1784 [1:35:15<21:27, 2.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:36,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▌ | 1147/1784 [1:35:15<21:27, 2.02s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:36,057 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▌ | 1148/1784 [1:35:16<19:23, 1.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:38,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▌ | 1148/1784 [1:35:16<19:23, 1.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:38,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3735, 'learning_rate': 0.0005031152647975078, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▌ | 1149/1784 [1:35:17<17:26, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:40,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▌ | 1149/1784 [1:35:17<17:26, 1.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:40,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▋ | 1150/1784 [1:35:19<17:40, 1.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:40,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▋ | 1150/1784 [1:35:19<17:40, 1.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:43,157 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|█████████████████████████████████████████████████▋ | 1150/1784 [1:35:19<17:40, 1.67s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:43,157 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▋ | 1151/1784 [1:35:23<24:44, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:43,157 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▋ | 1151/1784 [1:35:23<24:44, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:43,157 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▋ | 1151/1784 [1:35:23<24:44, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:43,157 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▋ | 1152/1784 [1:35:27<29:11, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▊ | 1153/1784 [1:35:30<32:08, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▊ | 1153/1784 [1:35:30<32:08, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2717, 'learning_rate': 0.000499221183800623, 'epoch': 0.65} 65%|█████████████████████████████████████████████████▊ | 1154/1784 [1:35:34<34:04, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▊ | 1154/1784 [1:35:34<34:04, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3284, 'learning_rate': 0.0004984423676012461, 'epoch': 0.65} 65%|█████████████████████████████████████████████████▊ | 1154/1784 [1:35:34<34:04, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▊ | 1155/1784 [1:35:38<35:14, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▊ | 1155/1784 [1:35:38<35:14, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▊ | 1155/1784 [1:35:38<35:14, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▉ | 1156/1784 [1:35:41<36:04, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:21:07,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:21:07,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2763, 'learning_rate': 0.0004961059190031153, 'epoch': 0.65} 65%|█████████████████████████████████████████████████▉ | 1158/1784 [1:35:49<36:53, 3.54s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|█████████████████████████████████████████████████▉ | 1158/1784 [1:35:49<36:53, 3.54s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.339, 'learning_rate': 0.0004953271028037383, 'epoch': 0.65} 65%|██████████████████████████████████████████████████ | 1159/1784 [1:35:52<37:09, 3.57s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████ | 1159/1784 [1:35:52<37:09, 3.57s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1403, 'learning_rate': 0.0004945482866043614, 'epoch': 0.65} 65%|██████████████████████████████████████████████████ | 1159/1784 [1:35:52<37:09, 3.57s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████ | 1160/1784 [1:35:56<37:10, 3.57s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████ | 1160/1784 [1:35:56<37:10, 3.57s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████ | 1160/1784 [1:35:56<37:10, 3.57s/it]g-point operations will not be computed-03 02:20:50,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████ | 1161/1784 [1:35:59<36:54, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▏ | 1162/1784 [1:36:03<36:44, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▏ | 1162/1784 [1:36:03<36:44, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1121, 'learning_rate': 0.0004922118380062306, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▏ | 1162/1784 [1:36:03<36:44, 3.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▏ | 1163/1784 [1:36:06<36:24, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▏ | 1163/1784 [1:36:06<36:24, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▏ | 1163/1784 [1:36:06<36:24, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:23,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▏ | 1164/1784 [1:36:10<36:10, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▎ | 1165/1784 [1:36:13<35:59, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▎ | 1165/1784 [1:36:13<35:59, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0602, 'learning_rate': 0.0004898753894080997, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▎ | 1166/1784 [1:36:17<35:38, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▎ | 1166/1784 [1:36:17<35:38, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3484, 'learning_rate': 0.0004890965732087227, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▎ | 1166/1784 [1:36:17<35:38, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|██████████████████████████████████████████████████▎ | 1167/1784 [1:36:20<35:34, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:21:45,693 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:21:45,693 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9488, 'learning_rate': 0.00048753894080996886, 'epoch': 0.65} 66%|██████████████████████████████████████████████████▍ | 1169/1784 [1:36:27<35:17, 3.44s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▍ | 1169/1784 [1:36:27<35:17, 3.44s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2174, 'learning_rate': 0.00048676012461059195, 'epoch': 0.66} 66%|██████████████████████████████████████████████████▍ | 1169/1784 [1:36:27<35:17, 3.44s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▍ | 1170/1784 [1:36:30<34:59, 3.42s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:21:55,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:21:55,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.431, 'learning_rate': 0.00048520249221183803, 'epoch': 0.66} [WARNING|modeling_utils.py:388] 2022-03-03 02:21:55,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▌ | 1172/1784 [1:36:37<34:16, 3.36s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:02,421 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:02,421 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.828, 'learning_rate': 0.00048364485981308415, 'epoch': 0.66} 66%|██████████████████████████████████████████████████▋ | 1174/1784 [1:36:44<33:55, 3.34s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▋ | 1174/1784 [1:36:44<33:55, 3.34s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0935, 'learning_rate': 0.0004828660436137072, 'epoch': 0.66} 66%|██████████████████████████████████████████████████▋ | 1174/1784 [1:36:44<33:55, 3.34s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▋ | 1175/1784 [1:36:47<33:42, 3.32s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:12,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:12,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6197, 'learning_rate': 0.00048130841121495326, 'epoch': 0.66} 66%|██████████████████████████████████████████████████▊ | 1177/1784 [1:36:53<33:03, 3.27s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▊ | 1177/1784 [1:36:53<33:03, 3.27s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:18,626 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:18,626 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4918, 'learning_rate': 0.0004797507788161994, 'epoch': 0.66} 66%|██████████████████████████████████████████████████▉ | 1179/1784 [1:37:00<32:31, 3.23s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▉ | 1179/1784 [1:37:00<32:31, 3.23s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:24,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:24,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2911, 'learning_rate': 0.0004781931464174455, 'epoch': 0.66} 66%|██████████████████████████████████████████████████▉ | 1181/1784 [1:37:06<31:48, 3.16s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|██████████████████████████████████████████████████▉ | 1181/1784 [1:37:06<31:48, 3.16s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:31,032 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:31,032 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5437, 'learning_rate': 0.0004766355140186916, 'epoch': 0.66} 66%|███████████████████████████████████████████████████ | 1183/1784 [1:37:12<30:51, 3.08s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|███████████████████████████████████████████████████ | 1183/1784 [1:37:12<30:51, 3.08s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:36,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:36,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0653, 'learning_rate': 0.0004750778816199377, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▏ | 1185/1784 [1:37:18<29:56, 3.00s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|███████████████████████████████████████████████████▏ | 1185/1784 [1:37:18<29:56, 3.00s/it]g-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:42,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:42,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1006, 'learning_rate': 0.0004735202492211838, 'epoch': 0.66} [WARNING|modeling_utils.py:388] 2022-03-03 02:22:42,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:21:33,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▏ | 1187/1784 [1:37:23<29:02, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:46,988 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▎ | 1188/1784 [1:37:26<28:22, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:46,988 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▎ | 1188/1784 [1:37:26<28:22, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:46,988 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:50,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:46,988 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:22:50,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:46,988 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2392, 'learning_rate': 0.000471183800623053, 'epoch': 0.67} [WARNING|modeling_utils.py:388] 2022-03-03 02:22:50,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:46,988 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▎ | 1190/1784 [1:37:31<27:06, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:54,870 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▍ | 1191/1784 [1:37:34<26:16, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▍ | 1191/1784 [1:37:34<26:16, 2.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▍ | 1192/1784 [1:37:36<25:15, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▍ | 1192/1784 [1:37:36<25:15, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:00,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:00,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:02,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:02,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:04,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:04,457 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:06,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:06,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8921, 'learning_rate': 0.0004657320872274143, 'epoch': 0.67} [WARNING|modeling_utils.py:388] 2022-03-03 02:23:08,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:08,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:10,176 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:10,176 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2482, 'learning_rate': 0.00046339563862928353, 'epoch': 0.67} [WARNING|modeling_utils.py:388] 2022-03-03 02:23:11,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:15,719 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:15,719 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2866, 'learning_rate': 0.0004618380062305296, 'epoch': 0.67} [WARNING|modeling_utils.py:388] 2022-03-03 02:23:19,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:19,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1343, 'learning_rate': 0.00046105919003115264, 'epoch': 0.67} 67%|███████████████████████████████████████████████████▉ | 1203/1784 [1:38:01<29:24, 3.04s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▉ | 1203/1784 [1:38:01<29:24, 3.04s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1511, 'learning_rate': 0.00046028037383177573, 'epoch': 0.67} 67%|███████████████████████████████████████████████████▉ | 1204/1784 [1:38:05<31:22, 3.25s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|███████████████████████████████████████████████████▉ | 1204/1784 [1:38:05<31:22, 3.25s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0781, 'learning_rate': 0.00045950155763239877, 'epoch': 0.67} 68%|████████████████████████████████████████████████████ | 1205/1784 [1:38:09<32:23, 3.36s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████ | 1205/1784 [1:38:09<32:23, 3.36s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:34,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:34,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1752, 'learning_rate': 0.00045794392523364484, 'epoch': 0.68} 68%|████████████████████████████████████████████████████ | 1207/1784 [1:38:16<33:25, 3.48s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████ | 1207/1784 [1:38:16<33:25, 3.48s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.1712, 'learning_rate': 0.00045716510903426793, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▏ | 1208/1784 [1:38:19<33:48, 3.52s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▏ | 1208/1784 [1:38:19<33:48, 3.52s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.351, 'learning_rate': 0.00045638629283489097, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▏ | 1209/1784 [1:38:23<33:54, 3.54s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▏ | 1209/1784 [1:38:23<33:54, 3.54s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:48,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:23:48,490 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2923, 'learning_rate': 0.0004548286604361371, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▎ | 1211/1784 [1:38:30<33:34, 3.51s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▎ | 1211/1784 [1:38:30<33:34, 3.51s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6708, 'learning_rate': 0.00045404984423676013, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▎ | 1212/1784 [1:38:33<33:43, 3.54s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▎ | 1212/1784 [1:38:33<33:43, 3.54s/it]g-point operations will not be computed-03 02:22:57,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5055, 'learning_rate': 0.00045327102803738317, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▎ | 1213/1784 [1:38:37<33:26, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▎ | 1213/1784 [1:38:37<33:26, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▍ | 1214/1784 [1:38:41<33:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▍ | 1214/1784 [1:38:41<33:31, 3.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3091, 'learning_rate': 0.0004517133956386293, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▍ | 1215/1784 [1:38:44<33:21, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▍ | 1215/1784 [1:38:44<33:21, 3.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2832, 'learning_rate': 0.0004509345794392524, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▍ | 1216/1784 [1:38:47<32:54, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▍ | 1216/1784 [1:38:47<32:54, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:24:12,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:24:12,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0263, 'learning_rate': 0.00044937694704049846, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▌ | 1218/1784 [1:38:54<32:30, 3.45s/it]g-point operations will not be computed-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▌ | 1218/1784 [1:38:54<32:30, 3.45s/it]g-point operations will not be computed-03 02:24:00,868 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8196, 'learning_rate': 0.0004485981308411215, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▌ | 1219/1784 [1:38:58<32:12, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▌ | 1219/1784 [1:38:58<32:12, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▋ | 1220/1784 [1:39:01<32:00, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▋ | 1220/1784 [1:39:01<32:00, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5021, 'learning_rate': 0.0004470404984423676, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▋ | 1221/1784 [1:39:04<32:07, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▋ | 1221/1784 [1:39:04<32:07, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0788, 'learning_rate': 0.00044626168224299066, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▋ | 1222/1784 [1:39:08<31:50, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|████████████████████████████████████████████████████▋ | 1222/1784 [1:39:08<31:50, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:24:33,164 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:24:33,164 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3081, 'learning_rate': 0.0004447040498442368, 'epoch': 0.69} 69%|████████████████████████████████████████████████████▊ | 1224/1784 [1:39:14<31:10, 3.34s/it]g-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████▊ | 1224/1784 [1:39:14<31:10, 3.34s/it]g-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:24:39,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:24:39,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.802, 'learning_rate': 0.0004431464174454829, 'epoch': 0.69} 69%|████████████████████████████████████████████████████▉ | 1226/1784 [1:39:21<30:39, 3.30s/it]g-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████▉ | 1226/1784 [1:39:21<30:39, 3.30s/it]g-point operations will not be computed-03 02:24:21,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1533, 'learning_rate': 0.0004423676012461059, 'epoch': 0.69} 69%|████████████████████████████████████████████████████▉ | 1227/1784 [1:39:24<30:21, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:47,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████▉ | 1227/1784 [1:39:24<30:21, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:47,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████ | 1228/1784 [1:39:27<30:12, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:47,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████ | 1228/1784 [1:39:27<30:12, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:47,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0941, 'learning_rate': 0.000440809968847352, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████ | 1229/1784 [1:39:30<29:53, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████ | 1229/1784 [1:39:30<29:53, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████ | 1230/1784 [1:39:34<29:48, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████ | 1230/1784 [1:39:34<29:48, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6856, 'learning_rate': 0.00043925233644859815, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▏ | 1231/1784 [1:39:37<29:36, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████▏ | 1231/1784 [1:39:37<29:36, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:02,061 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:02,061 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.313, 'learning_rate': 0.0004376947040498442, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▏ | 1233/1784 [1:39:43<29:02, 3.16s/it]g-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████▏ | 1233/1784 [1:39:43<29:02, 3.16s/it]g-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:08,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:08,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0253, 'learning_rate': 0.00043613707165109035, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▎ | 1235/1784 [1:39:49<28:26, 3.11s/it]g-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████▎ | 1235/1784 [1:39:49<28:26, 3.11s/it]g-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:14,234 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:14,234 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2683, 'learning_rate': 0.0004345794392523365, 'epoch': 0.69} [WARNING|modeling_utils.py:388] 2022-03-03 02:25:14,234 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:24:54,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████▍ | 1237/1784 [1:39:55<27:24, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:18,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████▍ | 1238/1784 [1:39:58<26:45, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:18,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|█████████████████████████████████████████████████████▍ | 1238/1784 [1:39:58<26:45, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:18,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:22,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:18,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:22,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:18,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 6.2024, 'learning_rate': 0.00043224299065420564, 'epoch': 0.69} [WARNING|modeling_utils.py:388] 2022-03-03 02:25:22,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:18,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|█████████████████████████████████████████████████████▌ | 1240/1784 [1:40:03<25:29, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:26,662 