0%| | 0/1189 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8825, 'learning_rate': 0.0, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-02-28 16:33:55,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%| | 1/1189 [00:05<1:54:22, 5.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:33:58,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0739, 'learning_rate': 0.0, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:01,084 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▏ | 2/1189 [00:10<1:46:54, 5.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:03,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0609, 'learning_rate': 2e-08, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:06,331 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▏ | 3/1189 [00:16<1:47:35, 5.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:09,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8813, 'learning_rate': 4e-08, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:12,022 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 4/1189 [00:21<1:47:57, 5.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:14,666 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6007, 'learning_rate': 6.000000000000001e-08, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:17,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 5/1189 [00:27<1:45:11, 5.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:19,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:34:22,147 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 6/1189 [00:32<1:43:06, 5.23s/it] 1%|▍ | 6/1189 [00:32<1:43:06, 5.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:24,743 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.743, 'learning_rate': 1.0000000000000001e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:27,235 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 7/1189 [00:37<1:42:06, 5.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:29,825 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7243, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:32,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 8/1189 [00:42<1:41:15, 5.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:34,867 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9582, 'learning_rate': 1.2000000000000002e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:37,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 9/1189 [00:47<1:40:02, 5.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:39,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8108, 'learning_rate': 1.4e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:42,184 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▋ | 10/1189 [00:52<1:38:59, 5.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:44,682 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8627, 'learning_rate': 1.6e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:34:47,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▋ | 11/1189 [00:56<1:38:00, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:49,518 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:34:51,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 12/1189 [01:01<1:36:38, 4.93s/it] 1%|▊ | 12/1189 [01:01<1:36:38, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:54,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:34:56,720 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 13/1189 [01:06<1:36:14, 4.91s/it] 1%|▊ | 13/1189 [01:06<1:36:14, 4.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:34:59,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7932, 'learning_rate': 2.2e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:01,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▉ | 14/1189 [01:11<1:35:38, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:04,005 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6951, 'learning_rate': 2.4000000000000003e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:06,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▉ | 15/1189 [01:16<1:35:16, 4.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:08,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:35:11,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9232, 'learning_rate': 2.6e-07, 'epoch': 0.01} 1%|█ | 16/1189 [01:21<1:34:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:13,576 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:35:15,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█▏ | 17/1189 [01:25<1:33:56, 4.81s/it] 1%|█▏ | 17/1189 [01:25<1:33:56, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:18,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0363, 'learning_rate': 3.0000000000000004e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:20,558 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▏ | 18/1189 [01:30<1:33:02, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:22,951 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7808, 'learning_rate': 3.2e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:25,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▎ | 19/1189 [01:35<1:32:29, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:27,675 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:35:29,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▎ | 20/1189 [01:39<1:32:10, 4.73s/it] 2%|█▎ | 20/1189 [01:39<1:32:10, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:32,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9847, 'learning_rate': 3.6e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:34,594 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▍ | 21/1189 [01:44<1:31:36, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:36,895 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7493, 'learning_rate': 3.8e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:39,166 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▍ | 22/1189 [01:49<1:30:44, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:41,465 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9432, 'learning_rate': 4.0000000000000003e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:43,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 23/1189 [01:53<1:29:55, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:46,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0013, 'learning_rate': 4.2000000000000006e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 24/1189 [01:58<1:29:30, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:50,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7983, 'learning_rate': 4.4e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:52,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 25/1189 [02:02<1:28:57, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:55,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9729, 'learning_rate': 4.6000000000000004e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:35:57,249 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 26/1189 [02:07<1:28:04, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:35:59,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8627, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:36:01,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 27/1189 [02:11<1:27:06, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:03,894 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6941, 'learning_rate': 5.000000000000001e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:36:06,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 28/1189 [02:15<1:26:31, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:08,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7796, 'learning_rate': 5.2e-07, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-02-28 16:36:10,431 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▉ | 29/1189 [02:20<1:25:56, 4.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:12,625 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:14,760 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|█▉ | 30/1189 [02:24<1:25:11, 4.41s/it] 3%|█▉ | 30/1189 [02:24<1:25:11, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:16,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:18,904 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██ | 31/1189 [02:28<1:23:34, 4.33s/it] 3%|██ | 31/1189 [02:28<1:23:34, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:21,041 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:23,086 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▏ | 32/1189 [02:32<1:22:38, 4.29s/it] 3%|██▏ | 32/1189 [02:32<1:22:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:25,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:27,281 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▏ | 33/1189 [02:37<1:22:03, 4.26s/it] 3%|██▏ | 33/1189 [02:37<1:22:03, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:29,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:31,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 34/1189 [02:41<1:20:54, 4.20s/it] 3%|██▎ | 34/1189 [02:41<1:20:54, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:33,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:35,380 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 35/1189 [02:45<1:19:48, 4.15s/it] 3%|██▎ | 35/1189 [02:45<1:19:48, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:37,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:39,330 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 36/1189 [02:49<1:18:34, 4.09s/it] 3%|██▍ | 36/1189 [02:49<1:18:34, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:41,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:43,182 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 37/1189 [02:53<1:17:10, 4.02s/it] 3%|██▍ | 37/1189 [02:53<1:17:10, 4.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:45,136 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.745, 'learning_rate': 7.000000000000001e-07, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-02-28 16:36:46,965 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 38/1189 [02:56<1:15:44, 3.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:48,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.2413, 'learning_rate': 7.2e-07, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-02-28 16:36:50,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 39/1189 [03:00<1:14:12, 3.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:52,487 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8466, 'learning_rate': 7.4e-07, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-02-28 16:36:54,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 40/1189 [03:04<1:12:25, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:56,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:36:57,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 41/1189 [03:07<1:10:36, 3.69s/it] 3%|██▋ | 41/1189 [03:07<1:10:36, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:36:59,392 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7698, 'learning_rate': 7.8e-07, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-02-28 16:37:00,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 42/1189 [03:10<1:07:48, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:02,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:37:03,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 43/1189 [03:13<1:04:54, 3.40s/it] 4%|██▊ | 43/1189 [03:13<1:04:54, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:05,428 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8656, 'learning_rate': 8.200000000000001e-07, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-02-28 16:37:06,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 44/1189 [03:16<1:01:09, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:08,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0811, 'learning_rate': 8.400000000000001e-07, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-02-28 16:37:09,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 45/1189 [03:19<57:22, 3.01s/it] 4%|███ | 45/1189 [03:19<57:22, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:10,482 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:37:11,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 46/1189 [03:21<53:04, 2.79s/it] 4%|███▏ | 46/1189 [03:21<53:04, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:12,797 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:37:13,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 47/1189 [03:23<49:35, 2.61s/it] 4%|███▏ | 47/1189 [03:23<49:35, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:14,698 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:37:15,508 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 48/1189 [03:25<44:50, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:16,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6641, 'learning_rate': 9.200000000000001e-07, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-02-28 16:37:17,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 49/1189 [03:26<40:01, 2.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:17,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.6525, 'learning_rate': 9.200000000000001e-07, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-02-28 16:37:18,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 50/1189 [03:28<38:41, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:22,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 50/1189 [03:28<38:41, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:22,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 51/1189 [03:34<1:00:21, 3.18s/it]g-point operations will not be computed-28 16:37:22,042 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 51/1189 [03:34<1:00:21, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:27,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it]g-point operations will not be computed-28 16:37:27,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it]g-point operations will not be computed-28 16:37:27,542 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:32,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:40<1:13:05, 3.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:32,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 53/1189 [03:45<1:21:19, 4.30s/it]g-point operations will not be computed-28 16:37:32,928 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 53/1189 [03:45<1:21:19, 4.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:38,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 54/1189 [03:50<1:27:27, 4.62s/it]g-point operations will not be computed-28 16:37:38,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 54/1189 [03:50<1:27:27, 4.62s/it]g-point operations will not be computed-28 16:37:38,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 54/1189 [03:50<1:27:27, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:43,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 55/1189 [03:56<1:32:20, 4.89s/it]g-point operations will not be computed-28 16:37:43,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 55/1189 [03:56<1:32:20, 4.89s/it]g-point operations will not be computed-28 16:37:43,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 55/1189 [03:56<1:32:20, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:49,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [04:01<1:35:00, 5.03s/it]g-point operations will not be computed-28 16:37:49,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [04:01<1:35:00, 5.03s/it]g-point operations will not be computed-28 16:37:49,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [04:01<1:35:00, 5.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:54,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it]g-point operations will not be computed-28 16:37:54,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it]g-point operations will not be computed-28 16:37:54,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:59,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:06<1:36:18, 5.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:37:59,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 58/1189 [04:12<1:36:25, 5.12s/it]g-point operations will not be computed-28 16:37:59,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 58/1189 [04:12<1:36:25, 5.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:04,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 59/1189 [04:17<1:35:56, 5.09s/it]g-point operations will not be computed-28 16:38:04,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 59/1189 [04:17<1:35:56, 5.09s/it]g-point operations will not be computed-28 16:38:04,751 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 59/1189 [04:17<1:35:56, 5.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:09,796 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:38:12,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:38:09,796 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:38:12,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:38:09,796 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 60/1189 [04:22<1:35:35, 5.08s/it]g-point operations will not be computed-28 16:38:09,796 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 60/1189 [04:22<1:35:35, 5.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:14,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 61/1189 [04:27<1:34:50, 5.04s/it]g-point operations will not be computed-28 16:38:14,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 61/1189 [04:27<1:34:50, 5.04s/it]g-point operations will not be computed-28 16:38:14,789 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 61/1189 [04:27<1:34:50, 5.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:19,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 62/1189 [04:32<1:34:35, 5.04s/it]g-point operations will not be computed-28 16:38:19,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 62/1189 [04:32<1:34:35, 5.04s/it]g-point operations will not be computed-28 16:38:19,836 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 62/1189 [04:32<1:34:35, 5.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:24,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:37<1:35:29, 5.09s/it]g-point operations will not be computed-28 16:38:24,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:37<1:35:29, 5.09s/it]g-point operations will not be computed-28 16:38:24,925 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:37<1:35:29, 5.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:29,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it]g-point operations will not be computed-28 16:38:29,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it]g-point operations will not be computed-28 16:38:29,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:34,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 64/1189 [04:42<1:34:38, 5.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:34,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 65/1189 [04:47<1:33:06, 4.97s/it]g-point operations will not be computed-28 16:38:34,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 65/1189 [04:47<1:33:06, 4.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:39,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it]g-point operations will not be computed-28 16:38:39,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it]g-point operations will not be computed-28 16:38:39,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:44,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:52<1:32:41, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:44,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 67/1189 [04:57<1:33:56, 5.02s/it]g-point operations will not be computed-28 16:38:44,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 67/1189 [04:57<1:33:56, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:49,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 68/1189 [05:02<1:33:32, 5.01s/it]g-point operations will not be computed-28 16:38:49,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 68/1189 [05:02<1:33:32, 5.01s/it]g-point operations will not be computed-28 16:38:49,892 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 68/1189 [05:02<1:33:32, 5.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:54,717 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 69/1189 [05:06<1:32:12, 4.94s/it]g-point operations will not be computed-28 16:38:54,717 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 69/1189 [05:06<1:32:12, 4.94s/it]g-point operations will not be computed-28 16:38:54,717 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 69/1189 [05:06<1:32:12, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:38:59,434 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 70/1189 [05:11<1:30:22, 4.85s/it]g-point operations will not be computed-28 16:38:59,434 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 70/1189 [05:11<1:30:22, 4.85s/it]g-point operations will not be computed-28 16:38:59,434 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 70/1189 [05:11<1:30:22, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:04,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:16<1:29:02, 4.78s/it]g-point operations will not be computed-28 16:39:04,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:16<1:29:02, 4.78s/it]g-point operations will not be computed-28 16:39:04,051 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:16<1:29:02, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 72/1189 [05:20<1:28:40, 4.76s/it]g-point operations will not be computed-28 16:39:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 72/1189 [05:20<1:28:40, 4.76s/it]g-point operations will not be computed-28 16:39:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 72/1189 [05:20<1:28:40, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:13,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 73/1189 [05:25<1:27:37, 4.71s/it]g-point operations will not be computed-28 16:39:13,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 73/1189 [05:25<1:27:37, 4.71s/it]g-point operations will not be computed-28 16:39:13,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 73/1189 [05:25<1:27:37, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 74/1189 [05:30<1:27:16, 4.70s/it]g-point operations will not be computed-28 16:39:18,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 74/1189 [05:30<1:27:16, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:22,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 74/1189 [05:30<1:27:16, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:22,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:34<1:26:46, 4.67s/it]g-point operations will not be computed-28 16:39:22,667 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:34<1:26:46, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:27,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:34<1:26:46, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:27,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 76/1189 [05:39<1:25:47, 4.62s/it]g-point operations will not be computed-28 16:39:27,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 76/1189 [05:39<1:25:47, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:31,739 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 76/1189 [05:39<1:25:47, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:31,739 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 77/1189 [05:43<1:25:05, 4.59s/it]g-point operations will not be computed-28 16:39:31,739 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 77/1189 [05:43<1:25:05, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:36,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 78/1189 [05:48<1:24:39, 4.57s/it]g-point operations will not be computed-28 16:39:36,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 78/1189 [05:48<1:24:39, 4.57s/it]g-point operations will not be computed-28 16:39:36,244 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 78/1189 [05:48<1:24:39, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:40,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 79/1189 [05:52<1:23:41, 4.52s/it]g-point operations will not be computed-28 16:39:40,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 79/1189 [05:52<1:23:41, 4.52s/it]g-point operations will not be computed-28 16:39:40,758 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 79/1189 [05:52<1:23:41, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:45,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:39:47,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:39:45,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:39:47,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:39:45,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 80/1189 [05:57<1:23:01, 4.49s/it]g-point operations will not be computed-28 16:39:45,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 80/1189 [05:57<1:23:01, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:49,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 80/1189 [05:57<1:23:01, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:49,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 81/1189 [06:01<1:21:56, 4.44s/it]g-point operations will not be computed-28 16:39:49,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 81/1189 [06:01<1:21:56, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:53,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 81/1189 [06:01<1:21:56, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:39:53,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 82/1189 [06:05<1:20:54, 4.38s/it]g-point operations will not be computed-28 16:39:53,798 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it]g-point operations will not be computed-28 16:39:58,012 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it]g-point operations will not be computed-28 16:39:58,012 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:02,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:09<1:19:56, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:02,174 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 84/1189 [06:14<1:18:24, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:06,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 85/1189 [06:18<1:17:22, 4.21s/it]g-point operations will not be computed-28 16:40:06,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 85/1189 [06:18<1:17:22, 4.21s/it]g-point operations will not be computed-28 16:40:06,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 85/1189 [06:18<1:17:22, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:10,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 86/1189 [06:22<1:16:34, 4.17s/it]g-point operations will not be computed-28 16:40:10,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 86/1189 [06:22<1:16:34, 4.17s/it]g-point operations will not be computed-28 16:40:10,337 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 86/1189 [06:22<1:16:34, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 87/1189 [06:26<1:14:51, 4.08s/it]g-point operations will not be computed-28 16:40:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 87/1189 [06:26<1:14:51, 4.08s/it]g-point operations will not be computed-28 16:40:14,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 87/1189 [06:26<1:14:51, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:18,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 88/1189 [06:29<1:13:01, 3.98s/it]g-point operations will not be computed-28 16:40:18,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 88/1189 [06:29<1:13:01, 3.98s/it]g-point operations will not be computed-28 16:40:18,139 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 88/1189 [06:29<1:13:01, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:21,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▉ | 89/1189 [06:33<1:12:07, 3.93s/it]g-point operations will not be computed-28 16:40:21,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▉ | 89/1189 [06:33<1:12:07, 3.93s/it]g-point operations will not be computed-28 16:40:21,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▉ | 89/1189 [06:33<1:12:07, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:25,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 90/1189 [06:37<1:09:25, 3.79s/it]g-point operations will not be computed-28 16:40:25,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 90/1189 [06:37<1:09:25, 3.79s/it]g-point operations will not be computed-28 16:40:25,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it]g-point operations will not be computed-28 16:40:28,917 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it]g-point operations will not be computed-28 16:40:28,917 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 91/1189 [06:40<1:06:23, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 92/1189 [06:43<1:03:43, 3.48s/it]g-point operations will not be computed-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 92/1189 [06:43<1:03:43, 3.48s/it]g-point operations will not be computed-28 16:40:32,105 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:40:36,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:40:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:40:36,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:40:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▏ | 93/1189 [06:46<1:00:25, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:37,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▏ | 93/1189 [06:46<1:00:25, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:37,879 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 94/1189 [06:49<56:37, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:40,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 95/1189 [06:51<52:45, 2.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:42,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 95/1189 [06:51<52:45, 2.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:42,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8917, 'learning_rate': 1.8200000000000002e-06, 'epoch': 0.08} 8%|██████▌ | 96/1189 [06:53<48:32, 2.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:44,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 96/1189 [06:53<48:32, 2.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:44,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 97/1189 [06:55<44:44, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:46,677 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 97/1189 [06:55<44:44, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:46,677 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8917, 'learning_rate': 1.8800000000000002e-06, 'epoch': 0.08} 8%|██████▋ | 99/1189 [06:58<37:15, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:48,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:40:49,011 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 99/1189 [06:58<37:15, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:48,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 100/1189 [07:00<36:21, 2.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:49,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:40:50,903 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 100/1189 [07:00<36:21, 2.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:53,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 100/1189 [07:00<36:21, 2.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:53,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▊ | 101/1189 [07:06<55:41, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:53,820 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▊ | 101/1189 [07:06<55:41, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:59,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▊ | 101/1189 [07:06<55:41, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:59,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 102/1189 [07:11<1:08:10, 3.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:40:59,211 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 102/1189 [07:11<1:08:10, 3.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:04,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 102/1189 [07:11<1:08:10, 3.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:04,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 103/1189 [07:17<1:16:28, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:04,533 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 103/1189 [07:17<1:16:28, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:09,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 103/1189 [07:17<1:16:28, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:09,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 104/1189 [07:22<1:22:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:09,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 104/1189 [07:22<1:22:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:15,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:15,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:15,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:20,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:27<1:26:17, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:20,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 106/1189 [07:32<1:28:24, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:20,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 106/1189 [07:32<1:28:24, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:25,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:25,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:25,585 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:30,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 107/1189 [07:37<1:29:29, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:30,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 108/1189 [07:43<1:29:59, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:30,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 108/1189 [07:43<1:29:59, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:35,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:35,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:35,728 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:40,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:48<1:30:19, 5.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:40,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 110/1189 [07:53<1:29:40, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:40,711 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 110/1189 [07:53<1:29:40, 4.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:45,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 111/1189 [07:57<1:28:50, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:45,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 111/1189 [07:57<1:28:50, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:45,587 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 111/1189 [07:57<1:28:50, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:50,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:50,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:50,440 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:55,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [08:02<1:28:22, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:55,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 113/1189 [08:07<1:28:09, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:41:55,303 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 113/1189 [08:07<1:28:09, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:00,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:00,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:00,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:05,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 114/1189 [08:12<1:28:34, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:05,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 115/1189 [08:17<1:28:40, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:05,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 115/1189 [08:17<1:28:40, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:10,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:22<1:28:28, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:10,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:22<1:28:28, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:10,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:22<1:28:28, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:15,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:15,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:15,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:20,025 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 117/1189 [08:27<1:28:14, 4.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:20,025 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 118/1189 [08:32<1:27:26, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:20,025 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 118/1189 [08:32<1:27:26, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:24,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:24,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:24,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:29,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 119/1189 [08:37<1:27:00, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:29,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 120/1189 [08:41<1:26:13, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:29,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 120/1189 [08:41<1:26:13, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:34,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 120/1189 [08:41<1:26:13, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:34,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 121/1189 [08:46<1:25:31, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:34,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 121/1189 [08:46<1:25:31, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:39,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:51<1:24:36, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:39,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:51<1:24:36, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:39,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:51<1:24:36, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:43,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 123/1189 [08:55<1:23:55, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:43,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 123/1189 [08:55<1:23:55, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:43,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 123/1189 [08:55<1:23:55, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████▏ | 124/1189 [09:00<1:22:50, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████▏ | 124/1189 [09:00<1:22:50, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:48,274 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████▏ | 124/1189 [09:00<1:22:50, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:52,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 125/1189 [09:04<1:22:20, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:52,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 125/1189 [09:04<1:22:20, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:52,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 125/1189 [09:04<1:22:20, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 126/1189 [09:09<1:21:42, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 126/1189 [09:09<1:21:42, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:42:57,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 126/1189 [09:09<1:21:42, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:01,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:14<1:20:56, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:01,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:14<1:20:56, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:01,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:14<1:20:56, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:06,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 128/1189 [09:18<1:20:15, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:06,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 128/1189 [09:18<1:20:15, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:06,391 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 128/1189 [09:18<1:20:15, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:10,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 129/1189 [09:22<1:19:43, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:10,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 129/1189 [09:22<1:19:43, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:10,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 129/1189 [09:22<1:19:43, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:15,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:15,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:15,275 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:19,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:27<1:18:54, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:19,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 131/1189 [09:31<1:18:01, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:19,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 131/1189 [09:31<1:18:01, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:23,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 132/1189 [09:35<1:17:18, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:23,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 132/1189 [09:35<1:17:18, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:23,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 132/1189 [09:35<1:17:18, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:28,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 133/1189 [09:40<1:16:21, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:28,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 133/1189 [09:40<1:16:21, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:28,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 133/1189 [09:40<1:16:21, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:32,327 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 134/1189 [09:44<1:14:46, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:32,327 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 134/1189 [09:44<1:14:46, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:32,327 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 134/1189 [09:44<1:14:46, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:36,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 135/1189 [09:48<1:13:18, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:36,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 135/1189 [09:48<1:13:18, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:36,375 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 135/1189 [09:48<1:13:18, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:40,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 136/1189 [09:52<1:11:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:40,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 136/1189 [09:52<1:11:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:40,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 136/1189 [09:52<1:11:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:44,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|████████▉ | 137/1189 [09:56<1:10:58, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:44,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|████████▉ | 137/1189 [09:56<1:10:58, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:44,251 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|████████▉ | 137/1189 [09:56<1:10:58, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:48,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 138/1189 [09:59<1:09:48, 3.