0%| | 0/1189 [00:00> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:20:59,063 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%| | 1/1189 [00:05<1:55:48, 5.85s/it] 0%| | 1/1189 [00:05<1:55:48, 5.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:01,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0423, 'learning_rate': 0.0, 'epoch': 0.0} [WARNING|modeling_utils.py:388] 2022-03-01 08:21:04,248 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▏ | 2/1189 [00:11<1:47:57, 5.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:06,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:21:09,454 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▏ | 3/1189 [00:16<1:47:48, 5.45s/it] 0%|▏ | 3/1189 [00:16<1:47:48, 5.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:12,312 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:21:14,859 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 4/1189 [00:21<1:45:51, 5.36s/it] 0%|▎ | 4/1189 [00:21<1:45:51, 5.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:17,477 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:21:19,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 0%|▎ | 5/1189 [00:26<1:43:54, 5.27s/it] 0%|▎ | 5/1189 [00:26<1:43:54, 5.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:22,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9547, 'learning_rate': 2.4000000000000003e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-01 08:21:25,055 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 6/1189 [00:31<1:42:41, 5.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:27,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:21:30,175 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▍ | 7/1189 [00:37<1:42:01, 5.18s/it] 1%|▍ | 7/1189 [00:37<1:42:01, 5.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:32,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7239, 'learning_rate': 3.6e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-01 08:21:35,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 8/1189 [00:42<1:41:20, 5.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:37,843 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:21:40,316 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▌ | 9/1189 [00:47<1:40:22, 5.10s/it] 1%|▌ | 9/1189 [00:47<1:40:22, 5.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:42,854 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7796, 'learning_rate': 4.2e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-01 08:21:45,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▋ | 10/1189 [00:52<1:39:49, 5.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:47,816 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:21:50,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▋ | 11/1189 [00:57<1:38:38, 5.02s/it] 1%|▋ | 11/1189 [00:57<1:38:38, 5.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:52,679 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6947, 'learning_rate': 5.4e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-01 08:21:55,031 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 12/1189 [01:01<1:37:29, 4.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:21:57,498 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9776, 'learning_rate': 6.000000000000001e-07, 'epoch': 0.01} [WARNING|modeling_utils.py:388] 2022-03-01 08:21:59,876 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▊ | 13/1189 [01:06<1:36:39, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:02,362 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:04,721 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|▉ | 14/1189 [01:11<1:36:03, 4.90s/it] 1%|▉ | 14/1189 [01:11<1:36:03, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:07,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:09,529 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6509, 'learning_rate': 7.2e-07, 'epoch': 0.01} 1%|▉ | 15/1189 [01:16<1:35:24, 4.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:11,968 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:14,278 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█ | 16/1189 [01:21<1:34:35, 4.84s/it] 1%|█ | 16/1189 [01:21<1:34:35, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:16,727 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:19,079 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 1%|█▏ | 17/1189 [01:25<1:34:16, 4.83s/it] 1%|█▏ | 17/1189 [01:25<1:34:16, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:21,497 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:23,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9677, 'learning_rate': 9e-07, 'epoch': 0.02} 2%|█▏ | 18/1189 [01:30<1:33:28, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:26,187 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:28,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7116, 'learning_rate': 9.600000000000001e-07, 'epoch': 0.02} 2%|█▎ | 19/1189 [01:35<1:32:28, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:30,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:32,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▎ | 20/1189 [01:39<1:31:25, 4.69s/it] 2%|█▎ | 20/1189 [01:39<1:31:25, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:35,328 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:37,575 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▍ | 21/1189 [01:44<1:30:42, 4.66s/it] 2%|█▍ | 21/1189 [01:44<1:30:42, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:39,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:42,129 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▍ | 22/1189 [01:48<1:30:01, 4.63s/it] 2%|█▍ | 22/1189 [01:48<1:30:01, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:44,456 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8528, 'learning_rate': 1.2000000000000002e-06, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-01 08:22:46,714 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 23/1189 [01:53<1:29:41, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:49,066 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:51,291 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▌ | 24/1189 [01:58<1:29:23, 4.60s/it] 2%|█▌ | 24/1189 [01:58<1:29:23, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:53,614 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:22:55,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 25/1189 [02:02<1:28:39, 4.57s/it] 2%|█▋ | 25/1189 [02:02<1:28:39, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:22:58,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:00,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▋ | 26/1189 [02:07<1:27:54, 4.54s/it] 2%|█▋ | 26/1189 [02:07<1:27:54, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:02,506 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:04,669 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 27/1189 [02:11<1:27:14, 4.50s/it] 2%|█▊ | 27/1189 [02:11<1:27:14, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:06,943 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:09,096 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▊ | 28/1189 [02:15<1:26:42, 4.48s/it] 2%|█▊ | 28/1189 [02:15<1:26:42, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:11,290 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6476, 'learning_rate': 1.5599999999999999e-06, 'epoch': 0.02} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:13,423 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 2%|█▉ | 29/1189 [02:20<1:25:44, 4.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:15,614 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:17,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|█▉ | 30/1189 [02:24<1:24:45, 4.39s/it] 3%|█▉ | 30/1189 [02:24<1:24:45, 4.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:19,874 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:21,950 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██ | 31/1189 [02:28<1:23:52, 4.35s/it] 3%|██ | 31/1189 [02:28<1:23:52, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:24,094 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6104, 'learning_rate': 1.74e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:26,164 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▏ | 32/1189 [02:33<1:23:02, 4.31s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:28,315 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:30,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7272, 'learning_rate': 1.8e-06, 'epoch': 0.03} 3%|██▏ | 33/1189 [02:37<1:22:19, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:32,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:34,442 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 34/1189 [02:41<1:21:09, 4.22s/it] 3%|██▎ | 34/1189 [02:41<1:21:09, 4.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:36,480 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5867, 'learning_rate': 1.9200000000000003e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:38,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▎ | 35/1189 [02:45<1:19:41, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:40,448 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9098, 'learning_rate': 1.98e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:42,370 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 36/1189 [02:49<1:18:31, 4.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:44,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7237, 'learning_rate': 2.0400000000000004e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:46,179 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▍ | 37/1189 [02:53<1:16:53, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:48,087 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5612, 'learning_rate': 2.1000000000000002e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:49,883 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 38/1189 [02:56<1:15:04, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:51,776 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.0326, 'learning_rate': 2.16e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:23:53,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▌ | 39/1189 [03:00<1:13:22, 3.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:55,336 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:23:57,064 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6771, 'learning_rate': 2.22e-06, 'epoch': 0.03} 3%|██▋ | 40/1189 [03:03<1:11:43, 3.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:23:58,874 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5023, 'learning_rate': 2.28e-06, 'epoch': 0.03} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:00,492 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 3%|██▋ | 41/1189 [03:07<1:09:50, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:02,158 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5602, 'learning_rate': 2.34e-06, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:03,688 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 42/1189 [03:10<1:07:10, 3.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:05,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5688, 'learning_rate': 2.4000000000000003e-06, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:06,686 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▊ | 43/1189 [03:13<1:04:09, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:08,151 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:24:09,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|██▉ | 44/1189 [03:16<1:00:34, 3.17s/it] 4%|██▉ | 44/1189 [03:16<1:00:34, 3.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:10,752 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.8205, 'learning_rate': 2.52e-06, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:11,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███ | 45/1189 [03:18<56:27, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:13,068 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7995, 'learning_rate': 2.58e-06, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:14,065 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 46/1189 [03:20<51:54, 2.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:15,127 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.9812, 'learning_rate': 2.6399999999999997e-06, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:16,032 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▏ | 47/1189 [03:22<47:32, 2.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:16,966 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 5.1944, 'learning_rate': 2.7e-06, 'epoch': 0.04} [WARNING|modeling_utils.py:388] 2022-03-01 08:24:17,730 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 48/1189 [03:24<42:55, 2.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:18,522 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:24:19,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▎ | 49/1189 [03:26<38:14, 2.01s/it] {'loss': 5.3073, 'learning_rate': 2.76e-06, 'epoch': 0.04} 4%|███▎ | 49/1189 [03:26<38:14, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:19,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:24:20,957 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 50/1189 [03:27<36:35, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:23,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 50/1189 [03:27<36:35, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:23,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 51/1189 [03:33<57:21, 3.02s/it]g-point operations will not be computed-01 08:24:23,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 51/1189 [03:33<57:21, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:29,169 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it]g-point operations will not be computed-01 08:24:29,169 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it]g-point operations will not be computed-01 08:24:29,169 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:34,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▍ | 52/1189 [03:38<1:10:08, 3.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:34,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 53/1189 [03:43<1:17:59, 4.12s/it]g-point operations will not be computed-01 08:24:34,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 4%|███▌ | 53/1189 [03:43<1:17:59, 4.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 54/1189 [03:48<1:22:32, 4.36s/it]g-point operations will not be computed-01 08:24:39,338 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 54/1189 [03:48<1:22:32, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:44,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▌ | 54/1189 [03:48<1:22:32, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:44,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 55/1189 [03:53<1:26:21, 4.57s/it]g-point operations will not be computed-01 08:24:44,379 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 55/1189 [03:53<1:26:21, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:49,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it]g-point operations will not be computed-01 08:24:49,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it]g-point operations will not be computed-01 08:24:49,401 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:54,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▋ | 56/1189 [03:58<1:28:33, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:54,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:03<1:30:07, 4.78s/it]g-point operations will not be computed-01 08:24:54,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:03<1:30:07, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:59,357 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 57/1189 [04:03<1:30:07, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:24:59,357 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 58/1189 [04:08<1:30:58, 4.83s/it]g-point operations will not be computed-01 08:24:59,357 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▊ | 58/1189 [04:08<1:30:58, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:04,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 59/1189 [04:13<1:31:01, 4.83s/it]g-point operations will not be computed-01 08:25:04,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 59/1189 [04:13<1:31:01, 4.83s/it]g-point operations will not be computed-01 08:25:04,178 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 59/1189 [04:13<1:31:01, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:09,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it]g-point operations will not be computed-01 08:25:09,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it]g-point operations will not be computed-01 08:25:09,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:13,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|███▉ | 60/1189 [04:18<1:31:09, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:13,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 61/1189 [04:23<1:30:50, 4.83s/it]g-point operations will not be computed-01 08:25:13,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 61/1189 [04:23<1:30:50, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:18,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 62/1189 [04:27<1:30:27, 4.82s/it]g-point operations will not be computed-01 08:25:18,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 62/1189 [04:27<1:30:27, 4.82s/it]g-point operations will not be computed-01 08:25:18,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████ | 62/1189 [04:27<1:30:27, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:23,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it]g-point operations will not be computed-01 08:25:23,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it]g-point operations will not be computed-01 08:25:23,468 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:28,293 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▏ | 63/1189 [04:32<1:30:07, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:28,293 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 64/1189 [04:37<1:30:09, 4.81s/it]g-point operations will not be computed-01 08:25:28,293 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 64/1189 [04:37<1:30:09, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:33,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 65/1189 [04:42<1:29:17, 4.77s/it]g-point operations will not be computed-01 08:25:33,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 65/1189 [04:42<1:29:17, 4.77s/it]g-point operations will not be computed-01 08:25:33,029 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 5%|████▎ | 65/1189 [04:42<1:29:17, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:37,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it]g-point operations will not be computed-01 08:25:37,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it]g-point operations will not be computed-01 08:25:37,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:42,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 66/1189 [04:46<1:28:39, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:42,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 67/1189 [04:51<1:28:01, 4.71s/it]g-point operations will not be computed-01 08:25:42,335 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▍ | 67/1189 [04:51<1:28:01, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:46,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 68/1189 [04:55<1:27:00, 4.66s/it]g-point operations will not be computed-01 08:25:46,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 68/1189 [04:55<1:27:00, 4.66s/it]g-point operations will not be computed-01 08:25:46,907 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 68/1189 [04:55<1:27:00, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:51,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 69/1189 [05:00<1:26:39, 4.64s/it]g-point operations will not be computed-01 08:25:51,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 69/1189 [05:00<1:26:39, 4.64s/it]g-point operations will not be computed-01 08:25:51,526 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▌ | 69/1189 [05:00<1:26:39, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:25:56,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 70/1189 [05:05<1:25:56, 4.61s/it]g-point operations will not be computed-01 08:25:56,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 70/1189 [05:05<1:25:56, 4.61s/it]g-point operations will not be computed-01 08:25:56,073 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 70/1189 [05:05<1:25:56, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:00,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it]g-point operations will not be computed-01 08:26:00,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it]g-point operations will not be computed-01 08:26:00,603 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:05,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▋ | 71/1189 [05:09<1:25:28, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:05,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 72/1189 [05:14<1:25:14, 4.58s/it]g-point operations will not be computed-01 08:26:05,149 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 72/1189 [05:14<1:25:14, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:09,678 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 72/1189 [05:14<1:25:14, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:09,678 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 73/1189 [05:18<1:25:00, 4.57s/it]g-point operations will not be computed-01 08:26:09,678 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 73/1189 [05:18<1:25:00, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:14,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▊ | 73/1189 [05:18<1:25:00, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:14,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 74/1189 [05:23<1:24:57, 4.57s/it]g-point operations will not be computed-01 08:26:14,285 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 74/1189 [05:23<1:24:57, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:18,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it]g-point operations will not be computed-01 08:26:18,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it]g-point operations will not be computed-01 08:26:18,803 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:23,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|████▉ | 75/1189 [05:27<1:24:19, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:23,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 76/1189 [05:32<1:23:22, 4.49s/it]g-point operations will not be computed-01 08:26:23,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 76/1189 [05:32<1:23:22, 4.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:27,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 76/1189 [05:32<1:23:22, 4.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:27,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 77/1189 [05:36<1:22:32, 4.45s/it]g-point operations will not be computed-01 08:26:27,623 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 6%|█████ | 77/1189 [05:36<1:22:32, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:31,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 78/1189 [05:40<1:21:52, 4.42s/it]g-point operations will not be computed-01 08:26:31,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 78/1189 [05:40<1:21:52, 4.42s/it]g-point operations will not be computed-01 08:26:31,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 78/1189 [05:40<1:21:52, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:36,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 79/1189 [05:45<1:21:04, 4.38s/it]g-point operations will not be computed-01 08:26:36,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 79/1189 [05:45<1:21:04, 4.38s/it]g-point operations will not be computed-01 08:26:36,283 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▏ | 79/1189 [05:45<1:21:04, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:40,547 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:26:42,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:26:40,547 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:26:42,652 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:26:40,547 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▎ | 80/1189 [05:49<1:20:32, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:44,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 81/1189 [05:53<1:19:33, 4.31s/it]g-point operations will not be computed-01 08:26:44,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 81/1189 [05:53<1:19:33, 4.31s/it]g-point operations will not be computed-01 08:26:44,842 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 81/1189 [05:53<1:19:33, 4.31s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:48,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 82/1189 [05:57<1:18:37, 4.26s/it]g-point operations will not be computed-01 08:26:48,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 82/1189 [05:57<1:18:37, 4.26s/it]g-point operations will not be computed-01 08:26:48,987 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▍ | 82/1189 [05:57<1:18:37, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:53,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:01<1:17:30, 4.20s/it]g-point operations will not be computed-01 08:26:53,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:01<1:17:30, 4.20s/it]g-point operations will not be computed-01 08:26:53,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 83/1189 [06:01<1:17:30, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:26:57,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 84/1189 [06:05<1:16:10, 4.14s/it]g-point operations will not be computed-01 08:26:57,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 84/1189 [06:05<1:16:10, 4.14s/it]g-point operations will not be computed-01 08:26:57,107 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▌ | 84/1189 [06:05<1:16:10, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:01,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 85/1189 [06:09<1:14:41, 4.06s/it]g-point operations will not be computed-01 08:27:01,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 85/1189 [06:09<1:14:41, 4.06s/it]g-point operations will not be computed-01 08:27:01,053 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 85/1189 [06:09<1:14:41, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:04,931 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 86/1189 [06:13<1:13:34, 4.00s/it]g-point operations will not be computed-01 08:27:04,931 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 86/1189 [06:13<1:13:34, 4.00s/it]g-point operations will not be computed-01 08:27:04,931 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▋ | 86/1189 [06:13<1:13:34, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 87/1189 [06:17<1:12:09, 3.93s/it]g-point operations will not be computed-01 08:27:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 87/1189 [06:17<1:12:09, 3.93s/it]g-point operations will not be computed-01 08:27:08,738 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 87/1189 [06:17<1:12:09, 3.