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|█████████████████████████████████████████████████████▌ | 1241/1784 [1:40:06<24:49, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|█████████████████████████████████████████████████████▌ | 1241/1784 [1:40:06<24:49, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|█████████████████████████████████████████████████████▌ | 1242/1784 [1:40:08<23:50, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|█████████████████████████████████████████████████████▌ | 1242/1784 [1:40:08<23:50, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:32,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:32,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:34,598 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:34,598 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:36,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:36,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:38,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:38,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:41,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:41,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4442, 'learning_rate': 0.00042601246105919004, 'epoch': 0.7} [WARNING|modeling_utils.py:388] 2022-03-03 02:25:42,483 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:42,483 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:44,146 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:44,146 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5524, 'learning_rate': 0.0004236760124610592, 'epoch': 0.7} [WARNING|modeling_utils.py:388] 2022-03-03 02:25:48,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:48,049 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3266, 'learning_rate': 0.0004228971962616823, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████ | 1252/1784 [1:40:30<24:21, 2.75s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|██████████████████████████████████████████████████████ | 1252/1784 [1:40:30<24:21, 2.75s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.253, 'learning_rate': 0.0004221183800623053, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████ | 1252/1784 [1:40:30<24:21, 2.75s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|██████████████████████████████████████████████████████ | 1253/1784 [1:40:34<27:01, 3.05s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:59,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:25:59,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2668, 'learning_rate': 0.0004205607476635514, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▏ | 1255/1784 [1:40:41<30:03, 3.41s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|██████████████████████████████████████████████████████▏ | 1255/1784 [1:40:41<30:03, 3.41s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8363, 'learning_rate': 0.0004197819314641745, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▏ | 1256/1784 [1:40:45<30:39, 3.48s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|██████████████████████████████████████████████████████▏ | 1256/1784 [1:40:45<30:39, 3.48s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1588, 'learning_rate': 0.00041900311526479753, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▎ | 1257/1784 [1:40:48<31:08, 3.55s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|██████████████████████████████████████████████████████▎ | 1257/1784 [1:40:48<31:08, 3.55s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.038, 'learning_rate': 0.00041822429906542057, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▎ | 1257/1784 [1:40:48<31:08, 3.55s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▎ | 1258/1784 [1:40:52<31:24, 3.58s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:17,698 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:17,698 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1476, 'learning_rate': 0.0004166666666666667, 'epoch': 0.71} 71%|██████████████████████████████████████████████████████▍ | 1260/1784 [1:40:59<31:31, 3.61s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▍ | 1260/1784 [1:40:59<31:31, 3.61s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5123, 'learning_rate': 0.00041588785046728973, 'epoch': 0.71} 71%|██████████████████████████████████████████████████████▍ | 1261/1784 [1:41:03<31:04, 3.56s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▍ | 1261/1784 [1:41:03<31:04, 3.56s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:28,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:28,320 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2043, 'learning_rate': 0.0004143302180685358, 'epoch': 0.71} 71%|██████████████████████████████████████████████████████▌ | 1263/1784 [1:41:10<30:43, 3.54s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▌ | 1263/1784 [1:41:10<30:43, 3.54s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1004, 'learning_rate': 0.0004135514018691589, 'epoch': 0.71} 71%|██████████████████████████████████████████████████████▌ | 1264/1784 [1:41:13<30:29, 3.52s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▌ | 1264/1784 [1:41:13<30:29, 3.52s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:38,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:38,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.656, 'learning_rate': 0.000411993769470405, 'epoch': 0.71} 71%|██████████████████████████████████████████████████████▋ | 1266/1784 [1:41:20<30:14, 3.50s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▋ | 1266/1784 [1:41:20<30:14, 3.50s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2757, 'learning_rate': 0.00041121495327102806, 'epoch': 0.71} 71%|██████████████████████████████████████████████████████▋ | 1267/1784 [1:41:24<30:02, 3.49s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▋ | 1267/1784 [1:41:24<30:02, 3.49s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:49,159 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:49,159 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.139, 'learning_rate': 0.00040965732087227413, 'epoch': 0.71} [WARNING|modeling_utils.py:388] 2022-03-03 02:26:49,159 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▊ | 1269/1784 [1:41:31<29:41, 3.46s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▊ | 1269/1784 [1:41:31<29:41, 3.46s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▊ | 1269/1784 [1:41:31<29:41, 3.46s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▊ | 1270/1784 [1:41:34<29:29, 3.44s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:59,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:26:59,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4783, 'learning_rate': 0.00040732087227414335, 'epoch': 0.71} [WARNING|modeling_utils.py:388] 2022-03-03 02:26:59,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▉ | 1272/1784 [1:41:41<29:00, 3.40s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▉ | 1272/1784 [1:41:41<29:00, 3.40s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▉ | 1272/1784 [1:41:41<29:00, 3.40s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▉ | 1273/1784 [1:41:44<28:39, 3.36s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|██████████████████████████████████████████████████████▉ | 1273/1784 [1:41:44<28:39, 3.36s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:09,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:09,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:09,277 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|███████████████████████████████████████████████████████ | 1275/1784 [1:41:51<28:18, 3.34s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|███████████████████████████████████████████████████████ | 1275/1784 [1:41:51<28:18, 3.34s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|███████████████████████████████████████████████████████ | 1275/1784 [1:41:51<28:18, 3.34s/it]g-point operations will not be computed-03 02:25:29,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████ | 1276/1784 [1:41:54<28:14, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:17,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████ | 1276/1784 [1:41:54<28:14, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:17,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████ | 1277/1784 [1:41:57<27:54, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:17,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████ | 1277/1784 [1:41:57<27:54, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:17,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████ | 1277/1784 [1:41:57<27:54, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:17,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1278/1784 [1:42:00<27:46, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1278/1784 [1:42:00<27:46, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1279/1784 [1:42:04<27:27, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1279/1784 [1:42:04<27:27, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1279/1784 [1:42:04<27:27, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1280/1784 [1:42:07<27:08, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▏ | 1280/1784 [1:42:07<27:08, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:31,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:31,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:31,954 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:24,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▎ | 1282/1784 [1:42:13<26:39, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▎ | 1282/1784 [1:42:13<26:39, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▍ | 1283/1784 [1:42:16<26:19, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▍ | 1283/1784 [1:42:16<26:19, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▍ | 1284/1784 [1:42:19<26:11, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▍ | 1284/1784 [1:42:19<26:11, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:44,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:44,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0492, 'learning_rate': 0.0003964174454828661, 'epoch': 0.72} 72%|███████████████████████████████████████████████████████▌ | 1286/1784 [1:42:25<25:11, 3.04s/it]g-point operations will not be computed-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▌ | 1286/1784 [1:42:25<25:11, 3.04s/it]g-point operations will not be computed-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:50,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:50,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:36,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0677, 'learning_rate': 0.0003948598130841122, 'epoch': 0.72} 72%|███████████████████████████████████████████████████████▌ | 1288/1784 [1:42:31<24:26, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▌ | 1288/1784 [1:42:31<24:26, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0325, 'learning_rate': 0.0003940809968847352, 'epoch': 0.72} 72%|███████████████████████████████████████████████████████▋ | 1289/1784 [1:42:34<23:53, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▋ | 1289/1784 [1:42:34<23:53, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:58,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:27:58,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:01,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:01,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:01,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:27:54,347 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▊ | 1292/1784 [1:42:41<22:03, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:04,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▊ | 1292/1784 [1:42:41<22:03, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:04,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▊ | 1293/1784 [1:42:44<20:47, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:06,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|███████████████████████████████████████████████████████▊ | 1293/1784 [1:42:44<20:47, 2.54s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:06,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████▊ | 1294/1784 [1:42:46<19:44, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:08,926 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████▊ | 1294/1784 [1:42:46<19:44, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:08,926 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████▉ | 1295/1784 [1:42:48<18:44, 2.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:10,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████▉ | 1295/1784 [1:42:48<18:44, 2.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:10,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████▉ | 1297/1784 [1:42:51<16:18, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:12,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████▉ | 1297/1784 [1:42:51<16:18, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:12,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7809, 'learning_rate': 0.0003870716510903427, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████ | 1298/1784 [1:42:53<15:06, 1.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:15,593 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████ | 1298/1784 [1:42:53<15:06, 1.87s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:15,593 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████ | 1299/1784 [1:42:54<13:41, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:16,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████ | 1299/1784 [1:42:54<13:41, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:16,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████ | 1300/1784 [1:42:56<13:46, 1.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:16,779 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████ | 1300/1784 [1:42:56<13:46, 1.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████ | 1300/1784 [1:42:56<13:46, 1.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▏ | 1301/1784 [1:43:00<19:08, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▏ | 1301/1784 [1:43:00<19:08, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▏ | 1301/1784 [1:43:00<19:08, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▏ | 1302/1784 [1:43:04<22:34, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:29,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:29,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3053, 'learning_rate': 0.000382398753894081, 'epoch': 0.73} [WARNING|modeling_utils.py:388] 2022-03-03 02:28:29,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1304/1784 [1:43:11<26:14, 3.28s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1304/1784 [1:43:11<26:14, 3.28s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1304/1784 [1:43:11<26:14, 3.28s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1305/1784 [1:43:15<27:05, 3.39s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1305/1784 [1:43:15<27:05, 3.39s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1305/1784 [1:43:15<27:05, 3.39s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▎ | 1306/1784 [1:43:18<27:43, 3.48s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:44,020 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:44,020 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0027, 'learning_rate': 0.00037928348909657325, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████▍ | 1308/1784 [1:43:26<28:03, 3.54s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▍ | 1308/1784 [1:43:26<28:03, 3.54s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9218, 'learning_rate': 0.00037850467289719624, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████▍ | 1308/1784 [1:43:26<28:03, 3.54s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▍ | 1309/1784 [1:43:29<28:05, 3.55s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▍ | 1309/1784 [1:43:29<28:05, 3.55s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▍ | 1309/1784 [1:43:29<28:05, 3.55s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|████████████████████████████████████████████████████████▌ | 1310/1784 [1:43:33<28:04, 3.55s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:58,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:28:58,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.902, 'learning_rate': 0.00037616822429906545, 'epoch': 0.73} [WARNING|modeling_utils.py:388] 2022-03-03 02:28:58,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▋ | 1312/1784 [1:43:40<27:48, 3.54s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▋ | 1312/1784 [1:43:40<27:48, 3.54s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▋ | 1312/1784 [1:43:40<27:48, 3.54s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▋ | 1313/1784 [1:43:43<27:30, 3.50s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:08,662 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:08,662 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8196, 'learning_rate': 0.00037383177570093456, 'epoch': 0.74} [WARNING|modeling_utils.py:388] 2022-03-03 02:29:08,662 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▊ | 1315/1784 [1:43:50<27:01, 3.46s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▊ | 1315/1784 [1:43:50<27:01, 3.46s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▊ | 1315/1784 [1:43:50<27:01, 3.46s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▊ | 1316/1784 [1:43:53<26:48, 3.44s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:18,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:18,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9177, 'learning_rate': 0.0003714953271028038, 'epoch': 0.74} [WARNING|modeling_utils.py:388] 2022-03-03 02:29:18,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▉ | 1318/1784 [1:44:00<26:40, 3.44s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▉ | 1318/1784 [1:44:00<26:40, 3.44s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▉ | 1318/1784 [1:44:00<26:40, 3.44s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████▉ | 1319/1784 [1:44:04<26:29, 3.42s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:29,062 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:29,062 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8214, 'learning_rate': 0.0003691588785046729, 'epoch': 0.74} [WARNING|modeling_utils.py:388] 2022-03-03 02:29:29,062 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████ | 1321/1784 [1:44:10<26:15, 3.40s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████ | 1321/1784 [1:44:10<26:15, 3.40s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████ | 1321/1784 [1:44:10<26:15, 3.40s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████ | 1322/1784 [1:44:14<26:01, 3.38s/it]g-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:39,052 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:29:39,052 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4765, 'learning_rate': 0.00036682242990654205, 'epoch': 0.74} [WARNING|modeling_utils.py:388] 2022-03-03 02:29:39,052 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:28:19,942 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▏ | 1324/1784 [1:44:20<25:26, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▏ | 1325/1784 [1:44:23<25:12, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▏ | 1325/1784 [1:44:23<25:12, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0606, 'learning_rate': 0.0003652647975077882, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▏ | 1325/1784 [1:44:23<25:12, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▏ | 1326/1784 [1:44:27<24:58, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▏ | 1326/1784 [1:44:27<24:58, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▏ | 1326/1784 [1:44:27<24:58, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:43,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1327/1784 [1:44:30<24:41, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:53,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1327/1784 [1:44:30<24:41, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:53,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1328/1784 [1:44:33<24:35, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:53,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1328/1784 [1:44:33<24:35, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:53,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1328/1784 [1:44:33<24:35, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:53,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1329/1784 [1:44:36<24:19, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:59,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|█████████████████████████████████████████████████████████▎ | 1329/1784 [1:44:36<24:19, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:59,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1330/1784 [1:44:39<24:07, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:59,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1330/1784 [1:44:39<24:07, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:59,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1330/1784 [1:44:39<24:07, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:29:59,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1331/1784 [1:44:43<23:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:06,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1331/1784 [1:44:43<23:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:06,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1332/1784 [1:44:46<23:41, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:06,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1332/1784 [1:44:46<23:41, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:06,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▍ | 1332/1784 [1:44:46<23:41, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:06,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▌ | 1333/1784 [1:44:49<23:28, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▌ | 1333/1784 [1:44:49<23:28, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▌ | 1334/1784 [1:44:52<23:02, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:16,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:16,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.878, 'learning_rate': 0.0003574766355140187, 'epoch': 0.75} [WARNING|modeling_utils.py:388] 2022-03-03 02:30:16,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▋ | 1336/1784 [1:44:57<22:15, 2.98s/it]g-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:22,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:22,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1854, 'learning_rate': 0.00035591900311526483, 'epoch': 0.75} [WARNING|modeling_utils.py:388] 2022-03-03 02:30:22,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:12,273 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▊ | 1338/1784 [1:45:03<21:27, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:26,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▊ | 1338/1784 [1:45:03<21:27, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:26,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▊ | 1339/1784 [1:45:06<20:58, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:26,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:30,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:26,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:30,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:26,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4792, 'learning_rate': 0.00035358255451713394, 'epoch': 0.75} [WARNING|modeling_utils.py:388] 2022-03-03 02:30:30,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:26,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▉ | 1341/1784 [1:45:11<19:50, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:34,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▉ | 1341/1784 [1:45:11<19:50, 2.