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:48,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 138/1189 [09:59<1:09:48, 3.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:48,125 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 139/1189 [10:03<1:08:49, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:51,887 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 139/1189 [10:03<1:08:49, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 139/1189 [10:03<1:08:49, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [10:07<1:06:39, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [10:07<1:06:39, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:55,616 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [10:07<1:06:39, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:59,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 141/1189 [10:10<1:04:00, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:59,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 141/1189 [10:10<1:04:00, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:43:59,106 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:02,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:02,250 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▎ | 142/1189 [10:13<1:00:46, 3.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 143/1189 [10:16<57:29, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:07,947 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 143/1189 [10:16<57:29, 3.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:07,947 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▋ | 144/1189 [10:19<53:56, 3.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:07,947 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 145/1189 [10:21<50:10, 2.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:10,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 145/1189 [10:21<50:10, 2.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:10,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 146/1189 [10:23<46:34, 2.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:12,774 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 146/1189 [10:23<46:34, 2.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:12,774 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▉ | 147/1189 [10:25<42:47, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:14,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▉ | 147/1189 [10:25<42:47, 2.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:14,855 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.444, 'learning_rate': 2.86e-06, 'epoch': 0.12} 12%|█████████▉ | 148/1189 [10:27<38:52, 2.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:16,689 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 149/1189 [10:28<34:52, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 149/1189 [10:28<34:52, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:19,650 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:23,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:30<33:53, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:23,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 151/1189 [10:36<52:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:23,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 151/1189 [10:36<52:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:29,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 151/1189 [10:36<52:40, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:29,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 152/1189 [10:41<1:04:24, 3.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:29,056 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 152/1189 [10:41<1:04:24, 3.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:34,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 152/1189 [10:41<1:04:24, 3.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:34,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 153/1189 [10:46<1:11:57, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:34,341 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 153/1189 [10:46<1:11:57, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:39,554 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 153/1189 [10:46<1:11:57, 4.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:39,554 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 154/1189 [10:52<1:17:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:39,554 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 154/1189 [10:52<1:17:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:44,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 154/1189 [10:52<1:17:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:44,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:57<1:20:32, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:44,725 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:57<1:20:32, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:49,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:57<1:20:32, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:49,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 156/1189 [11:02<1:22:42, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:49,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 156/1189 [11:02<1:22:42, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:54,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:54,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:54,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:59,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [11:07<1:23:28, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:59,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 158/1189 [11:12<1:24:07, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:44:59,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 158/1189 [11:12<1:24:07, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 158/1189 [11:12<1:24:07, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:17<1:25:01, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:17<1:25:01, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:17<1:25:01, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 160/1189 [11:22<1:24:57, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 160/1189 [11:22<1:24:57, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 161/1189 [11:27<1:24:45, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 161/1189 [11:27<1:24:45, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3716, 'learning_rate': 3.1400000000000004e-06, 'epoch': 0.14} 14%|██████████▌ | 161/1189 [11:27<1:24:45, 4.95s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 162/1189 [11:32<1:24:19, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 162/1189 [11:32<1:24:19, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 162/1189 [11:32<1:24:19, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 163/1189 [11:36<1:23:51, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 163/1189 [11:36<1:23:51, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 164/1189 [11:41<1:23:31, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 164/1189 [11:41<1:23:31, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0612, 'learning_rate': 3.2000000000000003e-06, 'epoch': 0.14} 14%|██████████▊ | 164/1189 [11:41<1:23:31, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 165/1189 [11:46<1:22:41, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 165/1189 [11:46<1:22:41, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 165/1189 [11:46<1:22:41, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 166/1189 [11:51<1:22:07, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 166/1189 [11:51<1:22:07, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3229, 'learning_rate': 3.2600000000000006e-06, 'epoch': 0.14} [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 168/1189 [12:00<1:21:00, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 168/1189 [12:00<1:21:00, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 168/1189 [12:00<1:21:00, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 169/1189 [12:05<1:20:40, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 169/1189 [12:05<1:20:40, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 169/1189 [12:05<1:20:40, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 170/1189 [12:09<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 170/1189 [12:09<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 171/1189 [12:14<1:19:11, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 171/1189 [12:14<1:19:11, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3623, 'learning_rate': 3.3400000000000006e-06, 'epoch': 0.14} 14%|███████████▏ | 171/1189 [12:14<1:19:11, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 172/1189 [12:19<1:18:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 172/1189 [12:19<1:18:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 172/1189 [12:19<1:18:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▎ | 173/1189 [12:23<1:18:19, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▎ | 173/1189 [12:23<1:18:19, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▎ | 173/1189 [12:23<1:18:19, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 174/1189 [12:28<1:18:00, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 174/1189 [12:28<1:18:00, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 175/1189 [12:32<1:17:03, 4.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 175/1189 [12:32<1:17:03, 4.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3485, 'learning_rate': 3.4200000000000007e-06, 'epoch': 0.15} 15%|███████████▍ | 175/1189 [12:32<1:17:03, 4.56s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 176/1189 [12:37<1:16:10, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 176/1189 [12:37<1:16:10, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 177/1189 [12:41<1:15:31, 4.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 177/1189 [12:41<1:15:31, 4.48s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4658, 'learning_rate': 3.46e-06, 'epoch': 0.15} 15%|███████████▋ | 178/1189 [12:45<1:14:51, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 178/1189 [12:45<1:14:51, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2413, 'learning_rate': 3.48e-06, 'epoch': 0.15} 15%|███████████▋ | 179/1189 [12:50<1:14:36, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 179/1189 [12:50<1:14:36, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2862, 'learning_rate': 3.5e-06, 'epoch': 0.15} 15%|███████████▊ | 180/1189 [12:54<1:14:03, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▊ | 180/1189 [12:54<1:14:03, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4141, 'learning_rate': 3.52e-06, 'epoch': 0.15} [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3774, 'learning_rate': 3.54e-06, 'epoch': 0.15} 15%|███████████▉ | 182/1189 [13:03<1:12:36, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▉ | 182/1189 [13:03<1:12:36, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4269, 'learning_rate': 3.5600000000000002e-06, 'epoch': 0.15} 15%|████████████ | 183/1189 [13:07<1:11:48, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 183/1189 [13:07<1:11:48, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2487, 'learning_rate': 3.58e-06, 'epoch': 0.15} 15%|████████████ | 184/1189 [13:11<1:10:41, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 184/1189 [13:11<1:10:41, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3575, 'learning_rate': 3.6000000000000003e-06, 'epoch': 0.15} 16%|████████████▏ | 185/1189 [13:15<1:09:34, 4.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 185/1189 [13:15<1:09:34, 4.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1065, 'learning_rate': 3.62e-06, 'epoch': 0.16} 16%|████████████▏ | 186/1189 [13:19<1:08:07, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 186/1189 [13:19<1:08:07, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2595, 'learning_rate': 3.6400000000000003e-06, 'epoch': 0.16} 16%|████████████▎ | 187/1189 [13:23<1:06:45, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 187/1189 [13:23<1:06:45, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5998, 'learning_rate': 3.66e-06, 'epoch': 0.16} 16%|████████████▎ | 188/1189 [13:26<1:04:50, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 188/1189 [13:26<1:04:50, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3651, 'learning_rate': 3.6800000000000003e-06, 'epoch': 0.16} 16%|████████████▍ | 189/1189 [13:30<1:02:55, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 189/1189 [13:30<1:02:55, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:47:23,648 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:47:23,648 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1233, 'learning_rate': 3.7200000000000004e-06, 'epoch': 0.16} 16%|████████████▊ | 191/1189 [13:36<57:30, 3.46s/it]g-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▊ | 191/1189 [13:36<57:30, 3.46s/it]g-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:47:29,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:47:29,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.569, 'learning_rate': 3.7600000000000004e-06, 'epoch': 0.16} [WARNING|modeling_utils.py:388] 2022-02-28 16:47:29,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:45:04,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▉ | 193/1189 [13:42<51:32, 3.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:33,620 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 194/1189 [13:44<48:13, 2.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:35,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 194/1189 [13:44<48:13, 2.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:35,960 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 195/1189 [13:46<45:07, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:38,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 195/1189 [13:46<45:07, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:38,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████▏ | 196/1189 [13:49<42:15, 2.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:40,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████▏ | 196/1189 [13:49<42:15, 2.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:40,231 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 197/1189 [13:50<38:58, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:42,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 197/1189 [13:50<38:58, 2.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:42,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 198/1189 [13:52<35:52, 2.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:43,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 198/1189 [13:52<35:52, 2.17s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:43,673 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 200/1189 [13:56<31:42, 1.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 200/1189 [13:56<31:42, 1.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:45,050 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.588, 'learning_rate': 3.900000000000001e-06, 'epoch': 0.17} 17%|█████████████▍ | 200/1189 [13:56<31:42, 1.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 201/1189 [14:01<49:10, 2.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 201/1189 [14:01<49:10, 2.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3844, 'learning_rate': 3.94e-06, 'epoch': 0.17} 17%|█████████████▌ | 201/1189 [14:01<49:10, 2.99s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 202/1189 [14:06<1:00:12, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 202/1189 [14:06<1:00:12, 3.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [14:11<1:06:57, 4.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [14:11<1:06:57, 4.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2721, 'learning_rate': 3.980000000000001e-06, 'epoch': 0.17} 17%|█████████████▍ | 204/1189 [14:16<1:11:18, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 204/1189 [14:16<1:11:18, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2226, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.17} 17%|█████████████▍ | 205/1189 [14:21<1:14:23, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 205/1189 [14:21<1:14:23, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1393, 'learning_rate': 4.0200000000000005e-06, 'epoch': 0.17} 17%|█████████████▌ | 206/1189 [14:26<1:16:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 206/1189 [14:26<1:16:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2505, 'learning_rate': 4.04e-06, 'epoch': 0.17} 17%|█████████████▌ | 207/1189 [14:31<1:18:03, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 207/1189 [14:31<1:18:03, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3549, 'learning_rate': 4.060000000000001e-06, 'epoch': 0.17} 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5281, 'learning_rate': 4.08e-06, 'epoch': 0.17} 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4086, 'learning_rate': 4.1e-06, 'epoch': 0.18} 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:36<1:18:55, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 210/1189 [14:46<1:19:22, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 210/1189 [14:46<1:19:22, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 211/1189 [14:51<1:19:31, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 211/1189 [14:51<1:19:31, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2584, 'learning_rate': 4.14e-06, 'epoch': 0.18} 18%|█████████████▊ | 211/1189 [14:51<1:19:31, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 212/1189 [14:56<1:19:01, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 212/1189 [14:56<1:19:01, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 212/1189 [14:56<1:19:01, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 213/1189 [15:00<1:18:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 213/1189 [15:00<1:18:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 213/1189 [15:00<1:18:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 214/1189 [15:05<1:17:52, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 214/1189 [15:05<1:17:52, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 214/1189 [15:05<1:17:52, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 215/1189 [15:10<1:17:46, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 215/1189 [15:10<1:17:46, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 215/1189 [15:10<1:17:46, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 216/1189 [15:15<1:17:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 216/1189 [15:15<1:17:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 216/1189 [15:15<1:17:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 217/1189 [15:19<1:16:26, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 217/1189 [15:19<1:16:26, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 218/1189 [15:24<1:16:14, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 218/1189 [15:24<1:16:14, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2388, 'learning_rate': 4.2800000000000005e-06, 'epoch': 0.18} 18%|██████████████▎ | 218/1189 [15:24<1:16:14, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 219/1189 [15:29<1:15:53, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 219/1189 [15:29<1:15:53, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 219/1189 [15:29<1:15:53, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 220/1189 [15:33<1:15:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 220/1189 [15:33<1:15:18, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 221/1189 [15:38<1:14:15, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 221/1189 [15:38<1:14:15, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2568, 'learning_rate': 4.34e-06, 'epoch': 0.19} 19%|██████████████▌ | 222/1189 [15:42<1:13:46, 4.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▌ | 222/1189 [15:42<1:13:46, 4.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.566, 'learning_rate': 4.360000000000001e-06, 'epoch': 0.19} 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3124, 'learning_rate': 4.38e-06, 'epoch': 0.19} 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3912, 'learning_rate': 4.4e-06, 'epoch': 0.19} 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 223/1189 [15:47<1:13:11, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 225/1189 [15:55<1:11:37, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 225/1189 [15:55<1:11:37, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 226/1189 [16:00<1:11:16, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▊ | 226/1189 [16:00<1:11:16, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.109, 'learning_rate': 4.440000000000001e-06, 'epoch': 0.19} 19%|██████████████▉ | 227/1189 [16:04<1:10:19, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 227/1189 [16:04<1:10:19, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2459, 'learning_rate': 4.4600000000000005e-06, 'epoch': 0.19} 19%|██████████████▉ | 227/1189 [16:04<1:10:19, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 228/1189 [16:08<1:10:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 228/1189 [16:08<1:10:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 229/1189 [16:13<1:09:07, 4.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 229/1189 [16:13<1:09:07, 4.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1719, 'learning_rate': 4.5e-06, 'epoch': 0.19} 19%|███████████████ | 230/1189 [16:17<1:08:28, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 230/1189 [16:17<1:08:28, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3651, 'learning_rate': 4.520000000000001e-06, 'epoch': 0.19} 19%|███████████████▏ | 231/1189 [16:21<1:07:51, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████▏ | 231/1189 [16:21<1:07:51, 4.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3436, 'learning_rate': 4.540000000000001e-06, 'epoch': 0.19} 20%|███████████████▏ | 232/1189 [16:25<1:06:59, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▏ | 232/1189 [16:25<1:06:59, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3034, 'learning_rate': 4.56e-06, 'epoch': 0.2} 20%|███████████████▎ | 233/1189 [16:29<1:06:45, 4.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 233/1189 [16:29<1:06:45, 4.19s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2627, 'learning_rate': 4.58e-06, 'epoch': 0.2} 20%|███████████████▎ | 234/1189 [16:33<1:05:33, 4.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 234/1189 [16:33<1:05:33, 4.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2283, 'learning_rate': 4.600000000000001e-06, 'epoch': 0.2} 20%|███████████████▍ | 235/1189 [16:37<1:04:34, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 235/1189 [16:37<1:04:34, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2872, 'learning_rate': 4.620000000000001e-06, 'epoch': 0.2} 20%|███████████████▍ | 236/1189 [16:41<1:03:39, 4.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 236/1189 [16:41<1:03:39, 4.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4579, 'learning_rate': 4.6400000000000005e-06, 'epoch': 0.2} 20%|███████████████▌ | 237/1189 [16:45<1:02:45, 3.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 237/1189 [16:45<1:02:45, 3.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1832, 'learning_rate': 4.66e-06, 'epoch': 0.2} 20%|███████████████▌ | 238/1189 [16:49<1:01:36, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 238/1189 [16:49<1:01:36, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3195, 'learning_rate': 4.680000000000001e-06, 'epoch': 0.2} 20%|███████████████▌ | 238/1189 [16:49<1:01:36, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 239/1189 [16:52<1:00:20, 3.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:50:46,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:50:46,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.341, 'learning_rate': 4.7200000000000005e-06, 'epoch': 0.2} 20%|████████████████▏ | 241/1189 [16:59<57:37, 3.65s/it]g-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 241/1189 [16:59<57:37, 3.65s/it]g-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4422, 'learning_rate': 4.74e-06, 'epoch': 0.2} 20%|████████████████▏ | 241/1189 [16:59<57:37, 3.65s/it]g-point operations will not be computed-28 16:47:48,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 242/1189 [17:02<55:30, 3.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 243/1189 [17:06<53:26, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 243/1189 [17:06<53:26, 3.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:50:58,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:50:58,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3036, 'learning_rate': 4.800000000000001e-06, 'epoch': 0.21} [WARNING|modeling_utils.py:388] 2022-02-28 16:50:58,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:50:54,641 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▍ | 245/1189 [17:11<47:40, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:02,782 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 246/1189 [17:13<44:14, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:04,974 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 246/1189 [17:13<44:14, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:04,974 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 247/1189 [17:15<40:41, 2.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:06,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 247/1189 [17:15<40:41, 2.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:06,921 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.818, 'learning_rate': 4.86e-06, 'epoch': 0.21} 21%|████████████████▋ | 248/1189 [17:17<36:55, 2.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:08,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 248/1189 [17:17<36:55, 2.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:08,572 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▊ | 249/1189 [17:19<33:07, 2.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▊ | 249/1189 [17:19<33:07, 2.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▊ | 250/1189 [17:21<31:45, 2.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▊ | 250/1189 [17:21<31:45, 2.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 251/1189 [17:26<47:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 251/1189 [17:26<47:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3932, 'learning_rate': 4.94e-06, 'epoch': 0.21} 21%|████████████████▉ | 251/1189 [17:26<47:06, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 252/1189 [17:31<57:00, 3.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 252/1189 [17:31<57:00, 3.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3453, 'learning_rate': 4.980000000000001e-06, 'epoch': 0.21} 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.077, 'learning_rate': 5e-06, 'epoch': 0.21} 21%|████████████████▌ | 253/1189 [17:36<1:03:15, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0752, 'learning_rate': 5.02e-06, 'epoch': 0.21} 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2665, 'learning_rate': 5.04e-06, 'epoch': 0.22} 21%|████████████████▋ | 255/1189 [17:46<1:10:28, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 257/1189 [17:56<1:13:33, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 257/1189 [17:56<1:13:33, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0714, 'learning_rate': 5.060000000000001e-06, 'epoch': 0.22} 22%|████████████████▉ | 258/1189 [18:01<1:13:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 258/1189 [18:01<1:13:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5038, 'learning_rate': 5.0800000000000005e-06, 'epoch': 0.22} 22%|████████████████▉ | 258/1189 [18:01<1:13:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 259/1189 [18:06<1:14:20, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 259/1189 [18:06<1:14:20, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 260/1189 [18:10<1:14:48, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 260/1189 [18:10<1:14:48, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2644, 'learning_rate': 5.12e-06, 'epoch': 0.22} 22%|█████████████████ | 261/1189 [18:15<1:14:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 261/1189 [18:15<1:14:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2386, 'learning_rate': 5.140000000000001e-06, 'epoch': 0.22} 22%|█████████████████▏ | 262/1189 [18:20<1:14:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▏ | 262/1189 [18:20<1:14:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2262, 'learning_rate': 5.1600000000000006e-06, 'epoch': 0.22} 22%|█████████████████▎ | 263/1189 [18:25<1:14:27, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▎ | 263/1189 [18:25<1:14:27, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3571, 'learning_rate': 5.18e-06, 'epoch': 0.22} 22%|█████████████████▎ | 264/1189 [18:30<1:14:09, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▎ | 264/1189 [18:30<1:14:09, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3429, 'learning_rate': 5.2e-06, 'epoch': 0.22} 22%|█████████████████▍ | 265/1189 [18:34<1:13:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 265/1189 [18:34<1:13:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2446, 'learning_rate': 5.220000000000001e-06, 'epoch': 0.22} 22%|█████████████████▍ | 266/1189 [18:39<1:12:44, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 266/1189 [18:39<1:12:44, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3092, 'learning_rate': 5.240000000000001e-06, 'epoch': 0.22} 22%|█████████████████▌ | 267/1189 [18:44<1:12:18, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▌ | 267/1189 [18:44<1:12:18, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1785, 'learning_rate': 5.2600000000000005e-06, 'epoch': 0.22} 23%|█████████████████▌ | 268/1189 [18:48<1:12:07, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▌ | 268/1189 [18:48<1:12:07, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2174, 'learning_rate': 5.28e-06, 'epoch': 0.23} 23%|█████████████████▋ | 269/1189 [18:53<1:11:39, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 269/1189 [18:53<1:11:39, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2146, 'learning_rate': 5.300000000000001e-06, 'epoch': 0.23} 23%|█████████████████▋ | 270/1189 [18:57<1:11:05, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 270/1189 [18:57<1:11:05, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1565, 'learning_rate': 5.320000000000001e-06, 'epoch': 0.23} 23%|█████████████████▊ | 271/1189 [19:02<1:10:39, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 271/1189 [19:02<1:10:39, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4837, 'learning_rate': 5.3400000000000005e-06, 'epoch': 0.23} 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1145, 'learning_rate': 5.36e-06, 'epoch': 0.23} 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2404, 'learning_rate': 5.380000000000001e-06, 'epoch': 0.23} 23%|█████████████████▊ | 272/1189 [19:07<1:09:53, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 274/1189 [19:15<1:08:25, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 274/1189 [19:15<1:08:25, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 274/1189 [19:15<1:08:25, 4.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 275/1189 [19:20<1:08:01, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 275/1189 [19:20<1:08:01, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 275/1189 [19:20<1:08:01, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 276/1189 [19:24<1:07:15, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 276/1189 [19:24<1:07:15, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 276/1189 [19:24<1:07:15, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 277/1189 [19:28<1:06:44, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 277/1189 [19:28<1:06:44, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 277/1189 [19:28<1:06:44, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 278/1189 [19:33<1:05:43, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 278/1189 [19:33<1:05:43, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 278/1189 [19:33<1:05:43, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 279/1189 [19:37<1:04:56, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 279/1189 [19:37<1:04:56, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 279/1189 [19:37<1:04:56, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 280/1189 [19:41<1:04:17, 4.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 280/1189 [19:41<1:04:17, 4.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 280/1189 [19:41<1:04:17, 4.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 281/1189 [19:45<1:03:42, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 281/1189 [19:45<1:03:42, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 281/1189 [19:45<1:03:42, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 282/1189 [19:49<1:02:40, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 282/1189 [19:49<1:02:40, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 282/1189 [19:49<1:02:40, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 283/1189 [19:53<1:01:47, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 283/1189 [19:53<1:01:47, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 283/1189 [19:53<1:01:47, 4.09s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 284/1189 [19:57<1:01:06, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 284/1189 [19:57<1:01:06, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 284/1189 [19:57<1:01:06, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 285/1189 [20:01<59:58, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 285/1189 [20:01<59:58, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 285/1189 [20:01<59:58, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 286/1189 [20:05<58:57, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 286/1189 [20:05<58:57, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 286/1189 [20:05<58:57, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▎ | 287/1189 [20:08<57:39, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:02,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:02,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2194, 'learning_rate': 5.68e-06, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-02-28 16:54:02,321 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▍ | 289/1189 [20:15<55:08, 3.68s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▍ | 289/1189 [20:15<55:08, 3.68s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▍ | 289/1189 [20:15<55:08, 3.68s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▌ | 290/1189 [20:19<53:43, 3.59s/it]g-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:12,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:12,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3521, 'learning_rate': 5.74e-06, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-02-28 16:54:12,325 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:51:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 292/1189 [20:25<49:02, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 292/1189 [20:25<49:02, 3.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 293/1189 [20:27<45:53, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 293/1189 [20:27<45:53, 3.07s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:20,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:20,223 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:22,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:22,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:24,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:24,399 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:26,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:26,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:27,684 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:27,684 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7455, 'learning_rate': 5.92e-06, 'epoch': 0.25} [WARNING|modeling_utils.py:388] 2022-02-28 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:54:30,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 301/1189 [20:46<42:56, 2.90s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 301/1189 [20:46<42:56, 2.90s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 301/1189 [20:46<42:56, 2.90s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 302/1189 [20:51<52:41, 3.56s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 302/1189 [20:51<52:41, 3.56s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 302/1189 [20:51<52:41, 3.56s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▍ | 303/1189 [20:56<59:12, 4.01s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▍ | 303/1189 [20:56<59:12, 4.01s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|███████████████████▉ | 304/1189 [21:01<1:03:55, 4.33s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|███████████████████▉ | 304/1189 [21:01<1:03:55, 4.33s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.8708, 'learning_rate': 6e-06, 'epoch': 0.26} 26%|███████████████████▉ | 304/1189 [21:01<1:03:55, 4.33s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0563, 'learning_rate': 6.040000000000001e-06, 'epoch': 0.26} 26%|████████████████████ | 305/1189 [21:06<1:06:56, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 307/1189 [21:16<1:09:45, 4.75s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 307/1189 [21:16<1:09:45, 4.75s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 307/1189 [21:16<1:09:45, 4.75s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 308/1189 [21:21<1:10:10, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 308/1189 [21:21<1:10:10, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 309/1189 [21:26<1:10:20, 4.80s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 309/1189 [21:26<1:10:20, 4.80s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.9649, 'learning_rate': 6.1e-06, 'epoch': 0.26} 26%|████████████████████▎ | 309/1189 [21:26<1:10:20, 4.80s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 310/1189 [21:30<1:10:37, 4.82s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 310/1189 [21:30<1:10:37, 4.82s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 311/1189 [21:35<1:10:48, 4.84s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 311/1189 [21:35<1:10:48, 4.84s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1021, 'learning_rate': 6.1400000000000005e-06, 'epoch': 0.26} 26%|████████████████████▍ | 312/1189 [21:40<1:10:39, 4.83s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 312/1189 [21:40<1:10:39, 4.83s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1044, 'learning_rate': 6.16e-06, 'epoch': 0.26} 26%|████████████████████▍ | 312/1189 [21:40<1:10:39, 4.83s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 313/1189 [21:45<1:10:12, 4.81s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 313/1189 [21:45<1:10:12, 4.81s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 314/1189 [21:50<1:09:49, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 314/1189 [21:50<1:09:49, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1376, 'learning_rate': 6.200000000000001e-06, 'epoch': 0.26} 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0619, 'learning_rate': 6.220000000000001e-06, 'epoch': 0.26} 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▋ | 315/1189 [21:54<1:09:39, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▋ | 316/1189 [21:59<1:09:33, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▋ | 316/1189 [21:59<1:09:33, 4.78s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 317/1189 [22:04<1:09:35, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 317/1189 [22:04<1:09:35, 4.79s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3625, 'learning_rate': 6.26e-06, 'epoch': 0.27} 27%|████████████████████▊ | 318/1189 [22:09<1:09:18, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 318/1189 [22:09<1:09:18, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2863, 'learning_rate': 6.280000000000001e-06, 'epoch': 0.27} 27%|████████████████████▊ | 318/1189 [22:09<1:09:18, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 319/1189 [22:14<1:09:10, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 319/1189 [22:14<1:09:10, 4.77s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 320/1189 [22:18<1:08:35, 4.74s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 320/1189 [22:18<1:08:35, 4.74s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2889, 'learning_rate': 6.3200000000000005e-06, 'epoch': 0.27} 27%|█████████████████████ | 321/1189 [22:23<1:08:09, 4.71s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████ | 321/1189 [22:23<1:08:09, 4.71s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1358, 'learning_rate': 6.360000000000001e-06, 'epoch': 0.27} [WARNING|modeling_utils.py:388] 2022-02-28 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:56:18,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▏ | 323/1189 [22:32<1:07:06, 4.65s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▏ | 323/1189 [22:32<1:07:06, 4.65s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 324/1189 [22:37<1:06:37, 4.62s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 324/1189 [22:37<1:06:37, 4.62s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2859, 'learning_rate': 6.4000000000000006e-06, 'epoch': 0.27} 27%|█████████████████████▎ | 325/1189 [22:41<1:05:52, 4.57s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 325/1189 [22:41<1:05:52, 4.57s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2048, 'learning_rate': 6.42e-06, 'epoch': 0.27} 27%|█████████████████████▍ | 326/1189 [22:45<1:05:14, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▍ | 326/1189 [22:45<1:05:14, 4.54s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3831, 'learning_rate': 6.440000000000001e-06, 'epoch': 0.27} 28%|█████████████████████▍ | 327/1189 [22:50<1:04:49, 4.51s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▍ | 327/1189 [22:50<1:04:49, 4.51s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3815, 'learning_rate': 6.460000000000001e-06, 'epoch': 0.27} 28%|█████████████████████▍ | 327/1189 [22:50<1:04:49, 4.51s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 328/1189 [22:54<1:04:22, 4.49s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 328/1189 [22:54<1:04:22, 4.49s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 329/1189 [22:59<1:03:43, 4.45s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 329/1189 [22:59<1:03:43, 4.45s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1473, 'learning_rate': 6.5000000000000004e-06, 'epoch': 0.28} 28%|█████████████████████▋ | 330/1189 [23:03<1:03:00, 4.40s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▋ | 330/1189 [23:03<1:03:00, 4.40s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3793, 'learning_rate': 6.520000000000001e-06, 'epoch': 0.28} 28%|█████████████████████▋ | 331/1189 [23:07<1:02:21, 4.36s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▋ | 331/1189 [23:07<1:02:21, 4.36s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0783, 'learning_rate': 6.540000000000001e-06, 'epoch': 0.28} 28%|█████████████████████▊ | 332/1189 [23:11<1:01:41, 4.32s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 332/1189 [23:11<1:01:41, 4.32s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2146, 'learning_rate': 6.560000000000001e-06, 'epoch': 0.28} 28%|█████████████████████▊ | 333/1189 [23:16<1:00:53, 4.27s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 333/1189 [23:16<1:00:53, 4.27s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2755, 'learning_rate': 6.5800000000000005e-06, 'epoch': 0.28} 28%|█████████████████████▉ | 334/1189 [23:20<1:00:20, 4.23s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▉ | 334/1189 [23:20<1:00:20, 4.23s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0445, 'learning_rate': 6.600000000000001e-06, 'epoch': 0.28} 28%|██████████████████████▌ | 335/1189 [23:24<59:22, 4.17s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 335/1189 [23:24<59:22, 4.17s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2928, 'learning_rate': 6.620000000000001e-06, 'epoch': 0.28} 28%|██████████████████████▌ | 336/1189 [23:28<58:21, 4.11s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 336/1189 [23:28<58:21, 4.11s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3136, 'learning_rate': 6.640000000000001e-06, 'epoch': 0.28} 28%|██████████████████████▌ | 336/1189 [23:28<58:21, 4.11s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 337/1189 [23:32<57:04, 4.02s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 337/1189 [23:32<57:04, 4.02s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 337/1189 [23:32<57:04, 4.02s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 338/1189 [23:35<56:01, 3.95s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 338/1189 [23:35<56:01, 3.95s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 338/1189 [23:35<56:01, 3.95s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|██████████████████████▊ | 339/1189 [23:39<54:48, 3.87s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:57:33,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:57:33,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2516, 'learning_rate': 6.720000000000001e-06, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-02-28 16:57:33,185 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|██████████████████████▉ | 341/1189 [23:46<51:27, 3.64s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|██████████████████████▉ | 341/1189 [23:46<51:27, 3.64s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|██████████████████████▉ | 341/1189 [23:46<51:27, 3.64s/it]g-point operations will not be computed-28 16:54:16,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████ | 342/1189 [23:49<49:15, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████ | 342/1189 [23:49<49:15, 3.49s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████ | 343/1189 [23:52<46:45, 3.