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:12,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 88/1189 [06:21<1:10:32, 3.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▊ | 88/1189 [06:21<1:10:32, 3.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▉ | 89/1189 [06:24<1:08:44, 3.75s/it]g-point operations will not be computed-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▉ | 89/1189 [06:24<1:08:44, 3.75s/it]g-point operations will not be computed-01 08:27:16,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 7%|█████▉ | 89/1189 [06:24<1:08:44, 3.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:19,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 90/1189 [06:27<1:06:25, 3.63s/it]g-point operations will not be computed-01 08:27:19,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 90/1189 [06:27<1:06:25, 3.63s/it]g-point operations will not be computed-01 08:27:19,481 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|█████▉ | 90/1189 [06:27<1:06:25, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:22,749 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 91/1189 [06:31<1:03:55, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:25,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 91/1189 [06:31<1:03:55, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:25,849 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4315, 'learning_rate': 5.22e-06, 'epoch': 0.08} [WARNING|modeling_utils.py:388] 2022-03-01 08:27:27,324 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 92/1189 [06:34<1:01:32, 3.37s/it] 8%|██████ | 92/1189 [06:34<1:01:32, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████ | 92/1189 [06:34<1:01:32, 3.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:28,794 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▎ | 93/1189 [06:36<58:18, 3.19s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:31,443 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 94/1189 [06:39<54:31, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:33,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 94/1189 [06:39<54:31, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:33,844 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 95/1189 [06:41<50:45, 2.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:36,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▍ | 95/1189 [06:41<50:45, 2.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:36,040 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 96/1189 [06:43<46:43, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:37,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 96/1189 [06:43<46:43, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:37,958 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 97/1189 [06:45<42:34, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:39,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▌ | 97/1189 [06:45<42:34, 2.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:39,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 99/1189 [06:48<35:01, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:41,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:27:41,897 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 99/1189 [06:48<35:01, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:41,265 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6356, 'learning_rate': 5.64e-06, 'epoch': 0.08} 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:42,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:27:43,679 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:42,600 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:46,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▋ | 100/1189 [06:50<34:12, 1.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:46,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▊ | 101/1189 [06:55<52:54, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:46,513 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▊ | 101/1189 [06:55<52:54, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:51,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 8%|██████▊ | 101/1189 [06:55<52:54, 2.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:51,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 102/1189 [07:00<1:04:48, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:51,602 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 102/1189 [07:00<1:04:48, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:56,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▋ | 102/1189 [07:00<1:04:48, 3.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:56,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 103/1189 [07:06<1:12:50, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:27:56,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 103/1189 [07:06<1:12:50, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:01,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 104/1189 [07:10<1:17:48, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:01,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 104/1189 [07:10<1:17:48, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:01,690 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▊ | 104/1189 [07:10<1:17:48, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:06,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:06,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:06,692 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:11,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 105/1189 [07:15<1:21:13, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:11,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:11,606 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:16,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:16,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|██████▉ | 106/1189 [07:20<1:23:57, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:16,699 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 107/1189 [07:25<1:25:48, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:21,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 107/1189 [07:25<1:25:48, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:21,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 108/1189 [07:30<1:26:36, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:21,646 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 108/1189 [07:30<1:26:36, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:26,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████ | 108/1189 [07:30<1:26:36, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:26,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:35<1:27:02, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:26,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:35<1:27:02, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:31,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 109/1189 [07:35<1:27:02, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:31,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 110/1189 [07:40<1:27:35, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:31,451 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 110/1189 [07:40<1:27:35, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:36,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▏ | 110/1189 [07:40<1:27:35, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:36,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 111/1189 [07:45<1:27:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:36,319 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 111/1189 [07:45<1:27:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:41,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:41,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:41,115 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:45,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 9%|███████▎ | 112/1189 [07:50<1:26:58, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:45,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 113/1189 [07:55<1:26:29, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:45,972 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 113/1189 [07:55<1:26:29, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 113/1189 [07:55<1:26:29, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 114/1189 [07:59<1:26:28, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:50,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▍ | 114/1189 [07:59<1:26:28, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:55,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 115/1189 [08:04<1:26:49, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:55,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 115/1189 [08:04<1:26:49, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:28:55,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:00,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:00,449 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:05,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▌ | 116/1189 [08:09<1:26:21, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:05,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 117/1189 [08:14<1:25:45, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:05,219 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 117/1189 [08:14<1:25:45, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:09,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 118/1189 [08:19<1:25:05, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:09,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 118/1189 [08:19<1:25:05, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:09,946 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▋ | 118/1189 [08:19<1:25:05, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:14,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 119/1189 [08:23<1:24:55, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:14,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 119/1189 [08:23<1:24:55, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:14,643 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.189, 'learning_rate': 6.900000000000001e-06, 'epoch': 0.1} 10%|███████▊ | 119/1189 [08:23<1:24:55, 4.76s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:19,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 120/1189 [08:28<1:24:23, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:19,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 120/1189 [08:28<1:24:23, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:19,374 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▊ | 120/1189 [08:28<1:24:23, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:24,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 121/1189 [08:33<1:24:09, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:24,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 121/1189 [08:33<1:24:09, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:24,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|███████▉ | 121/1189 [08:33<1:24:09, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:28,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:28,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:28,702 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:33,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 122/1189 [08:37<1:23:32, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:33,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 123/1189 [08:42<1:22:41, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:33,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 123/1189 [08:42<1:22:41, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:37,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████ | 123/1189 [08:42<1:22:41, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:37,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████▏ | 124/1189 [08:46<1:21:39, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:37,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 10%|████████▏ | 124/1189 [08:46<1:21:39, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:42,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 125/1189 [08:51<1:21:07, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:42,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 125/1189 [08:51<1:21:07, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:42,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▏ | 125/1189 [08:51<1:21:07, 4.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:46,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 126/1189 [08:55<1:20:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:46,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 126/1189 [08:55<1:20:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:46,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 126/1189 [08:55<1:20:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:51,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:51,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:51,253 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▎ | 127/1189 [09:00<1:19:46, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 128/1189 [09:04<1:18:44, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:55,613 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 129/1189 [09:08<1:18:04, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:59,968 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 129/1189 [09:08<1:18:04, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:29:59,968 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▍ | 129/1189 [09:08<1:18:04, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:13<1:17:59, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:04,402 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:13<1:17:59, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:08,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 130/1189 [09:13<1:17:59, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:08,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 131/1189 [09:17<1:17:14, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:08,731 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 131/1189 [09:17<1:17:14, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:12,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▌ | 131/1189 [09:17<1:17:14, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:12,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 132/1189 [09:21<1:16:17, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:12,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 132/1189 [09:21<1:16:17, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:17,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 132/1189 [09:21<1:16:17, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:17,188 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 133/1189 [09:26<1:15:41, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:21,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▋ | 133/1189 [09:26<1:15:41, 4.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:21,297 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 134/1189 [09:30<1:14:09, 4.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:25,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:30:25,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:30:25,333 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▊ | 135/1189 [09:34<1:12:40, 4.14s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:29,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 136/1189 [09:37<1:11:12, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:29,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 136/1189 [09:37<1:11:12, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:29,236 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 11%|████████▉ | 136/1189 [09:37<1:11:12, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:33,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|████████▉ | 137/1189 [09:41<1:09:49, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:33,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|████████▉ | 137/1189 [09:41<1:09:49, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:33,070 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|████████▉ | 137/1189 [09:41<1:09:49, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:36,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 138/1189 [09:45<1:08:30, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:36,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 138/1189 [09:45<1:08:30, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:36,805 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 138/1189 [09:45<1:08:30, 3.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:40,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 139/1189 [09:49<1:06:42, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:40,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████ | 139/1189 [09:49<1:06:42, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:40,512 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:44,041 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:44,041 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:47,390 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 140/1189 [09:52<1:04:57, 3.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:47,390 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▏ | 141/1189 [09:55<1:02:05, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:47,390 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 142/1189 [09:58<59:04, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:50,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 142/1189 [09:58<59:04, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:50,459 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 142/1189 [09:58<59:04, 3.39s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:53,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 143/1189 [10:01<55:50, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:53,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▌ | 143/1189 [10:01<55:50, 3.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:53,360 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1636, 'learning_rate': 8.340000000000001e-06, 'epoch': 0.12} 12%|█████████▋ | 144/1189 [10:04<52:43, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:56,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▋ | 144/1189 [10:04<52:43, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:56,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 145/1189 [10:06<49:54, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:30:58,567 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 145/1189 [10:06<49:54, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:00,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▊ | 145/1189 [10:06<49:54, 2.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:00,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.6044, 'learning_rate': 8.52e-06, 'epoch': 0.12} 12%|█████████▉ | 147/1189 [10:10<42:27, 2.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:03,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▉ | 147/1189 [10:10<42:27, 2.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:03,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▉ | 148/1189 [10:12<38:40, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:04,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 12%|█████████▉ | 148/1189 [10:12<38:40, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:04,845 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 149/1189 [10:13<34:44, 2.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:07,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 149/1189 [10:13<34:44, 2.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:07,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:15<33:41, 1.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:07,806 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:15<33:41, 1.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:11,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 150/1189 [10:15<33:41, 1.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:11,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 151/1189 [10:21<52:26, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:11,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 151/1189 [10:21<52:26, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:17,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 151/1189 [10:21<52:26, 3.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:17,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 152/1189 [10:26<1:03:38, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:17,138 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 152/1189 [10:26<1:03:38, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:22,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|█████████▉ | 152/1189 [10:26<1:03:38, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:22,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 153/1189 [10:31<1:11:20, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:22,358 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 153/1189 [10:31<1:11:20, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:27,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 153/1189 [10:31<1:11:20, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:27,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 154/1189 [10:36<1:16:51, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:27,509 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████ | 154/1189 [10:36<1:16:51, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:32,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:32,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:32,658 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:37,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 155/1189 [10:41<1:20:01, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:37,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 156/1189 [10:47<1:22:15, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:37,726 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▏ | 156/1189 [10:47<1:22:15, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:47,766 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 157/1189 [10:52<1:23:11, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:47,766 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 158/1189 [10:57<1:24:00, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:47,766 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▎ | 158/1189 [10:57<1:24:00, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:52,765 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:52,765 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:52,765 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.98, 'learning_rate': 9.36e-06, 'epoch': 0.13} 13%|██████████▍ | 159/1189 [11:02<1:24:34, 4.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 161/1189 [11:11<1:24:40, 4.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▌ | 161/1189 [11:11<1:24:40, 4.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2868, 'learning_rate': 9.42e-06, 'epoch': 0.14} 14%|██████████▋ | 162/1189 [11:16<1:24:07, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 162/1189 [11:16<1:24:07, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2953, 'learning_rate': 9.48e-06, 'epoch': 0.14} 14%|██████████▋ | 162/1189 [11:16<1:24:07, 4.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 163/1189 [11:21<1:23:35, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▋ | 163/1189 [11:21<1:23:35, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 164/1189 [11:26<1:23:02, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 164/1189 [11:26<1:23:02, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0061, 'learning_rate': 9.600000000000001e-06, 'epoch': 0.14} 14%|██████████▊ | 165/1189 [11:31<1:21:58, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▊ | 165/1189 [11:31<1:21:58, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2366, 'learning_rate': 9.66e-06, 'epoch': 0.14} 14%|██████████▊ | 165/1189 [11:31<1:21:58, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 166/1189 [11:35<1:21:15, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 166/1189 [11:35<1:21:15, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 166/1189 [11:35<1:21:15, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 167/1189 [11:40<1:20:54, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|██████████▉ | 167/1189 [11:40<1:20:54, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 168/1189 [11:45<1:20:17, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 168/1189 [11:45<1:20:17, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1252, 'learning_rate': 9.84e-06, 'epoch': 0.14} 14%|███████████ | 169/1189 [11:49<1:20:30, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████ | 169/1189 [11:49<1:20:30, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3622, 'learning_rate': 9.9e-06, 'epoch': 0.14} 14%|███████████ | 169/1189 [11:49<1:20:30, 4.