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:34,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▉ | 1342/1784 [1:45:13<19:01, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:36,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▉ | 1342/1784 [1:45:13<19:01, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:36,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▉ | 1343/1784 [1:45:15<18:00, 2.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:38,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|█████████████████████████████████████████████████████████▉ | 1343/1784 [1:45:15<18:00, 2.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:38,458 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|██████████████████████████████████████████████████████████ | 1344/1784 [1:45:17<17:01, 2.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:40,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|██████████████████████████████████████████████████████████ | 1344/1784 [1:45:17<17:01, 2.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:40,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|██████████████████████████████████████████████████████████ | 1345/1784 [1:45:19<16:01, 2.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:42,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|██████████████████████████████████████████████████████████ | 1345/1784 [1:45:19<16:01, 2.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:42,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▏ | 1347/1784 [1:45:22<13:41, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:43,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▏ | 1347/1784 [1:45:22<13:41, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:43,826 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.8315, 'learning_rate': 0.00034813084112149536, 'epoch': 0.76} 76%|██████████████████████████████████████████████████████████▏ | 1348/1784 [1:45:24<12:33, 1.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:46,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▏ | 1348/1784 [1:45:24<12:33, 1.73s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:46,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:47,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:30:47,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▎ | 1350/1784 [1:45:27<11:41, 1.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:50,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▎ | 1351/1784 [1:45:31<17:00, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:50,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▎ | 1351/1784 [1:45:31<17:00, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:50,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▎ | 1351/1784 [1:45:31<17:00, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▎ | 1352/1784 [1:45:35<20:06, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▎ | 1352/1784 [1:45:35<20:06, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3054, 'learning_rate': 0.0003442367601246106, 'epoch': 0.76} 76%|██████████████████████████████████████████████████████████▎ | 1352/1784 [1:45:35<20:06, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1353/1784 [1:45:38<22:08, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1353/1784 [1:45:38<22:08, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1353/1784 [1:45:38<22:08, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1354/1784 [1:45:42<23:23, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1354/1784 [1:45:42<23:23, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1354/1784 [1:45:42<23:23, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▍ | 1355/1784 [1:45:46<24:18, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:11,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:11,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2424, 'learning_rate': 0.0003411214953271028, 'epoch': 0.76} 76%|██████████████████████████████████████████████████████████▌ | 1357/1784 [1:45:53<25:06, 3.53s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▌ | 1357/1784 [1:45:53<25:06, 3.53s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.745, 'learning_rate': 0.0003403426791277259, 'epoch': 0.76} 76%|██████████████████████████████████████████████████████████▌ | 1357/1784 [1:45:53<25:06, 3.53s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▌ | 1358/1784 [1:45:57<25:15, 3.56s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▌ | 1358/1784 [1:45:57<25:15, 3.56s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▌ | 1358/1784 [1:45:57<25:15, 3.56s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▋ | 1359/1784 [1:46:00<25:15, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:25,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:25,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5997, 'learning_rate': 0.000338006230529595, 'epoch': 0.76} 76%|██████████████████████████████████████████████████████████▋ | 1361/1784 [1:46:07<25:10, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▋ | 1361/1784 [1:46:07<25:10, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9694, 'learning_rate': 0.0003372274143302181, 'epoch': 0.76} 76%|██████████████████████████████████████████████████████████▋ | 1361/1784 [1:46:07<25:10, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▊ | 1362/1784 [1:46:11<25:06, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▊ | 1362/1784 [1:46:11<25:06, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▊ | 1362/1784 [1:46:11<25:06, 3.57s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|██████████████████████████████████████████████████████████▊ | 1363/1784 [1:46:15<24:59, 3.56s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:40,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:40,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5148, 'learning_rate': 0.0003348909657320872, 'epoch': 0.76} 77%|██████████████████████████████████████████████████████████▉ | 1365/1784 [1:46:22<24:40, 3.53s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████▉ | 1365/1784 [1:46:22<24:40, 3.53s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5671, 'learning_rate': 0.0003341121495327103, 'epoch': 0.77} 77%|██████████████████████████████████████████████████████████▉ | 1365/1784 [1:46:22<24:40, 3.53s/it]g-point operations will not be computed-03 02:30:54,847 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████▉ | 1366/1784 [1:46:25<24:18, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████ | 1367/1784 [1:46:28<23:57, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████ | 1367/1784 [1:46:28<23:57, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0792, 'learning_rate': 0.0003325545171339564, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████ | 1367/1784 [1:46:28<23:57, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████ | 1368/1784 [1:46:32<23:42, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:57,123 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:31:57,123 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1372, 'learning_rate': 0.0003309968847352025, 'epoch': 0.77} [WARNING|modeling_utils.py:388] 2022-03-03 02:32:00,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:00,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1357, 'learning_rate': 0.0003302180685358255, 'epoch': 0.77} [WARNING|modeling_utils.py:388] 2022-03-03 02:32:00,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▏ | 1371/1784 [1:46:42<23:07, 3.36s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:07,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:07,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8684, 'learning_rate': 0.00032866043613707165, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▎ | 1373/1784 [1:46:48<22:54, 3.34s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▎ | 1373/1784 [1:46:48<22:54, 3.34s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5748, 'learning_rate': 0.00032788161993769474, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▎ | 1373/1784 [1:46:48<22:54, 3.34s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▎ | 1374/1784 [1:46:52<22:46, 3.33s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:16,993 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:16,993 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2246, 'learning_rate': 0.0003263239875389408, 'epoch': 0.77} [WARNING|modeling_utils.py:388] 2022-03-03 02:32:16,993 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▍ | 1376/1784 [1:46:58<22:24, 3.30s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:23,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:23,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5553, 'learning_rate': 0.00032476635514018694, 'epoch': 0.77} [WARNING|modeling_utils.py:388] 2022-03-03 02:32:23,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▍ | 1378/1784 [1:47:05<21:58, 3.25s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▍ | 1378/1784 [1:47:05<21:58, 3.25s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▍ | 1378/1784 [1:47:05<21:58, 3.25s/it]g-point operations will not be computed-03 02:31:48,767 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▌ | 1379/1784 [1:47:08<21:45, 3.22s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▌ | 1380/1784 [1:47:11<21:35, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▌ | 1380/1784 [1:47:11<21:35, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0296, 'learning_rate': 0.00032242990654205605, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▌ | 1380/1784 [1:47:11<21:35, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|███████████████████████████████████████████████████████████▌ | 1381/1784 [1:47:14<21:26, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:39,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:39,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1008, 'learning_rate': 0.0003208722741433022, 'epoch': 0.77} [WARNING|modeling_utils.py:388] 2022-03-03 02:32:39,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▋ | 1383/1784 [1:47:20<21:17, 3.19s/it]g-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:45,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:32:45,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1655, 'learning_rate': 0.00031931464174454825, 'epoch': 0.78} [WARNING|modeling_utils.py:388] 2022-03-03 02:32:45,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:31,470 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▊ | 1385/1784 [1:47:27<20:38, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:50,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▊ | 1386/1784 [1:47:29<20:11, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:50,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▊ | 1386/1784 [1:47:29<20:11, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:50,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0537, 'learning_rate': 0.0003177570093457944, 'epoch': 0.78} 78%|███████████████████████████████████████████████████████████▊ | 1386/1784 [1:47:29<20:11, 3.04s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:50,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▊ | 1387/1784 [1:47:32<19:44, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:55,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▊ | 1387/1784 [1:47:32<19:44, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:55,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▉ | 1388/1784 [1:47:35<19:28, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:32:55,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:00,013 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:55,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:00,013 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:55,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9623, 'learning_rate': 0.00031542056074766354, 'epoch': 0.78} [WARNING|modeling_utils.py:388] 2022-03-03 02:33:00,013 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:32:55,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▉ | 1390/1784 [1:47:41<18:36, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:04,046 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████▉ | 1390/1784 [1:47:41<18:36, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:04,046 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|████████████████████████████████████████████████████████████ | 1391/1784 [1:47:43<18:05, 2.76s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|████████████████████████████████████████████████████████████ | 1392/1784 [1:47:46<17:29, 2.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|████████████████████████████████████████████████████████████ | 1392/1784 [1:47:46<17:29, 2.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:10,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:10,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:12,081 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:12,081 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:13,963 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:13,963 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:15,679 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:15,679 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8895, 'learning_rate': 0.0003099688473520249, 'epoch': 0.78} [WARNING|modeling_utils.py:388] 2022-03-03 02:33:18,687 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:18,687 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:19,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:19,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:21,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:21,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.035, 'learning_rate': 0.0003068535825545171, 'epoch': 0.78} [WARNING|modeling_utils.py:388] 2022-03-03 02:33:21,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:25,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:25,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:25,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▌ | 1402/1784 [1:48:07<17:28, 2.74s/it]g-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▌ | 1402/1784 [1:48:07<17:28, 2.74s/it]g-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▌ | 1402/1784 [1:48:07<17:28, 2.74s/it]g-point operations will not be computed-03 02:33:06,591 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▌ | 1403/1784 [1:48:11<19:08, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▌ | 1404/1784 [1:48:14<20:14, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▌ | 1404/1784 [1:48:14<20:14, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.973, 'learning_rate': 0.00030373831775700936, 'epoch': 0.79} 79%|████████████████████████████████████████████████████████████▌ | 1404/1784 [1:48:14<20:14, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▋ | 1405/1784 [1:48:18<20:58, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▋ | 1405/1784 [1:48:18<20:58, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▋ | 1405/1784 [1:48:18<20:58, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▋ | 1406/1784 [1:48:22<21:18, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:47,284 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:33:47,284 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0098, 'learning_rate': 0.0003014018691588785, 'epoch': 0.79} 79%|████████████████████████████████████████████████████████████▊ | 1408/1784 [1:48:29<21:55, 3.50s/it]g-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▊ | 1408/1784 [1:48:29<21:55, 3.50s/it]g-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4956, 'learning_rate': 0.00030062305295950156, 'epoch': 0.79} 79%|████████████████████████████████████████████████████████████▊ | 1409/1784 [1:48:32<21:59, 3.52s/it]g-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▊ | 1409/1784 [1:48:32<21:59, 3.52s/it]g-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0559, 'learning_rate': 0.00029984423676012465, 'epoch': 0.79} 79%|████████████████████████████████████████████████████████████▊ | 1409/1784 [1:48:32<21:59, 3.52s/it]g-point operations will not be computed-03 02:33:34,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▊ | 1410/1784 [1:48:36<21:50, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▉ | 1411/1784 [1:48:39<21:48, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▉ | 1411/1784 [1:48:39<21:48, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9184, 'learning_rate': 0.0002982866043613707, 'epoch': 0.79} 79%|████████████████████████████████████████████████████████████▉ | 1412/1784 [1:48:43<21:33, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▉ | 1412/1784 [1:48:43<21:33, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8348, 'learning_rate': 0.00029750778816199376, 'epoch': 0.79} 79%|████████████████████████████████████████████████████████████▉ | 1412/1784 [1:48:43<21:33, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████▉ | 1413/1784 [1:48:46<21:30, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:11,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:11,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4589, 'learning_rate': 0.0002959501557632399, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████ | 1415/1784 [1:48:53<21:19, 3.47s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|█████████████████████████████████████████████████████████████ | 1415/1784 [1:48:53<21:19, 3.47s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0411, 'learning_rate': 0.0002951713395638629, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████ | 1415/1784 [1:48:53<21:19, 3.47s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|█████████████████████████████████████████████████████████████ | 1416/1784 [1:48:57<21:19, 3.48s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:22,210 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:22,210 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1757, 'learning_rate': 0.00029361370716510905, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▏ | 1418/1784 [1:49:03<20:57, 3.43s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|█████████████████████████████████████████████████████████████▏ | 1418/1784 [1:49:03<20:57, 3.43s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.6576, 'learning_rate': 0.0002928348909657321, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▏ | 1418/1784 [1:49:03<20:57, 3.43s/it]g-point operations will not be computed-03 02:33:59,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▏ | 1419/1784 [1:49:07<20:43, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▎ | 1420/1784 [1:49:10<20:32, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▎ | 1420/1784 [1:49:10<20:32, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8022, 'learning_rate': 0.00029127725856697815, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▎ | 1421/1784 [1:49:14<20:23, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▎ | 1421/1784 [1:49:14<20:23, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:38,801 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:38,801 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1439, 'learning_rate': 0.0002897196261682243, 'epoch': 0.8} [WARNING|modeling_utils.py:388] 2022-03-03 02:34:42,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:42,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.919, 'learning_rate': 0.00028894080996884737, 'epoch': 0.8} [WARNING|modeling_utils.py:388] 2022-03-03 02:34:42,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▍ | 1424/1784 [1:49:23<19:43, 3.29s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:48,461 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:48,461 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.4473, 'learning_rate': 0.00028738317757009345, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▌ | 1426/1784 [1:49:30<19:17, 3.23s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▌ | 1426/1784 [1:49:30<19:17, 3.23s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:54,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:34:54,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8075, 'learning_rate': 0.00028582554517133957, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▋ | 1428/1784 [1:49:36<19:00, 3.20s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▋ | 1428/1784 [1:49:36<19:00, 3.20s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:01,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:01,189 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3454, 'learning_rate': 0.0002842679127725857, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▋ | 1430/1784 [1:49:42<18:45, 3.18s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▋ | 1430/1784 [1:49:42<18:45, 3.18s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:07,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:07,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.7627, 'learning_rate': 0.00028271028037383177, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▊ | 1432/1784 [1:49:48<18:25, 3.14s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▊ | 1432/1784 [1:49:48<18:25, 3.14s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:13,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:13,568 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3451, 'learning_rate': 0.0002811526479750779, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▉ | 1434/1784 [1:49:55<17:57, 3.08s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▉ | 1434/1784 [1:49:55<17:57, 3.08s/it]g-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:19,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:19,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:34:30,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.248, 'learning_rate': 0.00027959501557632397, 'epoch': 0.8} 80%|█████████████████████████████████████████████████████████████▉ | 1436/1784 [1:50:00<17:08, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:23,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|█████████████████████████████████████████████████████████████▉ | 1436/1784 [1:50:00<17:08, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:23,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████ | 1437/1784 [1:50:03<16:46, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:23,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████ | 1437/1784 [1:50:03<16:46, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:23,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:27,757 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:23,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:27,757 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:23,691 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9584, 'learning_rate': 0.00027725856697819314, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████ | 1439/1784 [1:50:08<15:56, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████ | 1439/1784 [1:50:08<15:56, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████▏ | 1440/1784 [1:50:11<15:30, 2.