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:57:45,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 16:57:45,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4456, 'learning_rate': 6.800000000000001e-06, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-02-28 16:57:45,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:57:41,217 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▏ | 345/1189 [23:57<41:20, 2.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:49,000 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▏ | 345/1189 [23:57<41:20, 2.94s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:49,000 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▎ | 346/1189 [23:59<38:31, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:51,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▎ | 346/1189 [23:59<38:31, 2.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:51,103 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▎ | 347/1189 [24:01<35:12, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:52,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▎ | 347/1189 [24:01<35:12, 2.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:52,967 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6718, 'learning_rate': 6.88e-06, 'epoch': 0.29} 29%|███████████████████████▍ | 349/1189 [24:05<28:30, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:54,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▍ | 349/1189 [24:05<28:30, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:54,584 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▌ | 350/1189 [24:07<27:31, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:55,940 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▌ | 350/1189 [24:07<27:31, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▌ | 350/1189 [24:07<27:31, 1.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 351/1189 [24:12<41:34, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 351/1189 [24:12<41:34, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 352/1189 [24:17<50:34, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 352/1189 [24:17<50:34, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.157, 'learning_rate': 6.96e-06, 'epoch': 0.3} 30%|███████████████████████▋ | 352/1189 [24:17<50:34, 3.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▊ | 353/1189 [24:22<56:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▊ | 353/1189 [24:22<56:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▊ | 353/1189 [24:22<56:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▏ | 354/1189 [24:27<1:00:18, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▏ | 354/1189 [24:27<1:00:18, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 355/1189 [24:32<1:02:48, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 355/1189 [24:32<1:02:48, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1486, 'learning_rate': 7.0200000000000006e-06, 'epoch': 0.3} 30%|███████████████████████▎ | 355/1189 [24:32<1:02:48, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 356/1189 [24:37<1:04:29, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 356/1189 [24:37<1:04:29, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▍ | 357/1189 [24:42<1:05:24, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▍ | 357/1189 [24:42<1:05:24, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3384, 'learning_rate': 7.06e-06, 'epoch': 0.3} 30%|███████████████████████▍ | 358/1189 [24:47<1:06:01, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▍ | 358/1189 [24:47<1:06:01, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0699, 'learning_rate': 7.08e-06, 'epoch': 0.3} 30%|███████████████████████▌ | 359/1189 [24:52<1:06:32, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 359/1189 [24:52<1:06:32, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.238, 'learning_rate': 7.100000000000001e-06, 'epoch': 0.3} 30%|███████████████████████▌ | 360/1189 [24:56<1:06:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 360/1189 [24:56<1:06:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3706, 'learning_rate': 7.1200000000000004e-06, 'epoch': 0.3} 30%|███████████████████████▌ | 360/1189 [24:56<1:06:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 361/1189 [25:01<1:06:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 361/1189 [25:01<1:06:40, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 362/1189 [25:06<1:06:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 362/1189 [25:06<1:06:26, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0899, 'learning_rate': 7.16e-06, 'epoch': 0.3} 31%|███████████████████████▊ | 363/1189 [25:11<1:06:12, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▊ | 363/1189 [25:11<1:06:12, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1032, 'learning_rate': 7.180000000000001e-06, 'epoch': 0.31} 31%|███████████████████████▉ | 364/1189 [25:16<1:06:22, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▉ | 364/1189 [25:16<1:06:22, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2998, 'learning_rate': 7.2000000000000005e-06, 'epoch': 0.31} 31%|███████████████████████▉ | 365/1189 [25:20<1:05:49, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▉ | 365/1189 [25:20<1:05:49, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2338, 'learning_rate': 7.22e-06, 'epoch': 0.31} 31%|████████████████████████ | 366/1189 [25:25<1:05:35, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████ | 366/1189 [25:25<1:05:35, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1811, 'learning_rate': 7.24e-06, 'epoch': 0.31} 31%|████████████████████████ | 367/1189 [25:30<1:04:49, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████ | 367/1189 [25:30<1:04:49, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0937, 'learning_rate': 7.260000000000001e-06, 'epoch': 0.31} 31%|████████████████████████▏ | 368/1189 [25:34<1:04:30, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▏ | 368/1189 [25:34<1:04:30, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5385, 'learning_rate': 7.280000000000001e-06, 'epoch': 0.31} 31%|████████████████████████▏ | 369/1189 [25:39<1:04:07, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▏ | 369/1189 [25:39<1:04:07, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3573, 'learning_rate': 7.3e-06, 'epoch': 0.31} 31%|████████████████████████▏ | 369/1189 [25:39<1:04:07, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 370/1189 [25:44<1:03:43, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 370/1189 [25:44<1:03:43, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 370/1189 [25:44<1:03:43, 4.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:57:59,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0908, 'learning_rate': 7.360000000000001e-06, 'epoch': 0.31} 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 371/1189 [25:48<1:03:13, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▍ | 373/1189 [25:57<1:02:09, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▍ | 373/1189 [25:57<1:02:09, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▍ | 373/1189 [25:57<1:02:09, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▌ | 374/1189 [26:02<1:01:30, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▌ | 374/1189 [26:02<1:01:30, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▌ | 374/1189 [26:02<1:01:30, 4.53s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▌ | 375/1189 [26:06<1:01:00, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▌ | 375/1189 [26:06<1:01:00, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▋ | 376/1189 [26:11<1:00:30, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▋ | 376/1189 [26:11<1:00:30, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2195, 'learning_rate': 7.440000000000001e-06, 'epoch': 0.32} 32%|█████████████████████████▎ | 377/1189 [26:15<59:59, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▎ | 377/1189 [26:15<59:59, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1713, 'learning_rate': 7.4600000000000006e-06, 'epoch': 0.32} 32%|█████████████████████████▍ | 378/1189 [26:19<59:30, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▍ | 378/1189 [26:19<59:30, 4.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1561, 'learning_rate': 7.48e-06, 'epoch': 0.32} 32%|█████████████████████████▌ | 379/1189 [26:24<59:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▌ | 379/1189 [26:24<59:01, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1195, 'learning_rate': 7.500000000000001e-06, 'epoch': 0.32} 32%|█████████████████████████▌ | 380/1189 [26:28<58:32, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▌ | 380/1189 [26:28<58:32, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:00:22,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:00:22,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0967, 'learning_rate': 7.540000000000001e-06, 'epoch': 0.32} 32%|█████████████████████████▋ | 382/1189 [26:36<57:39, 4.29s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 382/1189 [26:36<57:39, 4.29s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2816, 'learning_rate': 7.5600000000000005e-06, 'epoch': 0.32} 32%|█████████████████████████▊ | 383/1189 [26:40<56:12, 4.18s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 383/1189 [26:40<56:12, 4.18s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0563, 'learning_rate': 7.58e-06, 'epoch': 0.32} 32%|█████████████████████████▊ | 384/1189 [26:44<54:56, 4.10s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 384/1189 [26:44<54:56, 4.10s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3362, 'learning_rate': 7.600000000000001e-06, 'epoch': 0.32} 32%|█████████████████████████▉ | 385/1189 [26:48<53:51, 4.02s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 385/1189 [26:48<53:51, 4.02s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3688, 'learning_rate': 7.620000000000001e-06, 'epoch': 0.32} 32%|█████████████████████████▉ | 386/1189 [26:52<53:06, 3.97s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 386/1189 [26:52<53:06, 3.97s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1055, 'learning_rate': 7.640000000000001e-06, 'epoch': 0.32} 33%|██████████████████████████ | 387/1189 [26:56<52:08, 3.90s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████ | 387/1189 [26:56<52:08, 3.90s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3171, 'learning_rate': 7.660000000000001e-06, 'epoch': 0.33} 33%|██████████████████████████ | 388/1189 [26:59<51:05, 3.83s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████ | 388/1189 [26:59<51:05, 3.83s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:00:53,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:00:53,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4034, 'learning_rate': 7.7e-06, 'epoch': 0.33} 33%|██████████████████████████▏ | 390/1189 [27:06<48:24, 3.63s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▏ | 390/1189 [27:06<48:24, 3.63s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3698, 'learning_rate': 7.72e-06, 'epoch': 0.33} 33%|██████████████████████████▏ | 390/1189 [27:06<48:24, 3.63s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▎ | 391/1189 [27:09<46:20, 3.48s/it]g-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:02,818 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:02,818 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:05,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:05,574 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 16:59:41,150 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1896, 'learning_rate': 7.78e-06, 'epoch': 0.33} 33%|██████████████████████████▌ | 394/1189 [27:18<39:45, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▌ | 394/1189 [27:18<39:45, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▌ | 395/1189 [27:20<37:18, 2.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▌ | 395/1189 [27:20<37:18, 2.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:12,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:12,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:14,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:14,501 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3534, 'learning_rate': 7.860000000000001e-06, 'epoch': 0.33} [WARNING|modeling_utils.py:388] 2022-02-28 17:01:17,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:17,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:19,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:19,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6628, 'learning_rate': 7.92e-06, 'epoch': 0.34} [WARNING|modeling_utils.py:388] 2022-02-28 17:01:24,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:01:24,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0486, 'learning_rate': 7.94e-06, 'epoch': 0.34} 34%|███████████████████████████ | 402/1189 [27:39<47:09, 3.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████ | 402/1189 [27:39<47:09, 3.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1799, 'learning_rate': 7.960000000000002e-06, 'epoch': 0.34} 34%|███████████████████████████ | 403/1189 [27:44<53:08, 4.06s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████ | 403/1189 [27:44<53:08, 4.06s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1841, 'learning_rate': 7.980000000000002e-06, 'epoch': 0.34} 34%|███████████████████████████▏ | 404/1189 [27:49<56:51, 4.35s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 404/1189 [27:49<56:51, 4.35s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2834, 'learning_rate': 8.000000000000001e-06, 'epoch': 0.34} 34%|███████████████████████████▏ | 405/1189 [27:54<59:41, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 405/1189 [27:54<59:41, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1536, 'learning_rate': 8.020000000000001e-06, 'epoch': 0.34} 34%|███████████████████████████▏ | 405/1189 [27:54<59:41, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 406/1189 [28:00<1:01:33, 4.72s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 406/1189 [28:00<1:01:33, 4.72s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 406/1189 [28:00<1:01:33, 4.72s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 407/1189 [28:05<1:02:43, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 407/1189 [28:05<1:02:43, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 407/1189 [28:05<1:02:43, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1054, 'learning_rate': 8.1e-06, 'epoch': 0.34} 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [28:10<1:03:21, 4.87s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 410/1189 [28:19<1:03:22, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 410/1189 [28:19<1:03:22, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 410/1189 [28:19<1:03:22, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|██████████████████████████▉ | 411/1189 [28:24<1:03:20, 4.88s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2693, 'learning_rate': 8.16e-06, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-02-28 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:02:19,583 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████ | 413/1189 [28:34<1:02:12, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████ | 413/1189 [28:34<1:02:12, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████ | 413/1189 [28:34<1:02:12, 4.81s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 414/1189 [28:38<1:01:33, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 414/1189 [28:38<1:01:33, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 415/1189 [28:43<1:01:30, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 415/1189 [28:43<1:01:30, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1823, 'learning_rate': 8.220000000000001e-06, 'epoch': 0.35} 35%|███████████████████████████▏ | 415/1189 [28:43<1:01:30, 4.77s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 416/1189 [28:48<1:01:12, 4.75s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 416/1189 [28:48<1:01:12, 4.75s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 416/1189 [28:48<1:01:12, 4.75s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 417/1189 [28:53<1:00:47, 4.73s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 417/1189 [28:53<1:00:47, 4.73s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▍ | 418/1189 [28:57<1:00:15, 4.69s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▍ | 418/1189 [28:57<1:00:15, 4.69s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0802, 'learning_rate': 8.28e-06, 'epoch': 0.35} 35%|████████████████████████████▏ | 419/1189 [29:02<59:53, 4.67s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▏ | 419/1189 [29:02<59:53, 4.67s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2756, 'learning_rate': 8.3e-06, 'epoch': 0.35} 35%|████████████████████████████▏ | 419/1189 [29:02<59:53, 4.67s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 420/1189 [29:06<59:13, 4.62s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 420/1189 [29:06<59:13, 4.62s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 420/1189 [29:06<59:13, 4.62s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 421/1189 [29:11<58:52, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 421/1189 [29:11<58:52, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▍ | 422/1189 [29:15<58:48, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▍ | 422/1189 [29:15<58:48, 4.60s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2496, 'learning_rate': 8.36e-06, 'epoch': 0.35} 36%|████████████████████████████▍ | 423/1189 [29:20<58:20, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▍ | 423/1189 [29:20<58:20, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2382, 'learning_rate': 8.380000000000001e-06, 'epoch': 0.36} 36%|████████████████████████████▍ | 423/1189 [29:20<58:20, 4.57s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 424/1189 [29:24<57:36, 4.52s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 424/1189 [29:24<57:36, 4.52s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 424/1189 [29:24<57:36, 4.52s/it]g-point operations will not be computed-28 17:01:09,504 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2347, 'learning_rate': 8.44e-06, 'epoch': 0.36} 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 425/1189 [29:29<56:49, 4.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:21,475 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1574, 'learning_rate': 8.48e-06, 'epoch': 0.36} 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▋ | 427/1189 [29:37<56:01, 4.41s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:30,202 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▊ | 429/1189 [29:46<55:09, 4.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3594, 'learning_rate': 8.52e-06, 'epoch': 0.36} 36%|████████████████████████████▉ | 431/1189 [29:55<54:23, 4.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▉ | 431/1189 [29:55<54:23, 4.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2223, 'learning_rate': 8.540000000000001e-06, 'epoch': 0.36} 36%|█████████████████████████████ | 432/1189 [29:59<53:44, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████ | 432/1189 [29:59<53:44, 4.26s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1815, 'learning_rate': 8.560000000000001e-06, 'epoch': 0.36} 36%|█████████████████████████████▏ | 433/1189 [30:03<53:06, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████▏ | 433/1189 [30:03<53:06, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2792, 'learning_rate': 8.580000000000001e-06, 'epoch': 0.36} 37%|█████████████████████████████▏ | 434/1189 [30:07<52:10, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▏ | 434/1189 [30:07<52:10, 4.15s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1954, 'learning_rate': 8.6e-06, 'epoch': 0.36} 37%|█████████████████████████████▎ | 435/1189 [30:11<51:14, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 435/1189 [30:11<51:14, 4.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4341, 'learning_rate': 8.62e-06, 'epoch': 0.37} 37%|█████████████████████████████▎ | 436/1189 [30:14<50:13, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 436/1189 [30:14<50:13, 4.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1195, 'learning_rate': 8.64e-06, 'epoch': 0.37} 37%|█████████████████████████████▍ | 437/1189 [30:18<49:16, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▍ | 437/1189 [30:18<49:16, 3.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1726, 'learning_rate': 8.66e-06, 'epoch': 0.37} 37%|█████████████████████████████▍ | 438/1189 [30:22<48:02, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▍ | 438/1189 [30:22<48:02, 3.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:15,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:15,977 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3113, 'learning_rate': 8.700000000000001e-06, 'epoch': 0.37} 37%|█████████████████████████████▌ | 440/1189 [30:29<45:10, 3.62s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▌ | 440/1189 [30:29<45:10, 3.62s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2111, 'learning_rate': 8.720000000000001e-06, 'epoch': 0.37} 37%|█████████████████████████████▋ | 441/1189 [30:32<43:26, 3.48s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▋ | 441/1189 [30:32<43:26, 3.48s/it]g-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:25,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:25,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2824, 'learning_rate': 8.76e-06, 'epoch': 0.37} [WARNING|modeling_utils.py:388] 2022-02-28 17:04:25,510 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:03:38,815 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▊ | 443/1189 [30:38<39:49, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▊ | 444/1189 [30:40<37:37, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▊ | 444/1189 [30:40<37:37, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:33,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:33,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:35,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:35,488 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:37,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:37,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:39,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:39,088 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4837, 'learning_rate': 8.880000000000001e-06, 'epoch': 0.38} [WARNING|modeling_utils.py:388] 2022-02-28 17:04:42,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:04:42,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.591, 'learning_rate': 8.920000000000001e-06, 'epoch': 0.38} [WARNING|modeling_utils.py:388] 2022-02-28 17:04:42,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:57<36:32, 2.97s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:57<36:32, 2.97s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1316, 'learning_rate': 8.94e-06, 'epoch': 0.38} 38%|██████████████████████████████▎ | 451/1189 [30:57<36:32, 2.97s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▍ | 452/1189 [31:02<44:18, 3.61s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▍ | 452/1189 [31:02<44:18, 3.61s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▍ | 453/1189 [31:07<49:27, 4.03s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▍ | 453/1189 [31:07<49:27, 4.03s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1289, 'learning_rate': 8.98e-06, 'epoch': 0.38} 38%|██████████████████████████████▍ | 453/1189 [31:07<49:27, 4.03s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 454/1189 [31:12<52:52, 4.32s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 454/1189 [31:12<52:52, 4.32s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 455/1189 [31:17<54:57, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 455/1189 [31:17<54:57, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0944, 'learning_rate': 9.020000000000002e-06, 'epoch': 0.38} 38%|██████████████████████████████▋ | 456/1189 [31:22<56:34, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 456/1189 [31:22<56:34, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1625, 'learning_rate': 9.040000000000002e-06, 'epoch': 0.38} 38%|██████████████████████████████▋ | 456/1189 [31:22<56:34, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 457/1189 [31:27<57:17, 4.70s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 457/1189 [31:27<57:17, 4.70s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 457/1189 [31:27<57:17, 4.70s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▊ | 458/1189 [31:32<57:46, 4.74s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▊ | 458/1189 [31:32<57:46, 4.74s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 459/1189 [31:37<58:09, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 459/1189 [31:37<58:09, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0962, 'learning_rate': 9.100000000000001e-06, 'epoch': 0.39} 39%|██████████████████████████████▉ | 459/1189 [31:37<58:09, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 460/1189 [31:41<58:08, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 460/1189 [31:41<58:08, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 460/1189 [31:41<58:08, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 461/1189 [31:46<57:57, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 461/1189 [31:46<57:57, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 462/1189 [31:51<57:54, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 462/1189 [31:51<57:54, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2095, 'learning_rate': 9.16e-06, 'epoch': 0.39} 39%|███████████████████████████████ | 462/1189 [31:51<57:54, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 463/1189 [31:56<58:05, 4.80s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 463/1189 [31:56<58:05, 4.80s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 463/1189 [31:56<58:05, 4.80s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 464/1189 [32:01<57:50, 4.79s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 464/1189 [32:01<57:50, 4.79s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2855, 'learning_rate': 9.220000000000002e-06, 'epoch': 0.39} 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 465/1189 [32:05<57:39, 4.78s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 466/1189 [32:10<57:20, 4.76s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 466/1189 [32:10<57:20, 4.76s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 466/1189 [32:10<57:20, 4.76s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▍ | 467/1189 [32:15<56:49, 4.72s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▍ | 467/1189 [32:15<56:49, 4.72s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▍ | 468/1189 [32:19<56:22, 4.69s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▍ | 468/1189 [32:19<56:22, 4.69s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2952, 'learning_rate': 9.280000000000001e-06, 'epoch': 0.39} 39%|███████████████████████████████▌ | 469/1189 [32:24<56:09, 4.68s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▌ | 469/1189 [32:24<56:09, 4.68s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0674, 'learning_rate': 9.3e-06, 'epoch': 0.39} 39%|███████████████████████████████▌ | 469/1189 [32:24<56:09, 4.68s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▌ | 470/1189 [32:29<55:43, 4.65s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▌ | 470/1189 [32:29<55:43, 4.65s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▌ | 470/1189 [32:29<55:43, 4.65s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▋ | 471/1189 [32:33<55:21, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▋ | 471/1189 [32:33<55:21, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▋ | 471/1189 [32:33<55:21, 4.63s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 472/1189 [32:38<54:52, 4.59s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 472/1189 [32:38<54:52, 4.59s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 472/1189 [32:38<54:52, 4.59s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 473/1189 [32:42<54:29, 4.57s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 473/1189 [32:42<54:29, 4.57s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▉ | 474/1189 [32:47<54:08, 4.54s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▉ | 474/1189 [32:47<54:08, 4.54s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3065, 'learning_rate': 9.4e-06, 'epoch': 0.4} 40%|███████████████████████████████▉ | 475/1189 [32:51<53:29, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▉ | 475/1189 [32:51<53:29, 4.49s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3725, 'learning_rate': 9.42e-06, 'epoch': 0.4} 40%|████████████████████████████████ | 476/1189 [32:55<52:59, 4.46s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████ | 476/1189 [32:55<52:59, 4.46s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2321, 'learning_rate': 9.440000000000001e-06, 'epoch': 0.4} 40%|████████████████████████████████ | 477/1189 [33:00<52:23, 4.42s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████ | 477/1189 [33:00<52:23, 4.42s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0517, 'learning_rate': 9.460000000000001e-06, 'epoch': 0.4} 40%|████████████████████████████████▏ | 478/1189 [33:04<51:45, 4.37s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▏ | 478/1189 [33:04<51:45, 4.37s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1719, 'learning_rate': 9.48e-06, 'epoch': 0.4} 40%|████████████████████████████████▏ | 479/1189 [33:08<51:21, 4.34s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▏ | 479/1189 [33:08<51:21, 4.34s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2294, 'learning_rate': 9.5e-06, 'epoch': 0.4} g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2519, 'learning_rate': 9.52e-06, 'epoch': 0.4} 40%|████████████████████████████████▎ | 481/1189 [33:17<50:14, 4.26s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 481/1189 [33:17<50:14, 4.26s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1538, 'learning_rate': 9.54e-06, 'epoch': 0.4} 41%|████████████████████████████████▍ | 482/1189 [33:21<49:57, 4.24s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 482/1189 [33:21<49:57, 4.24s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2508, 'learning_rate': 9.56e-06, 'epoch': 0.41} 41%|████████████████████████████████▍ | 483/1189 [33:25<49:27, 4.20s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 483/1189 [33:25<49:27, 4.20s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2302, 'learning_rate': 9.58e-06, 'epoch': 0.41} 41%|████████████████████████████████▌ | 484/1189 [33:29<48:29, 4.13s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▌ | 484/1189 [33:29<48:29, 4.13s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2961, 'learning_rate': 9.600000000000001e-06, 'epoch': 0.41} 41%|████████████████████████████████▋ | 485/1189 [33:33<47:41, 4.06s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 485/1189 [33:33<47:41, 4.06s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2522, 'learning_rate': 9.620000000000001e-06, 'epoch': 0.41} 41%|████████████████████████████████▋ | 485/1189 [33:33<47:41, 4.06s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 486/1189 [33:37<47:07, 4.02s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 486/1189 [33:37<47:07, 4.02s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 487/1189 [33:41<46:20, 3.96s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 487/1189 [33:41<46:20, 3.96s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0833, 'learning_rate': 9.66e-06, 'epoch': 0.41} 41%|████████████████████████████████▊ | 487/1189 [33:41<46:20, 3.96s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 488/1189 [33:44<45:27, 3.89s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 488/1189 [33:44<45:27, 3.89s/it]g-point operations will not be computed-28 17:04:29,793 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▉ | 489/1189 [33:48<44:20, 3.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▉ | 489/1189 [33:48<44:20, 3.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▉ | 490/1189 [33:51<43:12, 3.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▉ | 490/1189 [33:51<43:12, 3.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2419, 'learning_rate': 9.72e-06, 'epoch': 0.41} 41%|█████████████████████████████████ | 491/1189 [33:55<41:51, 3.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████ | 491/1189 [33:55<41:51, 3.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:07:48,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:07:48,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1422, 'learning_rate': 9.760000000000001e-06, 'epoch': 0.41} [WARNING|modeling_utils.py:388] 2022-02-28 17:07:48,484 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████▏ | 493/1189 [34:01<38:31, 3.32s/it]g-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████▏ | 493/1189 [34:01<38:31, 3.32s/it]g-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:07:54,193 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:07:56,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-02-28 17:07:56,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5124, 'learning_rate': 9.820000000000001e-06, 'epoch': 0.42} [WARNING|modeling_utils.py:388] 2022-02-28 17:07:56,639 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:07:40,310 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▎ | 496/1189 [34:08<31:26, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:59,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▎ | 496/1189 [34:08<31:26, 2.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:07:59,912 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3506, 'learning_rate': 9.86e-06, 'epoch': 0.42} 42%|█████████████████████████████████▌ | 498/1189 [34:12<25:44, 2.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:01,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▌ | 498/1189 [34:12<25:44, 2.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:01,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▌ | 499/1189 [34:13<23:07, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:04,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▌ | 499/1189 [34:13<23:07, 2.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:08:04,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-02-28 17:08:05,927 >> Num examples = 2642 | 500/1189 [34:15<22:25, 1.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 2%|█▌ | 4/221 [00:08<08:58, 2.48s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 2%|█▉ | 5/221 [00:11<09:42, 2.70s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 3%|██▎ | 6/221 [00:15<10:21, 2.89s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 3%|██▋ | 7/221 [00:19<11:19, 3.17s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███ | 8/221 [00:22<11:06, 3.13s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███▍ | 9/221 [00:25<10:58, 3.11s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|███▋ | 10/221 [00:29<11:50, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████ | 11/221 [00:33<12:46, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████▍ | 12/221 [00:36<12:00, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 6%|████▊ | 13/221 [00:39<11:36, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 6%|█████▏ | 14/221 [00:42<11:38, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 7%|█████▌ | 15/221 [00:47<13:03, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 7%|█████▉ | 16/221 [00:52<13:57, 4.09s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 8%|██████▎ | 17/221 [00:55<13:18, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 8%|██████▋ | 18/221 [00:59<13:07, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 9%|███████ | 19/221 [01:03<12:25, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 9%|███████▍ | 20/221 [01:06<11:50, 3.53s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|███████▊ | 21/221 [01:09<11:08, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▏ | 22/221 [01:12<10:55, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▌ | 23/221 [01:15<10:43, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|████████▉ | 24/221 [01:19<11:15, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|█████████▎ | 25/221 [01:23<11:46, 3.61s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 12%|█████████▋ | 26/221 [01:27<11:59, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 12%|██████████ | 27/221 [01:29<10:59, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▍ | 28/221 [01:33<11:30, 3.58s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▊ | 29/221 [01:38<12:12, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▏ | 30/221 [01:41<11:21, 3.57s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▌ | 31/221 [01:43<10:20, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▊ | 32/221 [01:47<10:16, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▏ | 33/221 [01:50<10:40, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▌ | 34/221 [01:54<10:46, 3.46s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|████████████▉ | 35/221 [01:57<10:21, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|█████████████▎ | 36/221 [02:00<10:15, 3.33s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 17%|█████████████▋ | 37/221 [02:05<11:08, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 17%|██████████████ | 38/221 [02:08<10:32, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▍ | 39/221 [02:11<10:46, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▊ | 40/221 [02:14<10:13, 3.39s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▏ | 41/221 [02:18<10:24, 3.47s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▌ | 42/221 [02:23<11:17, 3.79s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▉ | 43/221 [02:26<10:49, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▎ | 44/221 [02:31<11:50, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▋ | 45/221 [02:35<12:21, 4.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████ | 46/221 [02:40<12:12, 4.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████▍ | 47/221 [02:44<11:56, 4.12s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|█████████████████▊ | 48/221 [02:48<11:51, 4.11s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|██████████████████▏ | 49/221 [02:51<11:23, 3.