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 170/1189 [11:54<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 170/1189 [11:54<1:19:49, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 171/1189 [11:59<1:18:58, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▏ | 171/1189 [11:59<1:18:58, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2973, 'learning_rate': 1.002e-05, 'epoch': 0.14} 14%|███████████▎ | 172/1189 [12:03<1:18:24, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 14%|███████████▎ | 172/1189 [12:03<1:18:24, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.116, 'learning_rate': 1.008e-05, 'epoch': 0.14} 15%|███████████▎ | 173/1189 [12:08<1:18:20, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▎ | 173/1189 [12:08<1:18:20, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0488, 'learning_rate': 1.0140000000000001e-05, 'epoch': 0.15} 15%|███████████▎ | 173/1189 [12:08<1:18:20, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▍ | 174/1189 [12:12<1:18:05, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:33:10,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:33:10,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:33:10,424 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2722, 'learning_rate': 1.0260000000000002e-05, 'epoch': 0.15} 15%|███████████▌ | 176/1189 [12:21<1:16:00, 4.50s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 176/1189 [12:21<1:16:00, 4.50s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2434, 'learning_rate': 1.032e-05, 'epoch': 0.15} 15%|███████████▌ | 177/1189 [12:25<1:15:01, 4.45s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▌ | 177/1189 [12:25<1:15:01, 4.45s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3755, 'learning_rate': 1.0379999999999999e-05, 'epoch': 0.15} 15%|███████████▋ | 178/1189 [12:30<1:14:27, 4.42s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 178/1189 [12:30<1:14:27, 4.42s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1772, 'learning_rate': 1.044e-05, 'epoch': 0.15} 15%|███████████▋ | 179/1189 [12:34<1:13:46, 4.38s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▋ | 179/1189 [12:34<1:13:46, 4.38s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2407, 'learning_rate': 1.05e-05, 'epoch': 0.15} 15%|███████████▊ | 180/1189 [12:38<1:13:11, 4.35s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▊ | 180/1189 [12:38<1:13:11, 4.35s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3553, 'learning_rate': 1.0559999999999999e-05, 'epoch': 0.15} 15%|███████████▊ | 181/1189 [12:43<1:12:51, 4.34s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▊ | 181/1189 [12:43<1:12:51, 4.34s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.327, 'learning_rate': 1.062e-05, 'epoch': 0.15} 15%|███████████▉ | 182/1189 [12:47<1:11:44, 4.27s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|███████████▉ | 182/1189 [12:47<1:11:44, 4.27s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3378, 'learning_rate': 1.068e-05, 'epoch': 0.15} 15%|████████████ | 183/1189 [12:51<1:10:55, 4.23s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 183/1189 [12:51<1:10:55, 4.23s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2012, 'learning_rate': 1.074e-05, 'epoch': 0.15} 15%|████████████ | 183/1189 [12:51<1:10:55, 4.23s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 184/1189 [12:55<1:09:49, 4.17s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 184/1189 [12:55<1:09:49, 4.17s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 15%|████████████ | 184/1189 [12:55<1:09:49, 4.17s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 185/1189 [12:59<1:08:51, 4.11s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 185/1189 [12:59<1:08:51, 4.11s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 185/1189 [12:59<1:08:51, 4.11s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 186/1189 [13:03<1:07:43, 4.05s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 186/1189 [13:03<1:07:43, 4.05s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▏ | 186/1189 [13:03<1:07:43, 4.05s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 187/1189 [13:07<1:06:18, 3.97s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 187/1189 [13:07<1:06:18, 3.97s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 187/1189 [13:07<1:06:18, 3.97s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▎ | 188/1189 [13:10<1:04:49, 3.89s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:34:07,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:34:07,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.422, 'learning_rate': 1.11e-05, 'epoch': 0.16} [WARNING|modeling_utils.py:388] 2022-03-01 08:34:07,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 190/1189 [13:17<1:00:13, 3.62s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 190/1189 [13:17<1:00:13, 3.62s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▍ | 190/1189 [13:17<1:00:13, 3.62s/it]g-point operations will not be computed-01 08:31:57,745 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▊ | 191/1189 [13:20<57:36, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▊ | 191/1189 [13:20<57:36, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▉ | 192/1189 [13:23<54:41, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|████████████▉ | 192/1189 [13:23<54:41, 3.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:34:19,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:34:19,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:34:19,478 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:15,430 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 194/1189 [13:28<48:40, 2.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:23,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 194/1189 [13:28<48:40, 2.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:23,243 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 195/1189 [13:31<45:37, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:25,479 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████ | 195/1189 [13:31<45:37, 2.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:25,479 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████▏ | 196/1189 [13:33<42:26, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:27,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 16%|█████████████▏ | 196/1189 [13:33<42:26, 2.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:27,505 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 197/1189 [13:35<39:19, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:29,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 197/1189 [13:35<39:19, 2.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:29,368 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5566, 'learning_rate': 1.164e-05, 'epoch': 0.17} 17%|█████████████▎ | 198/1189 [13:37<36:16, 2.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:31,002 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3267, 'learning_rate': 1.1760000000000001e-05, 'epoch': 0.17} 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 200/1189 [13:40<31:52, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 201/1189 [13:45<49:14, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 201/1189 [13:45<49:14, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 202/1189 [13:50<59:57, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 202/1189 [13:50<59:57, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1833, 'learning_rate': 1.1880000000000001e-05, 'epoch': 0.17} 17%|█████████████▌ | 202/1189 [13:50<59:57, 3.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1851, 'learning_rate': 1.2e-05, 'epoch': 0.17} 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▎ | 203/1189 [13:55<1:06:36, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 205/1189 [14:05<1:14:22, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▍ | 205/1189 [14:05<1:14:22, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 206/1189 [14:10<1:16:12, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 206/1189 [14:10<1:16:12, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1966, 'learning_rate': 1.2120000000000001e-05, 'epoch': 0.17} 17%|█████████████▌ | 206/1189 [14:10<1:16:12, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 207/1189 [14:15<1:17:44, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 207/1189 [14:15<1:17:44, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▌ | 207/1189 [14:15<1:17:44, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3371, 'learning_rate': 1.2299999999999999e-05, 'epoch': 0.18} 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 17%|█████████████▋ | 208/1189 [14:20<1:18:28, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 210/1189 [14:30<1:19:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 210/1189 [14:30<1:19:07, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.217, 'learning_rate': 1.242e-05, 'epoch': 0.18} 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2961, 'learning_rate': 1.2479999999999999e-05, 'epoch': 0.18} 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▊ | 211/1189 [14:35<1:19:26, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 213/1189 [14:45<1:18:32, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|█████████████▉ | 213/1189 [14:45<1:18:32, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 214/1189 [14:49<1:17:59, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 214/1189 [14:49<1:17:59, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2395, 'learning_rate': 1.26e-05, 'epoch': 0.18} 18%|██████████████ | 215/1189 [14:54<1:17:26, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████ | 215/1189 [14:54<1:17:26, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3181, 'learning_rate': 1.2659999999999999e-05, 'epoch': 0.18} 18%|██████████████ | 215/1189 [14:54<1:17:26, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 216/1189 [14:59<1:17:04, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 216/1189 [14:59<1:17:04, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 217/1189 [15:03<1:16:33, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▏ | 217/1189 [15:03<1:16:33, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3477, 'learning_rate': 1.278e-05, 'epoch': 0.18} 18%|██████████████▎ | 218/1189 [15:08<1:16:22, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 218/1189 [15:08<1:16:22, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2062, 'learning_rate': 1.284e-05, 'epoch': 0.18} 18%|██████████████▎ | 219/1189 [15:13<1:16:10, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 18%|██████████████▎ | 219/1189 [15:13<1:16:10, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.9255, 'learning_rate': 1.29e-05, 'epoch': 0.18} 18%|██████████████▎ | 219/1189 [15:13<1:16:10, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 220/1189 [15:17<1:15:37, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 220/1189 [15:17<1:15:37, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 221/1189 [15:22<1:14:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▍ | 221/1189 [15:22<1:14:50, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.212, 'learning_rate': 1.302e-05, 'epoch': 0.19} 19%|██████████████▌ | 222/1189 [15:26<1:14:07, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▌ | 222/1189 [15:26<1:14:07, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5293, 'learning_rate': 1.308e-05, 'epoch': 0.19} 19%|██████████████▋ | 223/1189 [15:31<1:13:42, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 223/1189 [15:31<1:13:42, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2978, 'learning_rate': 1.314e-05, 'epoch': 0.19} 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3409, 'learning_rate': 1.32e-05, 'epoch': 0.19} 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1193, 'learning_rate': 1.326e-05, 'epoch': 0.19} 19%|██████████████▋ | 224/1189 [15:35<1:13:13, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2107, 'learning_rate': 1.338e-05, 'epoch': 0.19} [WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:36:37,992 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 228/1189 [15:53<1:11:02, 4.44s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 228/1189 [15:53<1:11:02, 4.44s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|██████████████▉ | 228/1189 [15:53<1:11:02, 4.44s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 229/1189 [15:57<1:10:02, 4.38s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 229/1189 [15:57<1:10:02, 4.38s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 229/1189 [15:57<1:10:02, 4.38s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 230/1189 [16:02<1:09:20, 4.34s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 230/1189 [16:02<1:09:20, 4.34s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████ | 230/1189 [16:02<1:09:20, 4.34s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████▏ | 231/1189 [16:06<1:08:41, 4.30s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████▏ | 231/1189 [16:06<1:08:41, 4.30s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 19%|███████████████▏ | 231/1189 [16:06<1:08:41, 4.30s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▏ | 232/1189 [16:10<1:07:42, 4.24s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▏ | 232/1189 [16:10<1:07:42, 4.24s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▏ | 232/1189 [16:10<1:07:42, 4.24s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 233/1189 [16:14<1:07:07, 4.21s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 233/1189 [16:14<1:07:07, 4.21s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 233/1189 [16:14<1:07:07, 4.21s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 234/1189 [16:18<1:05:55, 4.14s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 234/1189 [16:18<1:05:55, 4.14s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▎ | 234/1189 [16:18<1:05:55, 4.14s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 235/1189 [16:22<1:04:47, 4.08s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 235/1189 [16:22<1:04:47, 4.08s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 235/1189 [16:22<1:04:47, 4.08s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 236/1189 [16:26<1:03:41, 4.01s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 236/1189 [16:26<1:03:41, 4.01s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▍ | 236/1189 [16:26<1:03:41, 4.01s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 237/1189 [16:30<1:02:43, 3.95s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 237/1189 [16:30<1:02:43, 3.95s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 237/1189 [16:30<1:02:43, 3.95s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 238/1189 [16:33<1:01:37, 3.89s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 238/1189 [16:33<1:01:37, 3.89s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▌ | 238/1189 [16:33<1:01:37, 3.89s/it]g-point operations will not be computed-01 08:34:32,410 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 239/1189 [16:37<1:00:28, 3.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|███████████████▋ | 239/1189 [16:37<1:00:28, 3.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 240/1189 [16:41<59:12, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 240/1189 [16:41<59:12, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 240/1189 [16:41<59:12, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 241/1189 [16:44<57:53, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 241/1189 [16:44<57:53, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▏ | 241/1189 [16:44<57:53, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:32,534 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 242/1189 [16:47<55:58, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 242/1189 [16:47<55:58, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 243/1189 [16:50<53:46, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 243/1189 [16:50<53:46, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 20%|████████████████▎ | 243/1189 [16:50<53:46, 3.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:42,627 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▍ | 244/1189 [16:53<51:04, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:48,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▍ | 244/1189 [16:53<51:04, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:48,359 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▍ | 245/1189 [16:56<48:04, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▍ | 245/1189 [16:56<48:04, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 246/1189 [16:58<44:46, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 246/1189 [16:58<44:46, 2.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:54,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:54,047 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:55,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:55,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:57,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:57,405 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:59,213 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:59,213 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:37:59,213 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 251/1189 [17:11<47:22, 3.03s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 251/1189 [17:11<47:22, 3.03s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 251/1189 [17:11<47:22, 3.03s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 252/1189 [17:16<57:26, 3.68s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 252/1189 [17:16<57:26, 3.68s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▉ | 252/1189 [17:16<57:26, 3.68s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0302, 'learning_rate': 1.5e-05, 'epoch': 0.21} 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▌ | 253/1189 [17:21<1:04:03, 4.11s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 255/1189 [17:31<1:10:52, 4.55s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 255/1189 [17:31<1:10:52, 4.55s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 21%|████████████████▋ | 255/1189 [17:31<1:10:52, 4.55s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 256/1189 [17:36<1:13:09, 4.70s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 256/1189 [17:36<1:13:09, 4.70s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 256/1189 [17:36<1:13:09, 4.70s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 257/1189 [17:41<1:13:55, 4.76s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▊ | 257/1189 [17:41<1:13:55, 4.76s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 258/1189 [17:46<1:14:22, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 258/1189 [17:46<1:14:22, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4877, 'learning_rate': 1.524e-05, 'epoch': 0.22} 22%|████████████████▉ | 259/1189 [17:51<1:14:44, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|████████████████▉ | 259/1189 [17:51<1:14:44, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.269, 'learning_rate': 1.53e-05, 'epoch': 0.22} 22%|████████████████▉ | 259/1189 [17:51<1:14:44, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 260/1189 [17:56<1:15:09, 4.85s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 260/1189 [17:56<1:15:09, 4.85s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 261/1189 [18:01<1:15:10, 4.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████ | 261/1189 [18:01<1:15:10, 4.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2159, 'learning_rate': 1.542e-05, 'epoch': 0.22} 22%|█████████████████ | 261/1189 [18:01<1:15:10, 4.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▏ | 262/1189 [18:05<1:14:40, 4.83s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▏ | 262/1189 [18:05<1:14:40, 4.83s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▏ | 262/1189 [18:05<1:14:40, 4.83s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▎ | 263/1189 [18:10<1:14:24, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▎ | 263/1189 [18:10<1:14:24, 4.82s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▎ | 264/1189 [18:15<1:14:10, 4.81s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▎ | 264/1189 [18:15<1:14:10, 4.81s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3023, 'learning_rate': 1.56e-05, 'epoch': 0.22} 22%|█████████████████▎ | 264/1189 [18:15<1:14:10, 4.81s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 265/1189 [18:20<1:13:43, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 265/1189 [18:20<1:13:43, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 265/1189 [18:20<1:13:43, 4.79s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 266/1189 [18:24<1:13:08, 4.75s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▍ | 266/1189 [18:24<1:13:08, 4.75s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▌ | 267/1189 [18:29<1:12:41, 4.73s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 22%|█████████████████▌ | 267/1189 [18:29<1:12:41, 4.73s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1519, 'learning_rate': 1.578e-05, 'epoch': 0.22} 22%|█████████████████▌ | 267/1189 [18:29<1:12:41, 4.73s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▌ | 268/1189 [18:34<1:12:30, 4.72s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:39:32,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:39:32,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.188, 'learning_rate': 1.59e-05, 'epoch': 0.23} [WARNING|modeling_utils.py:388] 2022-03-01 08:39:32,100 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 270/1189 [18:43<1:11:22, 4.66s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▋ | 270/1189 [18:43<1:11:22, 4.66s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1215, 'learning_rate': 1.596e-05, 'epoch': 0.23} 23%|█████████████████▊ | 271/1189 [18:48<1:10:54, 4.63s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 271/1189 [18:48<1:10:54, 4.63s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4414, 'learning_rate': 1.6020000000000002e-05, 'epoch': 0.23} 23%|█████████████████▊ | 272/1189 [18:52<1:10:10, 4.59s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▊ | 272/1189 [18:52<1:10:10, 4.59s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0973, 'learning_rate': 1.6080000000000002e-05, 'epoch': 0.23} 23%|█████████████████▉ | 273/1189 [18:57<1:09:19, 4.54s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 273/1189 [18:57<1:09:19, 4.54s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1955, 'learning_rate': 1.614e-05, 'epoch': 0.23} 23%|█████████████████▉ | 274/1189 [19:01<1:08:29, 4.49s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|█████████████████▉ | 274/1189 [19:01<1:08:29, 4.49s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.249, 'learning_rate': 1.62e-05, 'epoch': 0.23} 23%|██████████████████ | 275/1189 [19:05<1:08:06, 4.47s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 275/1189 [19:05<1:08:06, 4.47s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2878, 'learning_rate': 1.626e-05, 'epoch': 0.23} 23%|██████████████████ | 275/1189 [19:05<1:08:06, 4.47s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 276/1189 [19:10<1:07:29, 4.44s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████ | 276/1189 [19:10<1:07:29, 4.44s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 277/1189 [19:14<1:07:03, 4.41s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 277/1189 [19:14<1:07:03, 4.41s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0002, 'learning_rate': 1.6380000000000002e-05, 'epoch': 0.23} 23%|██████████████████▏ | 278/1189 [19:18<1:06:09, 4.36s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▏ | 278/1189 [19:18<1:06:09, 4.36s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1866, 'learning_rate': 1.6440000000000002e-05, 'epoch': 0.23} 23%|██████████████████▏ | 278/1189 [19:18<1:06:09, 4.36s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 279/1189 [19:23<1:05:33, 4.32s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 23%|██████████████████▎ | 279/1189 [19:23<1:05:33, 4.32s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 280/1189 [19:27<1:04:44, 4.27s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▎ | 280/1189 [19:27<1:04:44, 4.27s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1737, 'learning_rate': 1.656e-05, 'epoch': 0.24} 24%|██████████████████▍ | 281/1189 [19:31<1:04:12, 4.24s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 281/1189 [19:31<1:04:12, 4.24s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1932, 'learning_rate': 1.6620000000000004e-05, 'epoch': 0.24} 24%|██████████████████▍ | 282/1189 [19:35<1:03:08, 4.18s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▍ | 282/1189 [19:35<1:03:08, 4.18s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.307, 'learning_rate': 1.6680000000000003e-05, 'epoch': 0.24} 24%|██████████████████▍ | 282/1189 [19:35<1:03:08, 4.18s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 283/1189 [19:39<1:02:12, 4.12s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 283/1189 [19:39<1:02:12, 4.12s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▌ | 283/1189 [19:39<1:02:12, 4.12s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 284/1189 [19:43<1:01:13, 4.06s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 284/1189 [19:43<1:01:13, 4.06s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|██████████████████▋ | 284/1189 [19:43<1:01:13, 4.06s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 285/1189 [19:47<59:59, 3.98s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 285/1189 [19:47<59:59, 3.98s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 285/1189 [19:47<59:59, 3.98s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 286/1189 [19:50<59:02, 3.92s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 286/1189 [19:50<59:02, 3.92s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▏ | 286/1189 [19:50<59:02, 3.92s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▎ | 287/1189 [19:54<58:01, 3.86s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:40:51,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:40:51,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1832, 'learning_rate': 1.704e-05, 'epoch': 0.24} [WARNING|modeling_utils.py:388] 2022-03-01 08:40:51,269 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▍ | 289/1189 [20:01<55:18, 3.69s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▍ | 289/1189 [20:01<55:18, 3.69s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▍ | 289/1189 [20:01<55:18, 3.69s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▌ | 290/1189 [20:04<53:40, 3.58s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 24%|███████████████████▌ | 290/1189 [20:04<53:40, 3.58s/it]g-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:01,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:01,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:01,197 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:37:50,837 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 292/1189 [20:10<48:42, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 292/1189 [20:10<48:42, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 293/1189 [20:13<45:35, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|███████████████████▋ | 293/1189 [20:13<45:35, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:09,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:09,006 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:11,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:11,198 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:13,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:13,154 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:14,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:14,896 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:16,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:16,435 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.7354, 'learning_rate': 1.776e-05, 'epoch': 0.25} [WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:41:19,596 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 301/1189 [20:31<42:18, 2.86s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 301/1189 [20:31<42:18, 2.86s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 301/1189 [20:31<42:18, 2.86s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 302/1189 [20:36<52:02, 3.