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████▏ | 1440/1784 [1:50:11<15:30, 2.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:35,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:37,721 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:37,721 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:39,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:39,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:42,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:42,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:43,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:43,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:45,682 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:45,682 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:47,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:47,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2024, 'learning_rate': 0.0002702492211838006, 'epoch': 0.81} [WARNING|modeling_utils.py:388] 2022-03-03 02:35:49,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:49,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:51,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:51,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9458, 'learning_rate': 0.0002679127725856698, 'epoch': 0.81} [WARNING|modeling_utils.py:388] 2022-03-03 02:35:55,536 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:35:55,536 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.098, 'learning_rate': 0.0002671339563862928, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████▋ | 1452/1784 [1:50:37<15:22, 2.78s/it]g-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████▋ | 1452/1784 [1:50:37<15:22, 2.78s/it]g-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0626, 'learning_rate': 0.00026635514018691586, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████▋ | 1453/1784 [1:50:41<17:05, 3.10s/it]g-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|██████████████████████████████████████████████████████████████▋ | 1453/1784 [1:50:41<17:05, 3.10s/it]g-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8657, 'learning_rate': 0.00026557632398753895, 'epoch': 0.81} 82%|██████████████████████████████████████████████████████████████▊ | 1454/1784 [1:50:45<18:00, 3.27s/it]g-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████▊ | 1454/1784 [1:50:45<18:00, 3.27s/it]g-point operations will not be computed-03 02:35:31,709 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8222, 'learning_rate': 0.000264797507788162, 'epoch': 0.82} 82%|██████████████████████████████████████████████████████████████▊ | 1455/1784 [1:50:49<18:42, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:12,495 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████▊ | 1455/1784 [1:50:49<18:42, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:12,495 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1035, 'learning_rate': 0.0002640186915887851, 'epoch': 0.82} 82%|██████████████████████████████████████████████████████████████▊ | 1456/1784 [1:50:52<19:07, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████▉ | 1457/1784 [1:50:56<19:21, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████▉ | 1457/1784 [1:50:56<19:21, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3442, 'learning_rate': 0.00026246105919003115, 'epoch': 0.82} 82%|██████████████████████████████████████████████████████████████▉ | 1458/1784 [1:51:00<19:24, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████▉ | 1458/1784 [1:51:00<19:24, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2567, 'learning_rate': 0.0002616822429906542, 'epoch': 0.82} 82%|██████████████████████████████████████████████████████████████▉ | 1459/1784 [1:51:03<19:29, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████▉ | 1459/1784 [1:51:03<19:29, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1102, 'learning_rate': 0.0002609034267912773, 'epoch': 0.82} 82%|██████████████████████████████████████████████████████████████▉ | 1459/1784 [1:51:03<19:29, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:16,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████ | 1460/1784 [1:51:07<19:30, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████ | 1461/1784 [1:51:10<19:23, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████ | 1461/1784 [1:51:10<19:23, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9823, 'learning_rate': 0.00025934579439252335, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████ | 1462/1784 [1:51:14<19:18, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████ | 1462/1784 [1:51:14<19:18, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1301, 'learning_rate': 0.0002585669781931464, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▏ | 1463/1784 [1:51:18<19:15, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▏ | 1463/1784 [1:51:18<19:15, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8129, 'learning_rate': 0.0002577881619937695, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▏ | 1464/1784 [1:51:21<19:08, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▏ | 1464/1784 [1:51:21<19:08, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:36:46,664 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:36:46,664 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3481, 'learning_rate': 0.0002562305295950156, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▎ | 1466/1784 [1:51:28<18:34, 3.50s/it]g-point operations will not be computed-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▎ | 1466/1784 [1:51:28<18:34, 3.50s/it]g-point operations will not be computed-03 02:36:30,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0102, 'learning_rate': 0.0002554517133956386, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▎ | 1467/1784 [1:51:31<18:27, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▎ | 1467/1784 [1:51:31<18:27, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1034, 'learning_rate': 0.0002546728971962617, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▎ | 1468/1784 [1:51:35<18:13, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▎ | 1468/1784 [1:51:35<18:13, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▎ | 1468/1784 [1:51:35<18:13, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▍ | 1469/1784 [1:51:38<18:07, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▍ | 1469/1784 [1:51:38<18:07, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▍ | 1469/1784 [1:51:38<18:07, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▍ | 1470/1784 [1:51:42<18:04, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|███████████████████████████████████████████████████████████████▍ | 1470/1784 [1:51:42<18:04, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:07,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:07,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:07,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▌ | 1472/1784 [1:51:49<17:47, 3.42s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▌ | 1472/1784 [1:51:49<17:47, 3.42s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▌ | 1472/1784 [1:51:49<17:47, 3.42s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▌ | 1473/1784 [1:51:52<17:40, 3.41s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▌ | 1473/1784 [1:51:52<17:40, 3.41s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:17,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:17,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:17,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▋ | 1475/1784 [1:51:59<17:23, 3.38s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:24,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:24,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1813, 'learning_rate': 0.00024766355140186917, 'epoch': 0.83} [WARNING|modeling_utils.py:388] 2022-03-03 02:37:24,008 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▋ | 1477/1784 [1:52:05<16:59, 3.32s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▋ | 1477/1784 [1:52:05<16:59, 3.32s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▋ | 1477/1784 [1:52:05<16:59, 3.32s/it]g-point operations will not be computed-03 02:36:55,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▊ | 1478/1784 [1:52:08<16:50, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▊ | 1478/1784 [1:52:08<16:50, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▊ | 1479/1784 [1:52:12<16:41, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▊ | 1479/1784 [1:52:12<16:41, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▊ | 1479/1784 [1:52:12<16:41, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▉ | 1480/1784 [1:52:15<16:33, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:40,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:40,122 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9763, 'learning_rate': 0.00024376947040498443, 'epoch': 0.83} 83%|███████████████████████████████████████████████████████████████▉ | 1482/1784 [1:52:21<16:13, 3.22s/it]g-point operations will not be computed-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████▉ | 1482/1784 [1:52:21<16:13, 3.22s/it]g-point operations will not be computed-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.5776, 'learning_rate': 0.00024299065420560747, 'epoch': 0.83} 83%|███████████████████████████████████████████████████████████████▉ | 1482/1784 [1:52:21<16:13, 3.22s/it]g-point operations will not be computed-03 02:37:32,160 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████ | 1483/1784 [1:52:24<15:56, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████ | 1484/1784 [1:52:27<15:44, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████ | 1484/1784 [1:52:27<15:44, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:52,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:52,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:52,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████▏ | 1486/1784 [1:52:33<15:07, 3.05s/it]g-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████▏ | 1486/1784 [1:52:33<15:07, 3.05s/it]g-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:58,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:37:58,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.161, 'learning_rate': 0.00023909657320872276, 'epoch': 0.83} [WARNING|modeling_utils.py:388] 2022-03-03 02:37:58,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:37:48,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████▏ | 1488/1784 [1:52:39<14:24, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████▎ | 1489/1784 [1:52:42<13:58, 2.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|████████████████████████████████████████████████████████████████▎ | 1489/1784 [1:52:42<13:58, 2.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:38:06,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:38:06,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.789, 'learning_rate': 0.0002367601246105919, 'epoch': 0.84} [WARNING|modeling_utils.py:388] 2022-03-03 02:38:08,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:38:08,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:38:08,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:38:02,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▍ | 1492/1784 [1:52:49<12:45, 2.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:12,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▍ | 1492/1784 [1:52:49<12:45, 2.62s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:12,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▍ | 1493/1784 [1:52:52<12:27, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:14,833 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▍ | 1493/1784 [1:52:52<12:27, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:14,833 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▍ | 1494/1784 [1:52:54<11:53, 2.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:16,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▍ | 1494/1784 [1:52:54<11:53, 2.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:16,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▌ | 1495/1784 [1:52:56<11:08, 2.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:18,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▌ | 1495/1784 [1:52:56<11:08, 2.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:18,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▌ | 1496/1784 [1:52:58<10:20, 2.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:20,477 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▌ | 1496/1784 [1:52:58<10:20, 2.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:20,477 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0101, 'learning_rate': 0.00023130841121495329, 'epoch': 0.84} 84%|████████████████████████████████████████████████████████████████▋ | 1498/1784 [1:53:01<08:36, 1.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:21,979 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▋ | 1498/1784 [1:53:01<08:36, 1.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:21,979 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▋ | 1499/1784 [1:53:02<07:52, 1.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:24,580 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████▋ | 1499/1784 [1:53:02<07:52, 1.66s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:38:24,580 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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] 2022-03-03 02:38:25,851 >> Num examples = 2642 | 1500/1784 [1:53:04<08:01, 1.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:38:25,851 >> Num examples = 2642 | 1500/1784 [1:53:04<08:01, 1.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:38:25,851 >> Num examples = 2642 | 1500/1784 [1:53:04<08:01, 1.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:38:25,851 >> Num examples = 2642 | 1500/1784 [1:53:04<08:01, 1.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 1%|█ | 4/331 [00:06<09:56, 1.83s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▎ | 5/331 [00:09<11:23, 2.10s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▌ | 6/331 [00:11<12:20, 2.28s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█▊ | 7/331 [00:14<12:27, 2.31s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██ | 8/331 [00:16<12:51, 2.39s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▎ | 9/331 [00:19<13:23, 2.50s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▍ | 10/331 [00:22<14:18, 2.68s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▋ | 11/331 [00:25<13:52, 2.60s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██▉ | 12/331 [00:27<13:34, 2.55s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▏ | 13/331 [00:30<13:26, 2.54s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▍ | 14/331 [00:32<13:20, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▋ | 15/331 [00:35<14:31, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███▉ | 16/331 [00:39<15:31, 2.96s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▏ | 17/331 [00:42<15:42, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▍ | 18/331 [00:44<14:23, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▋ | 19/331 [00:47<14:05, 2.71s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████▉ | 20/331 [00:49<13:06, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▏ | 21/331 [00:52<13:35, 2.63s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▍ | 22/331 [00:55<14:49, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▋ | 23/331 [00:59<16:07, 3.14s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████▉ | 24/331 [01:03<17:01, 3.33s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▏ | 25/331 [01:06<16:24, 3.22s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▍ | 26/331 [01:08<15:13, 2.99s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▋ | 27/331 [01:11<15:12, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████▉ | 28/331 [01:14<14:42, 2.91s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▏ | 29/331 [01:16<14:16, 2.83s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▍ | 30/331 [01:19<13:40, 2.73s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▋ | 31/331 [01:21<13:04, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████▉ | 32/331 [01:24<12:46, 2.56s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▏ | 33/331 [01:26<12:52, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▍ | 34/331 [01:29<12:52, 2.60s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▋ | 35/331 [01:32<13:03, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████▉ | 36/331 [01:35<13:41, 2.78s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▏ | 37/331 [01:38<14:20, 2.93s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▍ | 38/331 [01:41<14:32, 2.98s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▋ | 39/331 [01:44<14:35, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████▉ | 40/331 [01:46<13:21, 2.75s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▏ | 41/331 [01:49<12:40, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▍ | 42/331 [01:52<13:37, 2.83s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▋ | 43/331 [01:55<14:18, 2.98s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████▉ | 44/331 [01:59<14:44, 3.08s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▏ | 45/331 [02:01<13:55, 2.92s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▍ | 46/331 [02:03<12:49, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▋ | 47/331 [02:06<12:02, 2.55s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████▉ | 48/331 [02:08<12:15, 2.60s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▏ | 49/331 [02:11<12:50, 2.73s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▍ | 50/331 [02:14<12:42, 2.71s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▋ | 51/331 [02:17<13:04, 2.80s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████▉ | 52/331 [02:20<12:37, 2.71s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▏ | 53/331 [02:22<12:40, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▍ | 54/331 [02:25<12:04, 2.61s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▋ | 55/331 [02:28<13:12, 2.87s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████▊ | 56/331 [02:31<12:58, 2.83s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████ | 57/331 [02:33<12:28, 2.73s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▎ | 58/331 [02:37<12:59, 2.86s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▌ | 59/331 [02:39<12:09, 2.68s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████▊ | 60/331 [02:41<11:53, 2.63s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████ | 61/331 [02:44<12:18, 2.73s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▎ | 62/331 [02:47<12:06, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▌ | 63/331 [02:51<13:10, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████▊ | 64/331 [02:53<12:44, 2.86s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████ | 65/331 [02:56<12:30, 2.82s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▎ | 66/331 [03:00<13:43, 3.11s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▌ | 67/331 [03:03<14:23, 3.27s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████▊ | 68/331 [03:07<14:29, 3.31s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████ | 69/331 [03:10<14:11, 3.25s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▎ | 70/331 [03:13<13:53, 3.19s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▌ | 71/331 [03:16<13:59, 3.23s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████▊ | 72/331 [03:19<13:49, 3.20s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████ | 73/331 [03:22<13:26, 3.13s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▎ | 74/331 [03:25<13:12, 3.08s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▌ | 75/331 [03:29<13:24, 3.14s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████▊ | 76/331 [03:31<12:44, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████ | 77/331 [03:34<12:30, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▎ | 78/331 [03:37<11:57, 2.84s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▌ | 79/331 [03:39<11:30, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▌ | 79/331 [03:39<11:30, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████▌ | 79/331 [03:39<11:30, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████ | 81/331 [03:45<11:48, 2.83s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▎ | 82/331 [03:48<11:28, 2.77s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▌ | 83/331 [03:51<11:53, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████▊ | 84/331 [03:54<12:37, 3.07s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████ | 85/331 [03:56<11:40, 2.85s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▎ | 86/331 [04:00<12:14, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▌ | 87/331 [04:03<11:47, 2.90s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████▊ | 88/331 [04:05<11:25, 2.82s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████ | 89/331 [04:07<10:33, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▎ | 90/331 [04:10<10:04, 2.51s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▌ | 91/331 [04:13<10:34, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████▊ | 92/331 [04:15<09:52, 2.48s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████ | 93/331 [04:17<10:01, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▎ | 94/331 [04:20<10:16, 2.60s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▌ | 95/331 [04:23<10:22, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████▊ | 96/331 [04:25<10:27, 2.67s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████ | 97/331 [04:28<10:04, 2.58s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▎ | 98/331 [04:31<10:26, 2.