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▌ | 50/221 [02:55<11:21, 3.99s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▉ | 51/221 [02:59<10:39, 3.76s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▎ | 52/221 [03:02<09:57, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▋ | 53/221 [03:05<09:24, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|████████████████████ | 54/221 [03:08<09:40, 3.47s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▍ | 55/221 [03:12<09:42, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▊ | 56/221 [03:16<10:28, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▏ | 57/221 [03:20<10:31, 3.85s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▌ | 58/221 [03:24<10:06, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|█████████████████████▉ | 59/221 [03:27<09:32, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|██████████████████████▎ | 60/221 [03:29<08:47, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|██████████████████████▋ | 61/221 [03:33<09:00, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|███████████████████████ | 62/221 [03:36<08:50, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|███████████████████████▍ | 63/221 [03:40<08:56, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|███████████████████████▋ | 64/221 [03:43<08:50, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|████████████████████████ | 65/221 [03:47<08:44, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▍ | 66/221 [03:50<08:49, 3.42s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▊ | 67/221 [03:53<08:16, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▏ | 68/221 [03:57<08:56, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▌ | 69/221 [04:00<08:32, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▉ | 70/221 [04:03<08:24, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|██████████████████████████▎ | 71/221 [04:07<08:13, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|██████████████████████████▋ | 72/221 [04:09<07:48, 3.15s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|███████████████████████████ | 73/221 [04:13<08:05, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|███████████████████████████▍ | 74/221 [04:16<08:02, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|███████████████████████████▊ | 75/221 [04:19<07:58, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|████████████████████████████▏ | 76/221 [04:23<07:52, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▌ | 77/221 [04:26<07:48, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▉ | 78/221 [04:29<07:56, 3.33s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▎ | 79/221 [04:32<07:38, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▋ | 80/221 [04:36<07:33, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|██████████████████████████████ | 81/221 [04:39<07:56, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|██████████████████████████████▍ | 82/221 [04:44<08:28, 3.66s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▊ | 83/221 [04:48<08:53, 3.87s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▏ | 84/221 [04:52<08:54, 3.91s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▌ | 85/221 [04:57<09:14, 4.08s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████▉ | 86/221 [05:00<09:01, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|████████████████████████████████▎ | 87/221 [05:05<09:17, 4.16s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|████████████████████████████████▋ | 88/221 [05:08<08:42, 3.93s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|█████████████████████████████████ | 89/221 [05:12<08:11, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▍ | 90/221 [05:15<08:07, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▊ | 91/221 [05:19<08:20, 3.85s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|██████████████████████████████████▏ | 92/221 [05:24<08:32, 3.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|██████████████████████████████████▌ | 93/221 [05:28<08:37, 4.04s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▉ | 94/221 [05:32<08:24, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|███████████████████████████████████▏ | 95/221 [05:36<08:23, 3.99s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|███████████████████████████████████▌ | 96/221 [05:40<08:12, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▉ | 97/221 [05:44<08:22, 4.06s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|████████████████████████████████████▎ | 98/221 [05:48<08:09, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 99/221 [05:51<07:25, 3.66s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 100/221 [05:54<07:23, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████ | 101/221 [05:57<07:02, 3.52s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████▍ | 102/221 [06:00<06:38, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|█████████████████████████████████████▊ | 103/221 [06:04<06:54, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|██████████████████████████████████████ | 104/221 [06:08<07:06, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▍ | 105/221 [06:13<07:27, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▊ | 106/221 [06:17<07:26, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|███████████████████████████████████████▏ | 107/221 [06:20<06:54, 3.64s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|███████████████████████████████████████▌ | 108/221 [06:24<07:13, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|███████████████████████████████████████▉ | 109/221 [06:28<07:16, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▎ | 110/221 [06:31<06:56, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▋ | 111/221 [06:35<06:39, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████ | 112/221 [06:39<06:42, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████▍ | 113/221 [06:42<06:37, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|█████████████████████████████████████████▊ | 114/221 [06:46<06:23, 3.59s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|██████████████████████████████████████████▏ | 115/221 [06:49<06:16, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|██████████████████████████████████████████▌ | 116/221 [06:52<06:02, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|██████████████████████████████████████████▉ | 117/221 [06:56<05:55, 3.42s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|███████████████████████████████████████████▏ | 118/221 [06:59<06:05, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▌ | 119/221 [07:04<06:28, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▉ | 120/221 [07:08<06:42, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▎ | 121/221 [07:12<06:27, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▋ | 122/221 [07:14<05:43, 3.47s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████ | 123/221 [07:17<05:09, 3.16s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████▍ | 124/221 [07:20<05:04, 3.14s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|█████████████████████████████████████████████▊ | 125/221 [07:24<05:22, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████████▏ | 126/221 [07:27<05:03, 3.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████████▌ | 127/221 [07:29<04:50, 3.09s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|██████████████████████████████████████████████▉ | 128/221 [07:32<04:33, 2.94s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|███████████████████████████████████████████████▎ | 129/221 [07:36<04:51, 3.17s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|███████████████████████████████████████████████▋ | 130/221 [07:38<04:35, 3.03s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|████████████████████████████████████████████████ | 131/221 [07:42<04:48, 3.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▍ | 132/221 [07:45<04:29, 3.03s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▋ | 133/221 [07:48<04:30, 3.07s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████ | 134/221 [07:51<04:18, 2.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████▍ | 135/221 [07:54<04:22, 3.05s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|█████████████████████████████████████████████████▊ | 136/221 [07:58<04:38, 3.27s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▏ | 137/221 [08:01<04:42, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▌ | 138/221 [08:05<04:50, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|██████████████████████████████████████████████████▉ | 139/221 [08:09<04:52, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|███████████████████████████████████████████████████▎ | 140/221 [08:11<04:21, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|███████████████████████████████████████████████████▋ | 141/221 [08:14<04:18, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|████████████████████████████████████████████████████ | 142/221 [08:17<04:10, 3.17s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▍ | 143/221 [08:20<03:51, 2.97s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▊ | 144/221 [08:24<04:08, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|█████████████████████████████████████████████████████▏ | 145/221 [08:27<04:02, 3.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|█████████████████████████████████████████████████████▌ | 146/221 [08:31<04:12, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|█████████████████████████████████████████████████████▉ | 147/221 [08:33<03:57, 3.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▏ | 148/221 [08:37<03:57, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▌ | 149/221 [08:40<03:56, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|██████████████████████████████████████████████████████▉ | 150/221 [08:43<03:51, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|███████████████████████████████████████████████████████▎ | 151/221 [08:47<03:58, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|███████████████████████████████████████████████████████▋ | 152/221 [08:50<03:50, 3.34s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████████ | 153/221 [08:53<03:43, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▍ | 154/221 [08:57<03:43, 3.33s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▊ | 155/221 [09:00<03:40, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▏ | 156/221 [09:04<03:40, 3.39s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▌ | 157/221 [09:07<03:24, 3.19s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▉ | 158/221 [09:11<03:48, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|██████████████████████████████████████████████████████████▎ | 159/221 [09:15<03:47, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|██████████████████████████████████████████████████████████▋ | 160/221 [09:19<03:52, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████ | 161/221 [09:23<03:55, 3.93s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████▍ | 162/221 [09:27<03:52, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|███████████████████████████████████████████████████████████▋ | 163/221 [09:32<03:55, 4.07s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████████ | 164/221 [09:36<03:59, 4.21s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▍ | 165/221 [09:40<03:45, 4.03s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▊ | 166/221 [09:43<03:26, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▏ | 167/221 [09:46<03:19, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▌ | 168/221 [09:50<03:06, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▉ | 169/221 [09:53<03:07, 3.61s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▎ | 170/221 [09:57<03:07, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▋ | 171/221 [10:01<03:04, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████ | 172/221 [10:04<02:54, 3.57s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████▍ | 173/221 [10:08<02:50, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|███████████████████████████████████████████████████████████████▊ | 174/221 [10:11<02:40, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:14<02:32, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:14<02:32, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:14<02:32, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▊ | 177/221 [10:21<02:25, 3.31s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▏ | 178/221 [10:24<02:28, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▌ | 179/221 [10:28<02:22, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▉ | 180/221 [10:32<02:29, 3.64s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▎ | 181/221 [10:36<02:29, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▋ | 182/221 [10:39<02:24, 3.70s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████ | 183/221 [10:44<02:27, 3.87s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████▍ | 184/221 [10:48<02:22, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|███████████████████████████████████████████████████████████████████▊ | 185/221 [10:51<02:12, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████████▏ | 186/221 [10:55<02:16, 3.91s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▌ | 187/221 [10:59<02:08, 3.78s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▉ | 188/221 [11:03<02:08, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▎ | 189/221 [11:07<02:06, 3.96s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▋ | 190/221 [11:11<02:06, 4.10s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████████ | 191/221 [11:16<02:07, 4.24s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▎ | 192/221 [11:20<02:02, 4.23s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▋ | 193/221 [11:24<01:50, 3.95s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████ | 194/221 [11:27<01:40, 3.71s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████▍ | 195/221 [11:30<01:31, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|███████████████████████████████████████████████████████████████████████▊ | 196/221 [11:33<01:25, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████████▏ | 197/221 [11:36<01:18, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▌ | 198/221 [11:40<01:21, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▉ | 199/221 [11:44<01:23, 3.81s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████████▎ | 200/221 [11:48<01:18, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████████▋ | 201/221 [11:51<01:11, 3.60s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████████ | 202/221 [11:54<01:04, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▍ | 203/221 [11:58<01:02, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▊ | 204/221 [12:02<01:03, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▏ | 205/221 [12:07<01:05, 4.07s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▌ | 206/221 [12:12<01:03, 4.24s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|███████████████████████████████████████████████████████████████████████████▊ | 207/221 [12:15<00:56, 4.02s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████████▏ | 208/221 [12:19<00:51, 3.96s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████████▌ | 209/221 [12:22<00:45, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████████▉ | 210/221 [12:26<00:42, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████████▎ | 211/221 [12:31<00:40, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████████▋ | 212/221 [12:34<00:35, 3.93s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████████ | 213/221 [12:38<00:29, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▍ | 214/221 [12:41<00:25, 3.64s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▊ | 215/221 [12:45<00:22, 3.80s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:49<00:19, 3.89s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▌ | 217/221 [12:53<00:15, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████████▉ | 218/221 [12:57<00:11, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████████▎| 219/221 [13:01<00:07, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████████▋| 220/221 [13:05<00:04, 4.06s/it][INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|configuration_utils.py:438] 2022-02-28 17:21:17,260 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|configuration_utils.py:438] 2022-02-28 17:21:17,260 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 02/28/2022 17:21:17 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 02/28/2022 17:23:06 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20220228_163348-20lja62k/run-20lja62k.wandb']. This may take a bit of time if the files are large. [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1788, 'learning_rate': 9.940000000000001e-06, 'epoch': 0.42} [INFO|feature_extraction_utils.py:324] 2022-02-28 17:21:33,438 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████ | 502/1189 [49:55<37:56:34, 198.83s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████ | 502/1189 [49:55<37:56:34, 198.83s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3094, 'learning_rate': 9.960000000000001e-06, 'epoch': 0.42} 42%|████████████████████████████████▏ | 503/1189 [50:01<26:49:44, 140.79s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▏ | 503/1189 [50:01<26:49:44, 140.79s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1493, 'learning_rate': 9.980000000000001e-06, 'epoch': 0.42} 42%|████████████████████████████████▏ | 504/1189 [50:06<19:02:38, 100.08s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▏ | 504/1189 [50:06<19:02:38, 100.08s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9753, 'learning_rate': 1e-05, 'epoch': 0.42} 42%|████████████████████████████████▋ | 505/1189 [50:11<13:36:45, 71.65s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▋ | 505/1189 [50:11<13:36:45, 71.65s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2008, 'learning_rate': 9.985486211901307e-06, 'epoch': 0.42} 43%|█████████████████████████████████▏ | 506/1189 [50:16<9:48:30, 51.70s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▏ | 506/1189 [50:16<9:48:30, 51.70s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3298, 'learning_rate': 9.970972423802613e-06, 'epoch': 0.43} 43%|█████████████████████████████████▏ | 506/1189 [50:16<9:48:30, 51.70s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 507/1189 [50:21<7:08:44, 37.72s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 507/1189 [50:21<7:08:44, 37.72s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 507/1189 [50:21<7:08:44, 37.72s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:26<5:17:03, 27.93s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:26<5:17:03, 27.93s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:26<5:17:03, 27.93s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:26<5:17:03, 27.93s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2461, 'learning_rate': 9.927431059506532e-06, 'epoch': 0.43} 43%|█████████████████████████████████▎ | 508/1189 [50:26<5:17:03, 27.93s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:26<5:17:03, 27.93s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 510/1189 [50:37<3:05:04, 16.35s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 510/1189 [50:37<3:05:04, 16.35s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2255, 'learning_rate': 9.898403483309144e-06, 'epoch': 0.43} onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▌ | 512/1189 [50:47<1:59:06, 10.56s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▌ | 512/1189 [50:47<1:59:06, 10.56s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▌ | 512/1189 [50:47<1:59:06, 10.56s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 513/1189 [50:52<1:39:52, 8.86s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 513/1189 [50:52<1:39:52, 8.86s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 513/1189 [50:52<1:39:52, 8.86s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 514/1189 [50:56<1:26:20, 7.67s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 514/1189 [50:56<1:26:20, 7.67s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 514/1189 [50:56<1:26:20, 7.67s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▊ | 515/1189 [51:01<1:16:36, 6.82s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▊ | 515/1189 [51:01<1:16:36, 6.82s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▊ | 516/1189 [51:06<1:09:47, 6.22s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▊ | 516/1189 [51:06<1:09:47, 6.22s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1141, 'learning_rate': 9.825834542815675e-06, 'epoch': 0.43} 43%|█████████████████████████████████▊ | 516/1189 [51:06<1:09:47, 6.22s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▉ | 517/1189 [51:11<1:04:54, 5.80s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▉ | 517/1189 [51:11<1:04:54, 5.80s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▉ | 517/1189 [51:11<1:04:54, 5.80s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|█████████████████████████████████▉ | 518/1189 [51:16<1:01:17, 5.48s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|█████████████████████████████████▉ | 518/1189 [51:16<1:01:17, 5.48s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 519/1189 [51:20<58:41, 5.26s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 519/1189 [51:20<58:41, 5.26s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5685, 'learning_rate': 9.782293178519594e-06, 'epoch': 0.44} 44%|██████████████████████████████████▉ | 519/1189 [51:20<58:41, 5.26s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 520/1189 [51:25<56:42, 5.09s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 520/1189 [51:25<56:42, 5.09s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 520/1189 [51:25<56:42, 5.09s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 521/1189 [51:30<55:29, 4.98s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 521/1189 [51:30<55:29, 4.98s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 522/1189 [51:34<54:14, 4.88s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 522/1189 [51:34<54:14, 4.88s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2293, 'learning_rate': 9.738751814223512e-06, 'epoch': 0.44} 44%|███████████████████████████████████ | 522/1189 [51:34<54:14, 4.88s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 523/1189 [51:39<53:25, 4.81s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 523/1189 [51:39<53:25, 4.81s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 523/1189 [51:39<53:25, 4.81s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 524/1189 [51:44<52:44, 4.76s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 524/1189 [51:44<52:44, 4.76s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 524/1189 [51:44<52:44, 4.76s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 525/1189 [51:48<51:48, 4.68s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 525/1189 [51:48<51:48, 4.68s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 526/1189 [51:53<51:25, 4.65s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 526/1189 [51:53<51:25, 4.65s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0392, 'learning_rate': 9.680696661828739e-06, 'epoch': 0.44} 44%|███████████████████████████████████▍ | 527/1189 [51:57<50:44, 4.60s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 527/1189 [51:57<50:44, 4.60s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.188, 'learning_rate': 9.666182873730045e-06, 'epoch': 0.44} 44%|███████████████████████████████████▍ | 527/1189 [51:57<50:44, 4.60s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 527/1189 [51:57<50:44, 4.60s/it]onfig.jsonner.py:560] 2022-02-28 17:08:05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1156, 'learning_rate': 9.651669085631351e-06, 'epoch': 0.44} [WARNING|modeling_utils.py:388] 2022-02-28 17:25:56,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:25:56,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3848, 'learning_rate': 9.637155297532657e-06, 'epoch': 0.44} [WARNING|modeling_utils.py:388] 2022-02-28 17:25:56,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:25:56,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▋ | 530/1189 [52:11<49:16, 4.49s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▋ | 530/1189 [52:11<49:16, 4.49s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▋ | 531/1189 [52:15<48:58, 4.47s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▋ | 531/1189 [52:15<48:58, 4.47s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.37, 'learning_rate': 9.60812772133527e-06, 'epoch': 0.45} 45%|███████████████████████████████████▋ | 531/1189 [52:15<48:58, 4.47s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▊ | 532/1189 [52:19<48:28, 4.43s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▊ | 532/1189 [52:19<48:28, 4.43s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▊ | 533/1189 [52:24<47:37, 4.36s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▊ | 533/1189 [52:24<47:37, 4.36s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2271, 'learning_rate': 9.579100145137882e-06, 'epoch': 0.45} 45%|███████████████████████████████████▉ | 534/1189 [52:28<46:51, 4.29s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 534/1189 [52:28<46:51, 4.29s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2586, 'learning_rate': 9.564586357039188e-06, 'epoch': 0.45} 45%|███████████████████████████████████▉ | 535/1189 [52:32<45:52, 4.21s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 535/1189 [52:32<45:52, 4.21s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1681, 'learning_rate': 9.550072568940494e-06, 'epoch': 0.45} 45%|████████████████████████████████████ | 536/1189 [52:36<44:58, 4.13s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████ | 536/1189 [52:36<44:58, 4.13s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1042, 'learning_rate': 9.5355587808418e-06, 'epoch': 0.45} 45%|████████████████████████████████████ | 536/1189 [52:36<44:58, 4.13s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 537/1189 [52:40<44:01, 4.05s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 537/1189 [52:40<44:01, 4.05s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 537/1189 [52:40<44:01, 4.05s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 538/1189 [52:43<42:51, 3.95s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 538/1189 [52:43<42:51, 3.95s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 538/1189 [52:43<42:51, 3.95s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▎ | 539/1189 [52:47<41:50, 3.86s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:26:41,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:26:41,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2554, 'learning_rate': 9.477503628447025e-06, 'epoch': 0.45} [WARNING|modeling_utils.py:388] 2022-02-28 17:26:41,060 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 541/1189 [52:54<39:30, 3.66s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 541/1189 [52:54<39:30, 3.66s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 541/1189 [52:54<39:30, 3.66s/it]g-point operations will not be computed05,922 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 542/1189 [52:57<37:54, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:49,189 >> 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. 46%|████████████████████████████████████▍ | 542/1189 [52:57<37:54, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:49,189 >> 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. 46%|████████████████████████████████████▌ | 543/1189 [53:00<36:06, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:49,189 >> 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. 46%|████████████████████████████████████▌ | 543/1189 [53:00<36:06, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:49,189 >> 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. 46%|████████████████████████████████████▌ | 543/1189 [53:00<36:06, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:49,189 >> 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. 46%|████████████████████████████████████▌ | 544/1189 [53:03<34:13, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:54,796 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▌ | 544/1189 [53:03<34:13, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:54,796 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▋ | 545/1189 [53:05<32:10, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▋ | 545/1189 [53:05<32:10, 3.00s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▋ | 546/1189 [53:08<29:56, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▋ | 546/1189 [53:08<29:56, 2.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:00,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:00,377 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:02,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:02,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:05,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:05,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.568, 'learning_rate': 9.332365747460089e-06, 'epoch': 0.46} [WARNING|modeling_utils.py:388] 2022-02-28 17:27:05,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:11,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:11,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:27:11,014 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▏ | 552/1189 [53:26<39:06, 3.68s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▏ | 552/1189 [53:26<39:06, 3.68s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▏ | 552/1189 [53:26<39:06, 3.68s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▏ | 553/1189 [53:31<43:32, 4.11s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▏ | 553/1189 [53:31<43:32, 4.11s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▏ | 553/1189 [53:31<43:32, 4.11s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▎ | 554/1189 [53:36<46:39, 4.41s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▎ | 554/1189 [53:36<46:39, 4.41s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▎ | 555/1189 [53:41<49:19, 4.67s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▎ | 555/1189 [53:41<49:19, 4.67s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2894, 'learning_rate': 9.259796806966618e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▎ | 555/1189 [53:41<49:19, 4.67s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▍ | 556/1189 [53:46<50:30, 4.79s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▍ | 556/1189 [53:46<50:30, 4.79s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▍ | 557/1189 [53:51<51:43, 4.91s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▍ | 557/1189 [53:51<51:43, 4.91s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1136, 'learning_rate': 9.230769230769232e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▍ | 557/1189 [53:51<51:43, 4.91s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▌ | 558/1189 [53:56<52:09, 4.96s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▌ | 558/1189 [53:56<52:09, 4.96s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▌ | 559/1189 [54:01<52:19, 4.98s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▌ | 559/1189 [54:01<52:19, 4.98s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3735, 'learning_rate': 9.201741654571845e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▌ | 559/1189 [54:01<52:19, 4.98s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▌ | 559/1189 [54:01<52:19, 4.98s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0632, 'learning_rate': 9.187227866473151e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▌ | 559/1189 [54:01<52:19, 4.98s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▋ | 561/1189 [54:12<53:11, 5.08s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▋ | 561/1189 [54:12<53:11, 5.08s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1948, 'learning_rate': 9.172714078374455e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▊ | 562/1189 [54:17<53:11, 5.09s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▊ | 562/1189 [54:17<53:11, 5.09s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0541, 'learning_rate': 9.158200290275763e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▉ | 563/1189 [54:22<53:14, 5.10s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▉ | 563/1189 [54:22<53:14, 5.10s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2505, 'learning_rate': 9.14368650217707e-06, 'epoch': 0.47} 47%|█████████████████████████████████████▉ | 564/1189 [54:27<52:55, 5.08s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▉ | 564/1189 [54:27<52:55, 5.08s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9946, 'learning_rate': 9.129172714078376e-06, 'epoch': 0.47} 48%|██████████████████████████████████████ | 565/1189 [54:32<52:46, 5.07s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████ | 565/1189 [54:32<52:46, 5.07s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0665, 'learning_rate': 9.114658925979682e-06, 'epoch': 0.47} 48%|██████████████████████████████████████ | 565/1189 [54:32<52:46, 5.07s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████ | 565/1189 [54:32<52:46, 5.07s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2316, 'learning_rate': 9.100145137880988e-06, 'epoch': 0.48} 48%|██████████████████████████████████████▏ | 567/1189 [54:42<52:32, 5.07s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▏ | 567/1189 [54:42<52:32, 5.07s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1467, 'learning_rate': 9.085631349782294e-06, 'epoch': 0.48} 48%|██████████████████████████████████████▏ | 568/1189 [54:47<52:08, 5.04s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▏ | 568/1189 [54:47<52:08, 5.04s/it]g-point operations will not be computed-28 17:26:57,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.173, 'learning_rate': 9.0711175616836e-06, 'epoch': 0.48} 48%|██████████████████████████████████████▎ | 569/1189 [54:52<51:14, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▎ | 569/1189 [54:52<51:14, 4.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▎ | 570/1189 [54:57<50:50, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▎ | 570/1189 [54:57<50:50, 4.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1592, 'learning_rate': 9.042089985486213e-06, 'epoch': 0.48} 48%|██████████████████████████████████████▍ | 571/1189 [55:02<50:25, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▍ | 571/1189 [55:02<50:25, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1818, 'learning_rate': 9.027576197387519e-06, 'epoch': 0.48} 48%|██████████████████████████████████████▍ | 571/1189 [55:02<50:25, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▍ | 571/1189 [55:02<50:25, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3169, 'learning_rate': 9.013062409288825e-06, 'epoch': 0.48} 48%|██████████████████████████████████████▍ | 571/1189 [55:02<50:25, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▍ | 571/1189 [55:02<50:25, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▌ | 573/1189 [55:11<49:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▌ | 573/1189 [55:11<49:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▌ | 573/1189 [55:11<49:39, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▌ | 574/1189 [55:16<49:12, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▌ | 574/1189 [55:16<49:12, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▌ | 574/1189 [55:16<49:12, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▋ | 575/1189 [55:21<48:58, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▋ | 575/1189 [55:21<48:58, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▋ | 575/1189 [55:21<48:58, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▊ | 576/1189 [55:25<48:30, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▊ | 576/1189 [55:25<48:30, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▊ | 576/1189 [55:25<48:30, 4.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▊ | 577/1189 [55:30<48:10, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▊ | 577/1189 [55:30<48:10, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▊ | 577/1189 [55:30<48:10, 4.72s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▉ | 578/1189 [55:35<47:39, 4.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▉ | 578/1189 [55:35<47:39, 4.68s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▉ | 579/1189 [55:39<47:01, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▉ | 579/1189 [55:39<47:01, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:34,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:34,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2794, 'learning_rate': 8.896952104499275e-06, 'epoch': 0.49} [WARNING|modeling_utils.py:388] 2022-02-28 17:29:38,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:38,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.427, 'learning_rate': 8.882438316400581e-06, 'epoch': 0.49} [WARNING|modeling_utils.py:388] 2022-02-28 17:29:38,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:38,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9855, 'learning_rate': 8.867924528301887e-06, 'epoch': 0.49} [WARNING|modeling_utils.py:388] 2022-02-28 17:29:38,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:38,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:28:45,007 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▏ | 583/1189 [55:57<44:49, 4.44s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▎ | 584/1189 [56:01<43:57, 4.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▎ | 584/1189 [56:01<43:57, 4.36s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:55,473 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:29:55,473 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3482, 'learning_rate': 8.824383164005806e-06, 'epoch': 0.49} 49%|███████████████████████████████████████▍ | 586/1189 [56:09<42:17, 4.21s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▍ | 586/1189 [56:09<42:17, 4.21s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3232, 'learning_rate': 8.809869375907114e-06, 'epoch': 0.49} 49%|███████████████████████████████████████▍ | 587/1189 [56:13<41:41, 4.16s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▍ | 587/1189 [56:13<41:41, 4.16s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3642, 'learning_rate': 8.795355587808418e-06, 'epoch': 0.49} 49%|███████████████████████████████████████▌ | 588/1189 [56:17<40:57, 4.09s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▌ | 588/1189 [56:17<40:57, 4.09s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1983, 'learning_rate': 8.780841799709724e-06, 'epoch': 0.49} 50%|███████████████████████████████████████▋ | 589/1189 [56:21<39:53, 3.99s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▋ | 589/1189 [56:21<39:53, 3.99s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1152, 'learning_rate': 8.766328011611032e-06, 'epoch': 0.5} 50%|███████████████████████████████████████▋ | 590/1189 [56:24<38:40, 3.87s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▋ | 590/1189 [56:24<38:40, 3.87s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:18,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:18,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3222, 'learning_rate': 8.737300435413644e-06, 'epoch': 0.5} [WARNING|modeling_utils.py:388] 2022-02-28 17:30:18,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▊ | 592/1189 [56:31<35:35, 3.58s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:24,464 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:24,464 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:24,464 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5443, 'learning_rate': 8.708272859216255e-06, 'epoch': 0.5} 50%|███████████████████████████████████████▉ | 594/1189 [56:37<32:18, 3.26s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▉ | 594/1189 [56:37<32:18, 3.26s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:29,961 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:32,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:32,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:34,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:34,152 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3369, 'learning_rate': 8.650217706821482e-06, 'epoch': 0.5} [WARNING|modeling_utils.py:388] 2022-02-28 17:30:35,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:35,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:37,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:37,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:39,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:39,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:30:39,364 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▍ | 601/1189 [56:54<30:11, 3.08s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▍ | 601/1189 [56:54<30:11, 3.08s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▌ | 602/1189 [57:00<36:46, 3.76s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▌ | 602/1189 [57:00<36:46, 3.76s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2669, 'learning_rate': 8.577648766328013e-06, 'epoch': 0.51} 51%|████████████████████████████████████████▌ | 603/1189 [57:05<41:29, 4.25s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▌ | 603/1189 [57:05<41:29, 4.25s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4227, 'learning_rate': 8.563134978229319e-06, 'epoch': 0.51} 51%|████████████████████████████████████████▌ | 603/1189 [57:05<41:29, 4.25s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▋ | 604/1189 [57:10<44:40, 4.58s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▋ | 604/1189 [57:10<44:40, 4.58s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▋ | 605/1189 [57:16<46:49, 4.81s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▋ | 605/1189 [57:16<46:49, 4.81s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2073, 'learning_rate': 8.534107402031931e-06, 'epoch': 0.51} 51%|████████████████████████████████████████▊ | 606/1189 [57:21<48:05, 4.95s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▊ | 606/1189 [57:21<48:05, 4.95s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.294, 'learning_rate': 8.519593613933237e-06, 'epoch': 0.51} 51%|████████████████████████████████████████▊ | 607/1189 [57:26<48:23, 4.99s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▊ | 607/1189 [57:26<48:23, 4.99s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2053, 'learning_rate': 8.505079825834544e-06, 'epoch': 0.51} 51%|████████████████████████████████████████▉ | 608/1189 [57:31<48:29, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▉ | 608/1189 [57:31<48:29, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2851, 'learning_rate': 8.49056603773585e-06, 'epoch': 0.51} 51%|████████████████████████████████████████▉ | 609/1189 [57:36<48:37, 5.03s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▉ | 609/1189 [57:36<48:37, 5.03s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2182, 'learning_rate': 8.476052249637156e-06, 'epoch': 0.51} 51%|█████████████████████████████████████████ | 610/1189 [57:41<48:29, 5.03s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████ | 610/1189 [57:41<48:29, 5.03s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2754, 'learning_rate': 8.461538461538462e-06, 'epoch': 0.51} 51%|█████████████████████████████████████████ | 611/1189 [57:46<48:13, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████ | 611/1189 [57:46<48:13, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2814, 'learning_rate': 8.447024673439768e-06, 'epoch': 0.51} 51%|█████████████████████████████████████████ | 611/1189 [57:46<48:13, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▏ | 612/1189 [57:51<48:06, 5.00s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▏ | 612/1189 [57:51<48:06, 5.00s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▏ | 613/1189 [57:56<48:04, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▏ | 613/1189 [57:56<48:04, 5.01s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1668, 'learning_rate': 8.41799709724238e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▎ | 614/1189 [58:01<47:42, 4.98s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▎ | 614/1189 [58:01<47:42, 4.98s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.078, 'learning_rate': 8.403483309143687e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▍ | 615/1189 [58:06<47:24, 4.96s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▍ | 615/1189 [58:06<47:24, 4.96s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2407, 'learning_rate': 8.388969521044995e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▍ | 616/1189 [58:11<47:08, 4.94s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▍ | 616/1189 [58:11<47:08, 4.94s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1871, 'learning_rate': 8.3744557329463e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▍ | 616/1189 [58:11<47:08, 4.94s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▌ | 617/1189 [58:16<46:21, 4.86s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▌ | 617/1189 [58:16<46:21, 4.86s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▌ | 618/1189 [58:20<45:39, 4.80s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▌ | 618/1189 [58:20<45:39, 4.80s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1482, 'learning_rate': 8.345428156748913e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▌ | 618/1189 [58:20<45:39, 4.80s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▋ | 619/1189 [58:25<45:18, 4.77s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▋ | 619/1189 [58:25<45:18, 4.77s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▋ | 619/1189 [58:25<45:18, 4.77s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▋ | 620/1189 [58:30<44:55, 4.74s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▋ | 620/1189 [58:30<44:55, 4.74s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▊ | 621/1189 [58:34<44:34, 4.71s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▊ | 621/1189 [58:34<44:34, 4.71s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0035, 'learning_rate': 8.301886792452832e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▊ | 622/1189 [58:39<44:00, 4.66s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▊ | 622/1189 [58:39<44:00, 4.66s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9219, 'learning_rate': 8.287373004354136e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▉ | 623/1189 [58:43<43:23, 4.60s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▉ | 623/1189 [58:43<43:23, 4.60s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1855, 'learning_rate': 8.272859216255443e-06, 'epoch': 0.52} 52%|█████████████████████████████████████████▉ | 624/1189 [58:48<42:55, 4.56s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████▉ | 624/1189 [58:48<42:55, 4.56s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.248, 'learning_rate': 8.25834542815675e-06, 'epoch': 0.52} g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2014, 'learning_rate': 8.243831640058055e-06, 'epoch': 0.53} g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████ | 626/1189 [58:57<41:58, 4.47s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████ | 626/1189 [58:57<41:58, 4.47s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████ | 626/1189 [58:57<41:58, 4.47s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▏ | 627/1189 [59:01<41:30, 4.43s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▏ | 627/1189 [59:01<41:30, 4.43s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▎ | 628/1189 [59:05<41:18, 4.42s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▎ | 628/1189 [59:05<41:18, 4.42s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9968, 'learning_rate': 8.200290275761974e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▎ | 628/1189 [59:05<41:18, 4.42s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▎ | 629/1189 [59:09<40:42, 4.36s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▎ | 629/1189 [59:09<40:42, 4.36s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▍ | 630/1189 [59:14<40:27, 4.34s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▍ | 630/1189 [59:14<40:27, 4.34s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2435, 'learning_rate': 8.171262699564588e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▍ | 631/1189 [59:18<40:05, 4.31s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▍ | 631/1189 [59:18<40:05, 4.31s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2881, 'learning_rate': 8.156748911465894e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▌ | 632/1189 [59:22<39:43, 4.28s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▌ | 632/1189 [59:22<39:43, 4.28s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.144, 'learning_rate': 8.1422351233672e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▌ | 633/1189 [59:26<39:00, 4.21s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▌ | 633/1189 [59:26<39:00, 4.21s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1987, 'learning_rate': 8.127721335268506e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▋ | 634/1189 [59:30<38:25, 4.15s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▋ | 634/1189 [59:30<38:25, 4.15s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1523, 'learning_rate': 8.113207547169812e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▋ | 635/1189 [59:34<37:44, 4.09s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▋ | 635/1189 [59:34<37:44, 4.09s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3182, 'learning_rate': 8.098693759071119e-06, 'epoch': 0.53} 53%|██████████████████████████████████████████▊ | 636/1189 [59:38<37:04, 4.02s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▊ | 636/1189 [59:38<37:04, 4.02s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1759, 'learning_rate': 8.084179970972425e-06, 'epoch': 0.53} 54%|██████████████████████████████████████████▊ | 637/1189 [59:42<36:23, 3.96s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▊ | 637/1189 [59:42<36:23, 3.96s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9399, 'learning_rate': 8.069666182873731e-06, 'epoch': 0.54} 54%|██████████████████████████████████████████▉ | 638/1189 [59:46<35:36, 3.88s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▉ | 638/1189 [59:46<35:36, 3.88s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1084, 'learning_rate': 8.055152394775037e-06, 'epoch': 0.54} 54%|██████████████████████████████████████████▉ | 638/1189 [59:46<35:36, 3.88s/it]g-point operations will not be computed-28 17:29:49,406 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▉ | 639/1189 [59:49<34:42, 3.