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 302/1189 [20:36<52:02, 3.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▎ | 302/1189 [20:36<52:02, 3.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▍ | 303/1189 [20:41<58:47, 3.98s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 25%|████████████████████▍ | 303/1189 [20:41<58:47, 3.98s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|███████████████████▉ | 304/1189 [20:46<1:03:29, 4.30s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|███████████████████▉ | 304/1189 [20:46<1:03:29, 4.30s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.8823, 'learning_rate': 1.8e-05, 'epoch': 0.26} 26%|███████████████████▉ | 304/1189 [20:46<1:03:29, 4.30s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 305/1189 [20:51<1:06:42, 4.53s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 305/1189 [20:51<1:06:42, 4.53s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0446, 'learning_rate': 1.812e-05, 'epoch': 0.26} 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2072, 'learning_rate': 1.818e-05, 'epoch': 0.26} 26%|████████████████████ | 306/1189 [20:56<1:08:49, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 308/1189 [21:06<1:10:10, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▏ | 308/1189 [21:06<1:10:10, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.9454, 'learning_rate': 1.824e-05, 'epoch': 0.26} 26%|████████████████████▎ | 309/1189 [21:11<1:10:20, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 309/1189 [21:11<1:10:20, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.9268, 'learning_rate': 1.83e-05, 'epoch': 0.26} 26%|████████████████████▎ | 309/1189 [21:11<1:10:20, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 310/1189 [21:16<1:10:37, 4.82s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▎ | 310/1189 [21:16<1:10:37, 4.82s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 311/1189 [21:21<1:10:52, 4.84s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 311/1189 [21:21<1:10:52, 4.84s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.058, 'learning_rate': 1.842e-05, 'epoch': 0.26} 26%|████████████████████▍ | 312/1189 [21:26<1:10:34, 4.83s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▍ | 312/1189 [21:26<1:10:34, 4.83s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0705, 'learning_rate': 1.848e-05, 'epoch': 0.26} 26%|████████████████████▍ | 312/1189 [21:26<1:10:34, 4.83s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 313/1189 [21:30<1:10:01, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 313/1189 [21:30<1:10:01, 4.80s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 314/1189 [21:35<1:09:40, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▌ | 314/1189 [21:35<1:09:40, 4.78s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1257, 'learning_rate': 1.86e-05, 'epoch': 0.26} 26%|████████████████████▋ | 315/1189 [21:40<1:09:18, 4.76s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 26%|████████████████████▋ | 315/1189 [21:40<1:09:18, 4.76s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0073, 'learning_rate': 1.866e-05, 'epoch': 0.26} 27%|████████████████████▋ | 316/1189 [21:45<1:09:27, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▋ | 316/1189 [21:45<1:09:27, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3839, 'learning_rate': 1.872e-05, 'epoch': 0.27} 27%|████████████████████▊ | 317/1189 [21:49<1:09:20, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 317/1189 [21:49<1:09:20, 4.77s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3243, 'learning_rate': 1.878e-05, 'epoch': 0.27} 27%|████████████████████▊ | 318/1189 [21:54<1:08:48, 4.74s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▊ | 318/1189 [21:54<1:08:48, 4.74s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2505, 'learning_rate': 1.884e-05, 'epoch': 0.27} 27%|████████████████████▉ | 319/1189 [21:59<1:08:30, 4.72s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 319/1189 [21:59<1:08:30, 4.72s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0626, 'learning_rate': 1.8900000000000002e-05, 'epoch': 0.27} 27%|████████████████████▉ | 320/1189 [22:03<1:08:15, 4.71s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|████████████████████▉ | 320/1189 [22:03<1:08:15, 4.71s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2428, 'learning_rate': 1.896e-05, 'epoch': 0.27} 27%|█████████████████████ | 321/1189 [22:08<1:07:38, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████ | 321/1189 [22:08<1:07:38, 4.68s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0947, 'learning_rate': 1.902e-05, 'epoch': 0.27} 27%|█████████████████████ | 322/1189 [22:13<1:06:52, 4.63s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████ | 322/1189 [22:13<1:06:52, 4.63s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1172, 'learning_rate': 1.908e-05, 'epoch': 0.27} 27%|█████████████████████▏ | 323/1189 [22:17<1:06:33, 4.61s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▏ | 323/1189 [22:17<1:06:33, 4.61s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.048, 'learning_rate': 1.914e-05, 'epoch': 0.27} 27%|█████████████████████▏ | 323/1189 [22:17<1:06:33, 4.61s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 324/1189 [22:22<1:06:14, 4.59s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 324/1189 [22:22<1:06:14, 4.59s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 324/1189 [22:22<1:06:14, 4.59s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 325/1189 [22:26<1:05:51, 4.57s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 325/1189 [22:26<1:05:51, 4.57s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▎ | 325/1189 [22:26<1:05:51, 4.57s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▍ | 326/1189 [22:31<1:04:56, 4.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▍ | 326/1189 [22:31<1:04:56, 4.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 27%|█████████████████████▍ | 326/1189 [22:31<1:04:56, 4.52s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▍ | 327/1189 [22:35<1:04:18, 4.48s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▍ | 327/1189 [22:35<1:04:18, 4.48s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 328/1189 [22:39<1:03:50, 4.45s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 328/1189 [22:39<1:03:50, 4.45s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2394, 'learning_rate': 1.944e-05, 'epoch': 0.28} 28%|█████████████████████▌ | 328/1189 [22:39<1:03:50, 4.45s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 329/1189 [22:44<1:03:06, 4.40s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 329/1189 [22:44<1:03:06, 4.40s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▌ | 329/1189 [22:44<1:03:06, 4.40s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▋ | 331/1189 [22:52<1:01:50, 4.32s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▋ | 331/1189 [22:52<1:01:50, 4.32s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 332/1189 [22:56<1:01:16, 4.29s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 332/1189 [22:56<1:01:16, 4.29s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2261, 'learning_rate': 1.968e-05, 'epoch': 0.28} 28%|█████████████████████▊ | 332/1189 [22:56<1:01:16, 4.29s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 333/1189 [23:00<1:00:24, 4.23s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 333/1189 [23:00<1:00:24, 4.23s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|█████████████████████▊ | 333/1189 [23:00<1:00:24, 4.23s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▍ | 334/1189 [23:05<59:50, 4.20s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▍ | 334/1189 [23:05<59:50, 4.20s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▍ | 334/1189 [23:05<59:50, 4.20s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 335/1189 [23:09<58:51, 4.13s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 335/1189 [23:09<58:51, 4.13s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 335/1189 [23:09<58:51, 4.13s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 336/1189 [23:12<57:56, 4.08s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 336/1189 [23:12<57:56, 4.08s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▌ | 336/1189 [23:12<57:56, 4.08s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 337/1189 [23:16<56:53, 4.01s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 337/1189 [23:16<56:53, 4.01s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 337/1189 [23:16<56:53, 4.01s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 338/1189 [23:20<55:33, 3.92s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 338/1189 [23:20<55:33, 3.92s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 28%|██████████████████████▋ | 338/1189 [23:20<55:33, 3.92s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|██████████████████████▊ | 339/1189 [23:24<54:06, 3.82s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:20,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:20,747 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2188, 'learning_rate': 2.016e-05, 'epoch': 0.29} 29%|██████████████████████▉ | 341/1189 [23:30<50:48, 3.60s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|██████████████████████▉ | 341/1189 [23:30<50:48, 3.60s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2795, 'learning_rate': 2.0220000000000003e-05, 'epoch': 0.29} 29%|██████████████████████▉ | 341/1189 [23:30<50:48, 3.60s/it]g-point operations will not be computed-01 08:41:05,425 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████ | 342/1189 [23:33<48:33, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:28,655 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████ | 343/1189 [23:36<46:07, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████ | 343/1189 [23:36<46:07, 3.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▏ | 344/1189 [23:39<43:30, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 29%|███████████████████████▏ | 344/1189 [23:39<43:30, 3.09s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:35,142 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:37,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:37,387 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:39,373 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:41,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:41,132 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4257, 'learning_rate': 2.0580000000000003e-05, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-03-01 08:44:42,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:42,622 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.857, 'learning_rate': 2.07e-05, 'epoch': 0.29} [WARNING|modeling_utils.py:388] 2022-03-01 08:44:44,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:44:44,400 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 351/1189 [23:56<41:41, 2.99s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 351/1189 [23:56<41:41, 2.99s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4633, 'learning_rate': 2.082e-05, 'epoch': 0.3} 30%|███████████████████████▌ | 351/1189 [23:56<41:41, 2.99s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 352/1189 [24:01<50:47, 3.64s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 352/1189 [24:01<50:47, 3.64s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▊ | 353/1189 [24:06<56:36, 4.06s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▊ | 353/1189 [24:06<56:36, 4.06s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.14, 'learning_rate': 2.094e-05, 'epoch': 0.3} 30%|███████████████████████▊ | 353/1189 [24:06<56:36, 4.06s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▏ | 354/1189 [24:11<1:00:08, 4.32s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▏ | 354/1189 [24:11<1:00:08, 4.32s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▏ | 354/1189 [24:11<1:00:08, 4.32s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 355/1189 [24:16<1:02:34, 4.50s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 355/1189 [24:16<1:02:34, 4.50s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 355/1189 [24:16<1:02:34, 4.50s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 356/1189 [24:21<1:04:39, 4.66s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▎ | 356/1189 [24:21<1:04:39, 4.66s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▍ | 357/1189 [24:26<1:05:44, 4.74s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▍ | 357/1189 [24:26<1:05:44, 4.74s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2986, 'learning_rate': 2.118e-05, 'epoch': 0.3} 30%|███████████████████████▍ | 358/1189 [24:31<1:06:28, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▍ | 358/1189 [24:31<1:06:28, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0543, 'learning_rate': 2.124e-05, 'epoch': 0.3} 30%|███████████████████████▍ | 358/1189 [24:31<1:06:28, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 359/1189 [24:36<1:06:50, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 359/1189 [24:36<1:06:50, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 360/1189 [24:41<1:06:59, 4.85s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▌ | 360/1189 [24:41<1:06:59, 4.85s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3371, 'learning_rate': 2.136e-05, 'epoch': 0.3} 30%|███████████████████████▌ | 360/1189 [24:41<1:06:59, 4.85s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 361/1189 [24:46<1:06:38, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 361/1189 [24:46<1:06:38, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 361/1189 [24:46<1:06:38, 4.83s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 362/1189 [24:50<1:06:06, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 30%|███████████████████████▋ | 362/1189 [24:50<1:06:06, 4.80s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▊ | 363/1189 [24:55<1:05:38, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▊ | 363/1189 [24:55<1:05:38, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.126, 'learning_rate': 2.154e-05, 'epoch': 0.31} 31%|███████████████████████▉ | 364/1189 [25:00<1:05:33, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▉ | 364/1189 [25:00<1:05:33, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2623, 'learning_rate': 2.16e-05, 'epoch': 0.31} 31%|███████████████████████▉ | 364/1189 [25:00<1:05:33, 4.77s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▉ | 365/1189 [25:05<1:05:16, 4.75s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|███████████████████████▉ | 365/1189 [25:05<1:05:16, 4.75s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████ | 366/1189 [25:09<1:04:45, 4.72s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████ | 366/1189 [25:09<1:04:45, 4.72s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1573, 'learning_rate': 2.172e-05, 'epoch': 0.31} 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0573, 'learning_rate': 2.178e-05, 'epoch': 0.31} 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████ | 367/1189 [25:14<1:04:17, 4.69s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4715, 'learning_rate': 2.184e-05, 'epoch': 0.31} [WARNING|modeling_utils.py:388] 2022-03-01 08:46:16,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:46:16,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:46:16,705 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3253, 'learning_rate': 2.19e-05, 'epoch': 0.31} 31%|████████████████████████▎ | 370/1189 [25:28<1:03:00, 4.62s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 370/1189 [25:28<1:03:00, 4.62s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2055, 'learning_rate': 2.196e-05, 'epoch': 0.31} 31%|████████████████████████▎ | 371/1189 [25:32<1:02:49, 4.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▎ | 371/1189 [25:32<1:02:49, 4.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1163, 'learning_rate': 2.202e-05, 'epoch': 0.31} 31%|████████████████████████▍ | 372/1189 [25:37<1:02:10, 4.57s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▍ | 372/1189 [25:37<1:02:10, 4.57s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0746, 'learning_rate': 2.208e-05, 'epoch': 0.31} 31%|████████████████████████▍ | 373/1189 [25:41<1:01:50, 4.55s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▍ | 373/1189 [25:41<1:01:50, 4.55s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0822, 'learning_rate': 2.214e-05, 'epoch': 0.31} 31%|████████████████████████▍ | 373/1189 [25:41<1:01:50, 4.55s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▌ | 374/1189 [25:46<1:01:26, 4.52s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▌ | 374/1189 [25:46<1:01:26, 4.52s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 31%|████████████████████████▌ | 374/1189 [25:46<1:01:26, 4.52s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▌ | 375/1189 [25:50<1:00:54, 4.49s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▌ | 375/1189 [25:50<1:00:54, 4.49s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▌ | 375/1189 [25:50<1:00:54, 4.49s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▋ | 376/1189 [25:54<1:00:17, 4.45s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▋ | 376/1189 [25:54<1:00:17, 4.45s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|████████████████████████▋ | 376/1189 [25:54<1:00:17, 4.45s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▎ | 377/1189 [25:59<59:39, 4.41s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▎ | 377/1189 [25:59<59:39, 4.41s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▎ | 377/1189 [25:59<59:39, 4.41s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▍ | 378/1189 [26:03<58:50, 4.35s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▍ | 378/1189 [26:03<58:50, 4.35s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▍ | 378/1189 [26:03<58:50, 4.35s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▌ | 379/1189 [26:07<58:29, 4.33s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▌ | 379/1189 [26:07<58:29, 4.33s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▌ | 380/1189 [26:11<58:04, 4.31s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▌ | 380/1189 [26:11<58:04, 4.31s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2768, 'learning_rate': 2.256e-05, 'epoch': 0.32} 32%|█████████████████████████▌ | 380/1189 [26:11<58:04, 4.31s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 381/1189 [26:16<57:19, 4.26s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 381/1189 [26:16<57:19, 4.26s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 381/1189 [26:16<57:19, 4.26s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 382/1189 [26:20<56:40, 4.21s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 382/1189 [26:20<56:40, 4.21s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▋ | 382/1189 [26:20<56:40, 4.21s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 383/1189 [26:24<55:27, 4.13s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 383/1189 [26:24<55:27, 4.13s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 383/1189 [26:24<55:27, 4.13s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 384/1189 [26:28<54:42, 4.08s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 384/1189 [26:28<54:42, 4.08s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▊ | 384/1189 [26:28<54:42, 4.08s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 385/1189 [26:31<53:48, 4.02s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 385/1189 [26:31<53:48, 4.02s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 385/1189 [26:31<53:48, 4.02s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 386/1189 [26:35<53:13, 3.98s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 386/1189 [26:35<53:13, 3.98s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 32%|█████████████████████████▉ | 386/1189 [26:35<53:13, 3.98s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████ | 387/1189 [26:39<52:07, 3.90s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████ | 387/1189 [26:39<52:07, 3.90s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████ | 388/1189 [26:43<50:51, 3.81s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████ | 388/1189 [26:43<50:51, 3.81s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:47:39,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:47:39,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.365, 'learning_rate': 2.3100000000000002e-05, 'epoch': 0.33} [WARNING|modeling_utils.py:388] 2022-03-01 08:47:39,857 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▏ | 390/1189 [26:50<48:03, 3.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▏ | 390/1189 [26:50<48:03, 3.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▏ | 390/1189 [26:50<48:03, 3.61s/it]g-point operations will not be computed-01 08:44:31,418 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▎ | 391/1189 [26:53<46:08, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▍ | 392/1189 [26:56<43:53, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▍ | 392/1189 [26:56<43:53, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:47:51,989 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:47:51,989 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2523, 'learning_rate': 2.334e-05, 'epoch': 0.33} [WARNING|modeling_utils.py:388] 2022-03-01 08:47:51,989 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:47:47,885 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▌ | 394/1189 [27:01<39:09, 2.96s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:55,780 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▌ | 395/1189 [27:03<36:39, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:57,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▌ | 395/1189 [27:03<36:39, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:57,990 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▋ | 396/1189 [27:05<33:45, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:59,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▋ | 396/1189 [27:05<33:45, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:47:59,893 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▊ | 398/1189 [27:09<27:55, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:01,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 33%|██████████████████████████▊ | 398/1189 [27:09<27:55, 2.12s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:01,608 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4165, 'learning_rate': 2.358e-05, 'epoch': 0.33} 34%|██████████████████████████▊ | 399/1189 [27:10<25:02, 1.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 399/1189 [27:10<25:02, 1.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 400/1189 [27:12<24:25, 1.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 400/1189 [27:12<24:25, 1.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:04,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 400/1189 [27:12<24:25, 1.