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▌ | 99/331 [04:34<10:26, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▍ | 100/331 [04:36<09:59, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▋ | 101/331 [04:38<09:54, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████▉ | 102/331 [04:42<10:43, 2.81s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▏ | 103/331 [04:44<10:12, 2.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▍ | 104/331 [04:47<10:08, 2.68s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▋ | 105/331 [04:50<10:10, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████▉ | 106/331 [04:52<10:08, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▏ | 107/331 [04:54<09:27, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▍ | 108/331 [04:57<09:17, 2.50s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▋ | 109/331 [04:59<09:11, 2.48s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████▉ | 110/331 [05:02<09:44, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▏ | 111/331 [05:05<09:50, 2.68s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▍ | 112/331 [05:08<09:45, 2.67s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▋ | 113/331 [05:10<09:14, 2.54s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████▉ | 114/331 [05:13<09:20, 2.58s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▏ | 115/331 [05:15<09:18, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▍ | 116/331 [05:18<09:35, 2.68s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▋ | 117/331 [05:21<09:33, 2.68s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████▉ | 118/331 [05:23<09:18, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████ | 119/331 [05:26<09:16, 2.63s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▎ | 120/331 [05:29<09:13, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▌ | 121/331 [05:32<09:39, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████▊ | 122/331 [05:34<09:27, 2.71s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████ | 123/331 [05:38<10:04, 2.91s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▎ | 124/331 [05:40<09:58, 2.89s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▌ | 125/331 [05:44<10:34, 3.08s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████▊ | 126/331 [05:47<10:37, 3.11s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████ | 127/331 [05:51<10:59, 3.23s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▎ | 128/331 [05:54<11:00, 3.25s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▌ | 129/331 [05:57<10:40, 3.17s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████▊ | 130/331 [06:00<10:47, 3.22s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████ | 131/331 [06:04<11:02, 3.31s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▎ | 132/331 [06:07<10:26, 3.15s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▌ | 133/331 [06:09<09:48, 2.97s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████▊ | 134/331 [06:12<09:27, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████ | 135/331 [06:15<09:34, 2.93s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▎ | 136/331 [06:18<09:51, 3.03s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▌ | 137/331 [06:22<10:10, 3.15s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████▊ | 138/331 [06:25<10:25, 3.24s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████ | 139/331 [06:27<09:17, 2.90s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▎ | 140/331 [06:31<09:55, 3.12s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▌ | 141/331 [06:33<09:27, 2.98s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▋ | 142/331 [06:36<09:11, 2.92s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████▉ | 143/331 [06:40<09:33, 3.05s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▏ | 144/331 [06:42<09:12, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▍ | 145/331 [06:45<09:05, 2.93s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▋ | 146/331 [06:49<09:28, 3.07s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████▉ | 147/331 [06:51<09:06, 2.97s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▏ | 148/331 [06:54<08:33, 2.81s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▍ | 149/331 [06:56<08:06, 2.67s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▋ | 150/331 [06:59<08:25, 2.79s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████▉ | 151/331 [07:02<08:19, 2.77s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▏ | 152/331 [07:04<07:55, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▍ | 153/331 [07:07<07:49, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▋ | 154/331 [07:10<08:06, 2.75s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████▉ | 155/331 [07:13<08:27, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▏ | 156/331 [07:16<08:44, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▍ | 157/331 [07:20<09:03, 3.12s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▋ | 158/331 [07:23<09:07, 3.16s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████▉ | 159/331 [07:26<09:10, 3.20s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▏ | 160/331 [07:29<08:38, 3.03s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▍ | 161/331 [07:32<08:22, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▋ | 162/331 [07:35<08:45, 3.11s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████▉ | 163/331 [07:38<08:51, 3.17s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▏ | 164/331 [07:41<08:24, 3.02s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▍ | 165/331 [07:44<08:09, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▌ | 166/331 [07:47<07:58, 2.90s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████▊ | 167/331 [07:50<08:06, 2.97s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████ | 168/331 [07:52<07:40, 2.82s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▎ | 169/331 [07:55<07:48, 2.89s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▌ | 170/331 [07:58<07:22, 2.75s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████▊ | 171/331 [08:01<07:21, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████ | 172/331 [08:03<06:57, 2.63s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▎ | 173/331 [08:06<07:06, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▌ | 174/331 [08:08<06:46, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████▊ | 175/331 [08:11<06:52, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████ | 176/331 [08:13<06:39, 2.58s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▎ | 177/331 [08:16<07:04, 2.75s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▌ | 178/331 [08:20<07:31, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▌ | 178/331 [08:20<07:31, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████▌ | 178/331 [08:20<07:31, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████ | 180/331 [08:26<07:41, 3.05s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▎ | 181/331 [08:29<07:39, 3.06s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▌ | 182/331 [08:32<07:06, 2.86s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████▊ | 183/331 [08:34<06:34, 2.66s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████ | 184/331 [08:36<06:11, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▎ | 185/331 [08:38<05:46, 2.37s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▌ | 186/331 [08:41<05:53, 2.43s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████▊ | 187/331 [08:44<06:20, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████ | 188/331 [08:46<06:16, 2.63s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▎ | 189/331 [08:49<05:58, 2.52s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▍ | 190/331 [08:51<05:44, 2.44s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▋ | 191/331 [08:53<05:39, 2.42s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████▉ | 192/331 [08:56<05:32, 2.39s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▏ | 193/331 [08:59<06:01, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▍ | 194/331 [09:01<05:40, 2.49s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▋ | 195/331 [09:03<05:33, 2.45s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████▉ | 196/331 [09:06<05:41, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▏ | 197/331 [09:09<05:55, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▍ | 198/331 [09:11<05:39, 2.55s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▋ | 199/331 [09:14<05:44, 2.61s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████▉ | 200/331 [09:16<05:24, 2.48s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▏ | 201/331 [09:19<05:16, 2.44s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▍ | 202/331 [09:21<05:22, 2.50s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▋ | 203/331 [09:24<05:24, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████▉ | 204/331 [09:27<05:43, 2.71s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▏ | 205/331 [09:30<05:46, 2.75s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▍ | 206/331 [09:33<05:42, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▋ | 207/331 [09:36<05:57, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████▉ | 208/331 [09:39<06:03, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▏ | 209/331 [09:41<05:34, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▍ | 210/331 [09:43<05:12, 2.58s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▋ | 211/331 [09:46<05:16, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████▉ | 212/331 [09:48<05:02, 2.55s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████ | 213/331 [09:51<05:02, 2.57s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▎ | 214/331 [09:53<04:45, 2.44s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▌ | 215/331 [09:55<04:33, 2.36s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████▊ | 216/331 [09:59<05:01, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████ | 217/331 [10:01<05:00, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▎ | 218/331 [10:04<05:12, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▌ | 219/331 [10:07<05:06, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████▊ | 220/331 [10:09<04:54, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████ | 221/331 [10:12<04:56, 2.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▎ | 222/331 [10:15<04:42, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▌ | 223/331 [10:17<04:45, 2.64s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████▊ | 224/331 [10:20<04:44, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████ | 225/331 [10:23<04:40, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▎ | 226/331 [10:26<04:53, 2.80s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▌ | 227/331 [10:28<04:47, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████▊ | 228/331 [10:31<04:37, 2.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████ | 229/331 [10:34<04:34, 2.69s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▎ | 230/331 [10:36<04:25, 2.62s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▌ | 231/331 [10:39<04:33, 2.73s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████▊ | 232/331 [10:42<04:27, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████ | 233/331 [10:45<04:33, 2.79s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▎ | 234/331 [10:47<04:18, 2.66s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▌ | 235/331 [10:50<04:08, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▊ | 236/331 [10:53<04:33, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████▉ | 237/331 [10:56<04:44, 3.02s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▏ | 238/331 [10:59<04:39, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▍ | 239/331 [11:03<04:39, 3.04s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▋ | 240/331 [11:06<04:43, 3.12s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████▉ | 241/331 [11:09<04:49, 3.21s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▏ | 242/331 [11:13<04:46, 3.22s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▍ | 243/331 [11:16<04:44, 3.24s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▋ | 244/331 [11:19<04:50, 3.33s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████▉ | 245/331 [11:22<04:38, 3.24s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▏ | 246/331 [11:26<04:48, 3.40s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▍ | 247/331 [11:29<04:36, 3.29s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▋ | 248/331 [11:32<04:16, 3.09s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████▉ | 249/331 [11:34<03:54, 2.87s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▏ | 250/331 [11:37<03:40, 2.72s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 251/331 [11:39<03:42, 2.78s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▋ | 252/331 [11:42<03:30, 2.67s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▉ | 253/331 [11:45<03:38, 2.80s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▏ | 254/331 [11:48<03:30, 2.74s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 255/331 [11:51<03:35, 2.84s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▋ | 256/331 [11:53<03:27, 2.76s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▉ | 257/331 [11:56<03:31, 2.85s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▏ | 258/331 [11:59<03:18, 2.72s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 259/331 [12:01<03:14, 2.70s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▋ | 260/331 [12:04<03:15, 2.75s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▊ | 261/331 [12:06<03:02, 2.60s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 262/331 [12:09<02:58, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▎ | 263/331 [12:12<03:05, 2.73s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▌ | 264/331 [12:15<02:57, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▊ | 265/331 [12:17<02:50, 2.59s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████ | 266/331 [12:19<02:44, 2.53s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 267/331 [12:23<02:53, 2.72s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 268/331 [12:25<02:51, 2.72s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 269/331 [12:29<02:58, 2.88s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████ | 270/331 [12:31<02:54, 2.87s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▎ | 271/331 [12:35<02:58, 2.98s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 272/331 [12:37<02:50, 2.89s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▊ | 273/331 [12:40<02:49, 2.92s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████ | 274/331 [12:44<02:53, 3.05s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▎ | 275/331 [12:47<02:52, 3.08s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▌ | 276/331 [12:49<02:40, 2.91s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 277/331 [12:52<02:34, 2.86s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████ | 278/331 [12:55<02:29, 2.82s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 279/331 [12:58<02:38, 3.05s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▌ | 280/331 [13:01<02:33, 3.00s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▊ | 281/331 [13:05<02:35, 3.11s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████ | 282/331 [13:08<02:31, 3.10s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▎ | 283/331 [13:11<02:33, 3.19s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 284/331 [13:15<02:34, 3.29s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▋ | 285/331 [13:18<02:33, 3.34s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▉ | 286/331 [13:21<02:31, 3.36s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▏ | 287/331 [13:25<02:31, 3.45s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▍ | 288/331 [13:28<02:27, 3.42s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▋ | 289/331 [13:31<02:14, 3.21s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▉ | 290/331 [13:34<02:04, 3.03s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▏ | 291/331 [13:36<01:54, 2.85s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▍ | 292/331 [13:39<01:48, 2.78s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▋ | 293/331 [13:42<01:45, 2.77s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▉ | 294/331 [13:44<01:37, 2.65s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▏ | 295/331 [13:46<01:32, 2.57s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▍ | 296/331 [13:49<01:27, 2.51s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▋ | 297/331 [13:52<01:35, 2.81s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▉ | 298/331 [13:56<01:40, 3.04s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▏ | 299/331 [13:58<01:33, 2.93s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▍ | 300/331 [14:01<01:30, 2.92s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▋ | 301/331 [14:04<01:25, 2.86s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████▉ | 302/331 [14:07<01:21, 2.81s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▏ | 303/331 [14:09<01:15, 2.71s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▍ | 304/331 [14:12<01:15, 2.81s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▋ | 305/331 [14:15<01:15, 2.92s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████▉ | 306/331 [14:19<01:17, 3.09s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▏ | 307/331 [14:22<01:17, 3.23s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▎ | 308/331 [14:26<01:18, 3.41s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▌ | 309/331 [14:30<01:16, 3.46s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████▊ | 310/331 [14:33<01:07, 3.22s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████ | 311/331 [14:36<01:04, 3.23s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▎ | 312/331 [14:38<00:57, 3.01s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▌ | 313/331 [14:41<00:52, 2.93s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████▊ | 314/331 [14:44<00:50, 2.96s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████ | 315/331 [14:47<00:48, 3.03s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▎ | 316/331 [14:50<00:45, 3.05s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▌ | 317/331 [14:54<00:44, 3.18s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████▊ | 318/331 [14:56<00:38, 2.98s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████ | 319/331 [14:59<00:34, 2.86s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▎ | 320/331 [15:02<00:31, 2.90s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▌ | 321/331 [15:05<00:28, 2.87s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████████████▊ | 322/331 [15:08<00:27, 3.04s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████ | 323/331 [15:11<00:23, 2.95s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▎ | 324/331 [15:14<00:21, 3.06s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▌ | 325/331 [15:17<00:18, 3.08s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████████████▊ | 326/331 [15:21<00:15, 3.12s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████ | 327/331 [15:24<00:12, 3.13s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▎| 328/331 [15:27<00:09, 3.15s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████████████▌| 329/331 [15:30<00:06, 3.06s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████████| 331/331 [15:35<00:00, 2.78s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████████████████| 331/331 [15:35<00:00, 2.78s/it][INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 02:54:04 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|configuration_utils.py:438] 2022-03-03 02:54:04,246 >> Configuration saved in ./checkpoint-1500/config.json [INFO|trainer.