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:41,559 >> 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. 54%|███████████████████████████████████████████ | 640/1189 [59:53<33:44, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:41,559 >> 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. 54%|███████████████████████████████████████████ | 640/1189 [59:53<33:44, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:41,559 >> 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. {'loss': 4.2404, 'learning_rate': 8.02612481857765e-06, 'epoch': 0.54} 54%|███████████████████████████████████████████▏ | 641/1189 [59:56<32:37, 3.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:41,559 >> 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. 54%|███████████████████████████████████████████▏ | 641/1189 [59:56<32:37, 3.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:41,559 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:33:49,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:41,559 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:33:49,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:41,559 >> 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. {'loss': 4.1495, 'learning_rate': 7.997097242380262e-06, 'epoch': 0.54} [WARNING|modeling_utils.py:388] 2022-02-28 17:33:49,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:41,559 >> 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. 54%|██████████████████████████████████████████▏ | 643/1189 [1:00:02<29:20, 3.23s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:53,728 >> 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. 54%|██████████████████████████████████████████▏ | 644/1189 [1:00:04<27:23, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:53,728 >> 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. 54%|██████████████████████████████████████████▏ | 644/1189 [1:00:04<27:23, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:33:57,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:33:57,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:33:59,248 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:33:59,248 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:34:01,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:34:01,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:34:04,176 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:34:04,176 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.6098, 'learning_rate': 7.910014513788099e-06, 'epoch': 0.54} [WARNING|modeling_utils.py:388] 2022-02-28 17:34:06,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:34:06,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.2265, 'learning_rate': 7.880986937590711e-06, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-02-28 17:34:11,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:34:11,340 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.3677, 'learning_rate': 7.866473149492018e-06, 'epoch': 0.55} 55%|██████████████████████████████████████████▊ | 652/1189 [1:00:26<31:59, 3.57s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|██████████████████████████████████████████▊ | 652/1189 [1:00:26<31:59, 3.57s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1386, 'learning_rate': 7.851959361393324e-06, 'epoch': 0.55} 55%|██████████████████████████████████████████▊ | 653/1189 [1:00:31<36:18, 4.06s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|██████████████████████████████████████████▊ | 653/1189 [1:00:31<36:18, 4.06s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.3104, 'learning_rate': 7.837445573294632e-06, 'epoch': 0.55} 55%|██████████████████████████████████████████▊ | 653/1189 [1:00:31<36:18, 4.06s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|██████████████████████████████████████████▉ | 654/1189 [1:00:36<39:03, 4.38s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|██████████████████████████████████████████▉ | 654/1189 [1:00:36<39:03, 4.38s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. g-point operations will not be computed-28 17:33:53,728 >> 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. g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.2248, 'learning_rate': 7.808417997097242e-06, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 656/1189 [1:00:46<41:47, 4.70s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|███████████████████████████████████████████ | 656/1189 [1:00:46<41:47, 4.70s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1931, 'learning_rate': 7.79390420899855e-06, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 657/1189 [1:00:51<42:10, 4.76s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|███████████████████████████████████████████ | 657/1189 [1:00:51<42:10, 4.76s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.099, 'learning_rate': 7.779390420899855e-06, 'epoch': 0.55} 55%|███████████████████████████████████████████▏ | 658/1189 [1:00:56<42:32, 4.81s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|███████████████████████████████████████████▏ | 658/1189 [1:00:56<42:32, 4.81s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1726, 'learning_rate': 7.764876632801161e-06, 'epoch': 0.55} 55%|███████████████████████████████████████████▏ | 659/1189 [1:01:01<42:49, 4.85s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 55%|███████████████████████████████████████████▏ | 659/1189 [1:01:01<42:49, 4.85s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1437, 'learning_rate': 7.750362844702469e-06, 'epoch': 0.55} 56%|███████████████████████████████████████████▎ | 660/1189 [1:01:06<43:04, 4.88s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▎ | 660/1189 [1:01:06<43:04, 4.88s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1334, 'learning_rate': 7.735849056603775e-06, 'epoch': 0.55} 56%|███████████████████████████████████████████▎ | 661/1189 [1:01:11<42:53, 4.87s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▎ | 661/1189 [1:01:11<42:53, 4.87s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1649, 'learning_rate': 7.72133526850508e-06, 'epoch': 0.56} 56%|███████████████████████████████████████████▍ | 662/1189 [1:01:16<42:34, 4.85s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▍ | 662/1189 [1:01:16<42:34, 4.85s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.0725, 'learning_rate': 7.706821480406387e-06, 'epoch': 0.56} 56%|███████████████████████████████████████████▍ | 663/1189 [1:01:20<42:10, 4.81s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▍ | 663/1189 [1:01:20<42:10, 4.81s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.2534, 'learning_rate': 7.692307692307694e-06, 'epoch': 0.56} 56%|███████████████████████████████████████████▌ | 664/1189 [1:01:25<41:59, 4.80s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▌ | 664/1189 [1:01:25<41:59, 4.80s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.179, 'learning_rate': 7.677793904208998e-06, 'epoch': 0.56} 56%|███████████████████████████████████████████▌ | 664/1189 [1:01:25<41:59, 4.80s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▌ | 665/1189 [1:01:30<41:57, 4.80s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▌ | 665/1189 [1:01:30<41:57, 4.80s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▋ | 666/1189 [1:01:35<41:36, 4.77s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▋ | 666/1189 [1:01:35<41:36, 4.77s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.22, 'learning_rate': 7.648766328011612e-06, 'epoch': 0.56} g-point operations will not be computed-28 17:33:53,728 >> 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. g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.2909, 'learning_rate': 7.634252539912917e-06, 'epoch': 0.56} g-point operations will not be computed-28 17:33:53,728 >> 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. g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1742, 'learning_rate': 7.619738751814224e-06, 'epoch': 0.56} g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▉ | 669/1189 [1:01:49<40:41, 4.70s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▉ | 669/1189 [1:01:49<40:41, 4.70s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.0888, 'learning_rate': 7.605224963715531e-06, 'epoch': 0.56} 56%|███████████████████████████████████████████▉ | 670/1189 [1:01:53<40:28, 4.68s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|███████████████████████████████████████████▉ | 670/1189 [1:01:53<40:28, 4.68s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.0804, 'learning_rate': 7.590711175616836e-06, 'epoch': 0.56} 56%|████████████████████████████████████████████ | 671/1189 [1:01:58<40:19, 4.67s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 56%|████████████████████████████████████████████ | 671/1189 [1:01:58<40:19, 4.67s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.1934, 'learning_rate': 7.576197387518143e-06, 'epoch': 0.56} 57%|████████████████████████████████████████████ | 672/1189 [1:02:02<40:07, 4.66s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████ | 672/1189 [1:02:02<40:07, 4.66s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.128, 'learning_rate': 7.561683599419449e-06, 'epoch': 0.56} 57%|████████████████████████████████████████████▏ | 673/1189 [1:02:07<39:36, 4.61s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▏ | 673/1189 [1:02:07<39:36, 4.61s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.3061, 'learning_rate': 7.5471698113207555e-06, 'epoch': 0.57} 57%|████████████████████████████████████████████▏ | 674/1189 [1:02:11<39:23, 4.59s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▏ | 674/1189 [1:02:11<39:23, 4.59s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.2366, 'learning_rate': 7.532656023222062e-06, 'epoch': 0.57} 57%|████████████████████████████████████████████▎ | 675/1189 [1:02:16<38:50, 4.53s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▎ | 675/1189 [1:02:16<38:50, 4.53s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.142, 'learning_rate': 7.518142235123368e-06, 'epoch': 0.57} 57%|████████████████████████████████████████████▎ | 675/1189 [1:02:16<38:50, 4.53s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▎ | 676/1189 [1:02:20<38:32, 4.51s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▎ | 676/1189 [1:02:20<38:32, 4.51s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▎ | 676/1189 [1:02:20<38:32, 4.51s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▍ | 677/1189 [1:02:25<37:59, 4.45s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▍ | 677/1189 [1:02:25<37:59, 4.45s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▍ | 677/1189 [1:02:25<37:59, 4.45s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▍ | 678/1189 [1:02:29<37:35, 4.41s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▍ | 678/1189 [1:02:29<37:35, 4.41s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▌ | 679/1189 [1:02:33<37:09, 4.37s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▌ | 679/1189 [1:02:33<37:09, 4.37s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.0922, 'learning_rate': 7.4600870827285935e-06, 'epoch': 0.57} 57%|████████████████████████████████████████████▌ | 679/1189 [1:02:33<37:09, 4.37s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▌ | 680/1189 [1:02:37<36:38, 4.32s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▌ | 680/1189 [1:02:37<36:38, 4.32s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▌ | 680/1189 [1:02:37<36:38, 4.32s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▋ | 681/1189 [1:02:42<36:20, 4.29s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▋ | 681/1189 [1:02:42<36:20, 4.29s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▋ | 681/1189 [1:02:42<36:20, 4.29s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▋ | 682/1189 [1:02:46<35:57, 4.25s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▋ | 682/1189 [1:02:46<35:57, 4.25s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▋ | 682/1189 [1:02:46<35:57, 4.25s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 57%|████████████████████████████████████████████▊ | 683/1189 [1:02:50<35:32, 4.21s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:36:44,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:36:44,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.0092, 'learning_rate': 7.387518142235124e-06, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-02-28 17:36:44,612 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. 58%|████████████████████████████████████████████▉ | 685/1189 [1:02:58<34:24, 4.10s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|████████████████████████████████████████████▉ | 685/1189 [1:02:58<34:24, 4.10s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|████████████████████████████████████████████▉ | 685/1189 [1:02:58<34:24, 4.10s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████ | 686/1189 [1:03:02<33:38, 4.01s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████ | 686/1189 [1:03:02<33:38, 4.01s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████ | 686/1189 [1:03:02<33:38, 4.01s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████ | 687/1189 [1:03:06<33:01, 3.95s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████ | 687/1189 [1:03:06<33:01, 3.95s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████ | 687/1189 [1:03:06<33:01, 3.95s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████▏ | 688/1189 [1:03:09<32:14, 3.86s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:37:03,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. [WARNING|modeling_utils.py:388] 2022-02-28 17:37:03,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. {'loss': 4.375, 'learning_rate': 7.314949201741655e-06, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-02-28 17:37:03,294 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████▎ | 690/1189 [1:03:16<29:56, 3.60s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████▎ | 690/1189 [1:03:16<29:56, 3.60s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████▎ | 690/1189 [1:03:16<29:56, 3.60s/it]g-point operations will not be computed-28 17:33:53,728 >> 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. 58%|█████████████████████████████████████████████▎ | 691/1189 [1:03:19<28:43, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:11,242 >> 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. 58%|█████████████████████████████████████████████▎ | 691/1189 [1:03:19<28:43, 3.46s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:11,242 >> 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. 58%|█████████████████████████████████████████████▍ | 692/1189 [1:03:22<27:26, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:11,242 >> 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. 58%|█████████████████████████████████████████████▍ | 692/1189 [1:03:22<27:26, 3.31s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:11,242 >> 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] 2022-02-28 17:37:15,271 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:11,242 >> 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] 2022-02-28 17:37:17,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:11,242 >> 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] 2022-02-28 17:37:17,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:11,242 >> 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': 4.3964, 'learning_rate': 7.242380261248186e-06, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-02-28 17:37:17,635 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:11,242 >> 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. 58%|█████████████████████████████████████████████▌ | 695/1189 [1:03:29<21:48, 2.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:20,821 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▌ | 695/1189 [1:03:29<21:48, 2.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:20,821 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▋ | 697/1189 [1:03:33<18:23, 2.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:22,668 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▋ | 697/1189 [1:03:33<18:23, 2.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:22,668 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▊ | 698/1189 [1:03:34<16:48, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:24,366 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▊ | 698/1189 [1:03:34<16:48, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:24,366 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5925, 'learning_rate': 7.184325108853412e-06, 'epoch': 0.59} 59%|█████████████████████████████████████████████▊ | 699/1189 [1:03:36<15:16, 1.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:27,222 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▊ | 699/1189 [1:03:36<15:16, 1.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:27,222 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▉ | 700/1189 [1:03:38<15:02, 1.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:27,222 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▉ | 700/1189 [1:03:38<15:02, 1.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▉ | 701/1189 [1:03:43<23:43, 2.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▉ | 701/1189 [1:03:43<23:43, 2.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2578, 'learning_rate': 7.1407837445573305e-06, 'epoch': 0.59} 59%|█████████████████████████████████████████████▉ | 701/1189 [1:03:43<23:43, 2.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████ | 702/1189 [1:03:48<29:06, 3.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████ | 702/1189 [1:03:48<29:06, 3.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████ | 703/1189 [1:03:53<32:49, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████ | 703/1189 [1:03:53<32:49, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1689, 'learning_rate': 7.111756168359942e-06, 'epoch': 0.59} 59%|██████████████████████████████████████████████ | 703/1189 [1:03:53<32:49, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▏ | 704/1189 [1:03:59<35:20, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▏ | 704/1189 [1:03:59<35:20, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▏ | 705/1189 [1:04:04<37:06, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▏ | 705/1189 [1:04:04<37:06, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.12, 'learning_rate': 7.082728592162555e-06, 'epoch': 0.59} 59%|██████████████████████████████████████████████▏ | 705/1189 [1:04:04<37:06, 4.60s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▎ | 706/1189 [1:04:09<38:08, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▎ | 706/1189 [1:04:09<38:08, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▍ | 707/1189 [1:04:14<39:01, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▍ | 707/1189 [1:04:14<39:01, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.187, 'learning_rate': 7.053701015965168e-06, 'epoch': 0.59} 59%|██████████████████████████████████████████████▍ | 707/1189 [1:04:14<39:01, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▍ | 708/1189 [1:04:19<39:20, 4.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▍ | 708/1189 [1:04:19<39:20, 4.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▍ | 708/1189 [1:04:19<39:20, 4.91s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▌ | 709/1189 [1:04:24<39:21, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▌ | 709/1189 [1:04:24<39:21, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▌ | 709/1189 [1:04:24<39:21, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▌ | 710/1189 [1:04:29<39:14, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▌ | 710/1189 [1:04:29<39:14, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▌ | 710/1189 [1:04:29<39:14, 4.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▋ | 711/1189 [1:04:34<38:52, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▋ | 711/1189 [1:04:34<38:52, 4.88s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▋ | 712/1189 [1:04:38<38:31, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▋ | 712/1189 [1:04:38<38:31, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2809, 'learning_rate': 6.981132075471699e-06, 'epoch': 0.6} 60%|██████████████████████████████████████████████▊ | 713/1189 [1:04:43<38:25, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▊ | 713/1189 [1:04:43<38:25, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0982, 'learning_rate': 6.966618287373005e-06, 'epoch': 0.6} 60%|██████████████████████████████████████████████▊ | 714/1189 [1:04:48<38:10, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▊ | 714/1189 [1:04:48<38:10, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0377, 'learning_rate': 6.952104499274311e-06, 'epoch': 0.6} 60%|██████████████████████████████████████████████▉ | 715/1189 [1:04:53<37:47, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████▉ | 715/1189 [1:04:53<37:47, 4.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1616, 'learning_rate': 6.937590711175617e-06, 'epoch': 0.6} [WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0324, 'learning_rate': 6.923076923076923e-06, 'epoch': 0.6} [WARNING|modeling_utils.py:388] 2022-02-28 17:38:52,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:38:52,642 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1099, 'learning_rate': 6.90856313497823e-06, 'epoch': 0.6} 60%|███████████████████████████████████████████████ | 718/1189 [1:05:07<37:02, 4.72s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████ | 718/1189 [1:05:07<37:02, 4.72s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3045, 'learning_rate': 6.894049346879537e-06, 'epoch': 0.6} 60%|███████████████████████████████████████████████▏ | 719/1189 [1:05:11<36:34, 4.67s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▏ | 719/1189 [1:05:11<36:34, 4.67s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1416, 'learning_rate': 6.879535558780842e-06, 'epoch': 0.6} 61%|███████████████████████████████████████████████▏ | 720/1189 [1:05:16<36:10, 4.63s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▏ | 720/1189 [1:05:16<36:10, 4.63s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0256, 'learning_rate': 6.865021770682149e-06, 'epoch': 0.61} 61%|███████████████████████████████████████████████▏ | 720/1189 [1:05:16<36:10, 4.63s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▏ | 720/1189 [1:05:16<36:10, 4.63s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1352, 'learning_rate': 6.850507982583455e-06, 'epoch': 0.61} g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0131, 'learning_rate': 6.8359941944847605e-06, 'epoch': 0.61} g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▍ | 723/1189 [1:05:29<35:25, 4.56s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▍ | 723/1189 [1:05:29<35:25, 4.56s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▍ | 723/1189 [1:05:29<35:25, 4.56s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▍ | 724/1189 [1:05:34<35:13, 4.55s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▍ | 724/1189 [1:05:34<35:13, 4.55s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▍ | 724/1189 [1:05:34<35:13, 4.55s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▌ | 725/1189 [1:05:38<34:48, 4.50s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▌ | 725/1189 [1:05:38<34:48, 4.50s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▌ | 725/1189 [1:05:38<34:48, 4.50s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▋ | 726/1189 [1:05:43<34:24, 4.46s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▋ | 726/1189 [1:05:43<34:24, 4.46s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▋ | 726/1189 [1:05:43<34:24, 4.46s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▋ | 727/1189 [1:05:47<33:56, 4.41s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▋ | 727/1189 [1:05:47<33:56, 4.41s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▋ | 727/1189 [1:05:47<33:56, 4.41s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▊ | 728/1189 [1:05:51<33:31, 4.36s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▊ | 728/1189 [1:05:51<33:31, 4.36s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▊ | 728/1189 [1:05:51<33:31, 4.36s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▊ | 729/1189 [1:05:55<33:06, 4.32s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▊ | 729/1189 [1:05:55<33:06, 4.32s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▉ | 730/1189 [1:06:00<33:03, 4.32s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▉ | 730/1189 [1:06:00<33:03, 4.32s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3412, 'learning_rate': 6.719883889695211e-06, 'epoch': 0.61} 61%|███████████████████████████████████████████████▉ | 731/1189 [1:06:04<32:51, 4.31s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████▉ | 731/1189 [1:06:04<32:51, 4.31s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2805, 'learning_rate': 6.705370101596517e-06, 'epoch': 0.61} 62%|████████████████████████████████████████████████ | 732/1189 [1:06:08<32:34, 4.28s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████ | 732/1189 [1:06:08<32:34, 4.28s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2931, 'learning_rate': 6.690856313497823e-06, 'epoch': 0.62} 62%|████████████████████████████████████████████████ | 733/1189 [1:06:12<32:14, 4.24s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████ | 733/1189 [1:06:12<32:14, 4.24s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9637, 'learning_rate': 6.6763425253991295e-06, 'epoch': 0.62} 62%|████████████████████████████████████████████████▏ | 734/1189 [1:06:16<31:50, 4.20s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▏ | 734/1189 [1:06:16<31:50, 4.20s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2733, 'learning_rate': 6.6618287373004365e-06, 'epoch': 0.62} 62%|████████████████████████████████████████████████▏ | 735/1189 [1:06:20<31:10, 4.12s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▏ | 735/1189 [1:06:20<31:10, 4.12s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1742, 'learning_rate': 6.647314949201742e-06, 'epoch': 0.62} 62%|████████████████████████████████████████████████▏ | 735/1189 [1:06:20<31:10, 4.12s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▎ | 736/1189 [1:06:24<30:39, 4.06s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▎ | 736/1189 [1:06:24<30:39, 4.06s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▎ | 736/1189 [1:06:24<30:39, 4.06s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▎ | 737/1189 [1:06:28<30:12, 4.01s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▎ | 737/1189 [1:06:28<30:12, 4.01s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▎ | 737/1189 [1:06:28<30:12, 4.01s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▍ | 738/1189 [1:06:32<29:36, 3.94s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▍ | 738/1189 [1:06:32<29:36, 3.94s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▍ | 738/1189 [1:06:32<29:36, 3.94s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▍ | 739/1189 [1:06:36<28:54, 3.85s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:40:29,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:40:29,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0926, 'learning_rate': 6.574746008708274e-06, 'epoch': 0.62} [WARNING|modeling_utils.py:388] 2022-02-28 17:40:29,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▌ | 741/1189 [1:06:43<27:14, 3.65s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▌ | 741/1189 [1:06:43<27:14, 3.65s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▌ | 741/1189 [1:06:43<27:14, 3.65s/it]g-point operations will not be computed-28 17:37:31,154 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▋ | 742/1189 [1:06:46<25:52, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▋ | 742/1189 [1:06:46<25:52, 3.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▋ | 743/1189 [1:06:49<24:29, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▋ | 743/1189 [1:06:49<24:29, 3.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:40:41,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:40:41,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:40:41,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:37,781 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▊ | 745/1189 [1:06:54<21:27, 2.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:45,398 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▊ | 745/1189 [1:06:54<21:27, 2.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:45,398 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▉ | 746/1189 [1:06:56<19:50, 2.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:47,439 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████▉ | 746/1189 [1:06:56<19:50, 2.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:47,439 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5666, 'learning_rate': 6.473149492017418e-06, 'epoch': 0.63} 63%|█████████████████████████████████████████████████ | 747/1189 [1:06:58<18:03, 2.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:49,262 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████ | 747/1189 [1:06:58<18:03, 2.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:49,262 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▏ | 749/1189 [1:07:01<14:56, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:50,946 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▏ | 749/1189 [1:07:01<14:56, 2.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:50,946 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▏ | 750/1189 [1:07:03<14:20, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:52,349 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▏ | 750/1189 [1:07:03<14:20, 1.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▎ | 751/1189 [1:07:08<21:59, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▎ | 751/1189 [1:07:08<21:59, 3.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0266, 'learning_rate': 6.415094339622642e-06, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▎ | 752/1189 [1:07:13<26:42, 3.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▎ | 752/1189 [1:07:13<26:42, 3.67s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2239, 'learning_rate': 6.400580551523948e-06, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▍ | 753/1189 [1:07:19<29:51, 4.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▍ | 753/1189 [1:07:19<29:51, 4.11s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2583, 'learning_rate': 6.386066763425255e-06, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:07:24<31:40, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▍ | 754/1189 [1:07:24<31:40, 4.37s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1042, 'learning_rate': 6.37155297532656e-06, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▌ | 755/1189 [1:07:29<32:53, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▌ | 755/1189 [1:07:29<32:53, 4.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2795, 'learning_rate': 6.357039187227867e-06, 'epoch': 0.63} 64%|█████████████████████████████████████████████████▌ | 756/1189 [1:07:33<33:38, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▌ | 756/1189 [1:07:33<33:38, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1196, 'learning_rate': 6.3425253991291735e-06, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▋ | 757/1189 [1:07:38<34:17, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▋ | 757/1189 [1:07:38<34:17, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1597, 'learning_rate': 6.328011611030479e-06, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▋ | 758/1189 [1:07:43<34:36, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▋ | 758/1189 [1:07:43<34:36, 4.82s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.029, 'learning_rate': 6.313497822931786e-06, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▊ | 759/1189 [1:07:48<34:53, 4.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▊ | 759/1189 [1:07:48<34:53, 4.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.103, 'learning_rate': 6.298984034833092e-06, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▊ | 760/1189 [1:07:53<34:58, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▊ | 760/1189 [1:07:53<34:58, 4.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3008, 'learning_rate': 6.2844702467343975e-06, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▉ | 761/1189 [1:07:58<34:43, 4.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████▉ | 761/1189 [1:07:58<34:43, 4.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0217, 'learning_rate': 6.2699564586357045e-06, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1494, 'learning_rate': 6.255442670537011e-06, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-02-28 17:41:58,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:41:58,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1743, 'learning_rate': 6.240928882438318e-06, 'epoch': 0.64} [WARNING|modeling_utils.py:388] 2022-02-28 17:41:58,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:41:58,404 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████ | 764/1189 [1:08:13<34:02, 4.81s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████ | 764/1189 [1:08:13<34:02, 4.81s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████ | 764/1189 [1:08:13<34:02, 4.81s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▏ | 765/1189 [1:08:17<33:41, 4.77s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▏ | 765/1189 [1:08:17<33:41, 4.77s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▏ | 765/1189 [1:08:17<33:41, 4.77s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▏ | 765/1189 [1:08:17<33:41, 4.77s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1558, 'learning_rate': 6.197387518142236e-06, 'epoch': 0.64} 64%|██████████████████████████████████████████████████▏ | 765/1189 [1:08:17<33:41, 4.77s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▏ | 765/1189 [1:08:17<33:41, 4.77s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▎ | 767/1189 [1:08:27<33:23, 4.75s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▎ | 767/1189 [1:08:27<33:23, 4.75s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▎ | 767/1189 [1:08:27<33:23, 4.75s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▍ | 768/1189 [1:08:31<33:12, 4.73s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▍ | 768/1189 [1:08:31<33:12, 4.73s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:36<32:47, 4.69s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:36<32:47, 4.69s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1907, 'learning_rate': 6.153846153846155e-06, 'epoch': 0.65} g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.335, 'learning_rate': 6.13933236574746e-06, 'epoch': 0.65} g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▌ | 771/1189 [1:08:45<32:24, 4.65s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▌ | 771/1189 [1:08:45<32:24, 4.65s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▋ | 772/1189 [1:08:50<32:10, 4.63s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▋ | 772/1189 [1:08:50<32:10, 4.63s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2559, 'learning_rate': 6.1103047895500734e-06, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▋ | 772/1189 [1:08:50<32:10, 4.63s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▋ | 773/1189 [1:08:54<31:53, 4.60s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▋ | 773/1189 [1:08:54<31:53, 4.60s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▊ | 774/1189 [1:08:59<31:32, 4.56s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▊ | 774/1189 [1:08:59<31:32, 4.56s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.029, 'learning_rate': 6.081277213352685e-06, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▊ | 775/1189 [1:09:03<31:15, 4.53s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▊ | 775/1189 [1:09:03<31:15, 4.53s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0631, 'learning_rate': 6.066763425253992e-06, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▊ | 775/1189 [1:09:03<31:15, 4.53s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▉ | 776/1189 [1:09:08<30:54, 4.49s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▉ | 776/1189 [1:09:08<30:54, 4.49s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▉ | 776/1189 [1:09:08<30:54, 4.49s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▉ | 777/1189 [1:09:12<30:33, 4.45s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▉ | 777/1189 [1:09:12<30:33, 4.45s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████▉ | 777/1189 [1:09:12<30:33, 4.45s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████ | 778/1189 [1:09:16<30:07, 4.40s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████ | 778/1189 [1:09:16<30:07, 4.40s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████ | 779/1189 [1:09:21<29:48, 4.36s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████ | 779/1189 [1:09:21<29:48, 4.36s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0585, 'learning_rate': 6.008708272859218e-06, 'epoch': 0.65} 66%|███████████████████████████████████████████████████▏ | 780/1189 [1:09:25<29:30, 4.33s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▏ | 780/1189 [1:09:25<29:30, 4.33s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2947, 'learning_rate': 5.994194484760523e-06, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▏ | 780/1189 [1:09:25<29:30, 4.33s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▏ | 781/1189 [1:09:29<29:18, 4.31s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▏ | 781/1189 [1:09:29<29:18, 4.31s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▏ | 781/1189 [1:09:29<29:18, 4.31s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▎ | 782/1189 [1:09:33<28:58, 4.27s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▎ | 782/1189 [1:09:33<28:58, 4.27s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▎ | 782/1189 [1:09:33<28:58, 4.27s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▎ | 783/1189 [1:09:37<28:37, 4.23s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▎ | 783/1189 [1:09:37<28:37, 4.23s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▎ | 783/1189 [1:09:37<28:37, 4.23s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▍ | 784/1189 [1:09:41<28:08, 4.17s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▍ | 784/1189 [1:09:41<28:08, 4.17s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▍ | 784/1189 [1:09:41<28:08, 4.17s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▍ | 785/1189 [1:09:45<27:35, 4.10s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▍ | 785/1189 [1:09:45<27:35, 4.10s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▍ | 785/1189 [1:09:45<27:35, 4.10s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▌ | 786/1189 [1:09:49<27:01, 4.02s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▌ | 786/1189 [1:09:49<27:01, 4.02s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▌ | 786/1189 [1:09:49<27:01, 4.02s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▋ | 787/1189 [1:09:53<26:30, 3.96s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▋ | 787/1189 [1:09:53<26:30, 3.96s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▋ | 787/1189 [1:09:53<26:30, 3.96s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▋ | 788/1189 [1:09:57<25:48, 3.86s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:43:50,802 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:43:50,802 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0658, 'learning_rate': 5.863570391872279e-06, 'epoch': 0.66} [WARNING|modeling_utils.py:388] 2022-02-28 17:43:50,802 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▊ | 790/1189 [1:10:04<24:35, 3.70s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▊ | 790/1189 [1:10:04<24:35, 3.70s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▊ | 790/1189 [1:10:04<24:35, 3.70s/it]g-point operations will not be computed-28 17:40:56,243 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▉ | 791/1189 [1:10:07<23:34, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:43:59,123 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▉ | 791/1189 [1:10:07<23:34, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:43:59,123 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▉ | 792/1189 [1:10:10<22:31, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:43:59,123 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▉ | 792/1189 [1:10:10<22:31, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:43:59,123 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████▉ | 792/1189 [1:10:10<22:31, 3.40s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:43:59,123 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████ | 793/1189 [1:10:13<21:21, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:44:04,820 >> 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. 