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 401/1189 [27:17<38:44, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 401/1189 [27:17<38:44, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0445, 'learning_rate': 2.3820000000000002e-05, 'epoch': 0.34} 34%|███████████████████████████ | 402/1189 [27:22<47:17, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████ | 402/1189 [27:22<47:17, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1595, 'learning_rate': 2.3880000000000002e-05, 'epoch': 0.34} 34%|███████████████████████████ | 403/1189 [27:28<52:58, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████ | 403/1189 [27:28<52:58, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1869, 'learning_rate': 2.394e-05, 'epoch': 0.34} 34%|███████████████████████████ | 403/1189 [27:28<52:58, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1379, 'learning_rate': 2.4060000000000003e-05, 'epoch': 0.34} 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|███████████████████████████▏ | 404/1189 [27:33<56:38, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 406/1189 [27:42<1:00:46, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 406/1189 [27:42<1:00:46, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 407/1189 [27:47<1:01:58, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▋ | 407/1189 [27:47<1:01:58, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0632, 'learning_rate': 2.4180000000000002e-05, 'epoch': 0.34} 34%|██████████████████████████▋ | 407/1189 [27:47<1:01:58, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [27:52<1:02:43, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [27:52<1:02:43, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 408/1189 [27:52<1:02:43, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 409/1189 [27:57<1:02:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 409/1189 [27:57<1:02:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▊ | 409/1189 [27:57<1:02:52, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 410/1189 [28:02<1:02:57, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 410/1189 [28:02<1:02:57, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 34%|██████████████████████████▉ | 410/1189 [28:02<1:02:57, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|██████████████████████████▉ | 411/1189 [28:07<1:02:55, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|██████████████████████████▉ | 411/1189 [28:07<1:02:55, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2136, 'learning_rate': 2.448e-05, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-03-01 08:49:10,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:49:10,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2112, 'learning_rate': 2.454e-05, 'epoch': 0.35} [WARNING|modeling_utils.py:388] 2022-03-01 08:49:10,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 414/1189 [28:21<1:01:43, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 414/1189 [28:21<1:01:43, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 414/1189 [28:21<1:01:43, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 415/1189 [28:26<1:01:36, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▏ | 415/1189 [28:26<1:01:36, 4.78s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 416/1189 [28:31<1:01:14, 4.75s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 416/1189 [28:31<1:01:14, 4.75s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2702, 'learning_rate': 2.472e-05, 'epoch': 0.35} 35%|███████████████████████████▎ | 417/1189 [28:35<1:00:59, 4.74s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▎ | 417/1189 [28:35<1:00:59, 4.74s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.9489, 'learning_rate': 2.478e-05, 'epoch': 0.35} 35%|███████████████████████████▎ | 417/1189 [28:35<1:00:59, 4.74s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▍ | 418/1189 [28:40<1:00:12, 4.69s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|███████████████████████████▍ | 418/1189 [28:40<1:00:12, 4.69s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▏ | 419/1189 [28:45<59:50, 4.66s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▏ | 419/1189 [28:45<59:50, 4.66s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2809, 'learning_rate': 2.49e-05, 'epoch': 0.35} 35%|████████████████████████████▎ | 420/1189 [28:49<59:12, 4.62s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 420/1189 [28:49<59:12, 4.62s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.176, 'learning_rate': 2.4959999999999998e-05, 'epoch': 0.35} 35%|████████████████████████████▎ | 421/1189 [28:54<58:50, 4.60s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▎ | 421/1189 [28:54<58:50, 4.60s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1256, 'learning_rate': 2.502e-05, 'epoch': 0.35} 35%|████████████████████████████▍ | 422/1189 [28:58<58:24, 4.57s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 35%|████████████████████████████▍ | 422/1189 [28:58<58:24, 4.57s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2436, 'learning_rate': 2.508e-05, 'epoch': 0.35} 35%|████████████████████████████▍ | 422/1189 [28:58<58:24, 4.57s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▍ | 423/1189 [29:03<58:14, 4.56s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▍ | 423/1189 [29:03<58:14, 4.56s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 424/1189 [29:07<57:36, 4.52s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 424/1189 [29:07<57:36, 4.52s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1591, 'learning_rate': 2.52e-05, 'epoch': 0.36} 36%|████████████████████████████▌ | 425/1189 [29:12<56:57, 4.47s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▌ | 425/1189 [29:12<56:57, 4.47s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.4836, 'learning_rate': 2.526e-05, 'epoch': 0.36} 36%|████████████████████████████▋ | 426/1189 [29:16<56:14, 4.42s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▋ | 426/1189 [29:16<56:14, 4.42s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1937, 'learning_rate': 2.5319999999999998e-05, 'epoch': 0.36} 36%|████████████████████████████▋ | 427/1189 [29:20<55:56, 4.40s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▋ | 427/1189 [29:20<55:56, 4.40s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1032, 'learning_rate': 2.538e-05, 'epoch': 0.36} 36%|████████████████████████████▊ | 428/1189 [29:25<55:31, 4.38s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▊ | 428/1189 [29:25<55:31, 4.38s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1523, 'learning_rate': 2.544e-05, 'epoch': 0.36} 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.419, 'learning_rate': 2.55e-05, 'epoch': 0.36} 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3495, 'learning_rate': 2.556e-05, 'epoch': 0.36} 36%|████████████████████████████▊ | 429/1189 [29:29<55:20, 4.37s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▉ | 431/1189 [29:37<54:34, 4.32s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▉ | 431/1189 [29:37<54:34, 4.32s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|████████████████████████████▉ | 431/1189 [29:37<54:34, 4.32s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████ | 432/1189 [29:42<53:53, 4.27s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████ | 432/1189 [29:42<53:53, 4.27s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████ | 432/1189 [29:42<53:53, 4.27s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████▏ | 433/1189 [29:46<53:14, 4.23s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████▏ | 433/1189 [29:46<53:14, 4.23s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 36%|█████████████████████████████▏ | 433/1189 [29:46<53:14, 4.23s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▏ | 434/1189 [29:50<52:26, 4.17s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▏ | 434/1189 [29:50<52:26, 4.17s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▏ | 434/1189 [29:50<52:26, 4.17s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 435/1189 [29:54<51:27, 4.09s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 435/1189 [29:54<51:27, 4.09s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 435/1189 [29:54<51:27, 4.09s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 436/1189 [29:58<50:30, 4.02s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 436/1189 [29:58<50:30, 4.02s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▎ | 436/1189 [29:58<50:30, 4.02s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▍ | 437/1189 [30:01<49:22, 3.94s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▍ | 437/1189 [30:01<49:22, 3.94s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▍ | 437/1189 [30:01<49:22, 3.94s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▍ | 438/1189 [30:05<48:06, 3.84s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:51:02,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:51:02,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3237, 'learning_rate': 2.61e-05, 'epoch': 0.37} [WARNING|modeling_utils.py:388] 2022-03-01 08:51:02,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▌ | 440/1189 [30:12<45:19, 3.63s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▌ | 440/1189 [30:12<45:19, 3.63s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▌ | 440/1189 [30:12<45:19, 3.63s/it]g-point operations will not be computed-01 08:48:08,352 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▋ | 441/1189 [30:15<43:35, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▋ | 441/1189 [30:15<43:35, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▋ | 442/1189 [30:18<41:49, 3.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:51:14,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:51:14,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1628, 'learning_rate': 2.6340000000000002e-05, 'epoch': 0.37} [WARNING|modeling_utils.py:388] 2022-03-01 08:51:14,545 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:10,230 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▊ | 444/1189 [30:24<37:50, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:18,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▊ | 444/1189 [30:24<37:50, 3.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:18,446 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▉ | 445/1189 [30:26<35:27, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:20,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 37%|█████████████████████████████▉ | 445/1189 [30:26<35:27, 2.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:20,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████ | 446/1189 [30:28<32:40, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:22,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████ | 446/1189 [30:28<32:40, 2.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:22,811 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████ | 447/1189 [30:30<30:01, 2.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:24,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████ | 447/1189 [30:30<30:01, 2.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:24,618 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▏ | 448/1189 [30:32<27:19, 2.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:26,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▏ | 448/1189 [30:32<27:19, 2.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:26,205 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:27,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:27,597 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 450/1189 [30:35<23:49, 1.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0877, 'learning_rate': 2.688e-05, 'epoch': 0.38} 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▎ | 451/1189 [30:40<36:40, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▍ | 453/1189 [30:51<49:45, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▍ | 453/1189 [30:51<49:45, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 454/1189 [30:56<53:17, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 454/1189 [30:56<53:17, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2176, 'learning_rate': 2.7000000000000002e-05, 'epoch': 0.38} 38%|██████████████████████████████▌ | 454/1189 [30:56<53:17, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 455/1189 [31:01<55:17, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 455/1189 [31:01<55:17, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▌ | 455/1189 [31:01<55:17, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 456/1189 [31:06<56:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 456/1189 [31:06<56:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 456/1189 [31:06<56:47, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 457/1189 [31:10<57:25, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 457/1189 [31:10<57:25, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 38%|██████████████████████████████▋ | 457/1189 [31:10<57:25, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▊ | 458/1189 [31:15<57:55, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▊ | 458/1189 [31:15<57:55, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 459/1189 [31:20<58:13, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 459/1189 [31:20<58:13, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1156, 'learning_rate': 2.7300000000000003e-05, 'epoch': 0.39} 39%|██████████████████████████████▉ | 460/1189 [31:25<58:04, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|██████████████████████████████▉ | 460/1189 [31:25<58:04, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2531, 'learning_rate': 2.7360000000000002e-05, 'epoch': 0.39} 39%|██████████████████████████████▉ | 460/1189 [31:25<58:04, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 461/1189 [31:30<57:53, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 461/1189 [31:30<57:53, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 462/1189 [31:34<57:45, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████ | 462/1189 [31:34<57:45, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2243, 'learning_rate': 2.748e-05, 'epoch': 0.39} 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1874, 'learning_rate': 2.754e-05, 'epoch': 0.39} 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 463/1189 [31:39<57:52, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 464/1189 [31:44<57:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▏ | 464/1189 [31:44<57:38, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 465/1189 [31:49<57:22, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 465/1189 [31:49<57:22, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3213, 'learning_rate': 2.7660000000000003e-05, 'epoch': 0.39} 39%|███████████████████████████████▎ | 466/1189 [31:53<56:57, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▎ | 466/1189 [31:53<56:57, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0718, 'learning_rate': 2.7720000000000002e-05, 'epoch': 0.39} 39%|███████████████████████████████▍ | 467/1189 [31:58<56:35, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▍ | 467/1189 [31:58<56:35, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2087, 'learning_rate': 2.778e-05, 'epoch': 0.39} 39%|███████████████████████████████▍ | 468/1189 [32:03<56:12, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▍ | 468/1189 [32:03<56:12, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2517, 'learning_rate': 2.784e-05, 'epoch': 0.39} 39%|███████████████████████████████▌ | 469/1189 [32:07<55:51, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 39%|███████████████████████████████▌ | 469/1189 [32:07<55:51, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0324, 'learning_rate': 2.79e-05, 'epoch': 0.39} 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3931, 'learning_rate': 2.7960000000000003e-05, 'epoch': 0.4} 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2216, 'learning_rate': 2.8020000000000003e-05, 'epoch': 0.4} 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▌ | 470/1189 [32:12<55:22, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 472/1189 [32:21<54:43, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 472/1189 [32:21<54:43, 4.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 473/1189 [32:25<54:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▊ | 473/1189 [32:25<54:16, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 3.9645, 'learning_rate': 2.8139999999999998e-05, 'epoch': 0.4} 40%|███████████████████████████████▉ | 474/1189 [32:30<53:57, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▉ | 474/1189 [32:30<53:57, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.306, 'learning_rate': 2.8199999999999998e-05, 'epoch': 0.4} 40%|███████████████████████████████▉ | 475/1189 [32:34<53:19, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|███████████████████████████████▉ | 475/1189 [32:34<53:19, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3816, 'learning_rate': 2.826e-05, 'epoch': 0.4} 40%|████████████████████████████████ | 476/1189 [32:39<52:54, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████ | 476/1189 [32:39<52:54, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3026, 'learning_rate': 2.832e-05, 'epoch': 0.4} 40%|████████████████████████████████ | 477/1189 [32:43<52:24, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████ | 477/1189 [32:43<52:24, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.0065, 'learning_rate': 2.838e-05, 'epoch': 0.4} 40%|████████████████████████████████▏ | 478/1189 [32:47<51:47, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▏ | 478/1189 [32:47<51:47, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.2526, 'learning_rate': 2.844e-05, 'epoch': 0.4} 40%|████████████████████████████████▏ | 478/1189 [32:47<51:47, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▏ | 479/1189 [32:51<51:16, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▏ | 479/1189 [32:51<51:16, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▏ | 479/1189 [32:51<51:16, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 480/1189 [32:56<50:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 480/1189 [32:56<50:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 480/1189 [32:56<50:38, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 481/1189 [33:00<50:13, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 481/1189 [33:00<50:13, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 40%|████████████████████████████████▎ | 481/1189 [33:00<50:13, 4.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 482/1189 [33:04<49:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 482/1189 [33:04<49:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 482/1189 [33:04<49:38, 4.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 483/1189 [33:08<49:07, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 483/1189 [33:08<49:07, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▍ | 483/1189 [33:08<49:07, 4.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▌ | 484/1189 [33:12<48:08, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▌ | 484/1189 [33:12<48:08, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▌ | 484/1189 [33:12<48:08, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 485/1189 [33:16<47:36, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 485/1189 [33:16<47:36, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 485/1189 [33:16<47:36, 4.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 486/1189 [33:20<46:51, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 486/1189 [33:20<46:51, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▋ | 486/1189 [33:20<46:51, 4.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 487/1189 [33:23<46:10, 3.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 487/1189 [33:23<46:10, 3.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 487/1189 [33:23<46:10, 3.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 488/1189 [33:27<45:21, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 488/1189 [33:27<45:21, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▊ | 488/1189 [33:27<45:21, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▉ | 489/1189 [33:31<44:24, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|████████████████████████████████▉ | 489/1189 [33:31<44:24, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:54:28,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:54:28,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:54:28,001 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████ | 491/1189 [33:38<41:44, 3.59s/it]g-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████ | 491/1189 [33:38<41:44, 3.59s/it]g-point operations will not be computed-01 08:51:31,549 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.1793, 'learning_rate': 2.928e-05, 'epoch': 0.41} 41%|█████████████████████████████████ | 492/1189 [33:41<40:11, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████ | 492/1189 [33:41<40:11, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 41%|█████████████████████████████████▏ | 493/1189 [33:44<38:27, 3.31s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:54:40,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [WARNING|modeling_utils.py:388] 2022-03-01 08:54:40,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.3125, 'learning_rate': 2.94e-05, 'epoch': 0.42} [WARNING|modeling_utils.py:388] 2022-03-01 08:54:40,172 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 08:54:36,023 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▎ | 495/1189 [33:49<34:00, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:43,886 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▎ | 495/1189 [33:49<34:00, 2.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:43,886 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▎ | 496/1189 [33:51<31:40, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:45,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▎ | 496/1189 [33:51<31:40, 2.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:45,976 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▌ | 498/1189 [33:55<25:53, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:47,775 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▌ | 498/1189 [33:55<25:53, 2.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:47,775 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed {'loss': 4.5546, 'learning_rate': 2.964e-05, 'epoch': 0.42} 42%|█████████████████████████████████▌ | 499/1189 [33:56<23:13, 2.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:50,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed 42%|█████████████████████████████████▌ | 499/1189 [33:56<23:13, 2.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 08:54:50,710 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed [INFO|trainer.py:2366] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-01 08:54:51,982 >> Num examples = 2642 | 500/1189 [33:58<22:27, 1.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 2%|█▌ | 4/221 [00:08<08:52, 2.45s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 2%|█▉ | 5/221 [00:11<09:32, 2.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 3%|██▎ | 6/221 [00:15<10:18, 2.87s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 3%|██▋ | 7/221 [00:18<11:16, 3.16s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███ | 8/221 [00:21<11:01, 3.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███▍ | 9/221 [00:24<10:49, 3.07s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|███▋ | 10/221 [00:28<11:44, 3.34s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████ | 11/221 [00:33<12:39, 3.62s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████▍ | 12/221 [00:35<11:50, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 6%|████▊ | 13/221 [00:39<11:31, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 6%|█████▏ | 14/221 [00:42<11:37, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 7%|█████▌ | 15/221 [00:47<13:04, 3.81s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 7%|█████▉ | 16/221 [00:52<13:59, 4.09s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 8%|██████▎ | 17/221 [00:55<13:16, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 8%|██████▋ | 18/221 [00:59<13:02, 3.86s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 9%|███████ | 19/221 [01:02<12:24, 3.69s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 9%|███████▍ | 20/221 [01:05<11:45, 3.51s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|███████▊ | 21/221 [01:08<11:00, 3.30s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▏ | 22/221 [01:11<10:47, 3.25s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▌ | 23/221 [01:14<10:31, 3.19s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|████████▉ | 24/221 [01:18<11:03, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|█████████▎ | 25/221 [01:22<11:38, 3.56s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 12%|█████████▋ | 26/221 [01:26<11:52, 3.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 12%|██████████ | 27/221 [01:29<10:48, 3.34s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▍ | 28/221 [01:32<11:19, 3.52s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▊ | 29/221 [01:37<12:02, 3.76s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▏ | 30/221 [01:40<11:16, 3.54s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▌ | 31/221 [01:42<10:19, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▊ | 32/221 [01:46<10:16, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▏ | 33/221 [01:49<10:41, 3.41s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▌ | 34/221 [01:53<10:47, 3.46s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|████████████▉ | 35/221 [01:56<10:22, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|█████████████▎ | 36/221 [01:59<10:11, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 17%|█████████████▋ | 37/221 [02:04<11:00, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 17%|██████████████ | 38/221 [02:07<10:20, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▍ | 39/221 [02:10<10:37, 3.50s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▊ | 40/221 [02:13<10:01, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▏ | 41/221 [02:17<10:12, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▌ | 42/221 [02:21<11:08, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▉ | 43/221 [02:25<10:38, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▎ | 44/221 [02:29<11:39, 3.95s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▋ | 45/221 [02:34<12:10, 4.15s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████ | 46/221 [02:38<12:06, 4.15s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████▍ | 47/221 [02:42<11:55, 4.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|█████████████████▊ | 48/221 [02:46<11:50, 4.