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:54:09,339 >> Configuration saved in ./checkpoint-1500/preprocessor_config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:54:09,339 >> Configuration saved in ./checkpoint-1500/preprocessor_config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:54:09,339 >> Configuration saved in ./checkpoint-1500/preprocessor_config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-03 02:54:09,339 >> Configuration saved in ./checkpoint-1500/preprocessor_config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 1501/1784 [2:10:53<25:19:16, 322.11s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 1501/1784 [2:10:53<25:19:16, 322.11s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9201, 'learning_rate': 0.00022819314641744548, 'epoch': 0.84} 84%|█████████████████████████████████████████████████████████████▍ | 1502/1784 [2:10:57<17:45:25, 226.69s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 1502/1784 [2:10:57<17:45:25, 226.69s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0831, 'learning_rate': 0.00022741433021806855, 'epoch': 0.84} 84%|█████████████████████████████████████████████████████████████▍ | 1502/1784 [2:10:57<17:45:25, 226.69s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▌ | 1503/1784 [2:11:01<12:28:39, 159.86s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▌ | 1503/1784 [2:11:01<12:28:39, 159.86s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▌ | 1503/1784 [2:11:01<12:28:39, 159.86s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 1504/1784 [2:11:05<8:47:37, 113.06s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 1504/1784 [2:11:05<8:47:37, 113.06s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 1504/1784 [2:11:05<8:47:37, 113.06s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1505/1784 [2:11:09<6:13:24, 80.30s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1505/1784 [2:11:09<6:13:24, 80.30s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1505/1784 [2:11:09<6:13:24, 80.30s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1506/1784 [2:11:13<4:25:50, 57.37s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1506/1784 [2:11:13<4:25:50, 57.37s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1506/1784 [2:11:13<4:25:50, 57.37s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1507/1784 [2:11:17<3:10:36, 41.29s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1507/1784 [2:11:17<3:10:36, 41.29s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1507/1784 [2:11:17<3:10:36, 41.29s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1508/1784 [2:11:21<2:18:25, 30.09s/it]config.jsoner.py:560] 2022-03-03 02:38:25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:56:46,421 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:56:46,421 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0715, 'learning_rate': 0.0002219626168224299, 'epoch': 0.85} 85%|███████████████████████████████████████████████████████████████▍ | 1510/1784 [2:11:28<1:15:58, 16.64s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1510/1784 [2:11:28<1:15:58, 16.64s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9198, 'learning_rate': 0.00022118380062305295, 'epoch': 0.85} 85%|███████████████████████████████████████████████████████████████▍ | 1510/1784 [2:11:28<1:15:58, 16.64s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▏ | 1511/1784 [2:11:32<57:56, 12.73s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▏ | 1511/1784 [2:11:32<57:56, 12.73s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▏ | 1511/1784 [2:11:32<57:56, 12.73s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 1512/1784 [2:11:35<45:29, 10.03s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 1512/1784 [2:11:35<45:29, 10.03s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 1512/1784 [2:11:35<45:29, 10.03s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▎ | 1513/1784 [2:11:39<36:44, 8.13s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:04,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:04,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8144, 'learning_rate': 0.00021806853582554517, 'epoch': 0.85} [WARNING|modeling_utils.py:388] 2022-03-03 02:57:04,736 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1515/1784 [2:11:46<26:00, 5.80s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1515/1784 [2:11:46<26:00, 5.80s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1515/1784 [2:11:46<26:00, 5.80s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1516/1784 [2:11:50<22:54, 5.13s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:15,396 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:15,396 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7785, 'learning_rate': 0.00021573208722741434, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▌ | 1518/1784 [2:11:57<19:08, 4.32s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 1518/1784 [2:11:57<19:08, 4.32s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3844, 'learning_rate': 0.00021495327102803737, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▌ | 1518/1784 [2:11:57<19:08, 4.32s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 1519/1784 [2:12:00<18:01, 4.08s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:25,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:25,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2406, 'learning_rate': 0.0002133956386292835, 'epoch': 0.85} [WARNING|modeling_utils.py:388] 2022-03-03 02:57:25,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:25,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8977, 'learning_rate': 0.00021261682242990654, 'epoch': 0.85} [WARNING|modeling_utils.py:388] 2022-03-03 02:57:25,905 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1522/1784 [2:12:11<16:05, 3.69s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1522/1784 [2:12:11<16:05, 3.69s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1522/1784 [2:12:11<16:05, 3.69s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1523/1784 [2:12:14<15:44, 3.62s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:39,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:39,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7979, 'learning_rate': 0.0002102803738317757, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▊ | 1525/1784 [2:12:21<15:06, 3.50s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 1525/1784 [2:12:21<15:06, 3.50s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.804, 'learning_rate': 0.00020950155763239877, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▊ | 1525/1784 [2:12:21<15:06, 3.50s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 1526/1784 [2:12:24<14:48, 3.44s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:49,840 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:57:49,840 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0428, 'learning_rate': 0.00020794392523364486, 'epoch': 0.86} 86%|█████████████████████████████████████████████████████████████████▉ | 1528/1784 [2:12:31<14:35, 3.42s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▉ | 1528/1784 [2:12:31<14:35, 3.42s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7932, 'learning_rate': 0.0002071651090342679, 'epoch': 0.86} 86%|█████████████████████████████████████████████████████████████████▉ | 1528/1784 [2:12:31<14:35, 3.42s/it]g-point operations will not be computed25,848 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▉ | 1529/1784 [2:12:34<14:22, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████ | 1530/1784 [2:12:38<14:06, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████ | 1530/1784 [2:12:38<14:06, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8229, 'learning_rate': 0.00020560747663551403, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████ | 1530/1784 [2:12:38<14:06, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████ | 1531/1784 [2:12:41<13:55, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:06,158 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:06,158 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7603, 'learning_rate': 0.00020404984423676013, 'epoch': 0.86} [WARNING|modeling_utils.py:388] 2022-03-03 02:58:06,158 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▏ | 1533/1784 [2:12:47<13:29, 3.23s/it]g-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:12,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:12,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9258, 'learning_rate': 0.00020249221183800623, 'epoch': 0.86} [WARNING|modeling_utils.py:388] 2022-03-03 02:58:12,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▎ | 1535/1784 [2:12:53<13:06, 3.16s/it]g-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:18,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:18,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6404, 'learning_rate': 0.00020093457943925233, 'epoch': 0.86} [WARNING|modeling_utils.py:388] 2022-03-03 02:58:18,520 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▎ | 1537/1784 [2:12:59<12:34, 3.06s/it]g-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:24,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:24,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1859, 'learning_rate': 0.00019937694704049843, 'epoch': 0.86} [WARNING|modeling_utils.py:388] 2022-03-03 02:58:24,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:57:58,196 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▍ | 1539/1784 [2:13:05<12:02, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▍ | 1540/1784 [2:13:08<11:45, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▍ | 1540/1784 [2:13:08<11:45, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:32,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:32,530 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:35,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:58:35,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5998, 'learning_rate': 0.00019626168224299065, 'epoch': 0.86} [WARNING|modeling_utils.py:388] 2022-03-03 02:58:35,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:28,592 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▌ | 1543/1784 [2:13:15<10:35, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:38,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████▌ | 1543/1784 [2:13:15<10:35, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:38,651 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▋ | 1544/1784 [2:13:18<09:59, 2.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:40,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▋ | 1544/1784 [2:13:18<09:59, 2.50s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:40,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▋ | 1545/1784 [2:13:20<09:20, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:42,700 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▋ | 1545/1784 [2:13:20<09:20, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:42,700 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▊ | 1547/1784 [2:13:23<08:04, 2.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:44,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▊ | 1547/1784 [2:13:23<08:04, 2.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:44,493 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▊ | 1548/1784 [2:13:25<07:17, 1.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:47,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▊ | 1548/1784 [2:13:25<07:17, 1.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:47,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9865, 'learning_rate': 0.00019158878504672898, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▊ | 1549/1784 [2:13:26<06:35, 1.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:48,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▊ | 1549/1784 [2:13:26<06:35, 1.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:48,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▉ | 1550/1784 [2:13:28<06:35, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:48,559 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▉ | 1550/1784 [2:13:28<06:35, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:51,682 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▉ | 1550/1784 [2:13:28<06:35, 1.69s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:51,682 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▉ | 1551/1784 [2:13:32<09:18, 2.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▉ | 1552/1784 [2:13:35<10:51, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████▉ | 1552/1784 [2:13:35<10:51, 2.81s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0221, 'learning_rate': 0.00018847352024922118, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1553/1784 [2:13:39<11:52, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|███████████████████████████████████████████████████████████████████ | 1553/1784 [2:13:39<11:52, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8414, 'learning_rate': 0.00018769470404984424, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1554/1784 [2:13:43<12:31, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|███████████████████████████████████████████████████████████████████ | 1554/1784 [2:13:43<12:31, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9341, 'learning_rate': 0.00018691588785046728, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1554/1784 [2:13:43<12:31, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|███████████████████████████████████████████████████████████████████ | 1555/1784 [2:13:46<12:57, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:12,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:12,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:15,818 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:15,818 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1726, 'learning_rate': 0.00018457943925233644, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▏ | 1558/1784 [2:13:57<13:19, 3.54s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|███████████████████████████████████████████████████████████████████▏ | 1558/1784 [2:13:57<13:19, 3.54s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1287, 'learning_rate': 0.0001838006230529595, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▎ | 1559/1784 [2:14:01<13:14, 3.53s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|███████████████████████████████████████████████████████████████████▎ | 1559/1784 [2:14:01<13:14, 3.53s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:26,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:26,432 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1194, 'learning_rate': 0.0001822429906542056, 'epoch': 0.87} 88%|███████████████████████████████████████████████████████████████████▍ | 1561/1784 [2:14:08<13:04, 3.52s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▍ | 1561/1784 [2:14:08<13:04, 3.52s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0108, 'learning_rate': 0.00018146417445482864, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▍ | 1562/1784 [2:14:11<12:54, 3.49s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▍ | 1562/1784 [2:14:11<12:54, 3.49s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8349, 'learning_rate': 0.0001806853582554517, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▍ | 1562/1784 [2:14:11<12:54, 3.49s/it]g-point operations will not be computed-03 02:58:55,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▍ | 1563/1784 [2:14:15<12:48, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▌ | 1564/1784 [2:14:18<12:42, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▌ | 1564/1784 [2:14:18<12:42, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.12, 'learning_rate': 0.0001791277258566978, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▌ | 1565/1784 [2:14:22<12:44, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▌ | 1565/1784 [2:14:22<12:44, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0028, 'learning_rate': 0.00017834890965732087, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▌ | 1565/1784 [2:14:22<12:44, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▌ | 1566/1784 [2:14:25<12:36, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:50,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 02:59:50,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6724, 'learning_rate': 0.00017679127725856697, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▋ | 1568/1784 [2:14:32<12:23, 3.44s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▋ | 1568/1784 [2:14:32<12:23, 3.44s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0271, 'learning_rate': 0.00017601246105919003, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▋ | 1569/1784 [2:14:35<12:16, 3.42s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▋ | 1569/1784 [2:14:35<12:16, 3.42s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:00,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:00,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0105, 'learning_rate': 0.00017445482866043613, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▊ | 1571/1784 [2:14:42<12:04, 3.40s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▊ | 1571/1784 [2:14:42<12:04, 3.40s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8664, 'learning_rate': 0.0001736760124610592, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▊ | 1571/1784 [2:14:42<12:04, 3.40s/it]g-point operations will not be computed-03 02:59:38,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▊ | 1572/1784 [2:14:46<12:03, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▉ | 1573/1784 [2:14:49<12:00, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▉ | 1573/1784 [2:14:49<12:00, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0761, 'learning_rate': 0.0001721183800623053, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▉ | 1574/1784 [2:14:52<11:55, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▉ | 1574/1784 [2:14:52<11:55, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:17,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:17,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7017, 'learning_rate': 0.0001705607476635514, 'epoch': 0.88} [WARNING|modeling_utils.py:388] 2022-03-03 03:00:17,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1576/1784 [2:14:59<11:35, 3.34s/it]g-point operations will not be computed-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1576/1784 [2:14:59<11:35, 3.34s/it]g-point operations will not be computed-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1576/1784 [2:14:59<11:35, 3.34s/it]g-point operations will not be computed-03 03:00:09,411 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1577/1784 [2:15:02<11:25, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1577/1784 [2:15:02<11:25, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1578/1784 [2:15:05<11:17, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1578/1784 [2:15:05<11:17, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|████████████████████████████████████████████████████████████████████ | 1578/1784 [2:15:05<11:17, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▏ | 1579/1784 [2:15:09<11:04, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▏ | 1579/1784 [2:15:09<11:04, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:33,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:33,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:33,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▏ | 1581/1784 [2:15:15<10:45, 3.18s/it]g-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▏ | 1581/1784 [2:15:15<10:45, 3.18s/it]g-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:40,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:40,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:40,033 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:25,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▎ | 1583/1784 [2:15:21<10:33, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▎ | 1583/1784 [2:15:21<10:33, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▎ | 1584/1784 [2:15:24<10:22, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:49,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:49,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7851, 'learning_rate': 0.00016277258566978192, 'epoch': 0.89} [WARNING|modeling_utils.py:388] 2022-03-03 03:00:49,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:52,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:00:52,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:44,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8221, 'learning_rate': 0.00016121495327102802, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▍ | 1587/1784 [2:15:33<09:43, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:56,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▍ | 1587/1784 [2:15:33<09:43, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:56,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▌ | 1588/1784 [2:15:36<09:27, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▌ | 1588/1784 [2:15:36<09:27, 2.90s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▌ | 1589/1784 [2:15:38<09:12, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▌ | 1589/1784 [2:15:38<09:12, 2.83s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:02,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:02,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:02,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:00:59,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▋ | 1591/1784 [2:15:43<08:43, 2.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:06,760 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▋ | 1591/1784 [2:15:43<08:43, 2.71s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:06,760 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▋ | 1592/1784 [2:15:46<08:21, 2.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▋ | 1592/1784 [2:15:46<08:21, 2.61s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▊ | 1593/1784 [2:15:48<08:02, 2.