67%|████████████████████████████████████████████████████ | 793/1189 [1:10:13<21:21, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:44:04,820 >> 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. 67%|████████████████████████████████████████████████████ | 794/1189 [1:10:15<20:01, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████ | 794/1189 [1:10:15<20:01, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▏ | 795/1189 [1:10:18<18:34, 2.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▏ | 795/1189 [1:10:18<18:34, 2.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:10,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:10,486 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:12,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:12,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:14,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:14,097 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:17,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:17,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3116, 'learning_rate': 5.703918722786648e-06, 'epoch': 0.67} [WARNING|modeling_utils.py:388] 2022-02-28 17:44:17,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:44:17,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 801/1189 [1:10:32<19:08, 2.96s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 801/1189 [1:10:32<19:08, 2.96s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 801/1189 [1:10:32<19:08, 2.96s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 801/1189 [1:10:32<19:08, 2.96s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.094, 'learning_rate': 5.67489114658926e-06, 'epoch': 0.67} 67%|████████████████████████████████████████████████████▌ | 801/1189 [1:10:32<19:08, 2.96s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▋ | 803/1189 [1:10:42<25:59, 4.04s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▋ | 803/1189 [1:10:42<25:59, 4.04s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1113, 'learning_rate': 5.660377358490566e-06, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▋ | 804/1189 [1:10:47<27:34, 4.30s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▋ | 804/1189 [1:10:47<27:34, 4.30s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1253, 'learning_rate': 5.645863570391873e-06, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▋ | 804/1189 [1:10:47<27:34, 4.30s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▊ | 805/1189 [1:10:52<28:48, 4.50s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▊ | 805/1189 [1:10:52<28:48, 4.50s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▊ | 806/1189 [1:10:57<29:35, 4.64s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▊ | 806/1189 [1:10:57<29:35, 4.64s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1518, 'learning_rate': 5.616835994194485e-06, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▊ | 806/1189 [1:10:57<29:35, 4.64s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▉ | 807/1189 [1:11:02<30:12, 4.75s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▉ | 807/1189 [1:11:02<30:12, 4.75s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████ | 808/1189 [1:11:07<30:30, 4.80s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████ | 808/1189 [1:11:07<30:30, 4.80s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0623, 'learning_rate': 5.587808417997098e-06, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████ | 809/1189 [1:11:12<30:32, 4.82s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████ | 809/1189 [1:11:12<30:32, 4.82s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:45:07,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:45:07,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0337, 'learning_rate': 5.55878084179971e-06, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████▏ | 811/1189 [1:11:22<30:14, 4.80s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▏ | 811/1189 [1:11:22<30:14, 4.80s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1682, 'learning_rate': 5.5442670537010166e-06, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████▎ | 812/1189 [1:11:26<30:02, 4.78s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▎ | 812/1189 [1:11:26<30:02, 4.78s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1935, 'learning_rate': 5.529753265602322e-06, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████▎ | 812/1189 [1:11:26<30:02, 4.78s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▎ | 812/1189 [1:11:26<30:02, 4.78s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1785, 'learning_rate': 5.515239477503629e-06, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████▎ | 812/1189 [1:11:26<30:02, 4.78s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▎ | 812/1189 [1:11:26<30:02, 4.78s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▍ | 814/1189 [1:11:36<29:49, 4.77s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▍ | 814/1189 [1:11:36<29:49, 4.77s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▍ | 815/1189 [1:11:41<29:50, 4.79s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▍ | 815/1189 [1:11:41<29:50, 4.79s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.122, 'learning_rate': 5.486211901306241e-06, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▍ | 815/1189 [1:11:41<29:50, 4.79s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▌ | 816/1189 [1:11:45<29:38, 4.77s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▌ | 816/1189 [1:11:45<29:38, 4.77s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▌ | 816/1189 [1:11:45<29:38, 4.77s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▌ | 817/1189 [1:11:50<29:13, 4.71s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▌ | 817/1189 [1:11:50<29:13, 4.71s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▌ | 817/1189 [1:11:50<29:13, 4.71s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 818/1189 [1:11:54<28:55, 4.68s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 818/1189 [1:11:54<28:55, 4.68s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 818/1189 [1:11:54<28:55, 4.68s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 819/1189 [1:11:59<28:44, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 819/1189 [1:11:59<28:44, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 819/1189 [1:11:59<28:44, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2216, 'learning_rate': 5.413642960812773e-06, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▋ | 819/1189 [1:11:59<28:44, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 819/1189 [1:11:59<28:44, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▋ | 819/1189 [1:11:59<28:44, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▊ | 821/1189 [1:12:08<28:33, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▊ | 821/1189 [1:12:08<28:33, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▊ | 821/1189 [1:12:08<28:33, 4.66s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▉ | 822/1189 [1:12:13<28:14, 4.62s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▉ | 822/1189 [1:12:13<28:14, 4.62s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▉ | 822/1189 [1:12:13<28:14, 4.62s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▉ | 823/1189 [1:12:17<27:56, 4.58s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▉ | 823/1189 [1:12:17<27:56, 4.58s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████ | 824/1189 [1:12:22<27:48, 4.57s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████ | 824/1189 [1:12:22<27:48, 4.57s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3515, 'learning_rate': 5.355587808417998e-06, 'epoch': 0.69} 69%|██████████████████████████████████████████████████████ | 825/1189 [1:12:26<27:29, 4.53s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████ | 825/1189 [1:12:26<27:29, 4.53s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0397, 'learning_rate': 5.341074020319303e-06, 'epoch': 0.69} 69%|██████████████████████████████████████████████████████ | 825/1189 [1:12:26<27:29, 4.53s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▏ | 826/1189 [1:12:31<27:14, 4.50s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:46:25,827 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:46:25,827 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1617, 'learning_rate': 5.3120464441219165e-06, 'epoch': 0.7} [WARNING|modeling_utils.py:388] 2022-02-28 17:46:25,827 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▎ | 828/1189 [1:12:40<26:42, 4.44s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▎ | 828/1189 [1:12:40<26:42, 4.44s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▎ | 828/1189 [1:12:40<26:42, 4.44s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▍ | 829/1189 [1:12:44<26:31, 4.42s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▍ | 829/1189 [1:12:44<26:31, 4.42s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▍ | 829/1189 [1:12:44<26:31, 4.42s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▍ | 830/1189 [1:12:48<26:13, 4.38s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▍ | 830/1189 [1:12:48<26:13, 4.38s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▍ | 830/1189 [1:12:48<26:13, 4.38s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▌ | 831/1189 [1:12:53<26:02, 4.37s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▌ | 831/1189 [1:12:53<26:02, 4.37s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▌ | 831/1189 [1:12:53<26:02, 4.37s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▌ | 832/1189 [1:12:57<25:47, 4.34s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▌ | 832/1189 [1:12:57<25:47, 4.34s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▌ | 832/1189 [1:12:57<25:47, 4.34s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▋ | 833/1189 [1:13:01<25:30, 4.30s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▋ | 833/1189 [1:13:01<25:30, 4.30s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▋ | 834/1189 [1:13:05<25:05, 4.24s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▋ | 834/1189 [1:13:05<25:05, 4.24s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2332, 'learning_rate': 5.210449927431061e-06, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▊ | 835/1189 [1:13:09<24:51, 4.21s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▊ | 835/1189 [1:13:09<24:51, 4.21s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2404, 'learning_rate': 5.195936139332366e-06, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▊ | 836/1189 [1:13:13<24:23, 4.15s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▊ | 836/1189 [1:13:13<24:23, 4.15s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2952, 'learning_rate': 5.181422351233672e-06, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▊ | 836/1189 [1:13:13<24:23, 4.15s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▉ | 837/1189 [1:13:17<23:58, 4.09s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▉ | 837/1189 [1:13:17<23:58, 4.09s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▉ | 837/1189 [1:13:17<23:58, 4.09s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▉ | 838/1189 [1:13:21<23:32, 4.02s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▉ | 838/1189 [1:13:21<23:32, 4.02s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▉ | 838/1189 [1:13:21<23:32, 4.02s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████ | 839/1189 [1:13:25<22:57, 3.94s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████ | 839/1189 [1:13:25<22:57, 3.94s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████ | 839/1189 [1:13:25<22:57, 3.94s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████ | 840/1189 [1:13:29<22:24, 3.85s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████ | 840/1189 [1:13:29<22:24, 3.85s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████ | 840/1189 [1:13:29<22:24, 3.85s/it]g-point operations will not be computed-28 17:44:07,255 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▏ | 841/1189 [1:13:32<21:43, 3.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:24,372 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▏ | 841/1189 [1:13:32<21:43, 3.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:24,372 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▏ | 842/1189 [1:13:35<20:54, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:24,372 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▏ | 842/1189 [1:13:35<20:54, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:24,372 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▏ | 842/1189 [1:13:35<20:54, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:24,372 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▎ | 843/1189 [1:13:38<19:52, 3.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▎ | 843/1189 [1:13:38<19:52, 3.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▎ | 844/1189 [1:13:41<18:41, 3.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▎ | 844/1189 [1:13:41<18:41, 3.25s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:34,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:34,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:36,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:36,748 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:38,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:38,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:40,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:40,734 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:42,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:42,276 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:44,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:44,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:47:44,128 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▊ | 851/1189 [1:13:59<17:11, 3.05s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▊ | 851/1189 [1:13:59<17:11, 3.05s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▊ | 851/1189 [1:13:59<17:11, 3.05s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▉ | 852/1189 [1:14:04<20:43, 3.69s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▉ | 852/1189 [1:14:04<20:43, 3.69s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2258, 'learning_rate': 4.934687953555878e-06, 'epoch': 0.72} g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████ | 854/1189 [1:14:14<24:20, 4.36s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████ | 854/1189 [1:14:14<24:20, 4.36s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████ | 855/1189 [1:14:19<25:23, 4.56s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████ | 855/1189 [1:14:19<25:23, 4.56s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0969, 'learning_rate': 4.905660377358491e-06, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████ | 855/1189 [1:14:19<25:23, 4.56s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▏ | 856/1189 [1:14:24<25:57, 4.68s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▏ | 856/1189 [1:14:24<25:57, 4.68s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▏ | 857/1189 [1:14:29<26:12, 4.74s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▏ | 857/1189 [1:14:29<26:12, 4.74s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1198, 'learning_rate': 4.876632801161104e-06, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████▏ | 857/1189 [1:14:29<26:12, 4.74s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▎ | 858/1189 [1:14:34<26:28, 4.80s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▎ | 858/1189 [1:14:34<26:28, 4.80s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▎ | 859/1189 [1:14:39<26:37, 4.84s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▎ | 859/1189 [1:14:39<26:37, 4.84s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1519, 'learning_rate': 4.847605224963715e-06, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████▍ | 860/1189 [1:14:44<26:38, 4.86s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▍ | 860/1189 [1:14:44<26:38, 4.86s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1818, 'learning_rate': 4.8330914368650224e-06, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████▍ | 860/1189 [1:14:44<26:38, 4.86s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▍ | 861/1189 [1:14:49<26:28, 4.84s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▍ | 861/1189 [1:14:49<26:28, 4.84s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▌ | 862/1189 [1:14:53<26:20, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▌ | 862/1189 [1:14:53<26:20, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2424, 'learning_rate': 4.804063860667635e-06, 'epoch': 0.72} 73%|████████████████████████████████████████████████████████▌ | 863/1189 [1:14:58<26:13, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▌ | 863/1189 [1:14:58<26:13, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2388, 'learning_rate': 4.789550072568941e-06, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████▌ | 863/1189 [1:14:58<26:13, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▋ | 864/1189 [1:15:03<26:21, 4.87s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▋ | 864/1189 [1:15:03<26:21, 4.87s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▋ | 865/1189 [1:15:08<26:03, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▋ | 865/1189 [1:15:08<26:03, 4.83s/it]g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1204, 'learning_rate': 4.760522496371553e-06, 'epoch': 0.73} g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1002, 'learning_rate': 4.74600870827286e-06, 'epoch': 0.73} g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:47:30,502 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▉ | 867/1189 [1:15:17<25:17, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▉ | 867/1189 [1:15:17<25:17, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▉ | 868/1189 [1:15:22<24:56, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▉ | 868/1189 [1:15:22<24:56, 4.66s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████ | 869/1189 [1:15:26<24:40, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████ | 869/1189 [1:15:26<24:40, 4.63s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.28, 'learning_rate': 4.702467343976778e-06, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████ | 870/1189 [1:15:31<24:29, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████ | 870/1189 [1:15:31<24:29, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8426, 'learning_rate': 4.687953555878084e-06, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 871/1189 [1:15:35<24:13, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▏ | 871/1189 [1:15:35<24:13, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8959, 'learning_rate': 4.6734397677793905e-06, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:40<23:57, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:40<23:57, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0439, 'learning_rate': 4.658925979680697e-06, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:40<23:57, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:40<23:57, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:40<23:57, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1897, 'learning_rate': 4.644412191582004e-06, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:40<23:57, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▎ | 874/1189 [1:15:49<23:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▎ | 874/1189 [1:15:49<23:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▎ | 874/1189 [1:15:49<23:36, 4.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▍ | 875/1189 [1:15:53<23:23, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▍ | 875/1189 [1:15:53<23:23, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▍ | 875/1189 [1:15:53<23:23, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▍ | 876/1189 [1:15:57<23:13, 4.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▍ | 876/1189 [1:15:57<23:13, 4.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▍ | 876/1189 [1:15:57<23:13, 4.45s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▌ | 877/1189 [1:16:02<22:58, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▌ | 877/1189 [1:16:02<22:58, 4.42s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▌ | 878/1189 [1:16:06<22:45, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▌ | 878/1189 [1:16:06<22:45, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2283, 'learning_rate': 4.571843251088535e-06, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▌ | 878/1189 [1:16:06<22:45, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▋ | 879/1189 [1:16:10<22:24, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▋ | 879/1189 [1:16:10<22:24, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▋ | 879/1189 [1:16:10<22:24, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▋ | 880/1189 [1:16:14<22:03, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▋ | 880/1189 [1:16:14<22:03, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▋ | 880/1189 [1:16:14<22:03, 4.28s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▊ | 881/1189 [1:16:18<21:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▊ | 881/1189 [1:16:18<21:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▊ | 881/1189 [1:16:18<21:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▊ | 882/1189 [1:16:23<21:34, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▊ | 882/1189 [1:16:23<21:34, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▊ | 882/1189 [1:16:23<21:34, 4.22s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▉ | 883/1189 [1:16:27<21:24, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▉ | 883/1189 [1:16:27<21:24, 4.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▉ | 884/1189 [1:16:31<21:02, 4.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▉ | 884/1189 [1:16:31<21:02, 4.14s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2002, 'learning_rate': 4.484760522496372e-06, 'epoch': 0.74} 74%|██████████████████████████████████████████████████████████ | 885/1189 [1:16:35<20:45, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████ | 885/1189 [1:16:35<20:45, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0107, 'learning_rate': 4.470246734397678e-06, 'epoch': 0.74} 75%|██████████████████████████████████████████████████████████ | 886/1189 [1:16:39<20:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████ | 886/1189 [1:16:39<20:28, 4.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1442, 'learning_rate': 4.455732946298984e-06, 'epoch': 0.74} 75%|██████████████████████████████████████████████████████████▏ | 887/1189 [1:16:43<20:00, 3.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▏ | 887/1189 [1:16:43<20:00, 3.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3743, 'learning_rate': 4.4412191582002904e-06, 'epoch': 0.75} 75%|██████████████████████████████████████████████████████████▎ | 888/1189 [1:16:46<19:29, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▎ | 888/1189 [1:16:46<19:29, 3.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:40,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:40,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2912, 'learning_rate': 4.412191582002903e-06, 'epoch': 0.75} [WARNING|modeling_utils.py:388] 2022-02-28 17:50:40,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:43,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:43,932 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▍ | 891/1189 [1:16:57<17:39, 3.56s/it]g-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▍ | 891/1189 [1:16:57<17:39, 3.56s/it]g-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:50,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:50,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.222, 'learning_rate': 4.368650217706822e-06, 'epoch': 0.75} [WARNING|modeling_utils.py:388] 2022-02-28 17:50:50,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:49:09,999 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▌ | 893/1189 [1:17:02<15:47, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▌ | 893/1189 [1:17:02<15:47, 3.20s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▋ | 894/1189 [1:17:05<14:49, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▋ | 894/1189 [1:17:05<14:49, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:57,873 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:50:57,873 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:00,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:00,004 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:01,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:01,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:03,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:03,636 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:05,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:05,078 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:06,873 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:51:06,873 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████ | 901/1189 [1:17:22<14:30, 3.02s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████ | 901/1189 [1:17:22<14:30, 3.02s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1739, 'learning_rate': 4.238026124818578e-06, 'epoch': 0.76} 76%|███████████████████████████████████████████████████████████ | 901/1189 [1:17:22<14:30, 3.02s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▏ | 902/1189 [1:17:27<17:24, 3.64s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▏ | 902/1189 [1:17:27<17:24, 3.64s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▏ | 902/1189 [1:17:27<17:24, 3.64s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▏ | 903/1189 [1:17:32<19:31, 4.10s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▏ | 903/1189 [1:17:32<19:31, 4.10s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▏ | 903/1189 [1:17:32<19:31, 4.10s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▎ | 904/1189 [1:17:37<20:43, 4.36s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▎ | 904/1189 [1:17:37<20:43, 4.36s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▎ | 904/1189 [1:17:37<20:43, 4.36s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▎ | 905/1189 [1:17:42<21:41, 4.58s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▎ | 905/1189 [1:17:42<21:41, 4.58s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▎ | 905/1189 [1:17:42<21:41, 4.58s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▍ | 906/1189 [1:17:47<22:14, 4.71s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▍ | 906/1189 [1:17:47<22:14, 4.71s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▍ | 906/1189 [1:17:47<22:14, 4.71s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▌ | 907/1189 [1:17:52<22:34, 4.80s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▌ | 907/1189 [1:17:52<22:34, 4.80s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▌ | 907/1189 [1:17:52<22:34, 4.80s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▌ | 908/1189 [1:17:57<22:44, 4.85s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▌ | 908/1189 [1:17:57<22:44, 4.85s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▌ | 908/1189 [1:17:57<22:44, 4.85s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▋ | 909/1189 [1:18:02<22:39, 4.86s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▋ | 909/1189 [1:18:02<22:39, 4.86s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▋ | 910/1189 [1:18:07<22:41, 4.88s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▋ | 910/1189 [1:18:07<22:41, 4.88s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2648, 'learning_rate': 4.1074020319303345e-06, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▋ | 910/1189 [1:18:07<22:41, 4.88s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▊ | 911/1189 [1:18:12<22:37, 4.88s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▊ | 911/1189 [1:18:12<22:37, 4.88s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▊ | 911/1189 [1:18:12<22:37, 4.88s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▊ | 912/1189 [1:18:17<22:30, 4.87s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▊ | 912/1189 [1:18:17<22:30, 4.87s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▉ | 913/1189 [1:18:22<22:20, 4.86s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▉ | 913/1189 [1:18:22<22:20, 4.86s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1445, 'learning_rate': 4.063860667634253e-06, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▉ | 913/1189 [1:18:22<22:20, 4.86s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▉ | 914/1189 [1:18:26<22:07, 4.83s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▉ | 914/1189 [1:18:26<22:07, 4.83s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████▉ | 914/1189 [1:18:26<22:07, 4.83s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████ | 915/1189 [1:18:31<21:53, 4.80s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████ | 915/1189 [1:18:31<21:53, 4.80s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████ | 916/1189 [1:18:36<21:39, 4.76s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████ | 916/1189 [1:18:36<21:39, 4.76s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1319, 'learning_rate': 4.020319303338172e-06, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████ | 916/1189 [1:18:36<21:39, 4.76s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▏ | 917/1189 [1:18:40<21:27, 4.73s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▏ | 917/1189 [1:18:40<21:27, 4.73s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▏ | 917/1189 [1:18:40<21:27, 4.73s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▏ | 918/1189 [1:18:45<21:18, 4.72s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▏ | 918/1189 [1:18:45<21:18, 4.72s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▎ | 919/1189 [1:18:50<21:12, 4.71s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▎ | 919/1189 [1:18:50<21:12, 4.71s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3119, 'learning_rate': 3.97677793904209e-06, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▎ | 920/1189 [1:18:54<20:59, 4.68s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▎ | 920/1189 [1:18:54<20:59, 4.68s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1966, 'learning_rate': 3.962264150943396e-06, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▍ | 921/1189 [1:18:59<20:43, 4.64s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▍ | 921/1189 [1:18:59<20:43, 4.64s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1175, 'learning_rate': 3.947750362844703e-06, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▍ | 921/1189 [1:18:59<20:43, 4.64s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▍ | 922/1189 [1:19:04<20:34, 4.62s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▍ | 922/1189 [1:19:04<20:34, 4.62s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▍ | 922/1189 [1:19:04<20:34, 4.62s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▌ | 923/1189 [1:19:08<20:17, 4.58s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▌ | 923/1189 [1:19:08<20:17, 4.58s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▌ | 924/1189 [1:19:12<20:05, 4.55s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▌ | 924/1189 [1:19:12<20:05, 4.55s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.111, 'learning_rate': 3.904208998548621e-06, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▋ | 925/1189 [1:19:17<19:52, 4.52s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▋ | 925/1189 [1:19:17<19:52, 4.52s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.017, 'learning_rate': 3.889695210449927e-06, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▋ | 926/1189 [1:19:21<19:42, 4.50s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▋ | 926/1189 [1:19:21<19:42, 4.50s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.019, 'learning_rate': 3.875181422351234e-06, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▊ | 927/1189 [1:19:26<19:30, 4.47s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▊ | 927/1189 [1:19:26<19:30, 4.47s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1868, 'learning_rate': 3.86066763425254e-06, 'epoch': 0.78} g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2295, 'learning_rate': 3.846153846153847e-06, 'epoch': 0.78} g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0424, 'learning_rate': 3.831640058055153e-06, 'epoch': 0.78} [WARNING|modeling_utils.py:388] 2022-02-28 17:53:29,279 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:53:29,279 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9899, 'learning_rate': 3.817126269956458e-06, 'epoch': 0.78} [WARNING|modeling_utils.py:388] 2022-02-28 17:53:29,279 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████ | 931/1189 [1:19:43<18:38, 4.34s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████ | 931/1189 [1:19:43<18:38, 4.34s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▏ | 932/1189 [1:19:47<18:28, 4.31s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▏ | 932/1189 [1:19:47<18:28, 4.31s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2305, 'learning_rate': 3.7880986937590716e-06, 'epoch': 0.78} 78%|█████████████████████████████████████████████████████████████▏ | 932/1189 [1:19:47<18:28, 4.31s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▏ | 933/1189 [1:19:51<18:17, 4.29s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▏ | 933/1189 [1:19:51<18:17, 4.29s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▎ | 934/1189 [1:19:56<18:01, 4.24s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▎ | 934/1189 [1:19:56<18:01, 4.24s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2157, 'learning_rate': 3.759071117561684e-06, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▎ | 934/1189 [1:19:56<18:01, 4.24s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▎ | 935/1189 [1:20:00<17:45, 4.19s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▎ | 935/1189 [1:20:00<17:45, 4.19s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▍ | 936/1189 [1:20:04<17:23, 4.12s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▍ | 936/1189 [1:20:04<17:23, 4.12s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2321, 'learning_rate': 3.7300435413642967e-06, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▍ | 936/1189 [1:20:04<17:23, 4.12s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▍ | 937/1189 [1:20:08<17:01, 4.05s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▍ | 937/1189 [1:20:08<17:01, 4.05s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▍ | 937/1189 [1:20:08<17:01, 4.05s/it]g-point operations will not be computed-28 17:50:54,313 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▌ | 938/1189 [1:20:11<16:38, 3.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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. 79%|█████████████████████████████████████████████████████████████▌ | 939/1189 [1:20:15<16:14, 3.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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. 79%|█████████████████████████████████████████████████████████████▌ | 939/1189 [1:20:15<16:14, 3.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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': 4.1749, 'learning_rate': 3.6865021770682153e-06, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▋ | 940/1189 [1:20:19<15:44, 3.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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. 79%|█████████████████████████████████████████████████████████████▋ | 940/1189 [1:20:19<15:44, 3.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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': 4.1726, 'learning_rate': 3.671988388969521e-06, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▋ | 941/1189 [1:20:22<15:15, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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. 79%|█████████████████████████████████████████████████████████████▋ | 941/1189 [1:20:22<15:15, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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': 4.0525, 'learning_rate': 3.6574746008708277e-06, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▋ | 941/1189 [1:20:22<15:15, 3.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:03,838 >> 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. 79%|█████████████████████████████████████████████████████████████▊ | 942/1189 [1:20:25<14:37, 3.55s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:17,441 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▊ | 943/1189 [1:20:28<13:50, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:20,272 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▊ | 943/1189 [1:20:28<13:50, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:20,272 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▉ | 944/1189 [1:20:31<12:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:20,272 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▉ | 944/1189 [1:20:31<12:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:20,272 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2563, 'learning_rate': 3.6139332365747467e-06, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▉ | 944/1189 [1:20:31<12:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:20,272 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████▉ | 945/1189 [1:20:33<12:06, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:25,265 >> 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. 79%|█████████████████████████████████████████████████████████████▉ | 945/1189 [1:20:33<12:06, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:25,265 >> 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. 80%|██████████████████████████████████████████████████████████████ | 946/1189 [1:20:36<11:08, 2.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:27,378 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████ | 946/1189 [1:20:36<11:08, 2.75s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:27,378 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████ | 947/1189 [1:20:38<10:13, 2.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:29,287 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████ | 947/1189 [1:20:38<10:13, 2.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:29,287 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▎ | 949/1189 [1:20:41<08:12, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:30,878 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▎ | 949/1189 [1:20:41<08:12, 2.05s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:30,878 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▎ | 950/1189 [1:20:43<07:54, 1.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:32,239 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▎ | 950/1189 [1:20:43<07:54, 1.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:32,239 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▎ | 950/1189 [1:20:43<07:54, 1.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▍ | 951/1189 [1:20:48<11:49, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▍ | 951/1189 [1:20:48<11:49, 2.98s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0576, 'learning_rate': 3.5123367198838896e-06, 'epoch': 0.8} 80%|██████████████████████████████████████████████████████████████▍ | 952/1189 [1:20:53<14:17, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▍ | 952/1189 [1:20:53<14:17, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.216, 'learning_rate': 3.4978229317851962e-06, 'epoch': 0.8} 80%|██████████████████████████████████████████████████████████████▍ | 952/1189 [1:20:53<14:17, 3.