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|██████████████████▏ | 49/221 [02:50<11:24, 3.98s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▌ | 50/221 [02:54<11:24, 4.01s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▉ | 51/221 [02:57<10:44, 3.79s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▎ | 52/221 [03:00<09:59, 3.55s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▋ | 53/221 [03:03<09:23, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|████████████████████ | 54/221 [03:07<09:36, 3.45s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▍ | 55/221 [03:10<09:41, 3.50s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▊ | 56/221 [03:15<10:29, 3.81s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▏ | 57/221 [03:19<10:30, 3.85s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▌ | 58/221 [03:22<10:09, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|█████████████████████▉ | 59/221 [03:26<09:37, 3.56s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|██████████████████████▎ | 60/221 [03:28<08:49, 3.29s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|██████████████████████▋ | 61/221 [03:32<09:02, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|███████████████████████ | 62/221 [03:35<08:47, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|███████████████████████ | 62/221 [03:35<08:47, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|███████████████████████ | 62/221 [03:35<08:47, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|███████████████████████▋ | 64/221 [03:42<08:46, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|████████████████████████ | 65/221 [03:45<08:38, 3.33s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▍ | 66/221 [03:49<08:48, 3.41s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▊ | 67/221 [03:51<08:15, 3.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▏ | 68/221 [03:55<08:52, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▌ | 69/221 [03:59<08:33, 3.38s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|█████████████████████████▉ | 70/221 [04:02<08:27, 3.36s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|██████████████████████████▎ | 71/221 [04:05<08:16, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|██████████████████████████▋ | 72/221 [04:08<07:48, 3.14s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|███████████████████████████ | 73/221 [04:12<08:06, 3.29s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 33%|███████████████████████████▍ | 74/221 [04:15<07:59, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|███████████████████████████▊ | 75/221 [04:18<07:55, 3.25s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 34%|████████████████████████████▏ | 76/221 [04:21<07:49, 3.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▌ | 77/221 [04:24<07:46, 3.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▉ | 78/221 [04:28<07:53, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▉ | 78/221 [04:28<07:53, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▉ | 78/221 [04:28<07:53, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 36%|█████████████████████████████▋ | 80/221 [04:34<07:34, 3.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|██████████████████████████████ | 81/221 [04:38<07:56, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 37%|██████████████████████████████▍ | 82/221 [04:42<08:27, 3.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▊ | 83/221 [04:46<08:50, 3.85s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▏ | 84/221 [04:50<08:53, 3.89s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▌ | 85/221 [04:55<09:14, 4.07s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████▉ | 86/221 [04:59<08:53, 3.95s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|████████████████████████████████▎ | 87/221 [05:03<09:09, 4.10s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|████████████████████████████████▋ | 88/221 [05:06<08:33, 3.86s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|█████████████████████████████████ | 89/221 [05:10<08:03, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▍ | 90/221 [05:13<08:00, 3.67s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▊ | 91/221 [05:17<08:15, 3.81s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|██████████████████████████████████▏ | 92/221 [05:22<08:32, 3.98s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|██████████████████████████████████▌ | 93/221 [05:26<08:40, 4.06s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|██████████████████████████████████▉ | 94/221 [05:30<08:24, 3.97s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|███████████████████████████████████▏ | 95/221 [05:34<08:23, 3.99s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|███████████████████████████████████▌ | 96/221 [05:38<08:09, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▉ | 97/221 [05:42<08:20, 4.04s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|████████████████████████████████████▎ | 98/221 [05:46<08:07, 3.97s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 99/221 [05:48<07:21, 3.62s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 100/221 [05:52<07:20, 3.64s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████ | 101/221 [05:55<06:59, 3.49s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████▍ | 102/221 [05:58<06:36, 3.33s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|█████████████████████████████████████▊ | 103/221 [06:02<06:54, 3.51s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 47%|██████████████████████████████████████ | 104/221 [06:06<07:03, 3.62s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▍ | 105/221 [06:10<07:25, 3.84s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▊ | 106/221 [06:14<07:25, 3.88s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|███████████████████████████████████████▏ | 107/221 [06:18<06:56, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|███████████████████████████████████████▌ | 108/221 [06:22<07:13, 3.84s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 49%|███████████████████████████████████████▉ | 109/221 [06:26<07:16, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▎ | 110/221 [06:29<06:54, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▋ | 111/221 [06:32<06:35, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████ | 112/221 [06:36<06:40, 3.67s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████▍ | 113/221 [06:40<06:35, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|█████████████████████████████████████████▊ | 114/221 [06:43<06:19, 3.55s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|██████████████████████████████████████████▏ | 115/221 [06:47<06:14, 3.54s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|██████████████████████████████████████████▌ | 116/221 [06:50<06:01, 3.44s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|██████████████████████████████████████████▉ | 117/221 [06:53<05:55, 3.42s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|███████████████████████████████████████████▏ | 118/221 [06:57<06:03, 3.53s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▌ | 119/221 [07:01<06:24, 3.77s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▉ | 120/221 [07:06<06:38, 3.94s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▎ | 121/221 [07:09<06:24, 3.85s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▋ | 122/221 [07:12<05:39, 3.43s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████ | 123/221 [07:14<05:06, 3.12s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████▍ | 124/221 [07:17<05:01, 3.11s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|█████████████████████████████████████████████▊ | 125/221 [07:21<05:18, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████████▏ | 126/221 [07:24<05:00, 3.16s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 57%|██████████████████████████████████████████████▌ | 127/221 [07:27<04:46, 3.05s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|██████████████████████████████████████████████▉ | 128/221 [07:29<04:28, 2.89s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|███████████████████████████████████████████████▎ | 129/221 [07:33<04:49, 3.14s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|███████████████████████████████████████████████▋ | 130/221 [07:36<04:34, 3.02s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|████████████████████████████████████████████████ | 131/221 [07:39<04:48, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▍ | 132/221 [07:42<04:28, 3.01s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▋ | 133/221 [07:45<04:27, 3.04s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████ | 134/221 [07:48<04:16, 2.94s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████▍ | 135/221 [07:51<04:21, 3.05s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|█████████████████████████████████████████████████▊ | 136/221 [07:55<04:36, 3.26s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▏ | 137/221 [07:58<04:38, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▌ | 138/221 [08:02<04:47, 3.47s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|██████████████████████████████████████████████████▉ | 139/221 [08:06<04:49, 3.54s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|███████████████████████████████████████████████████▎ | 140/221 [08:08<04:20, 3.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|███████████████████████████████████████████████████▋ | 141/221 [08:11<04:17, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|████████████████████████████████████████████████████ | 142/221 [08:15<04:10, 3.17s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▍ | 143/221 [08:17<03:50, 2.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▊ | 144/221 [08:21<04:08, 3.23s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|█████████████████████████████████████████████████████▏ | 145/221 [08:24<04:03, 3.20s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|█████████████████████████████████████████████████████▌ | 146/221 [08:28<04:11, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|█████████████████████████████████████████████████████▉ | 147/221 [08:30<03:54, 3.16s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▏ | 148/221 [08:34<03:52, 3.18s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▌ | 149/221 [08:37<03:51, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|██████████████████████████████████████████████████████▉ | 150/221 [08:40<03:47, 3.20s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|███████████████████████████████████████████████████████▎ | 151/221 [08:44<03:56, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|███████████████████████████████████████████████████████▋ | 152/221 [08:47<03:49, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████████ | 153/221 [08:50<03:43, 3.28s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▍ | 154/221 [08:54<03:44, 3.35s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▊ | 155/221 [08:57<03:42, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▏ | 156/221 [09:01<03:42, 3.42s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▌ | 157/221 [09:03<03:25, 3.21s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▉ | 158/221 [09:08<03:48, 3.63s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|██████████████████████████████████████████████████████████▎ | 159/221 [09:12<03:47, 3.66s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 72%|██████████████████████████████████████████████████████████▋ | 160/221 [09:16<03:50, 3.79s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████ | 161/221 [09:20<03:54, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████▍ | 162/221 [09:24<03:51, 3.92s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|███████████████████████████████████████████████████████████▋ | 163/221 [09:28<03:55, 4.05s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████████ | 164/221 [09:33<03:59, 4.20s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▍ | 165/221 [09:36<03:44, 4.01s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▊ | 166/221 [09:40<03:25, 3.73s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▏ | 167/221 [09:43<03:18, 3.67s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▌ | 168/221 [09:46<03:04, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▉ | 169/221 [09:50<03:06, 3.58s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▎ | 170/221 [09:54<03:05, 3.63s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▋ | 171/221 [09:57<03:02, 3.64s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████ | 172/221 [10:01<02:52, 3.52s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████▍ | 173/221 [10:04<02:48, 3.50s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|███████████████████████████████████████████████████████████████▊ | 174/221 [10:07<02:39, 3.40s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:10<02:32, 3.32s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▌ | 176/221 [10:14<02:36, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▊ | 177/221 [10:17<02:25, 3.31s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▏ | 178/221 [10:21<02:29, 3.48s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▌ | 179/221 [10:24<02:23, 3.42s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▉ | 180/221 [10:28<02:29, 3.65s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▎ | 181/221 [10:32<02:29, 3.74s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▋ | 182/221 [10:36<02:25, 3.72s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████ | 183/221 [10:40<02:28, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████▍ | 184/221 [10:44<02:22, 3.86s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|███████████████████████████████████████████████████████████████████▊ | 185/221 [10:47<02:12, 3.69s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████████▏ | 186/221 [10:52<02:16, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▌ | 187/221 [10:55<02:07, 3.76s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▉ | 188/221 [10:59<02:07, 3.87s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▎ | 189/221 [11:03<02:05, 3.93s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▋ | 190/221 [11:08<02:06, 4.07s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████████ | 191/221 [11:12<02:06, 4.22s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▎ | 192/221 [11:17<02:02, 4.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▋ | 193/221 [11:20<01:50, 3.93s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████ | 194/221 [11:23<01:39, 3.70s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████▍ | 195/221 [11:26<01:30, 3.49s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|███████████████████████████████████████████████████████████████████████▊ | 196/221 [11:29<01:25, 3.43s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████████▏ | 197/221 [11:32<01:17, 3.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▌ | 198/221 [11:36<01:20, 3.52s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▉ | 199/221 [11:41<01:23, 3.80s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████████▎ | 200/221 [11:44<01:17, 3.70s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████████▋ | 201/221 [11:48<01:11, 3.59s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|██████████████████████████████████████████████████████████████████████████ | 202/221 [11:50<01:04, 3.37s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▍ | 203/221 [11:54<01:02, 3.45s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▊ | 204/221 [11:59<01:03, 3.75s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▏ | 205/221 [12:03<01:05, 4.08s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▌ | 206/221 [12:08<01:03, 4.24s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|███████████████████████████████████████████████████████████████████████████▊ | 207/221 [12:11<00:55, 4.00s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████████▏ | 208/221 [12:15<00:50, 3.91s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████████▌ | 209/221 [12:18<00:44, 3.70s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████████▉ | 210/221 [12:22<00:41, 3.77s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████████▎ | 211/221 [12:27<00:39, 3.96s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████████▋ | 212/221 [12:30<00:34, 3.88s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|██████████████████████████████████████████████████████████████████████████████ | 213/221 [12:33<00:28, 3.61s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▍ | 214/221 [12:37<00:25, 3.61s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▊ | 215/221 [12:41<00:22, 3.79s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:45<00:19, 3.89s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▌ | 217/221 [12:49<00:15, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████████▉ | 218/221 [12:53<00:11, 3.90s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████████▎| 219/221 [12:57<00:07, 3.87s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|████████████████████████████████████████████████████████████████████████████████▋| 220/221 [13:01<00:04, 4.06s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|█████████████████████████████████████████████████████████████████████████████████| 221/221 [13:03<00:00, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 100%|█████████████████████████████████████████████████████████████████████████████████| 221/221 [13:03<00:00, 3.39s/it][INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/01/2022 09:07:59 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|configuration_utils.py:438] 2022-03-01 09:07:59,039 >> Configuration saved in ./checkpoint-500/config.json [INFO|trainer.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/01/2022 09:09:48 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb']. This may take a bit of time if the files are large. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:08:15,475 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████ | 501/1189 [49:28<53:32:42, 280.18s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████ | 501/1189 [49:28<53:32:42, 280.18s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████ | 502/1189 [49:33<37:43:44, 197.71s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████ | 502/1189 [49:33<37:43:44, 197.71s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3156, 'learning_rate': 2.9880000000000002e-05, 'epoch': 0.42} 42%|████████████████████████████████ | 502/1189 [49:33<37:43:44, 197.71s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▏ | 503/1189 [49:38<26:40:40, 140.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▏ | 503/1189 [49:38<26:40:40, 140.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▋ | 504/1189 [49:43<18:56:32, 99.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▋ | 504/1189 [49:43<18:56:32, 99.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9769, 'learning_rate': 3e-05, 'epoch': 0.42} 42%|████████████████████████████████▋ | 504/1189 [49:43<18:56:32, 99.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▋ | 505/1189 [49:48<13:32:04, 71.24s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 42%|████████████████████████████████▋ | 505/1189 [49:48<13:32:04, 71.24s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3288, 'learning_rate': 2.9912917271407838e-05, 'epoch': 0.43} onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 507/1189 [49:59<7:06:48, 37.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 507/1189 [49:59<7:06:48, 37.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:04<5:15:50, 27.83s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▎ | 508/1189 [50:04<5:15:50, 27.83s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1491, 'learning_rate': 2.9825834542815675e-05, 'epoch': 0.43} 43%|█████████████████████████████████▍ | 509/1189 [50:09<3:57:57, 21.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 509/1189 [50:09<3:57:57, 21.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2185, 'learning_rate': 2.9782293178519592e-05, 'epoch': 0.43} 43%|█████████████████████████████████▍ | 510/1189 [50:14<3:04:30, 16.30s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▍ | 510/1189 [50:14<3:04:30, 16.30s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4993, 'learning_rate': 2.9738751814223512e-05, 'epoch': 0.43} 43%|█████████████████████████████████▌ | 511/1189 [50:20<2:26:28, 12.96s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▌ | 511/1189 [50:20<2:26:28, 12.96s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2993, 'learning_rate': 2.9695210449927432e-05, 'epoch': 0.43} 43%|█████████████████████████████████▌ | 512/1189 [50:25<1:59:02, 10.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▌ | 512/1189 [50:25<1:59:02, 10.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0531, 'learning_rate': 2.9651669085631353e-05, 'epoch': 0.43} 43%|█████████████████████████████████▋ | 513/1189 [50:30<1:41:02, 8.97s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 513/1189 [50:30<1:41:02, 8.97s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3561, 'learning_rate': 2.960812772133527e-05, 'epoch': 0.43} 43%|█████████████████████████████████▋ | 514/1189 [50:35<1:26:54, 7.73s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▋ | 514/1189 [50:35<1:26:54, 7.73s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0485, 'learning_rate': 2.956458635703919e-05, 'epoch': 0.43} 43%|█████████████████████████████████▊ | 515/1189 [50:39<1:17:05, 6.86s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▊ | 515/1189 [50:39<1:17:05, 6.86s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0402, 'learning_rate': 2.9521044992743107e-05, 'epoch': 0.43} 43%|█████████████████████████████████▊ | 516/1189 [50:44<1:10:09, 6.26s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▊ | 516/1189 [50:44<1:10:09, 6.26s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1555, 'learning_rate': 2.9477503628447024e-05, 'epoch': 0.43} 43%|█████████████████████████████████▉ | 517/1189 [50:49<1:04:58, 5.80s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 43%|█████████████████████████████████▉ | 517/1189 [50:49<1:04:58, 5.80s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2702, 'learning_rate': 2.9433962264150944e-05, 'epoch': 0.43} 44%|█████████████████████████████████▉ | 518/1189 [50:54<1:01:29, 5.50s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|█████████████████████████████████▉ | 518/1189 [50:54<1:01:29, 5.50s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1078, 'learning_rate': 2.9390420899854864e-05, 'epoch': 0.44} 44%|██████████████████████████████████▉ | 519/1189 [50:59<58:54, 5.28s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 519/1189 [50:59<58:54, 5.28s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5942, 'learning_rate': 2.934687953555878e-05, 'epoch': 0.44} 44%|██████████████████████████████████▉ | 520/1189 [51:03<57:09, 5.13s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|██████████████████████████████████▉ | 520/1189 [51:03<57:09, 5.13s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1278, 'learning_rate': 2.93033381712627e-05, 'epoch': 0.44} 44%|███████████████████████████████████ | 521/1189 [51:08<55:37, 5.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 521/1189 [51:08<55:37, 5.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2122, 'learning_rate': 2.925979680696662e-05, 'epoch': 0.44} 44%|███████████████████████████████████ | 521/1189 [51:08<55:37, 5.00s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 522/1189 [51:13<54:31, 4.91s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 522/1189 [51:13<54:31, 4.91s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████ | 522/1189 [51:13<54:31, 4.91s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 523/1189 [51:17<53:49, 4.85s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▏ | 523/1189 [51:17<53:49, 4.85s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 524/1189 [51:22<53:20, 4.81s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 524/1189 [51:22<53:20, 4.81s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2288, 'learning_rate': 2.9129172714078376e-05, 'epoch': 0.44} 44%|███████████████████████████████████▎ | 525/1189 [51:27<52:35, 4.75s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▎ | 525/1189 [51:27<52:35, 4.75s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2191, 'learning_rate': 2.9085631349782292e-05, 'epoch': 0.44} 44%|███████████████████████████████████▎ | 525/1189 [51:27<52:35, 4.75s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 526/1189 [51:31<51:51, 4.69s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 526/1189 [51:31<51:51, 4.69s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 526/1189 [51:31<51:51, 4.69s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 527/1189 [51:36<51:12, 4.64s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 527/1189 [51:36<51:12, 4.64s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▍ | 527/1189 [51:36<51:12, 4.64s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 528/1189 [51:40<50:31, 4.59s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 528/1189 [51:40<50:31, 4.59s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 529/1189 [51:45<50:01, 4.