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████▊ | 1593/1784 [2:15:48<08:02, 2.52s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:12,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:12,348 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:14,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:14,260 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:15,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:15,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0076, 'learning_rate': 0.00015342679127725855, 'epoch': 0.9} [WARNING|modeling_utils.py:388] 2022-03-03 03:01:18,979 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:18,979 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:20,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:20,222 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:21,941 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:21,941 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:21,941 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:25,996 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:25,996 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:25,996 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:09,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1602/1784 [2:16:08<08:28, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1602/1784 [2:16:08<08:28, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1603/1784 [2:16:11<09:11, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1603/1784 [2:16:11<09:11, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1603/1784 [2:16:11<09:11, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1604/1784 [2:16:15<09:42, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1604/1784 [2:16:15<09:42, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▏ | 1604/1784 [2:16:15<09:42, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▎ | 1605/1784 [2:16:19<09:57, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▎ | 1605/1784 [2:16:19<09:57, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▎ | 1605/1784 [2:16:19<09:57, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▎ | 1606/1784 [2:16:22<10:09, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:47,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:01:47,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0402, 'learning_rate': 0.00014563862928348908, 'epoch': 0.9} [WARNING|modeling_utils.py:388] 2022-03-03 03:01:47,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1608/1784 [2:16:29<10:18, 3.52s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1608/1784 [2:16:29<10:18, 3.52s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1608/1784 [2:16:29<10:18, 3.52s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1609/1784 [2:16:33<10:14, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1609/1784 [2:16:33<10:14, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1609/1784 [2:16:33<10:14, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▍ | 1610/1784 [2:16:36<10:10, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:02,109 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:02,109 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0062, 'learning_rate': 0.0001425233644859813, 'epoch': 0.9} [WARNING|modeling_utils.py:388] 2022-03-03 03:02:02,109 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▌ | 1612/1784 [2:16:43<10:03, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▌ | 1612/1784 [2:16:43<10:03, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▌ | 1612/1784 [2:16:43<10:03, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████▌ | 1613/1784 [2:16:47<10:00, 3.51s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:12,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:12,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7568, 'learning_rate': 0.00014018691588785047, 'epoch': 0.9} [WARNING|modeling_utils.py:388] 2022-03-03 03:02:12,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▋ | 1615/1784 [2:16:54<09:47, 3.47s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▋ | 1615/1784 [2:16:54<09:47, 3.47s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▋ | 1615/1784 [2:16:54<09:47, 3.47s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▋ | 1616/1784 [2:16:57<09:38, 3.45s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:22,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:22,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1144, 'learning_rate': 0.0001378504672897196, 'epoch': 0.91} [WARNING|modeling_utils.py:388] 2022-03-03 03:02:22,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▊ | 1618/1784 [2:17:04<09:26, 3.41s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▊ | 1618/1784 [2:17:04<09:26, 3.41s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▊ | 1618/1784 [2:17:04<09:26, 3.41s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▉ | 1619/1784 [2:17:07<09:19, 3.39s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:32,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:02:32,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8169, 'learning_rate': 0.00013551401869158877, 'epoch': 0.91} [WARNING|modeling_utils.py:388] 2022-03-03 03:02:32,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▉ | 1621/1784 [2:17:14<09:07, 3.36s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▉ | 1621/1784 [2:17:14<09:07, 3.36s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████▉ | 1621/1784 [2:17:14<09:07, 3.36s/it]g-point operations will not be computed-03 03:01:31,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████ | 1622/1784 [2:17:17<08:58, 3.33s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:41,020 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████ | 1623/1784 [2:17:21<08:53, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:41,020 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████ | 1623/1784 [2:17:21<08:53, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:41,020 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1454, 'learning_rate': 0.00013317757009345793, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████ | 1623/1784 [2:17:21<08:53, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:41,020 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████ | 1624/1784 [2:17:24<08:44, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1625/1784 [2:17:27<08:38, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1625/1784 [2:17:27<08:38, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9702, 'learning_rate': 0.00013161993769470403, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████▏ | 1625/1784 [2:17:27<08:38, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1626/1784 [2:17:30<08:33, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1626/1784 [2:17:30<08:33, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1626/1784 [2:17:30<08:33, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:47,489 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1627/1784 [2:17:33<08:29, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:57,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▏ | 1627/1784 [2:17:33<08:29, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:57,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1628/1784 [2:17:37<08:23, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:57,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1628/1784 [2:17:37<08:23, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:57,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1628/1784 [2:17:37<08:23, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:02:57,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1629/1784 [2:17:40<08:16, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:03,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1629/1784 [2:17:40<08:16, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:03,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1630/1784 [2:17:43<08:08, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:03,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1630/1784 [2:17:43<08:08, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:03,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▎ | 1630/1784 [2:17:43<08:08, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:03,438 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▍ | 1631/1784 [2:17:46<08:01, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:09,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▍ | 1631/1784 [2:17:46<08:01, 3.15s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:09,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▍ | 1632/1784 [2:17:49<07:52, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:09,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▍ | 1632/1784 [2:17:49<07:52, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:09,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████▍ | 1632/1784 [2:17:49<07:52, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:09,579 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▍ | 1633/1784 [2:17:52<07:45, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:15,569 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▍ | 1633/1784 [2:17:52<07:45, 3.08s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:15,569 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▌ | 1634/1784 [2:17:55<07:33, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:15,569 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:19,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:15,569 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:19,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:15,569 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0124, 'learning_rate': 0.00012383177570093458, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-03-03 03:03:19,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:15,569 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▌ | 1636/1784 [2:18:00<07:10, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:23,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▌ | 1636/1784 [2:18:00<07:10, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:23,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▋ | 1637/1784 [2:18:03<06:59, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:23,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:27,939 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:23,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:27,939 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:23,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.3605, 'learning_rate': 0.00012149532710280373, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-03-03 03:03:27,939 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:23,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▋ | 1639/1784 [2:18:08<06:36, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▋ | 1639/1784 [2:18:08<06:36, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▊ | 1640/1784 [2:18:11<06:21, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▊ | 1640/1784 [2:18:11<06:21, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:35,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:35,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:37,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:37,531 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:39,564 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:39,564 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:41,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:41,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:44,580 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:44,580 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:45,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:45,964 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0816, 'learning_rate': 0.00011448598130841121, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-03-03 03:03:48,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:48,384 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:50,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:50,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9195, 'learning_rate': 0.00011214953271028037, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-03-03 03:03:50,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:53,924 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:53,924 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:53,924 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:57,668 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:57,668 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:03:57,668 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1653/1784 [2:18:39<06:28, 2.97s/it]g-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1653/1784 [2:18:39<06:28, 2.97s/it]g-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1653/1784 [2:18:39<06:28, 2.97s/it]g-point operations will not be computed-03 03:03:31,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1654/1784 [2:18:43<06:51, 3.16s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1655/1784 [2:18:47<07:07, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1655/1784 [2:18:47<07:07, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6811, 'learning_rate': 0.00010825545171339564, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▍ | 1655/1784 [2:18:47<07:07, 3.32s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1656/1784 [2:18:50<07:13, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1656/1784 [2:18:50<07:13, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1656/1784 [2:18:50<07:13, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1657/1784 [2:18:54<07:18, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1657/1784 [2:18:54<07:18, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1657/1784 [2:18:54<07:18, 3.45s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1658/1784 [2:18:57<07:19, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1658/1784 [2:18:57<07:19, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:22,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:22,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:22,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1660/1784 [2:19:04<07:14, 3.51s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1660/1784 [2:19:04<07:14, 3.51s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1660/1784 [2:19:04<07:14, 3.51s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1661/1784 [2:19:08<07:10, 3.50s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:33,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:33,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.747, 'learning_rate': 0.00010280373831775701, 'epoch': 0.93} [WARNING|modeling_utils.py:388] 2022-03-03 03:04:33,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1663/1784 [2:19:15<07:00, 3.48s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1663/1784 [2:19:15<07:00, 3.48s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1663/1784 [2:19:15<07:00, 3.48s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1664/1784 [2:19:18<06:54, 3.45s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:43,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:04:43,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.665, 'learning_rate': 0.00010046728971962616, 'epoch': 0.93} [WARNING|modeling_utils.py:388] 2022-03-03 03:04:43,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1666/1784 [2:19:25<06:45, 3.43s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1666/1784 [2:19:25<06:45, 3.43s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1666/1784 [2:19:25<06:45, 3.43s/it]g-point operations will not be computed-03 03:04:06,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1667/1784 [2:19:28<06:39, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1668/1784 [2:19:32<06:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1668/1784 [2:19:32<06:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7492, 'learning_rate': 9.813084112149533e-05, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▉ | 1668/1784 [2:19:32<06:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1669/1784 [2:19:35<06:26, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:00,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:00,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0729, 'learning_rate': 9.657320872274143e-05, 'epoch': 0.94} [WARNING|modeling_utils.py:388] 2022-03-03 03:05:00,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1671/1784 [2:19:41<06:16, 3.33s/it]g-point operations will not be computed-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1671/1784 [2:19:41<06:16, 3.33s/it]g-point operations will not be computed-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1671/1784 [2:19:41<06:16, 3.33s/it]g-point operations will not be computed-03 03:04:52,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▏ | 1672/1784 [2:19:45<06:09, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▏ | 1672/1784 [2:19:45<06:09, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▏ | 1673/1784 [2:19:48<06:05, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▏ | 1673/1784 [2:19:48<06:05, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▏ | 1673/1784 [2:19:48<06:05, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1674/1784 [2:19:51<06:00, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:16,471 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:16,471 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2157, 'learning_rate': 9.267912772585669e-05, 'epoch': 0.94} [WARNING|modeling_utils.py:388] 2022-03-03 03:05:16,471 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1676/1784 [2:19:58<05:48, 3.22s/it]g-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:22,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:22,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5767, 'learning_rate': 9.11214953271028e-05, 'epoch': 0.94} [WARNING|modeling_utils.py:388] 2022-03-03 03:05:22,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▍ | 1678/1784 [2:20:04<05:35, 3.17s/it]g-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:28,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:28,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0619, 'learning_rate': 8.95638629283489e-05, 'epoch': 0.94} [WARNING|modeling_utils.py:388] 2022-03-03 03:05:28,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1680/1784 [2:20:10<05:24, 3.12s/it]g-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1680/1784 [2:20:10<05:24, 3.12s/it]g-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1680/1784 [2:20:10<05:24, 3.12s/it]g-point operations will not be computed-03 03:05:08,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1681/1784 [2:20:13<05:20, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:36,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1681/1784 [2:20:13<05:20, 3.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:36,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1682/1784 [2:20:16<05:15, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:36,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1682/1784 [2:20:16<05:15, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:36,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1682/1784 [2:20:16<05:15, 3.10s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:36,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1683/1784 [2:20:19<05:12, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:42,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1683/1784 [2:20:19<05:12, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:42,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1684/1784 [2:20:22<05:06, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:42,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1684/1784 [2:20:22<05:06, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:42,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1684/1784 [2:20:22<05:06, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:42,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1685/1784 [2:20:25<04:57, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1685/1784 [2:20:25<04:57, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▊ | 1686/1784 [2:20:28<04:50, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▊ | 1686/1784 [2:20:28<04:50, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:52,827 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:52,827 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:05:52,827 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:48,645 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▊ | 1688/1784 [2:20:33<04:33, 2.