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▌ | 953/1189 [1:20:58<15:58, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▌ | 953/1189 [1:20:58<15:58, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▌ | 954/1189 [1:21:03<16:58, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▌ | 954/1189 [1:21:03<16:58, 4.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8672, 'learning_rate': 3.4687953555878086e-06, 'epoch': 0.8} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.093, 'learning_rate': 3.454281567489115e-06, 'epoch': 0.8} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▋ | 956/1189 [1:21:13<18:14, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▋ | 956/1189 [1:21:13<18:14, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2003, 'learning_rate': 3.439767779390421e-06, 'epoch': 0.8} 80%|██████████████████████████████████████████████████████████████▊ | 957/1189 [1:21:18<18:23, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▊ | 957/1189 [1:21:18<18:23, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1416, 'learning_rate': 3.4252539912917276e-06, 'epoch': 0.8} 81%|██████████████████████████████████████████████████████████████▊ | 958/1189 [1:21:23<18:31, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▊ | 958/1189 [1:21:23<18:31, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0459, 'learning_rate': 3.4107402031930338e-06, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████▉ | 959/1189 [1:21:28<18:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 959/1189 [1:21:28<18:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0946, 'learning_rate': 3.3962264150943395e-06, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████▉ | 959/1189 [1:21:28<18:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 959/1189 [1:21:28<18:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 959/1189 [1:21:28<18:33, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.062, 'learning_rate': 3.381712626995646e-06, 'epoch': 0.81} 81%|███████████████████████████████████████████████████████████████ | 961/1189 [1:21:38<18:28, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████ | 961/1189 [1:21:38<18:28, 4.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.006, 'learning_rate': 3.3671988388969524e-06, 'epoch': 0.81} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2121, 'learning_rate': 3.3526850507982585e-06, 'epoch': 0.81} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▏ | 963/1189 [1:21:47<18:04, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▏ | 963/1189 [1:21:47<18:04, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▏ | 964/1189 [1:21:52<17:58, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▏ | 964/1189 [1:21:52<17:58, 4.79s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1986, 'learning_rate': 3.323657474600871e-06, 'epoch': 0.81} 81%|███████████████████████████████████████████████████████████████▎ | 965/1189 [1:21:57<17:46, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▎ | 965/1189 [1:21:57<17:46, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3211, 'learning_rate': 3.3091436865021775e-06, 'epoch': 0.81} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.971, 'learning_rate': 3.2946298984034837e-06, 'epoch': 0.81} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▍ | 967/1189 [1:22:06<17:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▍ | 967/1189 [1:22:06<17:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▍ | 967/1189 [1:22:06<17:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▌ | 968/1189 [1:22:11<17:24, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▌ | 968/1189 [1:22:11<17:24, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▌ | 968/1189 [1:22:11<17:24, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▌ | 969/1189 [1:22:16<17:15, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▌ | 969/1189 [1:22:16<17:15, 4.71s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1306, 'learning_rate': 3.236574746008709e-06, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▋ | 971/1189 [1:22:25<16:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▋ | 971/1189 [1:22:25<16:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9755, 'learning_rate': 3.2220609579100147e-06, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▋ | 971/1189 [1:22:25<16:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▊ | 972/1189 [1:22:29<16:40, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▊ | 972/1189 [1:22:29<16:40, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▊ | 972/1189 [1:22:29<16:40, 4.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▊ | 973/1189 [1:22:34<16:32, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▊ | 973/1189 [1:22:34<16:32, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▊ | 973/1189 [1:22:34<16:32, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▉ | 974/1189 [1:22:38<16:26, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▉ | 974/1189 [1:22:38<16:26, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▉ | 975/1189 [1:22:43<16:21, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▉ | 975/1189 [1:22:43<16:21, 4.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1472, 'learning_rate': 3.1640058055152394e-06, 'epoch': 0.82} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1512, 'learning_rate': 3.149492017416546e-06, 'epoch': 0.82} [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████ | 977/1189 [1:22:52<15:55, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:56:46,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:56:46,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1559, 'learning_rate': 3.120464441219159e-06, 'epoch': 0.82} [WARNING|modeling_utils.py:388] 2022-02-28 17:56:46,920 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▏ | 979/1189 [1:23:01<15:26, 4.41s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▏ | 979/1189 [1:23:01<15:26, 4.41s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▏ | 979/1189 [1:23:01<15:26, 4.41s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▎ | 980/1189 [1:23:05<15:14, 4.38s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▎ | 980/1189 [1:23:05<15:14, 4.38s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▎ | 981/1189 [1:23:09<15:03, 4.34s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▎ | 981/1189 [1:23:09<15:03, 4.34s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2255, 'learning_rate': 3.0769230769230774e-06, 'epoch': 0.82} 83%|████████████████████████████████████████████████████████████████▎ | 981/1189 [1:23:09<15:03, 4.34s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▍ | 982/1189 [1:23:13<14:48, 4.29s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▍ | 982/1189 [1:23:13<14:48, 4.29s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▍ | 982/1189 [1:23:13<14:48, 4.29s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▍ | 983/1189 [1:23:17<14:34, 4.25s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▍ | 983/1189 [1:23:17<14:34, 4.25s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▍ | 983/1189 [1:23:17<14:34, 4.25s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▌ | 984/1189 [1:23:21<14:14, 4.17s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▌ | 984/1189 [1:23:21<14:14, 4.17s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▌ | 984/1189 [1:23:21<14:14, 4.17s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▌ | 985/1189 [1:23:25<13:54, 4.09s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▌ | 985/1189 [1:23:25<13:54, 4.09s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▌ | 985/1189 [1:23:25<13:54, 4.09s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▋ | 986/1189 [1:23:29<13:36, 4.02s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▋ | 986/1189 [1:23:29<13:36, 4.02s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▋ | 986/1189 [1:23:29<13:36, 4.02s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▋ | 987/1189 [1:23:33<13:18, 3.95s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▋ | 987/1189 [1:23:33<13:18, 3.95s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▋ | 987/1189 [1:23:33<13:18, 3.95s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▊ | 988/1189 [1:23:37<12:58, 3.87s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:30,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:30,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1658, 'learning_rate': 2.9608127721335274e-06, 'epoch': 0.83} [WARNING|modeling_utils.py:388] 2022-02-28 17:57:30,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▉ | 990/1189 [1:23:44<12:12, 3.68s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▉ | 990/1189 [1:23:44<12:12, 3.68s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▉ | 990/1189 [1:23:44<12:12, 3.68s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████ | 991/1189 [1:23:47<11:44, 3.56s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████ | 991/1189 [1:23:47<11:44, 3.56s/it]g-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:40,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:40,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:40,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:54:36,155 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▏ | 993/1189 [1:23:53<10:54, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:45,393 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▏ | 993/1189 [1:23:53<10:54, 3.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:45,393 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▏ | 994/1189 [1:23:56<10:25, 3.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:45,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:49,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:57:45,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 17:57:49,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:57:45,393 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3022, 'learning_rate': 2.8737300435413645e-06, 'epoch': 0.84} [WARNING|modeling_utils.py:388] 2022-02-28 17:57:49,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 17:57:45,393 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▎ | 996/1189 [1:24:01<09:02, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:52,739 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▎ | 996/1189 [1:24:01<09:02, 2.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:52,739 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▍ | 998/1189 [1:24:05<07:24, 2.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:54,629 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▍ | 998/1189 [1:24:05<07:24, 2.33s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:54,629 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.404, 'learning_rate': 2.830188679245283e-06, 'epoch': 0.84} 84%|█████████████████████████████████████████████████████████████████▌ | 999/1189 [1:24:06<06:35, 2.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:57,674 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▌ | 999/1189 [1:24:06<06:35, 2.08s/it][WARNING|modeling_utils.py:388] 2022-02-28 17:57:57,674 >> Could not estimate the number of tokens of the input, floating-point operations will not 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] 2022-02-28 17:57:58,954 >> Num examples = 2642 | 1000/1189 [1:24:08<06:19, 2.01s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-02-28 17:57:58,954 >> Num examples = 2642 | 1000/1189 [1:24:08<06:19, 2.01s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-02-28 17:57:58,954 >> Num examples = 2642 | 1000/1189 [1:24:08<06:19, 2.01s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-02-28 17:57:58,954 >> Num examples = 2642 | 1000/1189 [1:24:08<06:19, 2.01s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 2%|█▌ | 4/221 [00:08<08:58, 2.48s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 2%|█▉ | 5/221 [00:11<09:39, 2.68s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 3%|██▎ | 6/221 [00:15<10:19, 2.88s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 3%|██▋ | 7/221 [00:18<11:16, 3.16s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███ | 8/221 [00:21<11:00, 3.10s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███▍ | 9/221 [00:25<10:54, 3.09s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|███▋ | 10/221 [00:29<11:49, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████ | 11/221 [00:33<12:42, 3.63s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████▍ | 12/221 [00:36<11:54, 3.42s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 6%|████▊ | 13/221 [00:39<11:29, 3.31s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 6%|█████▏ | 14/221 [00:42<11:34, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 7%|█████▌ | 15/221 [00:47<12:53, 3.76s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 7%|█████▉ | 16/221 [00:52<13:52, 4.06s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 8%|██████▎ | 17/221 [00:55<13:16, 3.91s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 8%|██████▋ | 18/221 [00:59<13:04, 3.87s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 9%|███████ | 19/221 [01:02<12:24, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 9%|███████▍ | 20/221 [01:05<11:53, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|███████▊ | 21/221 [01:08<11:12, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▏ | 22/221 [01:12<11:00, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▌ | 23/221 [01:15<10:45, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|████████▉ | 24/221 [01:19<11:15, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|█████████▎ | 25/221 [01:23<11:48, 3.62s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 12%|█████████▋ | 26/221 [01:26<11:56, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 12%|██████████ | 27/221 [01:29<10:51, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▍ | 28/221 [01:33<11:24, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▊ | 29/221 [01:37<12:06, 3.78s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▏ | 30/221 [01:40<11:20, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▌ | 31/221 [01:43<10:24, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▊ | 32/221 [01:46<10:22, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▏ | 33/221 [01:50<10:48, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▌ | 34/221 [01:54<10:54, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|████████████▉ | 35/221 [01:57<10:27, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|█████████████▎ | 36/221 [02:00<10:19, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 17%|█████████████▋ | 37/221 [02:04<11:06, 3.62s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 17%|██████████████ | 38/221 [02:07<10:27, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▍ | 39/221 [02:11<10:43, 3.53s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▊ | 40/221 [02:14<10:05, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▏ | 41/221 [02:18<10:17, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▌ | 42/221 [02:22<11:14, 3.77s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▉ | 43/221 [02:26<10:44, 3.62s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▎ | 44/221 [02:30<11:41, 3.96s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▋ | 45/221 [02:35<12:14, 4.17s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████ | 46/221 [02:39<12:09, 4.17s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████▍ | 47/221 [02:43<11:57, 4.12s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|█████████████████▊ | 48/221 [02:47<11:50, 4.11s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|██████████████████▏ | 49/221 [02:51<11:25, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▌ | 50/221 [02:55<11:25, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▉ | 51/221 [02:58<10:44, 3.79s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▎ | 52/221 [03:01<10:02, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▋ | 53/221 [03:04<09:24, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|████████████████████ | 54/221 [03:08<09:41, 3.48s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▍ | 55/221 [03:12<09:45, 3.53s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▊ | 56/221 [03:16<10:30, 3.82s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▏ | 57/221 [03:20<10:35, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▌ | 58/221 [03:24<10:11, 3.75s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|█████████████████████▉ | 59/221 [03:27<09:40, 3.58s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|██████████████████████▎ | 60/221 [03:29<08:51, 3.30s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|██████████████████████▋ | 61/221 [03:33<09:04, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|███████████████████████ | 62/221 [03:36<08:48, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|███████████████████████▍ | 63/221 [03:40<08:53, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|███████████████████████▋ | 64/221 [03:43<08:49, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|████████████████████████ | 65/221 [03:46<08:44, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▍ | 66/221 [03:50<08:51, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▊ | 67/221 [03:53<08:17, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▏ | 68/221 [03:57<08:55, 3.50s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▌ | 69/221 [04:00<08:35, 3.39s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▉ | 70/221 [04:03<08:26, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|██████████████████████████▎ | 71/221 [04:06<08:16, 3.31s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|██████████████████████████▋ | 72/221 [04:09<07:47, 3.14s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|███████████████████████████ | 73/221 [04:13<08:04, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|███████████████████████████▍ | 74/221 [04:16<08:01, 3.28s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|███████████████████████████▊ | 75/221 [04:19<07:56, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|████████████████████████████▏ | 76/221 [04:22<07:47, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▌ | 77/221 [04:26<07:44, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▉ | 78/221 [04:29<07:55, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▎ | 79/221 [04:32<07:35, 3.21s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▋ | 80/221 [04:35<07:34, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|██████████████████████████████ | 81/221 [04:39<07:57, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|██████████████████████████████▍ | 82/221 [04:44<08:30, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▊ | 83/221 [04:48<08:55, 3.88s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▏ | 84/221 [04:52<08:56, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▌ | 85/221 [04:57<09:19, 4.12s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████▉ | 86/221 [05:00<09:04, 4.03s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|████████████████████████████████▎ | 87/221 [05:05<09:20, 4.18s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|████████████████████████████████▋ | 88/221 [05:08<08:40, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|█████████████████████████████████ | 89/221 [05:11<08:08, 3.70s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▍ | 90/221 [05:15<08:05, 3.71s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▊ | 91/221 [05:19<08:19, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|██████████████████████████████████▏ | 92/221 [05:24<08:34, 3.99s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|██████████████████████████████████▌ | 93/221 [05:28<08:39, 4.06s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▉ | 94/221 [05:32<08:26, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|███████████████████████████████████▏ | 95/221 [05:36<08:23, 4.00s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|███████████████████████████████████▌ | 96/221 [05:39<08:13, 3.95s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▉ | 97/221 [05:44<08:25, 4.08s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|████████████████████████████████████▎ | 98/221 [05:48<08:12, 4.00s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 99/221 [05:51<07:27, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 100/221 [05:54<07:23, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████ | 101/221 [05:57<07:04, 3.54s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████▍ | 102/221 [06:00<06:42, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|█████████████████████████████████████▊ | 103/221 [06:04<06:59, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|██████████████████████████████████████ | 104/221 [06:08<07:10, 3.68s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▍ | 105/221 [06:13<07:34, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▊ | 106/221 [06:17<07:35, 3.96s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|███████████████████████████████████████▏ | 107/221 [06:20<07:04, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|███████████████████████████████████████▌ | 108/221 [06:24<07:20, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|███████████████████████████████████████▉ | 109/221 [06:28<07:19, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▎ | 110/221 [06:32<06:55, 3.74s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▋ | 111/221 [06:35<06:37, 3.61s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████ | 112/221 [06:39<06:40, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████▍ | 113/221 [06:43<06:38, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|█████████████████████████████████████████▊ | 114/221 [06:46<06:24, 3.59s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|██████████████████████████████████████████▏ | 115/221 [06:49<06:19, 3.58s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|██████████████████████████████████████████▌ | 116/221 [06:53<06:03, 3.46s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|██████████████████████████████████████████▉ | 117/221 [06:56<05:57, 3.44s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|███████████████████████████████████████████▏ | 118/221 [07:00<06:05, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▌ | 119/221 [07:04<06:27, 3.80s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▉ | 120/221 [07:09<06:41, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▎ | 121/221 [07:12<06:29, 3.89s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▋ | 122/221 [07:15<05:42, 3.46s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████ | 123/221 [07:17<05:08, 3.15s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████▍ | 124/221 [07:20<05:03, 3.13s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|█████████████████████████████████████████████▊ | 125/221 [07:24<05:22, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████████▏ | 126/221 [07:27<05:05, 3.22s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████████▌ | 127/221 [07:30<04:51, 3.10s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|██████████████████████████████████████████████▉ | 128/221 [07:33<04:34, 2.95s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|███████████████████████████████████████████████▎ | 129/221 [07:36<04:52, 3.18s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|███████████████████████████████████████████████▋ | 130/221 [07:39<04:38, 3.06s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|████████████████████████████████████████████████ | 131/221 [07:43<04:53, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▍ | 132/221 [07:45<04:33, 3.07s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▋ | 133/221 [07:49<04:34, 3.12s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████ | 134/221 [07:51<04:22, 3.02s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████▍ | 135/221 [07:55<04:26, 3.10s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|█████████████████████████████████████████████████▊ | 136/221 [07:58<04:40, 3.30s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▏ | 137/221 [08:02<04:42, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▌ | 138/221 [08:06<04:51, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|██████████████████████████████████████████████████▉ | 139/221 [08:10<04:54, 3.59s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|███████████████████████████████████████████████████▎ | 140/221 [08:12<04:23, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|███████████████████████████████████████████████████▋ | 141/221 [08:15<04:20, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|████████████████████████████████████████████████████ | 142/221 [08:18<04:13, 3.20s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▍ | 143/221 [08:21<03:53, 2.99s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▊ | 144/221 [08:25<04:08, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▊ | 144/221 [08:25<04:08, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▊ | 144/221 [08:25<04:08, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|█████████████████████████████████████████████████████▌ | 146/221 [08:32<04:12, 3.37s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|█████████████████████████████████████████████████████▉ | 147/221 [08:34<03:56, 3.20s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▏ | 148/221 [08:38<03:57, 3.25s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▌ | 149/221 [08:41<03:56, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|██████████████████████████████████████████████████████▉ | 150/221 [08:44<03:51, 3.26s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|███████████████████████████████████████████████████████▎ | 151/221 [08:48<03:59, 3.42s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|███████████████████████████████████████████████████████▋ | 152/221 [08:51<03:53, 3.38s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████████ | 153/221 [08:55<03:45, 3.32s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▍ | 154/221 [08:58<03:47, 3.39s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▊ | 155/221 [09:02<03:45, 3.41s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▏ | 156/221 [09:05<03:44, 3.45s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▌ | 157/221 [09:08<03:26, 3.23s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▉ | 158/221 [09:13<03:51, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|██████████████████████████████████████████████████████████▎ | 159/221 [09:16<03:49, 3.70s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|██████████████████████████████████████████████████████████▋ | 160/221 [09:20<03:53, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████ | 161/221 [09:25<03:57, 3.95s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████▍ | 162/221 [09:29<03:54, 3.97s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|███████████████████████████████████████████████████████████▋ | 163/221 [09:33<03:57, 4.09s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████████ | 164/221 [09:38<04:01, 4.24s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▍ | 165/221 [09:41<03:47, 4.07s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▊ | 166/221 [09:44<03:28, 3.80s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▏ | 167/221 [09:48<03:21, 3.73s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▌ | 168/221 [09:51<03:07, 3.53s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▉ | 169/221 [09:55<03:09, 3.65s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▎ | 170/221 [09:59<03:09, 3.71s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▋ | 171/221 [10:03<03:06, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████ | 172/221 [10:06<02:55, 3.58s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████▍ | 173/221 [10:09<02:50, 3.56s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|███████████████████████████████████████████████████████████████▊ | 174/221 [10:13<02:41, 3.43s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:16<02:34, 3.35s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▌ | 176/221 [10:20<02:38, 3.52s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▊ | 177/221 [10:23<02:28, 3.36s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▏ | 178/221 [10:27<02:31, 3.51s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▌ | 179/221 [10:30<02:25, 3.46s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▉ | 180/221 [10:34<02:31, 3.69s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▎ | 181/221 [10:38<02:31, 3.79s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▋ | 182/221 [10:42<02:26, 3.76s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████ | 183/221 [10:46<02:28, 3.91s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████▍ | 184/221 [10:50<02:23, 3.87s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|███████████████████████████████████████████████████████████████████▊ | 185/221 [10:53<02:13, 3.71s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████████▏ | 186/221 [10:58<02:18, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▌ | 187/221 [11:01<02:09, 3.80s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▉ | 188/221 [11:05<02:09, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▎ | 189/221 [11:10<02:08, 4.01s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▋ | 190/221 [11:14<02:08, 4.15s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████████ | 191/221 [11:19<02:08, 4.30s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▎ | 192/221 [11:23<02:04, 4.29s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▋ | 193/221 [11:26<01:51, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████ | 194/221 [11:29<01:41, 3.74s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████▍ | 195/221 [11:32<01:32, 3.55s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|███████████████████████████████████████████████████████████████████████▊ | 196/221 [11:36<01:27, 3.49s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████████▏ | 197/221 [11:39<01:18, 3.29s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▌ | 198/221 [11:43<01:22, 3.59s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▉ | 199/221 [11:47<01:24, 3.84s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████████▎ | 200/221 [11:51<01:18, 3.72s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████████▋ | 201/221 [11:54<01:11, 3.60s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████████ | 202/221 [11:57<01:04, 3.40s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▍ | 203/221 [12:01<01:02, 3.49s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▊ | 204/221 [12:05<01:04, 3.80s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▏ | 205/221 [12:10<01:06, 4.13s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▌ | 206/221 [12:15<01:04, 4.29s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|███████████████████████████████████████████████████████████████████████████▊ | 207/221 [12:18<00:56, 4.04s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████████▏ | 208/221 [12:22<00:51, 3.98s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████████▌ | 209/221 [12:25<00:45, 3.79s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████████▉ | 210/221 [12:29<00:42, 3.86s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████████▎ | 211/221 [12:34<00:40, 4.03s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████████▋ | 212/221 [12:38<00:35, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████████ | 213/221 [12:41<00:29, 3.67s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▍ | 214/221 [12:44<00:25, 3.66s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▊ | 215/221 [12:49<00:22, 3.83s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:53<00:19, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:53<00:19, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:53<00:19, 3.94s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████████▉ | 218/221 [13:01<00:11, 3.92s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████████▎| 219/221 [13:04<00:07, 3.90s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████████▋| 220/221 [13:09<00:04, 4.10s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████████▋| 220/221 [13:09<00:04, 4.10s/it][INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 02/28/2022 18:11:13 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|configuration_utils.py:438] 2022-02-28 18:11:13,407 >> Configuration saved in ./checkpoint-1000/config.json [INFO|trainer.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 18:11:18,732 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 18:11:18,732 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 18:11:18,732 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 18:11:18,732 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 1001/1189 [1:39:36<14:36:46, 279.82s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▍ | 1001/1189 [1:39:36<14:36:46, 279.82s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2529, 'learning_rate': 2.7866473149492017e-06, 'epoch': 0.84} 84%|█████████████████████████████████████████████████████████████▌ | 1002/1189 [1:39:42<10:15:30, 197.49s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████▌ | 1002/1189 [1:39:42<10:15:30, 197.49s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2023, 'learning_rate': 2.7721335268505083e-06, 'epoch': 0.84} 84%|█████████████████████████████████████████████████████████████▌ | 1002/1189 [1:39:42<10:15:30, 197.49s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 1003/1189 [1:39:47<7:13:26, 139.82s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████▍ | 1003/1189 [1:39:47<7:13:26, 139.82s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1004/1189 [1:39:52<5:06:34, 99.43s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▎ | 1004/1189 [1:39:52<5:06:34, 99.43s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.058, 'learning_rate': 2.7431059506531207e-06, 'epoch': 0.84} 84%|███████████████████████████████████████████████████████████████▎ | 1004/1189 [1:39:52<5:06:34, 99.43s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1005/1189 [1:39:57<3:38:13, 71.16s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1005/1189 [1:39:57<3:38:13, 71.16s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1005/1189 [1:39:57<3:38:13, 71.16s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1006/1189 [1:40:02<2:36:39, 51.36s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▍ | 1006/1189 [1:40:02<2:36:39, 51.36s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▌ | 1007/1189 [1:40:08<1:53:46, 37.51s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▌ | 1007/1189 [1:40:08<1:53:46, 37.51s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0825, 'learning_rate': 2.6995645863570397e-06, 'epoch': 0.85} 85%|███████████████████████████████████████████████████████████████▌ | 1007/1189 [1:40:08<1:53:46, 37.51s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▌ | 1008/1189 [1:40:13<1:23:52, 27.81s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▌ | 1008/1189 [1:40:13<1:23:52, 27.81s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▋ | 1009/1189 [1:40:18<1:03:03, 21.02s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████▋ | 1009/1189 [1:40:18<1:03:03, 21.02s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1022, 'learning_rate': 2.6705370101596516e-06, 'epoch': 0.85} 85%|███████████████████████████████████████████████████████████████▋ | 1009/1189 [1:40:18<1:03:03, 21.02s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1010/1189 [1:40:23<48:30, 16.26s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1010/1189 [1:40:23<48:30, 16.26s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1011/1189 [1:40:28<38:29, 12.97s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 1011/1189 [1:40:28<38:29, 12.97s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0737, 'learning_rate': 2.6415094339622644e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▍ | 1011/1189 [1:40:28<38:29, 12.97s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 1012/1189 [1:40:33<31:11, 10.57s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 1012/1189 [1:40:33<31:11, 10.57s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 1013/1189 [1:40:38<26:06, 8.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 1013/1189 [1:40:38<26:06, 8.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0142, 'learning_rate': 2.612481857764877e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▌ | 1013/1189 [1:40:38<26:06, 8.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1014/1189 [1:40:43<22:29, 7.71s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1014/1189 [1:40:43<22:29, 7.71s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:48<19:54, 6.86s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:48<19:54, 6.86s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1347, 'learning_rate': 2.5834542815674896e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:48<19:54, 6.86s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:48<19:54, 6.86s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2207, 'learning_rate': 2.568940493468796e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:48<19:54, 6.86s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:48<19:54, 6.86s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 1017/1189 [1:40:58<16:54, 5.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 1017/1189 [1:40:58<16:54, 5.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▉ | 1018/1189 [1:41:03<16:00, 5.62s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▉ | 1018/1189 [1:41:03<16:00, 5.62s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1704, 'learning_rate': 2.539912917271408e-06, 'epoch': 0.86} 86%|█████████████████████████████████████████████████████████████████▉ | 1018/1189 [1:41:03<16:00, 5.62s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▉ | 1019/1189 [1:41:08<15:17, 5.39s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▉ | 1019/1189 [1:41:08<15:17, 5.39s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████ | 1020/1189 [1:41:13<14:45, 5.24s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████ | 1020/1189 [1:41:13<14:45, 5.24s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9835, 'learning_rate': 2.51088534107402e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████ | 1021/1189 [1:41:18<14:30, 5.18s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████ | 1021/1189 [1:41:18<14:30, 5.18s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0653, 'learning_rate': 2.4963715529753268e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▏ | 1022/1189 [1:41:23<14:09, 5.09s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▏ | 1022/1189 [1:41:23<14:09, 5.09s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2703, 'learning_rate': 2.481857764876633e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▏ | 1023/1189 [1:41:28<13:49, 5.00s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▏ | 1023/1189 [1:41:28<13:49, 5.00s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2143, 'learning_rate': 2.467343976777939e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▏ | 1023/1189 [1:41:28<13:49, 5.00s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▎ | 1024/1189 [1:41:32<13:32, 4.93s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▎ | 1024/1189 [1:41:32<13:32, 4.93s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▎ | 1024/1189 [1:41:32<13:32, 4.93s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▍ | 1025/1189 [1:41:37<13:13, 4.84s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▍ | 1025/1189 [1:41:37<13:13, 4.84s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▍ | 1026/1189 [1:41:42<12:54, 4.75s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▍ | 1026/1189 [1:41:42<12:54, 4.75s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0597, 'learning_rate': 2.4238026124818577e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▌ | 1027/1189 [1:41:46<12:42, 4.71s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 1027/1189 [1:41:46<12:42, 4.71s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1458, 'learning_rate': 2.4092888243831643e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▌ | 1027/1189 [1:41:46<12:42, 4.71s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 1028/1189 [1:41:51<12:26, 4.64s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 1028/1189 [1:41:51<12:26, 4.64s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▌ | 1028/1189 [1:41:51<12:26, 4.64s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▋ | 1029/1189 [1:41:55<12:12, 4.58s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▋ | 1029/1189 [1:41:55<12:12, 4.58s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▋ | 1030/1189 [1:42:00<12:03, 4.55s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▋ | 1030/1189 [1:42:00<12:03, 4.55s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9322, 'learning_rate': 2.365747460087083e-06, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▊ | 1031/1189 [1:42:04<11:58, 4.55s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▊ | 1031/1189 [1:42:04<11:58, 4.55s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1389, 'learning_rate': 2.351233671988389e-06, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▊ | 1032/1189 [1:42:08<11:44, 4.49s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▊ | 1032/1189 [1:42:08<11:44, 4.49s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0368, 'learning_rate': 2.3367198838896953e-06, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▉ | 1033/1189 [1:42:13<11:29, 4.42s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▉ | 1033/1189 [1:42:13<11:29, 4.42s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1147, 'learning_rate': 2.322206095791002e-06, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▉ | 1034/1189 [1:42:17<11:10, 4.32s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████▉ | 1034/1189 [1:42:17<11:10, 4.32s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0622, 'learning_rate': 2.307692307692308e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1035/1189 [1:42:21<10:51, 4.23s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████ | 1035/1189 [1:42:21<10:51, 4.23s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9735, 'learning_rate': 2.293178519593614e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1036/1189 [1:42:25<10:35, 4.16s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████ | 1036/1189 [1:42:25<10:35, 4.16s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9822, 'learning_rate': 2.2786647314949205e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▏ | 1037/1189 [1:42:29<10:16, 4.06s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▏ | 1037/1189 [1:42:29<10:16, 4.06s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9537, 'learning_rate': 2.2641509433962266e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▏ | 1038/1189 [1:42:32<10:01, 3.98s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▏ | 1038/1189 [1:42:32<10:01, 3.98s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.3565, 'learning_rate': 2.249637155297533e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▎ | 1039/1189 [1:42:36<09:45, 3.