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 44%|███████████████████████████████████▌ | 529/1189 [51:45<50:01, 4.55s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4138, 'learning_rate': 2.8911465892597967e-05, 'epoch': 0.44} 45%|███████████████████████████████████▋ | 530/1189 [51:49<49:25, 4.50s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▋ | 530/1189 [51:49<49:25, 4.50s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3523, 'learning_rate': 2.8867924528301887e-05, 'epoch': 0.45} 45%|███████████████████████████████████▋ | 531/1189 [51:54<49:04, 4.47s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▋ | 531/1189 [51:54<49:04, 4.47s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3558, 'learning_rate': 2.8824383164005807e-05, 'epoch': 0.45} 45%|███████████████████████████████████▊ | 532/1189 [51:58<48:22, 4.42s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▊ | 532/1189 [51:58<48:22, 4.42s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3372, 'learning_rate': 2.8780841799709724e-05, 'epoch': 0.45} 45%|███████████████████████████████████▊ | 533/1189 [52:02<47:36, 4.35s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▊ | 533/1189 [52:02<47:36, 4.35s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2213, 'learning_rate': 2.8737300435413644e-05, 'epoch': 0.45} 45%|███████████████████████████████████▉ | 534/1189 [52:06<46:41, 4.28s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 534/1189 [52:06<46:41, 4.28s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2444, 'learning_rate': 2.8693759071117565e-05, 'epoch': 0.45} 45%|███████████████████████████████████▉ | 535/1189 [52:10<45:34, 4.18s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|███████████████████████████████████▉ | 535/1189 [52:10<45:34, 4.18s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1607, 'learning_rate': 2.865021770682148e-05, 'epoch': 0.45} 45%|████████████████████████████████████ | 536/1189 [52:14<44:40, 4.10s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████ | 536/1189 [52:14<44:40, 4.10s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.098, 'learning_rate': 2.86066763425254e-05, 'epoch': 0.45} 45%|████████████████████████████████████▏ | 537/1189 [52:18<43:44, 4.03s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 537/1189 [52:18<43:44, 4.03s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2933, 'learning_rate': 2.856313497822932e-05, 'epoch': 0.45} 45%|████████████████████████████████████▏ | 538/1189 [52:22<42:44, 3.94s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▏ | 538/1189 [52:22<42:44, 3.94s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9004, 'learning_rate': 2.8519593613933236e-05, 'epoch': 0.45} 45%|████████████████████████████████████▎ | 539/1189 [52:25<41:51, 3.86s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▎ | 539/1189 [52:25<41:51, 3.86s/it]onfig.jsonner.py:560] 2022-03-01 08:54:51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:13:22,552 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:13:22,552 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2941, 'learning_rate': 2.8432510885341076e-05, 'epoch': 0.45} [WARNING|modeling_utils.py:388] 2022-03-01 09:13:22,552 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 541/1189 [52:32<39:30, 3.66s/it]g-point operations will not be computed51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 541/1189 [52:32<39:30, 3.66s/it]g-point operations will not be computed51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 541/1189 [52:32<39:30, 3.66s/it]g-point operations will not be computed51,979 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▍ | 542/1189 [52:35<37:46, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:30,633 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [52:35<37:46, 3.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:30,633 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [52:38<36:01, 3.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:30,633 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:13:34,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:13:30,633 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:13:34,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:13:30,633 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.325, 'learning_rate': 2.825834542815675e-05, 'epoch': 0.46} [WARNING|modeling_utils.py:388] 2022-03-01 09:13:34,882 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:13:30,633 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [52:44<32:15, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:38,724 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [52:44<32:15, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:38,724 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [52:46<30:02, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:40,897 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [52:46<30:02, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:40,897 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▊ | 547/1189 [52:48<27:36, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:42,856 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▊ | 547/1189 [52:48<27:36, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:42,856 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████▊ | 548/1189 [52:50<25:09, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:44,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|████████████████████████████████████▊ | 548/1189 [52:50<25:09, 2.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:44,528 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.536, 'learning_rate': 2.804063860667634e-05, 'epoch': 0.46} 46%|█████████████████████████████████████ | 550/1189 [52:53<21:22, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:45,890 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████ | 550/1189 [52:53<21:22, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████ | 550/1189 [52:53<21:22, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████ | 551/1189 [52:59<32:29, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████ | 551/1189 [52:59<32:29, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████ | 551/1189 [52:59<32:29, 3.06s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:04<39:05, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:04<39:05, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:04<39:05, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:09<43:35, 4.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:09<43:35, 4.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:09<43:35, 4.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:09<43:35, 4.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3969, 'learning_rate': 2.7822931785195936e-05, 'epoch': 0.47} 47%|█████████████████████████████████████▏ | 553/1189 [53:09<43:35, 4.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:09<43:35, 4.11s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:19<48:51, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:19<48:51, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:19<48:51, 4.62s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:24<49:52, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:24<49:52, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:24<49:52, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:29<50:47, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:29<50:47, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:34<50:59, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:34<50:59, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1572, 'learning_rate': 2.764876632801161e-05, 'epoch': 0.47} 47%|█████████████████████████████████████▌ | 558/1189 [53:34<50:59, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:39<51:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:39<51:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:39<51:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▋ | 560/1189 [53:44<51:26, 4.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▋ | 560/1189 [53:44<51:26, 4.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████▋ | 560/1189 [53:44<51:26, 4.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:49<51:26, 4.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:49<51:26, 4.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:49<51:26, 4.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:54<51:12, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:54<51:12, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:59<50:42, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [53:59<50:42, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.36, 'learning_rate': 2.7431059506531205e-05, 'epoch': 0.47} 47%|█████████████████████████████████████▉ | 563/1189 [53:59<50:42, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:04<50:23, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:04<50:23, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:04<50:23, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:08<50:17, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:08<50:17, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████ | 566/1189 [54:13<50:09, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████ | 566/1189 [54:13<50:09, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 2.7300435413642962e-05, 'epoch': 0.48} 48%|██████████████████████████████████████ | 566/1189 [54:13<50:09, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:18<49:57, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:18<49:57, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:23<49:33, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:23<49:33, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3216, 'learning_rate': 2.72133526850508e-05, 'epoch': 0.48} 48%|██████████████████████████████████████▎ | 569/1189 [54:27<49:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:27<49:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0335, 'learning_rate': 2.716981132075472e-05, 'epoch': 0.48} 48%|██████████████████████████████████████▎ | 569/1189 [54:27<49:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:27<49:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1294, 'learning_rate': 2.7126269956458637e-05, 'epoch': 0.48} 48%|██████████████████████████████████████▎ | 569/1189 [54:27<49:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:27<49:05, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:37<48:16, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:37<48:16, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:37<48:16, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▍ | 572/1189 [54:41<47:49, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████▍ | 572/1189 [54:41<47:49, 4.65s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:46<47:19, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:46<47:19, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1821, 'learning_rate': 2.6995645863570394e-05, 'epoch': 0.48} 48%|██████████████████████████████████████▌ | 574/1189 [54:50<47:12, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:50<47:12, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3712, 'learning_rate': 2.695210449927431e-05, 'epoch': 0.48} 48%|██████████████████████████████████████▌ | 574/1189 [54:50<47:12, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:50<47:12, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:55<46:58, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:55<46:58, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:55<46:58, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:59<46:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [54:59<46:24, 4.54s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:04<46:12, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:04<46:12, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3666, 'learning_rate': 2.6821480406386065e-05, 'epoch': 0.49} 49%|██████████████████████████████████████▉ | 578/1189 [55:08<45:46, 4.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:08<45:46, 4.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1713, 'learning_rate': 2.6777939042089985e-05, 'epoch': 0.49} 49%|██████████████████████████████████████▉ | 579/1189 [55:13<45:19, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:13<45:19, 4.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2383, 'learning_rate': 2.6734397677793905e-05, 'epoch': 0.49} 49%|███████████████████████████████████████ | 580/1189 [55:17<44:44, 4.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████ | 580/1189 [55:17<44:44, 4.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2657, 'learning_rate': 2.6690856313497822e-05, 'epoch': 0.49} 49%|███████████████████████████████████████ | 581/1189 [55:21<44:08, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████ | 581/1189 [55:21<44:08, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4122, 'learning_rate': 2.6647314949201743e-05, 'epoch': 0.49} 49%|███████████████████████████████████████▏ | 582/1189 [55:25<43:46, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▏ | 582/1189 [55:25<43:46, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0174, 'learning_rate': 2.6603773584905663e-05, 'epoch': 0.49} 49%|███████████████████████████████████████▏ | 582/1189 [55:25<43:46, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:30<43:22, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:30<43:22, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:30<43:22, 4.29s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:34<42:40, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:34<42:40, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:34<42:40, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▎ | 585/1189 [55:38<41:50, 4.16s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▎ | 585/1189 [55:38<41:50, 4.16s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▎ | 585/1189 [55:38<41:50, 4.16s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:42<41:02, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:42<41:02, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:42<41:02, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:45<40:17, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:45<40:17, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:45<40:17, 4.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:49<39:24, 3.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:49<39:24, 3.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:49<39:24, 3.93s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [55:53<38:30, 3.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:16:49,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:16:49,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.194, 'learning_rate': 2.625544267053701e-05, 'epoch': 0.5} [WARNING|modeling_utils.py:388] 2022-03-01 09:16:49,944 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▊ | 591/1189 [56:00<35:57, 3.61s/it]g-point operations will not be computed-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▊ | 591/1189 [56:00<35:57, 3.61s/it]g-point operations will not be computed-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████▊ | 591/1189 [56:00<35:57, 3.61s/it]g-point operations will not be computed-01 09:13:49,851 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:03<34:22, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:16:57,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|███████████████████████████████████████▊ | 592/1189 [56:03<34:22, 3.46s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:16:57,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|███████████████████████████████████████▉ | 593/1189 [56:06<32:34, 3.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:16:57,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:17:01,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:16:57,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:17:01,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:16:57,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.224, 'learning_rate': 2.6081277213352686e-05, 'epoch': 0.5} [WARNING|modeling_utils.py:388] 2022-03-01 09:17:01,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:16:57,841 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████ | 595/1189 [56:11<28:35, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:05,453 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████ | 595/1189 [56:11<28:35, 2.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:05,453 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████ | 596/1189 [56:13<26:23, 2.67s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:07,511 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████ | 596/1189 [56:13<26:23, 2.67s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:07,511 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2776, 'learning_rate': 2.5950653120464443e-05, 'epoch': 0.5} 50%|████████████████████████████████████████▏ | 598/1189 [56:16<21:52, 2.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:09,311 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▏ | 598/1189 [56:16<21:52, 2.22s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:09,311 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▎ | 599/1189 [56:18<19:33, 1.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:12,234 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▎ | 599/1189 [56:18<19:33, 1.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:12,234 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▎ | 600/1189 [56:20<19:05, 1.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:12,234 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████▎ | 600/1189 [56:20<19:05, 1.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:25<29:15, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:25<29:15, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1329, 'learning_rate': 2.5776487663280117e-05, 'epoch': 0.51} 51%|████████████████████████████████████████▍ | 601/1189 [56:25<29:15, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:30<35:20, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:30<35:20, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:30<35:20, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:35<39:44, 4.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:35<39:44, 4.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:35<39:44, 4.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:40<42:36, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:40<42:36, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:40<42:36, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:40<42:36, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2021, 'learning_rate': 2.5602322206095792e-05, 'epoch': 0.51} 51%|████████████████████████████████████████▋ | 604/1189 [56:40<42:36, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:51<45:52, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:51<45:52, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:55<46:26, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [56:55<46:26, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1938, 'learning_rate': 2.551523947750363e-05, 'epoch': 0.51} [WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3898, 'learning_rate': 2.547169811320755e-05, 'epoch': 0.51} [WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:05<47:09, 4.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:05<47:09, 4.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2565, 'learning_rate': 2.5428156748911466e-05, 'epoch': 0.51} 51%|█████████████████████████████████████████ | 610/1189 [57:10<47:13, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:10<47:13, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:18:08,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:18:08,824 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2616, 'learning_rate': 2.5341074020319303e-05, 'epoch': 0.51} 51%|█████████████████████████████████████████▏ | 612/1189 [57:20<46:46, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:20<46:46, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0055, 'learning_rate': 2.529753265602322e-05, 'epoch': 0.51} 52%|█████████████████████████████████████████▏ | 613/1189 [57:25<46:41, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:25<46:41, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2784, 'learning_rate': 2.525399129172714e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▏ | 613/1189 [57:25<46:41, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:30<46:36, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:30<46:36, 4.86s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1826, 'learning_rate': 2.516690856313498e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▍ | 615/1189 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2279, 'learning_rate': 2.5123367198838898e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▍ | 615/1189 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1516, 'learning_rate': 2.5079825834542818e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▍ | 615/1189 [57:35<46:22, 4.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:49<44:54, 4.72s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:49<44:54, 4.72s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1771, 'learning_rate': 2.5036284470246735e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▋ | 619/1189 [57:53<44:43, 4.71s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:53<44:43, 4.71s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 2.4992743105950652e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▋ | 620/1189 [57:58<44:32, 4.70s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [57:58<44:32, 4.70s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1977, 'learning_rate': 2.4949201741654572e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▊ | 621/1189 [58:03<44:19, 4.68s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:03<44:19, 4.68s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9837, 'learning_rate': 2.4905660377358492e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▊ | 622/1189 [58:07<43:55, 4.65s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:07<43:55, 4.65s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8723, 'learning_rate': 2.486211901306241e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▉ | 623/1189 [58:12<43:28, 4.61s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:12<43:28, 4.61s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3487, 'learning_rate': 2.481857764876633e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▉ | 624/1189 [58:16<42:55, 4.56s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:16<42:55, 4.56s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2749, 'learning_rate': 2.477503628447025e-05, 'epoch': 0.52} 52%|█████████████████████████████████████████▉ | 624/1189 [58:16<42:55, 4.56s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████ | 625/1189 [58:21<42:29, 4.52s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████ | 625/1189 [58:21<42:29, 4.52s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:25<41:59, 4.47s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:25<41:59, 4.47s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4245, 'learning_rate': 2.4687953555878083e-05, 'epoch': 0.53} 53%|██████████████████████████████████████████▏ | 627/1189 [58:29<41:33, 4.44s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:29<41:33, 4.44s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 2.4644412191582004e-05, 'epoch': 0.53} 53%|██████████████████████████████████████████▎ | 628/1189 [58:34<41:20, 4.42s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:34<41:20, 4.42s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:19:31,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:19:31,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1001, 'learning_rate': 2.455732946298984e-05, 'epoch': 0.53} [WARNING|modeling_utils.py:388] 2022-03-01 09:19:31,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:19:31,555 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:42<40:36, 4.36s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:42<40:36, 4.36s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:42<40:36, 4.36s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:46<40:15, 4.33s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:46<40:15, 4.33s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:46<40:15, 4.33s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:51<39:47, 4.29s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:19:48,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:19:48,355 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2713, 'learning_rate': 2.4383164005805515e-05, 'epoch': 0.53} 53%|██████████████████████████████████████████▋ | 634/1189 [58:59<38:28, 4.16s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [58:59<38:28, 4.16s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1611, 'learning_rate': 2.4339622641509435e-05, 'epoch': 0.53} 53%|██████████████████████████████████████████▋ | 635/1189 [59:03<37:48, 4.09s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:03<37:48, 4.09s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3203, 'learning_rate': 2.4296081277213352e-05, 'epoch': 0.53} 53%|██████████████████████████████████████████▊ | 636/1189 [59:07<37:18, 4.05s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:07<37:18, 4.05s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1684, 'learning_rate': 2.4252539912917273e-05, 'epoch': 0.53} 54%|██████████████████████████████████████████▊ | 637/1189 [59:10<36:46, 4.00s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:10<36:46, 4.00s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8974, 'learning_rate': 2.4208998548621193e-05, 'epoch': 0.54} 54%|██████████████████████████████████████████▉ | 638/1189 [59:14<35:59, 3.92s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:14<35:59, 3.92s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.117, 'learning_rate': 2.416545718432511e-05, 'epoch': 0.54} 54%|██████████████████████████████████████████▉ | 639/1189 [59:18<35:16, 3.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:18<35:16, 3.85s/it]g-point operations will not be computed-01 09:17:16,238 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1567, 'learning_rate': 2.4121915820029027e-05, 'epoch': 0.54} 54%|███████████████████████████████████████████ | 640/1189 [59:21<34:11, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:16,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████ | 640/1189 [59:21<34:11, 3.74s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:16,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▏ | 641/1189 [59:25<32:51, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:16,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▏ | 641/1189 [59:25<32:51, 3.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:16,770 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.161, 'learning_rate': 2.4034833091436864e-05, 'epoch': 0.54} 54%|███████████████████████████████████████████▏ | 642/1189 [59:28<31:17, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████▏ | 642/1189 [59:28<31:17, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:30<29:24, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:30<29:24, 3.