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:56,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▊ | 1688/1784 [2:20:33<04:33, 2.84s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:56,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▉ | 1689/1784 [2:20:36<04:23, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▉ | 1689/1784 [2:20:36<04:23, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▉ | 1690/1784 [2:20:38<04:12, 2.68s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:02,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:02,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:05,118 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:05,118 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:07,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:07,137 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.1167, 'learning_rate': 7.866043613707164e-05, 'epoch': 0.95} [WARNING|modeling_utils.py:388] 2022-03-03 03:06:09,059 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:09,059 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:10,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:10,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:12,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:12,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:15,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:15,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2036, 'learning_rate': 7.476635514018691e-05, 'epoch': 0.95} [WARNING|modeling_utils.py:388] 2022-03-03 03:06:16,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:16,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:18,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:18,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:18,093 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:22,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:25,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:25,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7879, 'learning_rate': 7.165109034267912e-05, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▌ | 1703/1784 [2:21:07<04:04, 3.02s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▌ | 1703/1784 [2:21:07<04:04, 3.02s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7595, 'learning_rate': 7.087227414330217e-05, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▌ | 1703/1784 [2:21:07<04:04, 3.02s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1704/1784 [2:21:11<04:16, 3.21s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1704/1784 [2:21:11<04:16, 3.21s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1704/1784 [2:21:11<04:16, 3.21s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1705/1784 [2:21:15<04:22, 3.32s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:40,351 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:40,351 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5263, 'learning_rate': 6.853582554517133e-05, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▋ | 1707/1784 [2:21:22<04:27, 3.48s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1707/1784 [2:21:22<04:27, 3.48s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6897, 'learning_rate': 6.775700934579438e-05, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▋ | 1707/1784 [2:21:22<04:27, 3.48s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1708/1784 [2:21:25<04:25, 3.49s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1708/1784 [2:21:25<04:25, 3.49s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1708/1784 [2:21:25<04:25, 3.49s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▊ | 1709/1784 [2:21:29<04:24, 3.52s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:54,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:06:54,610 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0503, 'learning_rate': 6.542056074766355e-05, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▊ | 1711/1784 [2:21:36<04:16, 3.51s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▊ | 1711/1784 [2:21:36<04:16, 3.51s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.591, 'learning_rate': 6.46417445482866e-05, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▊ | 1711/1784 [2:21:36<04:16, 3.51s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▉ | 1712/1784 [2:21:40<04:12, 3.51s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:05,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:05,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2821, 'learning_rate': 6.308411214953271e-05, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▉ | 1714/1784 [2:21:46<04:04, 3.49s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▉ | 1714/1784 [2:21:46<04:04, 3.49s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.876, 'learning_rate': 6.230529595015576e-05, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▉ | 1714/1784 [2:21:46<04:04, 3.49s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████ | 1715/1784 [2:21:50<04:00, 3.48s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:15,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:15,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0203, 'learning_rate': 6.074766355140187e-05, 'epoch': 0.96} 96%|██████████████████████████████████████████████████████████████████████████ | 1717/1784 [2:21:57<03:50, 3.44s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████ | 1717/1784 [2:21:57<03:50, 3.44s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2117, 'learning_rate': 5.9968847352024924e-05, 'epoch': 0.96} 96%|██████████████████████████████████████████████████████████████████████████ | 1717/1784 [2:21:57<03:50, 3.44s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████▏ | 1718/1784 [2:22:00<03:46, 3.43s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:25,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:25,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9818, 'learning_rate': 5.841121495327103e-05, 'epoch': 0.96} 96%|██████████████████████████████████████████████████████████████████████████▏ | 1720/1784 [2:22:07<03:37, 3.40s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████▏ | 1720/1784 [2:22:07<03:37, 3.40s/it]g-point operations will not be computed-03 03:05:59,420 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7752, 'learning_rate': 5.763239875389408e-05, 'epoch': 0.96} 96%|██████████████████████████████████████████████████████████████████████████▎ | 1721/1784 [2:22:10<03:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████▎ | 1721/1784 [2:22:10<03:33, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▎ | 1722/1784 [2:22:14<03:29, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▎ | 1722/1784 [2:22:14<03:29, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0031, 'learning_rate': 5.607476635514019e-05, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▎ | 1722/1784 [2:22:14<03:29, 3.38s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▎ | 1723/1784 [2:22:17<03:24, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:42,272 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:07:42,272 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8312, 'learning_rate': 5.4517133956386294e-05, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▍ | 1725/1784 [2:22:23<03:14, 3.30s/it]g-point operations will not be computed-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▍ | 1725/1784 [2:22:23<03:14, 3.30s/it]g-point operations will not be computed-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.842, 'learning_rate': 5.3738317757009344e-05, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▍ | 1725/1784 [2:22:23<03:14, 3.30s/it]g-point operations will not be computed-03 03:07:34,045 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▍ | 1726/1784 [2:22:27<03:09, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:50,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▍ | 1726/1784 [2:22:27<03:09, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:50,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▌ | 1727/1784 [2:22:30<03:08, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:50,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▌ | 1727/1784 [2:22:30<03:08, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:50,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▌ | 1728/1784 [2:22:33<03:03, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:56,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▌ | 1728/1784 [2:22:33<03:03, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:56,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▋ | 1729/1784 [2:22:36<02:57, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:56,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▋ | 1729/1784 [2:22:36<02:57, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:07:56,919 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.2907, 'learning_rate': 5.062305295950156e-05, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▋ | 1730/1784 [2:22:39<02:52, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:03,168 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▋ | 1730/1784 [2:22:39<02:52, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:03,168 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▋ | 1731/1784 [2:22:43<02:48, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:03,168 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▋ | 1731/1784 [2:22:43<02:48, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:03,168 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4455, 'learning_rate': 4.9065420560747664e-05, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▊ | 1732/1784 [2:22:46<02:43, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▊ | 1732/1784 [2:22:46<02:43, 3.14s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▊ | 1733/1784 [2:22:49<02:38, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▊ | 1733/1784 [2:22:49<02:38, 3.11s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7372, 'learning_rate': 4.750778816199377e-05, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▊ | 1734/1784 [2:22:52<02:33, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▊ | 1734/1784 [2:22:52<02:33, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9109, 'learning_rate': 4.672897196261682e-05, 'epoch': 0.97} [WARNING|modeling_utils.py:388] 2022-03-03 03:08:16,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:16,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:16,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:09,302 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▉ | 1736/1784 [2:22:58<02:23, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:21,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▉ | 1736/1784 [2:22:58<02:23, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:21,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████▉ | 1737/1784 [2:23:00<02:18, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:21,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:25,180 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:21,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:25,180 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:21,102 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9642, 'learning_rate': 4.3613707165109034e-05, 'epoch': 0.97} 97%|███████████████████████████████████████████████████████████████████████████ | 1739/1784 [2:23:06<02:07, 2.82s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:29,209 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|███████████████████████████████████████████████████████████████████████████ | 1739/1784 [2:23:06<02:07, 2.82s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:29,209 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████ | 1740/1784 [2:23:08<02:00, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████ | 1740/1784 [2:23:08<02:00, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▏ | 1741/1784 [2:23:11<01:53, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▏ | 1741/1784 [2:23:11<01:53, 2.65s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:35,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:35,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:37,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:37,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:39,532 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:39,532 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:41,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:41,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:43,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:43,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:45,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:45,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:47,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:47,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6587, 'learning_rate': 3.582554517133956e-05, 'epoch': 0.98} [WARNING|modeling_utils.py:388] 2022-03-03 03:08:49,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:49,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8845, 'learning_rate': 3.426791277258567e-05, 'epoch': 0.98} [WARNING|modeling_utils.py:388] 2022-03-03 03:08:53,582 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:08:53,582 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6127, 'learning_rate': 3.3489096573208724e-05, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▌ | 1752/1784 [2:23:35<01:29, 2.81s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▌ | 1752/1784 [2:23:35<01:29, 2.81s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.7692, 'learning_rate': 3.2710280373831774e-05, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▋ | 1753/1784 [2:23:39<01:35, 3.08s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▋ | 1753/1784 [2:23:39<01:35, 3.08s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9454, 'learning_rate': 3.1931464174454823e-05, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▋ | 1754/1784 [2:23:43<01:37, 3.24s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▋ | 1754/1784 [2:23:43<01:37, 3.24s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.9908, 'learning_rate': 3.115264797507788e-05, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▋ | 1754/1784 [2:23:43<01:37, 3.24s/it]g-point operations will not be computed-03 03:08:31,715 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▋ | 1755/1784 [2:23:46<01:37, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▋ | 1755/1784 [2:23:46<01:37, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▊ | 1756/1784 [2:23:50<01:36, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▊ | 1756/1784 [2:23:50<01:36, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▊ | 1756/1784 [2:23:50<01:36, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▊ | 1757/1784 [2:23:53<01:33, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████▊ | 1757/1784 [2:23:53<01:33, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████▉ | 1758/1784 [2:23:57<01:29, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████▉ | 1758/1784 [2:23:57<01:29, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5652, 'learning_rate': 2.8037383177570094e-05, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-03-03 03:09:22,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:22,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:22,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████▉ | 1760/1784 [2:24:04<01:23, 3.47s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████▉ | 1760/1784 [2:24:04<01:23, 3.47s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████▉ | 1760/1784 [2:24:04<01:23, 3.47s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████ | 1761/1784 [2:24:07<01:19, 3.46s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:32,757 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:32,757 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:36,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:36,262 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8143, 'learning_rate': 2.4143302180685357e-05, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▏| 1764/1784 [2:24:18<01:08, 3.45s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▏| 1764/1784 [2:24:18<01:08, 3.45s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.055, 'learning_rate': 2.336448598130841e-05, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▏| 1764/1784 [2:24:18<01:08, 3.45s/it]g-point operations will not be computed-03 03:09:10,177 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▏| 1765/1784 [2:24:21<01:04, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▏| 1765/1784 [2:24:21<01:04, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▏| 1766/1784 [2:24:24<01:01, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▏| 1766/1784 [2:24:24<01:01, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▏| 1766/1784 [2:24:24<01:01, 3.42s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▎| 1767/1784 [2:24:28<00:57, 3.40s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:53,016 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:53,016 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6581, 'learning_rate': 2.0249221183800623e-05, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-03-03 03:09:53,016 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▎| 1769/1784 [2:24:34<00:49, 3.30s/it]g-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:59,386 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:09:59,386 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6828, 'learning_rate': 1.8691588785046727e-05, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-03-03 03:09:59,386 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▍| 1771/1784 [2:24:40<00:42, 3.24s/it]g-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:05,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:05,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6912, 'learning_rate': 1.7133956386292833e-05, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-03-03 03:10:05,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▌| 1773/1784 [2:24:47<00:34, 3.15s/it]g-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:11,629 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:11,629 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8006, 'learning_rate': 1.557632398753894e-05, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-03-03 03:10:11,629 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████▌| 1775/1784 [2:24:52<00:27, 3.02s/it]g-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:17,264 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:17,264 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:19,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:19,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:22,234 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-03 03:10:22,234 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.8303, 'learning_rate': 1.2461059190031152e-05, 'epoch': 1.0} [WARNING|modeling_utils.py:388] 2022-03-03 03:10:22,234 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-03 03:09:44,792 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████▊| 1779/1784 [2:25:02<00:12, 2.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:10:25,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████▊| 1779/1784 [2:25:02<00:12, 2.53s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:10:25,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████▊| 1781/1784 [2:25:06<00:06, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:10:27,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████▊| 1781/1784 [2:25:06<00:06, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:10:27,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 5.0697, 'learning_rate': 1.0124610591900312e-05, 'epoch': 1.0} 100%|████████████████████████████████████████████████████████████████████████████▉| 1782/1784 [2:25:07<00:03, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:10:30,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████▉| 1782/1784 [2:25:07<00:03, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-03 03:10:30,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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:2114] 2022-03-03 03:10:31,665 >> Saving model checkpoint to ./=)█| 1784/1784 [2:25:09<00:00, 1.50s/it][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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:2114] 2022-03-03 03:10:31,665 >> Saving model checkpoint to ./=)█| 1784/1784 [2:25:09<00:00, 1.50s/it][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0566, 'learning_rate': 7.78816199376947e-06, 'epoch': 1.0} [INFO|trainer.py:2114] 2022-03-03 03:10:49,235 >> Saving model checkpoint to ./ ./pytorch_model.bin:09<00:00, 1.50s/it][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|modeling_utils.py:1081] 2022-03-03 03:11:06,251 >> Model weights saved in ./pytorch_model.bin:09<00:00, 1.50s/it][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 0%|▏ | 11.7M/2.99G [00:01<04:22, 12.2MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 2%|▋ | 46.5M/2.99G [00:03<03:08, 16.8MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 3%|█▎ | 85.4M/2.99G [00:05<02:43, 19.0MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 4%|█▉ | 126M/2.99G [00:07<02:33, 20.1MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 5%|██▌ | 167M/2.99G [00:09<02:25, 20.9MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 7%|███▎ | 208M/2.99G [00:11<02:20, 21.2MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 8%|███▉ | 249M/2.99G [00:13<02:17, 21.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file pytorch_model.bin: 8%|███▉ | 249M/2.99G [00:13<02:17, 21.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [00:16<00:00, 16.4MB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 03:18:09 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.1M/48.1M [05:22<00:00, 88.9kB/s][INFO|trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|modelcard.py:460] 2022-03-03 03:18:12,068 >> Dropping the following result as it does not have all the necessary fields:trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 22%|██▍ | 10.5M/48.2M [00:01<00:03, 11.0MB/s]ields:trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 22%|██▍ | 10.5M/48.2M [00:01<00:03, 11.0MB/s]ields:trainer.py:1492] 2022-03-03 03:10:31,663 >> 1,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 03:18:33 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 64%|███████ | 30.7M/48.2M [00:02<00:01, 16.9MB/s]To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-searchimate the number of tokens of the input, floating-point operations will not be computed.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] 2022-03-03 03:18:36,671 >> Num examples = 2642in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-03 03:18:36,671 >> Num examples = 2642in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. ***** train metrics ***** epoch = 1.0 train_loss = 7.0053 train_runtime = 2:25:11.59 train_samples = 28538 train_samples_per_second = 3.276 train_steps_per_second = 0.205 0%| | 0/331 [00:00> Saving model checkpoint to ./ | 3/331 [00:05<10:34, 1.94s/it] argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2114] 2022-03-03 03:37:15,407 >> Saving model checkpoint to ./ | 3/331 [00:05<10:34, 1.94s/it] argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 03:37:15 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow ***** eval metrics ***** epoch = 1.0 eval_loss = 5.0542 eval_runtime = 0:18:38.73 eval_samples = 2642 eval_samples_per_second = 2.362 eval_steps_per_second = 0.296 [INFO|modeling_utils.py:1081] 2022-03-03 03:37:31,865 >> Model weights saved in ./pytorch_model.bin:05<10:34, 1.94s/it] argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 22%|██▍ | 10.6M/48.4M [00:01<00:03, 11.0MB/s] argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 22%|██▍ | 10.6M/48.4M [00:01<00:03, 11.0MB/s] argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/03/2022 03:38:02 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search Upload file wandb/run-20220303_004520-25bnjrx1/run-25bnjrx1.wandb: 100%|███████████| 48.4M/48.4M [00:03<00:00, 16.8MB/s] argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. return ModelInfo(**d)f.finetuned_from)formers/src/transformers/modelcard.py", line 611, in from_trainercard31, in mainule>ent in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. return ModelInfo(**d)f.finetuned_from)formers/src/transformers/modelcard.py", line 611, in from_trainercard31, in mainule>ent in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. return ModelInfo(**d)f.finetuned_from)formers/src/transformers/modelcard.py", line 611, in from_trainercard31, in mainule>ent in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.ut_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.