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▎ | 1039/1189 [1:42:36<09:45, 3.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1527, 'learning_rate': 2.235123367198839e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▎ | 1039/1189 [1:42:36<09:45, 3.90s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▎ | 1040/1189 [1:42:40<09:26, 3.81s/it]config.jsoner.py:560] 2022-02-28 17:57:58,951 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-02-28 18:16:33,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed58,951 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-02-28 18:16:33,772 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2147, 'learning_rate': 2.2060957910014514e-06, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▍ | 1042/1189 [1:42:46<08:45, 3.57s/it]g-point operations will not be computed58,951 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▍ | 1042/1189 [1:42:46<08:45, 3.57s/it]g-point operations will not be computed58,951 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-02-28 18:16:40,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed58,951 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-02-28 18:16:40,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed58,951 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.107, 'learning_rate': 2.177068214804064e-06, 'epoch': 0.88} 88%|███████████████████████████████████████████████████████████████████▌ | 1044/1189 [1:42:52<07:49, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:16:44,253 >> 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. 88%|███████████████████████████████████████████████████████████████████▌ | 1044/1189 [1:42:52<07:49, 3.24s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:16:44,253 >> 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. 88%|███████████████████████████████████████████████████████████████████▋ | 1045/1189 [1:42:55<07:14, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:16:44,253 >> 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. 88%|███████████████████████████████████████████████████████████████████▋ | 1045/1189 [1:42:55<07:14, 3.02s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:16:44,253 >> 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] 2022-02-28 18:16:47,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:47,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:49,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:49,615 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:51,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:51,397 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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': 4.4241, 'learning_rate': 2.104499274310595e-06, 'epoch': 0.88} [WARNING|modeling_utils.py:388] 2022-02-28 18:16:52,963 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:52,963 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:54,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:16:54,860 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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. 88%|████████████████████████████████████████████████████████████████████ | 1051/1189 [1:43:10<07:11, 3.13s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 88%|████████████████████████████████████████████████████████████████████ | 1051/1189 [1:43:10<07:11, 3.13s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.0961, 'learning_rate': 2.0609579100145137e-06, 'epoch': 0.88} 88%|████████████████████████████████████████████████████████████████████▏ | 1052/1189 [1:43:15<08:35, 3.76s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 88%|████████████████████████████████████████████████████████████████████▏ | 1052/1189 [1:43:15<08:35, 3.76s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.0602, 'learning_rate': 2.0464441219158204e-06, 'epoch': 0.88} 89%|████████████████████████████████████████████████████████████████████▏ | 1053/1189 [1:43:20<09:25, 4.16s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▏ | 1053/1189 [1:43:20<09:25, 4.16s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.0292, 'learning_rate': 2.0319303338171265e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▎ | 1054/1189 [1:43:25<09:59, 4.44s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▎ | 1054/1189 [1:43:25<09:59, 4.44s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.1502, 'learning_rate': 2.0174165457184327e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▎ | 1055/1189 [1:43:30<10:20, 4.63s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▎ | 1055/1189 [1:43:30<10:20, 4.63s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.2151, 'learning_rate': 2.002902757619739e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▍ | 1056/1189 [1:43:35<10:28, 4.73s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▍ | 1056/1189 [1:43:35<10:28, 4.73s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.2744, 'learning_rate': 1.988388969521045e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▍ | 1057/1189 [1:43:40<10:34, 4.81s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▍ | 1057/1189 [1:43:40<10:34, 4.81s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.2287, 'learning_rate': 1.9738751814223513e-06, 'epoch': 0.89} g-point operations will not be computed-28 18:16:44,253 >> 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. g-point operations will not be computed-28 18:16:44,253 >> 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': 3.9549, 'learning_rate': 1.959361393323658e-06, 'epoch': 0.89} g-point operations will not be computed-28 18:16:44,253 >> 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. g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▌ | 1059/1189 [1:43:50<10:34, 4.88s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▌ | 1059/1189 [1:43:50<10:34, 4.88s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▌ | 1059/1189 [1:43:50<10:34, 4.88s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▋ | 1060/1189 [1:43:55<10:28, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▋ | 1060/1189 [1:43:55<10:28, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▋ | 1061/1189 [1:44:00<10:23, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▋ | 1061/1189 [1:44:00<10:23, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.2533, 'learning_rate': 1.9158200290275765e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▋ | 1061/1189 [1:44:00<10:23, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▊ | 1062/1189 [1:44:05<10:18, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▊ | 1062/1189 [1:44:05<10:18, 4.87s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▊ | 1063/1189 [1:44:10<10:10, 4.85s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▊ | 1063/1189 [1:44:10<10:10, 4.85s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.1658, 'learning_rate': 1.8867924528301889e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▊ | 1063/1189 [1:44:10<10:10, 4.85s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▉ | 1064/1189 [1:44:14<10:00, 4.80s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▉ | 1064/1189 [1:44:14<10:00, 4.80s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 89%|████████████████████████████████████████████████████████████████████▉ | 1064/1189 [1:44:14<10:00, 4.80s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|████████████████████████████████████████████████████████████████████▉ | 1065/1189 [1:44:19<09:51, 4.77s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|████████████████████████████████████████████████████████████████████▉ | 1065/1189 [1:44:19<09:51, 4.77s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████ | 1066/1189 [1:44:24<09:43, 4.74s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████ | 1066/1189 [1:44:24<09:43, 4.74s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.0423, 'learning_rate': 1.8432510885341077e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████ | 1067/1189 [1:44:28<09:35, 4.72s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████ | 1067/1189 [1:44:28<09:35, 4.72s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.1094, 'learning_rate': 1.8287373004354138e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████ | 1067/1189 [1:44:28<09:35, 4.72s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▏ | 1068/1189 [1:44:33<09:30, 4.71s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▏ | 1068/1189 [1:44:33<09:30, 4.71s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▏ | 1068/1189 [1:44:33<09:30, 4.71s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▏ | 1069/1189 [1:44:38<09:23, 4.70s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▏ | 1069/1189 [1:44:38<09:23, 4.70s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▎ | 1070/1189 [1:44:42<09:17, 4.68s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▎ | 1070/1189 [1:44:42<09:17, 4.68s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.2625, 'learning_rate': 1.7851959361393326e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▎ | 1071/1189 [1:44:47<09:08, 4.65s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▎ | 1071/1189 [1:44:47<09:08, 4.65s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.1601, 'learning_rate': 1.7706821480406388e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▍ | 1072/1189 [1:44:52<09:01, 4.63s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▍ | 1072/1189 [1:44:52<09:01, 4.63s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.1046, 'learning_rate': 1.7561683599419448e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▍ | 1072/1189 [1:44:52<09:01, 4.63s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▍ | 1073/1189 [1:44:56<08:51, 4.59s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▍ | 1073/1189 [1:44:56<08:51, 4.59s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▍ | 1073/1189 [1:44:56<08:51, 4.59s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▌ | 1074/1189 [1:45:01<08:45, 4.57s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▌ | 1074/1189 [1:45:01<08:45, 4.57s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▌ | 1074/1189 [1:45:01<08:45, 4.57s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▌ | 1075/1189 [1:45:05<08:35, 4.52s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▌ | 1075/1189 [1:45:05<08:35, 4.52s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▋ | 1076/1189 [1:45:09<08:28, 4.50s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 90%|█████████████████████████████████████████████████████████████████████▋ | 1076/1189 [1:45:09<08:28, 4.50s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.0277, 'learning_rate': 1.6981132075471698e-06, 'epoch': 0.9} 91%|█████████████████████████████████████████████████████████████████████▋ | 1077/1189 [1:45:14<08:20, 4.47s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|█████████████████████████████████████████████████████████████████████▋ | 1077/1189 [1:45:14<08:20, 4.47s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.2872, 'learning_rate': 1.6835994194484762e-06, 'epoch': 0.91} 91%|█████████████████████████████████████████████████████████████████████▊ | 1078/1189 [1:45:18<08:12, 4.44s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|█████████████████████████████████████████████████████████████████████▊ | 1078/1189 [1:45:18<08:12, 4.44s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 4.1383, 'learning_rate': 1.6690856313497824e-06, 'epoch': 0.91} g-point operations will not be computed-28 18:16:44,253 >> 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. g-point operations will not be computed-28 18:16:44,253 >> 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': 4.136, 'learning_rate': 1.6545718432510888e-06, 'epoch': 0.91} 91%|█████████████████████████████████████████████████████████████████████▉ | 1080/1189 [1:45:27<07:54, 4.35s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|█████████████████████████████████████████████████████████████████████▉ | 1080/1189 [1:45:27<07:54, 4.35s/it]g-point operations will not be computed-28 18:16:44,253 >> 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': 3.9465, 'learning_rate': 1.6400580551523947e-06, 'epoch': 0.91} 91%|█████████████████████████████████████████████████████████████████████▉ | 1080/1189 [1:45:27<07:54, 4.35s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████ | 1081/1189 [1:45:31<07:47, 4.33s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████ | 1081/1189 [1:45:31<07:47, 4.33s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████ | 1081/1189 [1:45:31<07:47, 4.33s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████ | 1082/1189 [1:45:35<07:38, 4.29s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████ | 1082/1189 [1:45:35<07:38, 4.29s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████ | 1082/1189 [1:45:35<07:38, 4.29s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▏ | 1083/1189 [1:45:39<07:30, 4.25s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▏ | 1083/1189 [1:45:39<07:30, 4.25s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▏ | 1083/1189 [1:45:39<07:30, 4.25s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▏ | 1084/1189 [1:45:43<07:20, 4.19s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▏ | 1084/1189 [1:45:43<07:20, 4.19s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▏ | 1084/1189 [1:45:43<07:20, 4.19s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▎ | 1085/1189 [1:45:47<07:07, 4.11s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▎ | 1085/1189 [1:45:47<07:07, 4.11s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▎ | 1085/1189 [1:45:47<07:07, 4.11s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▎ | 1086/1189 [1:45:51<06:56, 4.04s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▎ | 1086/1189 [1:45:51<06:56, 4.04s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▎ | 1086/1189 [1:45:51<06:56, 4.04s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▍ | 1087/1189 [1:45:55<06:41, 3.94s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▍ | 1087/1189 [1:45:55<06:41, 3.94s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 91%|██████████████████████████████████████████████████████████████████████▍ | 1087/1189 [1:45:55<06:41, 3.94s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 92%|██████████████████████████████████████████████████████████████████████▍ | 1088/1189 [1:45:59<06:28, 3.85s/it]g-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:19:52,713 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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] 2022-02-28 18:19:52,713 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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': 4.0712, 'learning_rate': 1.509433962264151e-06, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-02-28 18:19:52,713 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:16:44,253 >> 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. 92%|██████████████████████████████████████████████████████████████████████▌ | 1090/1189 [1:46:06<06:01, 3.65s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 92%|██████████████████████████████████████████████████████████████████████▌ | 1090/1189 [1:46:06<06:01, 3.65s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 92%|██████████████████████████████████████████████████████████████████████▌ | 1090/1189 [1:46:06<06:01, 3.65s/it]g-point operations will not be computed-28 18:16:44,253 >> 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. 92%|██████████████████████████████████████████████████████████████████████▋ | 1091/1189 [1:46:09<05:43, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:00,911 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▋ | 1091/1189 [1:46:09<05:43, 3.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:00,911 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▋ | 1092/1189 [1:46:12<05:27, 3.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:00,911 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:20:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:20:00,911 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:20:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:20:00,911 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1395, 'learning_rate': 1.4513788098693759e-06, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-02-28 18:20:05,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:20:00,911 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▊ | 1094/1189 [1:46:17<04:48, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:09,105 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▊ | 1094/1189 [1:46:17<04:48, 3.04s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:09,105 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▉ | 1095/1189 [1:46:20<04:26, 2.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:11,333 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▉ | 1095/1189 [1:46:20<04:26, 2.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:11,333 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▉ | 1096/1189 [1:46:22<04:02, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:13,292 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████▉ | 1096/1189 [1:46:22<04:02, 2.61s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:13,292 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████ | 1097/1189 [1:46:24<03:39, 2.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:15,027 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████ | 1097/1189 [1:46:24<03:39, 2.38s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:15,027 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▏ | 1099/1189 [1:46:27<02:54, 1.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:16,550 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▏ | 1099/1189 [1:46:27<02:54, 1.93s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:16,550 >> Could not estimate the number of tokens of the input, floating-point operations will not be 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': 1.3642960812772134e-06, 'epoch': 0.92} 93%|███████████████████████████████████████████████████████████████████████▏ | 1100/1189 [1:46:28<02:47, 1.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:17,882 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▏ | 1100/1189 [1:46:28<02:47, 1.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▏ | 1100/1189 [1:46:28<02:47, 1.89s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▎ | 1101/1189 [1:46:34<04:20, 2.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▎ | 1101/1189 [1:46:34<04:20, 2.96s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▎ | 1102/1189 [1:46:39<05:16, 3.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▎ | 1102/1189 [1:46:39<05:16, 3.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1164, 'learning_rate': 1.3207547169811322e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▎ | 1102/1189 [1:46:39<05:16, 3.64s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:44<05:49, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:44<05:49, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:44<05:49, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:44<05:49, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9618, 'learning_rate': 1.2917271407837448e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:44<05:49, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:44<05:49, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▌ | 1105/1189 [1:46:54<06:23, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▌ | 1105/1189 [1:46:54<06:23, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▌ | 1106/1189 [1:46:59<06:30, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▌ | 1106/1189 [1:46:59<06:30, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.938, 'learning_rate': 1.2626995645863572e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▌ | 1106/1189 [1:46:59<06:30, 4.70s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▋ | 1107/1189 [1:47:04<06:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▋ | 1107/1189 [1:47:04<06:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▋ | 1107/1189 [1:47:04<06:31, 4.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:47:09<06:29, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:47:09<06:29, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:47:09<06:29, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:47:09<06:29, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1992, 'learning_rate': 1.219158200290276e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:47:09<06:29, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:47:09<06:29, 4.80s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▉ | 1110/1189 [1:47:19<06:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▉ | 1110/1189 [1:47:19<06:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▉ | 1111/1189 [1:47:24<06:21, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████▉ | 1111/1189 [1:47:24<06:21, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.061, 'learning_rate': 1.1901306240928884e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▉ | 1111/1189 [1:47:24<06:21, 4.90s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████ | 1112/1189 [1:47:29<06:13, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████ | 1112/1189 [1:47:29<06:13, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████ | 1112/1189 [1:47:29<06:13, 4.85s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████ | 1113/1189 [1:47:33<06:07, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████ | 1113/1189 [1:47:33<06:07, 4.84s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▏ | 1114/1189 [1:47:38<06:00, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▏ | 1114/1189 [1:47:38<06:00, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8364, 'learning_rate': 1.146589259796807e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▏ | 1114/1189 [1:47:38<06:00, 4.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▏ | 1115/1189 [1:47:43<05:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▏ | 1115/1189 [1:47:43<05:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▏ | 1115/1189 [1:47:43<05:52, 4.76s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▎ | 1116/1189 [1:47:48<05:45, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▎ | 1116/1189 [1:47:48<05:45, 4.74s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▎ | 1117/1189 [1:47:52<05:40, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▎ | 1117/1189 [1:47:52<05:40, 4.73s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1667, 'learning_rate': 1.1030478955007257e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:57<05:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:57<05:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9982, 'learning_rate': 1.088534107402032e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:57<05:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:57<05:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8337, 'learning_rate': 1.0740203193033383e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:57<05:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▌ | 1120/1189 [1:48:06<05:20, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▌ | 1120/1189 [1:48:06<05:20, 4.65s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1695, 'learning_rate': 1.0595065312046445e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▌ | 1121/1189 [1:48:11<05:14, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▌ | 1121/1189 [1:48:11<05:14, 4.62s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1488, 'learning_rate': 1.0449927431059507e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▋ | 1122/1189 [1:48:15<05:06, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▋ | 1122/1189 [1:48:15<05:06, 4.57s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1877, 'learning_rate': 1.0304789550072569e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▋ | 1123/1189 [1:48:20<04:59, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▋ | 1123/1189 [1:48:20<04:59, 4.54s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0255, 'learning_rate': 1.0159651669085633e-06, 'epoch': 0.94} 95%|████████████████████████████████████████████████████████████████████████▊ | 1124/1189 [1:48:24<04:53, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▊ | 1124/1189 [1:48:24<04:53, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1761, 'learning_rate': 1.0014513788098695e-06, 'epoch': 0.94} 95%|████████████████████████████████████████████████████████████████████████▊ | 1124/1189 [1:48:24<04:53, 4.52s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▊ | 1125/1189 [1:48:28<04:48, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▊ | 1125/1189 [1:48:28<04:48, 4.51s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▉ | 1126/1189 [1:48:33<04:41, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▉ | 1126/1189 [1:48:33<04:41, 4.47s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1163, 'learning_rate': 9.724238026124818e-07, 'epoch': 0.95} 95%|████████████████████████████████████████████████████████████████████████▉ | 1127/1189 [1:48:37<04:34, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▉ | 1127/1189 [1:48:37<04:34, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2633, 'learning_rate': 9.579100145137882e-07, 'epoch': 0.95} 95%|████████████████████████████████████████████████████████████████████████▉ | 1127/1189 [1:48:37<04:34, 4.43s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████ | 1128/1189 [1:48:42<04:27, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████ | 1128/1189 [1:48:42<04:27, 4.39s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████ | 1129/1189 [1:48:46<04:20, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████ | 1129/1189 [1:48:46<04:20, 4.34s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1479, 'learning_rate': 9.288824383164006e-07, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▏ | 1130/1189 [1:48:50<04:15, 4.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▏ | 1130/1189 [1:48:50<04:15, 4.32s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2254, 'learning_rate': 9.143686502177069e-07, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▏ | 1131/1189 [1:48:54<04:09, 4.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▏ | 1131/1189 [1:48:54<04:09, 4.30s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9276, 'learning_rate': 8.998548621190131e-07, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▎ | 1132/1189 [1:48:58<04:03, 4.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▎ | 1132/1189 [1:48:58<04:03, 4.27s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9613, 'learning_rate': 8.853410740203194e-07, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▎ | 1133/1189 [1:49:03<03:55, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▎ | 1133/1189 [1:49:03<03:55, 4.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2874, 'learning_rate': 8.708272859216256e-07, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▍ | 1134/1189 [1:49:07<03:48, 4.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▍ | 1134/1189 [1:49:07<03:48, 4.16s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1779, 'learning_rate': 8.563134978229319e-07, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▌ | 1135/1189 [1:49:11<03:41, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 1135/1189 [1:49:11<03:41, 4.10s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3097, 'learning_rate': 8.417997097242381e-07, 'epoch': 0.95} 96%|█████████████████████████████████████████████████████████████████████████▌ | 1136/1189 [1:49:14<03:34, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 1136/1189 [1:49:14<03:34, 4.06s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0715, 'learning_rate': 8.272859216255444e-07, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▋ | 1137/1189 [1:49:18<03:26, 3.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▋ | 1137/1189 [1:49:18<03:26, 3.97s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0906, 'learning_rate': 8.127721335268506e-07, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▋ | 1138/1189 [1:49:22<03:16, 3.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▋ | 1138/1189 [1:49:22<03:16, 3.86s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:16,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:16,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0879, 'learning_rate': 7.837445573294631e-07, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▊ | 1140/1189 [1:49:29<02:58, 3.64s/it]g-point operations will not be computed-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▊ | 1140/1189 [1:49:29<02:58, 3.64s/it]g-point operations will not be computed-28 18:20:21,831 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9786, 'learning_rate': 7.692307692307694e-07, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▉ | 1141/1189 [1:49:32<02:47, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:24,112 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▉ | 1141/1189 [1:49:32<02:47, 3.50s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:24,112 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▉ | 1142/1189 [1:49:35<02:37, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:24,112 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▉ | 1142/1189 [1:49:35<02:37, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:24,112 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1353, 'learning_rate': 7.402031930333818e-07, 'epoch': 0.96} 96%|█████████████████████████████████████████████████████████████████████████▉ | 1142/1189 [1:49:35<02:37, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:24,112 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 1143/1189 [1:49:38<02:27, 3.21s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:29,766 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 1144/1189 [1:49:40<02:16, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 1144/1189 [1:49:40<02:16, 3.03s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 1145/1189 [1:49:43<02:06, 2.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 1145/1189 [1:49:43<02:06, 2.87s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:35,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:35,683 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:37,655 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:37,655 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:39,433 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:39,433 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:40,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:40,955 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:42,808 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:23:42,808 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3997, 'learning_rate': 6.240928882438317e-07, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▌ | 1151/1189 [1:49:58<01:56, 3.07s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 1151/1189 [1:49:58<01:56, 3.07s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0219, 'learning_rate': 6.09579100145138e-07, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▌ | 1151/1189 [1:49:58<01:56, 3.07s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 1152/1189 [1:50:03<02:17, 3.73s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 1152/1189 [1:50:03<02:17, 3.73s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 1152/1189 [1:50:03<02:17, 3.73s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 1153/1189 [1:50:08<02:29, 4.15s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 1153/1189 [1:50:08<02:29, 4.15s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 1153/1189 [1:50:08<02:29, 4.15s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 1154/1189 [1:50:13<02:34, 4.43s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 1154/1189 [1:50:13<02:34, 4.43s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 1154/1189 [1:50:13<02:34, 4.43s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▊ | 1155/1189 [1:50:18<02:36, 4.60s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▊ | 1155/1189 [1:50:18<02:36, 4.60s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▊ | 1155/1189 [1:50:18<02:36, 4.60s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▊ | 1156/1189 [1:50:23<02:35, 4.72s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▊ | 1156/1189 [1:50:23<02:35, 4.72s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▊ | 1156/1189 [1:50:23<02:35, 4.72s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1157/1189 [1:50:28<02:33, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1157/1189 [1:50:28<02:33, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1157/1189 [1:50:28<02:33, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1157/1189 [1:50:28<02:33, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1354, 'learning_rate': 5.079825834542816e-07, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▉ | 1157/1189 [1:50:28<02:33, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1157/1189 [1:50:28<02:33, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 1159/1189 [1:50:38<02:27, 4.90s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 1159/1189 [1:50:38<02:27, 4.90s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 1159/1189 [1:50:38<02:27, 4.90s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 1160/1189 [1:50:43<02:22, 4.92s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 1160/1189 [1:50:43<02:22, 4.92s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 1160/1189 [1:50:43<02:22, 4.92s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 1161/1189 [1:50:48<02:17, 4.91s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 1161/1189 [1:50:48<02:17, 4.91s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 1161/1189 [1:50:48<02:17, 4.91s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 1162/1189 [1:50:53<02:11, 4.87s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 1162/1189 [1:50:53<02:11, 4.87s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 1162/1189 [1:50:53<02:11, 4.87s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▍ | 1164/1189 [1:51:02<02:00, 4.81s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▍ | 1164/1189 [1:51:02<02:00, 4.81s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▍ | 1164/1189 [1:51:02<02:00, 4.81s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▍ | 1165/1189 [1:51:07<01:55, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▍ | 1165/1189 [1:51:07<01:55, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▍ | 1165/1189 [1:51:07<01:55, 4.80s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 1166/1189 [1:51:12<01:49, 4.78s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 1166/1189 [1:51:12<01:49, 4.78s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 1166/1189 [1:51:12<01:49, 4.78s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 1167/1189 [1:51:17<01:44, 4.75s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 1167/1189 [1:51:17<01:44, 4.75s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 1167/1189 [1:51:17<01:44, 4.75s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▋ | 1168/1189 [1:51:21<01:38, 4.70s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▋ | 1168/1189 [1:51:21<01:38, 4.70s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▋ | 1168/1189 [1:51:21<01:38, 4.70s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▋ | 1169/1189 [1:51:26<01:33, 4.68s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▋ | 1169/1189 [1:51:26<01:33, 4.68s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 1170/1189 [1:51:30<01:28, 4.65s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 1170/1189 [1:51:30<01:28, 4.65s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1257, 'learning_rate': 3.3381712626995645e-07, 'epoch': 0.98} g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1431, 'learning_rate': 3.193033381712627e-07, 'epoch': 0.98} g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▉ | 1172/1189 [1:51:39<01:17, 4.56s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:25:34,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:25:34,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2092, 'learning_rate': 2.9027576197387524e-07, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-02-28 18:25:34,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:25:34,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 1174/1189 [1:51:48<01:07, 4.47s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 1174/1189 [1:51:48<01:07, 4.47s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 1174/1189 [1:51:48<01:07, 4.47s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 1175/1189 [1:51:52<01:01, 4.42s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 1175/1189 [1:51:52<01:01, 4.42s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 1175/1189 [1:51:52<01:01, 4.42s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▏| 1176/1189 [1:51:57<00:56, 4.35s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▏| 1176/1189 [1:51:57<00:56, 4.35s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▏| 1176/1189 [1:51:57<00:56, 4.35s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▏| 1177/1189 [1:52:01<00:51, 4.26s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▏| 1177/1189 [1:52:01<00:51, 4.26s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▏| 1177/1189 [1:52:01<00:51, 4.26s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▎| 1178/1189 [1:52:05<00:45, 4.17s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▎| 1178/1189 [1:52:05<00:45, 4.17s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▎| 1178/1189 [1:52:05<00:45, 4.17s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▎| 1179/1189 [1:52:09<00:40, 4.09s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▎| 1179/1189 [1:52:09<00:40, 4.09s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▎| 1179/1189 [1:52:09<00:40, 4.09s/it]g-point operations will not be computed-28 18:23:32,412 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍| 1180/1189 [1:52:12<00:36, 4.01s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:04,915 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍| 1181/1189 [1:52:16<00:31, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:04,915 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍| 1181/1189 [1:52:16<00:31, 3.92s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:04,915 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1438, 'learning_rate': 1.741654571843251e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▌| 1182/1189 [1:52:20<00:26, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:04,915 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌| 1182/1189 [1:52:20<00:26, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:04,915 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1192, 'learning_rate': 1.5965166908563135e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▌| 1182/1189 [1:52:20<00:26, 3.78s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:04,915 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌| 1183/1189 [1:52:23<00:21, 3.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌| 1183/1189 [1:52:23<00:21, 3.58s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▋| 1184/1189 [1:52:25<00:16, 3.35s/it][WARNING|modeling_utils.py:388] 2022-02-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:18,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:18,543 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:20,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:20,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:22,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:22,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2023, 'learning_rate': 8.708272859216255e-08, 'epoch': 1.0} [WARNING|modeling_utils.py:388] 2022-02-28 18:26:24,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-02-28 18:26:24,186 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4211, 'learning_rate': 5.805515239477504e-08, 'epoch': 1.0} [INFO|configuration_utils.py:438] 2022-02-28 18:26:25,638 >> Configuration saved in ./config.json52:35<00:00, 5.68s/it]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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|configuration_utils.py:438] 2022-02-28 18:26:42,449 >> Configuration saved in ./config.jsoncessor_config.jsons/it]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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|feature_extraction_utils.py:324] 2022-02-28 18:26:58,785 >> Configuration saved in ./preprocessor_config.jsons/it]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 35%|███▊ | 12.5M/35.7M [00:01<00:01, 13.0MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 83%|█████████▏ | 29.7M/35.7M [00:02<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.7M/35.7M [00:20<00:00, 15.9MB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|████████████| 35.7M/35.7M [03:29<00:00, 121kB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|████████████| 35.7M/35.7M [03:29<00:00, 121kB/s]g-point operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 02/28/2022 18:32:07 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search [INFO|modelcard.py:460] 2022-02-28 18:32:09,992 >> Dropping the following result as it does not have all the necessary fields:t operations will not be computed-28 18:26:14,762 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 0%| | 32.0k/35.8M [00:00> Could not estimate the number of tokens of the input, floating-point operations will not 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-20220228_163348-20lja62k/run-20lja62k.wandb: 31%|███▎ | 10.9M/35.8M [00:01<00:02, 11.4MB/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. Upload file wandb/run-20220228_163348-20lja62k/run-20lja62k.wandb: 31%|███▎ | 10.9M/35.8M [00:01<00:02, 11.4MB/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. 02/28/2022 18:32:15 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search 9257686..08366aa main -> main ***** train metrics ***** epoch = 1.0 train_loss = 4.2681 train_runtime = 1:52:37.01 train_samples = 28538 train_samples_per_second = 4.223 train_steps_per_second = 0.176 [INFO|trainer.py:2366] 2022-02-28 18:32:18,176 >> 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. 0%| | 0/221 [00:00> Saving model checkpoint to ./ | 3/221 [00:06<08:53, 2.45s/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|modeling_utils.py:1081] 2022-02-28 18:48:25,276 >> Model weights saved in ./pytorch_model.bin:06<08:53, 2.45s/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-20220228_163348-20lja62k/run-20lja62k.wandb: 51%|█████▌ | 18.2M/35.9M [00:01<00:00, 19.1MB/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-20220228_163348-20lja62k/run-20lja62k.wandb: 51%|█████▌ | 18.2M/35.9M [00:01<00:00, 19.1MB/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. 02/28/2022 18:48:54 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search Upload file wandb/run-20220228_163348-20lja62k/run-20lja62k.wandb: 100%|███████████| 35.9M/35.9M [00:02<00:00, 18.8MB/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.