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:26,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:26,647 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:28,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:28,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:30,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:30,975 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:32,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:32,858 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:34,518 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:34,518 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:35,938 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:35,938 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:37,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:37,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6649, 'learning_rate': 2.3642960812772136e-05, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-03-01 09:20:37,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:20:37,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3659, 'learning_rate': 2.3599419448476053e-05, 'epoch': 0.55} [WARNING|modeling_utils.py:388] 2022-03-01 09:20:37,704 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:54<31:56, 3.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [59:54<31:56, 3.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1146, 'learning_rate': 2.3555878084179973e-05, 'epoch': 0.55} 55%|███████████████████████████████████████████▊ | 652/1189 [59:54<31:56, 3.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:00<36:13, 4.05s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:00<36:13, 4.05s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:05<38:53, 4.36s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:05<38:53, 4.36s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.228, 'learning_rate': 2.3468795355587807e-05, 'epoch': 0.55} 55%|██████████████████████████████████████████▉ | 655/1189 [1:00:10<40:39, 4.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████▉ | 655/1189 [1:00:10<40:39, 4.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2048, 'learning_rate': 2.3425253991291727e-05, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 656/1189 [1:00:15<41:46, 4.70s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:15<41:46, 4.70s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.186, 'learning_rate': 2.3381712626995647e-05, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 657/1189 [1:00:20<42:16, 4.77s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:20<42:16, 4.77s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 2.3338171262699564e-05, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 657/1189 [1:00:20<42:16, 4.77s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:20<42:16, 4.77s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:20<42:16, 4.77s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2268, 'learning_rate': 2.3294629898403485e-05, 'epoch': 0.55} 55%|███████████████████████████████████████████ | 657/1189 [1:00:20<42:16, 4.77s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:30<43:01, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:30<43:01, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:30<43:01, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:35<42:57, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:35<42:57, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:35<42:57, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:35<42:57, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2022, 'learning_rate': 2.316400580551524e-05, 'epoch': 0.56} 56%|███████████████████████████████████████████▎ | 660/1189 [1:00:35<42:57, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:35<42:57, 4.87s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:44<42:36, 4.85s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:44<42:36, 4.85s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:44<42:36, 4.85s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:49<42:26, 4.84s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:49<42:26, 4.84s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:54<42:16, 4.83s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:54<42:16, 4.83s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1408, 'learning_rate': 2.3033381712626996e-05, 'epoch': 0.56} 56%|███████████████████████████████████████████▌ | 664/1189 [1:00:54<42:16, 4.83s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:59<42:07, 4.82s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:00:59<42:07, 4.82s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:03<41:37, 4.78s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:03<41:37, 4.78s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2757, 'learning_rate': 2.2946298984034833e-05, 'epoch': 0.56} 56%|███████████████████████████████████████████▊ | 667/1189 [1:01:08<41:08, 4.73s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████▊ | 667/1189 [1:01:08<41:08, 4.73s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3083, 'learning_rate': 2.290275761973875e-05, 'epoch': 0.56} 56%|███████████████████████████████████████████▊ | 668/1189 [1:01:12<40:39, 4.68s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████▊ | 668/1189 [1:01:12<40:39, 4.68s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1377, 'learning_rate': 2.285921625544267e-05, 'epoch': 0.56} 56%|███████████████████████████████████████████▊ | 668/1189 [1:01:12<40:39, 4.68s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:17<40:27, 4.67s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:17<40:27, 4.67s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:22<40:20, 4.66s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:22<40:20, 4.66s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1153, 'learning_rate': 2.2772133526850507e-05, 'epoch': 0.56} 56%|████████████████████████████████████████████ | 671/1189 [1:01:26<40:06, 4.65s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:26<40:06, 4.65s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2722, 'learning_rate': 2.2728592162554428e-05, 'epoch': 0.56} 57%|████████████████████████████████████████████ | 672/1189 [1:01:31<39:51, 4.62s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:31<39:51, 4.62s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1801, 'learning_rate': 2.2685050798258348e-05, 'epoch': 0.56} 57%|████████████████████████████████████████████▏ | 673/1189 [1:01:35<39:24, 4.58s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:35<39:24, 4.58s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2868, 'learning_rate': 2.2641509433962265e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▏ | 674/1189 [1:01:40<39:14, 4.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:40<39:14, 4.57s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2577, 'learning_rate': 2.259796806966618e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▎ | 675/1189 [1:01:44<38:45, 4.52s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:44<38:45, 4.52s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1359, 'learning_rate': 2.2554426705370102e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▎ | 676/1189 [1:01:49<38:29, 4.50s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:49<38:29, 4.50s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9345, 'learning_rate': 2.2510885341074022e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▍ | 677/1189 [1:01:53<38:00, 4.45s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:53<38:00, 4.45s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3573, 'learning_rate': 2.246734397677794e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▍ | 678/1189 [1:01:57<37:32, 4.41s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:01:57<37:32, 4.41s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1647, 'learning_rate': 2.242380261248186e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▌ | 679/1189 [1:02:02<37:07, 4.37s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:02<37:07, 4.37s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1087, 'learning_rate': 2.238026124818578e-05, 'epoch': 0.57} 57%|████████████████████████████████████████████▌ | 679/1189 [1:02:02<37:07, 4.37s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:06<36:42, 4.33s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:06<36:42, 4.33s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:06<36:42, 4.33s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:10<36:25, 4.30s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:10<36:25, 4.30s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:10<36:25, 4.30s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:14<36:07, 4.28s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:14<36:07, 4.28s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:14<36:07, 4.28s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:19<35:35, 4.22s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:19<35:35, 4.22s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:19<35:35, 4.22s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████▊ | 684/1189 [1:02:23<34:56, 4.15s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████▊ | 684/1189 [1:02:23<34:56, 4.15s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████▊ | 684/1189 [1:02:23<34:56, 4.15s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:26<34:22, 4.09s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:26<34:22, 4.09s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:26<34:22, 4.09s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:30<33:39, 4.01s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:30<33:39, 4.01s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:30<33:39, 4.01s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:34<33:04, 3.95s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:34<33:04, 3.95s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:34<33:04, 3.95s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:38<32:22, 3.88s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:34,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:34,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3217, 'learning_rate': 2.1944847605224965e-05, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-03-01 09:23:34,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:44<29:51, 3.59s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:41,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:41,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.5591, 'learning_rate': 2.1857764876632802e-05, 'epoch': 0.58} [WARNING|modeling_utils.py:388] 2022-03-01 09:23:41,224 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:50<27:04, 3.27s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:50<27:04, 3.27s/it]g-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:46,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:46,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:23:46,696 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:20:22,835 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:02:58<21:39, 2.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:50,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|█████████████████████████████████████████████▌ | 695/1189 [1:02:58<21:39, 2.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:50,199 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▋ | 696/1189 [1:02:59<19:54, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:52,228 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████▋ | 696/1189 [1:02:59<19:54, 2.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:52,228 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1249, 'learning_rate': 2.1640058055152394e-05, 'epoch': 0.59} 59%|█████████████████████████████████████████████▋ | 697/1189 [1:03:01<18:17, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:54,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▋ | 697/1189 [1:03:01<18:17, 2.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:54,074 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▊ | 698/1189 [1:03:03<16:44, 2.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:55,776 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:03:03<16:44, 2.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:55,776 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:03:04<15:06, 1.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:58,570 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:03:04<15:06, 1.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:58,570 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:03:06<14:50, 1.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:23:58,570 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:03:06<14:50, 1.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▉ | 700/1189 [1:03:06<14:50, 1.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▉ | 701/1189 [1:03:11<23:41, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▉ | 701/1189 [1:03:11<23:41, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|█████████████████████████████████████████████▉ | 701/1189 [1:03:11<23:41, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████ | 702/1189 [1:03:17<29:07, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████ | 702/1189 [1:03:17<29:07, 3.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████ | 703/1189 [1:03:22<32:38, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████ | 703/1189 [1:03:22<32:38, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1881, 'learning_rate': 2.1335268505079825e-05, 'epoch': 0.59} 59%|██████████████████████████████████████████████ | 703/1189 [1:03:22<32:38, 4.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▏ | 704/1189 [1:03:27<35:02, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▏ | 704/1189 [1:03:27<35:02, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▏ | 704/1189 [1:03:27<35:02, 4.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▏ | 705/1189 [1:03:32<36:42, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▏ | 705/1189 [1:03:32<36:42, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▏ | 705/1189 [1:03:32<36:42, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▎ | 706/1189 [1:03:37<37:44, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▎ | 706/1189 [1:03:37<37:44, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▍ | 707/1189 [1:03:42<38:33, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|██████████████████████████████████████████████▍ | 707/1189 [1:03:42<38:33, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1645, 'learning_rate': 2.1161103047895503e-05, 'epoch': 0.59} 59%|██████████████████████████████████████████████▍ | 707/1189 [1:03:42<38:33, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 708/1189 [1:03:47<38:55, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 708/1189 [1:03:47<38:55, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▍ | 708/1189 [1:03:47<38:55, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 709/1189 [1:03:52<38:59, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 709/1189 [1:03:52<38:59, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 709/1189 [1:03:52<38:59, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 710/1189 [1:03:57<39:02, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 710/1189 [1:03:57<39:02, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▌ | 710/1189 [1:03:57<39:02, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▋ | 711/1189 [1:04:01<38:45, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▋ | 711/1189 [1:04:01<38:45, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▋ | 711/1189 [1:04:01<38:45, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▋ | 712/1189 [1:04:06<38:35, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▋ | 712/1189 [1:04:06<38:35, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.165, 'learning_rate': 2.0899854862119014e-05, 'epoch': 0.6} [WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▊ | 714/1189 [1:04:16<38:17, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▊ | 714/1189 [1:04:16<38:17, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▉ | 715/1189 [1:04:21<37:57, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▉ | 715/1189 [1:04:21<37:57, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1871, 'learning_rate': 2.0812772133526848e-05, 'epoch': 0.6} 60%|██████████████████████████████████████████████▉ | 716/1189 [1:04:25<37:45, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▉ | 716/1189 [1:04:25<37:45, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0522, 'learning_rate': 2.076923076923077e-05, 'epoch': 0.6} 60%|██████████████████████████████████████████████▉ | 716/1189 [1:04:25<37:45, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|██████████████████████████████████████████████▉ | 716/1189 [1:04:25<37:45, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0718, 'learning_rate': 2.072568940493469e-05, 'epoch': 0.6} 60%|██████████████████████████████████████████████▉ | 716/1189 [1:04:25<37:45, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|███████████████████████████████████████████████ | 718/1189 [1:04:35<37:18, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|███████████████████████████████████████████████ | 718/1189 [1:04:35<37:18, 4.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3626, 'learning_rate': 2.068214804063861e-05, 'epoch': 0.6} 60%|███████████████████████████████████████████████▏ | 719/1189 [1:04:40<36:56, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|███████████████████████████████████████████████▏ | 719/1189 [1:04:40<36:56, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1405, 'learning_rate': 2.0638606676342526e-05, 'epoch': 0.6} 61%|███████████████████████████████████████████████▏ | 720/1189 [1:04:44<36:39, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▏ | 720/1189 [1:04:44<36:39, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0301, 'learning_rate': 2.0595065312046446e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▏ | 720/1189 [1:04:44<36:39, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▏ | 720/1189 [1:04:44<36:39, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.111, 'learning_rate': 2.0551523947750363e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▏ | 720/1189 [1:04:44<36:39, 4.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 722/1189 [1:04:53<36:02, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▎ | 722/1189 [1:04:53<36:02, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9836, 'learning_rate': 2.050798258345428e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▍ | 723/1189 [1:04:58<35:43, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▍ | 723/1189 [1:04:58<35:43, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1762, 'learning_rate': 2.04644412191582e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▍ | 724/1189 [1:05:02<35:20, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▍ | 724/1189 [1:05:02<35:20, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0696, 'learning_rate': 2.042089985486212e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▌ | 725/1189 [1:05:07<35:01, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▌ | 725/1189 [1:05:07<35:01, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.217, 'learning_rate': 2.0377358490566037e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▋ | 726/1189 [1:05:11<34:52, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▋ | 726/1189 [1:05:11<34:52, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2628, 'learning_rate': 2.0333817126269958e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▋ | 726/1189 [1:05:11<34:52, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▋ | 727/1189 [1:05:16<34:28, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▋ | 727/1189 [1:05:16<34:28, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▋ | 727/1189 [1:05:16<34:28, 4.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:24:02,517 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▊ | 728/1189 [1:05:20<34:04, 4.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▊ | 729/1189 [1:05:24<33:47, 4.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▊ | 729/1189 [1:05:24<33:47, 4.41s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9628, 'learning_rate': 2.020319303338171e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▉ | 730/1189 [1:05:29<33:21, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▉ | 730/1189 [1:05:29<33:21, 4.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.308, 'learning_rate': 2.0159651669085632e-05, 'epoch': 0.61} 61%|███████████████████████████████████████████████▉ | 731/1189 [1:05:33<32:57, 4.32s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|███████████████████████████████████████████████▉ | 731/1189 [1:05:33<32:57, 4.32s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2634, 'learning_rate': 2.011611030478955e-05, 'epoch': 0.61} 62%|████████████████████████████████████████████████ | 732/1189 [1:05:37<32:33, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 732/1189 [1:05:37<32:33, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4191, 'learning_rate': 2.007256894049347e-05, 'epoch': 0.62} 62%|████████████████████████████████████████████████ | 732/1189 [1:05:37<32:33, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 733/1189 [1:05:41<32:09, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 733/1189 [1:05:41<32:09, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████ | 733/1189 [1:05:41<32:09, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▏ | 734/1189 [1:05:45<31:52, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▏ | 734/1189 [1:05:45<31:52, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▏ | 734/1189 [1:05:45<31:52, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▏ | 735/1189 [1:05:49<31:25, 4.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▏ | 735/1189 [1:05:49<31:25, 4.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▏ | 735/1189 [1:05:49<31:25, 4.15s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▎ | 736/1189 [1:05:53<30:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▎ | 736/1189 [1:05:53<30:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▎ | 736/1189 [1:05:53<30:55, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▎ | 737/1189 [1:05:57<30:24, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▎ | 737/1189 [1:05:57<30:24, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▎ | 737/1189 [1:05:57<30:24, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▍ | 738/1189 [1:06:01<29:54, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▍ | 738/1189 [1:06:01<29:54, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▍ | 738/1189 [1:06:01<29:54, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▍ | 739/1189 [1:06:05<29:02, 3.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:27:01,790 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:27:01,790 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0711, 'learning_rate': 1.972423802612482e-05, 'epoch': 0.62} [WARNING|modeling_utils.py:388] 2022-03-01 09:27:01,790 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▌ | 741/1189 [1:06:11<27:14, 3.65s/it]g-point operations will not be computed-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▌ | 741/1189 [1:06:11<27:14, 3.65s/it]g-point operations will not be computed-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▌ | 741/1189 [1:06:11<27:14, 3.65s/it]g-point operations will not be computed-01 09:26:15,864 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|████████████████████████████████████████████████▋ | 742/1189 [1:06:15<25:54, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:09,755 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:06:15<25:54, 3.48s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:09,755 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:06:17<24:30, 3.30s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:09,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:27:13,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:27:09,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:27:13,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:27:09,755 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3362, 'learning_rate': 1.9550072568940492e-05, 'epoch': 0.63} [WARNING|modeling_utils.py:388] 2022-03-01 09:27:13,787 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:27:09,755 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:06:23<21:30, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:17,389 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:06:23<21:30, 2.91s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:17,389 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:06:25<19:49, 2.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:19,435 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:06:25<19:49, 2.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:19,435 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████ | 748/1189 [1:06:28<16:29, 2.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:21,257 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████ | 748/1189 [1:06:28<16:29, 2.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:21,257 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.6952, 'learning_rate': 1.937590711175617e-05, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▏ | 749/1189 [1:06:30<14:52, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:24,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|█████████████████████████████████████████████████▏ | 749/1189 [1:06:30<14:52, 2.03s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:24,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|█████████████████████████████████████████████████▏ | 750/1189 [1:06:32<14:23, 1.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:24,314 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|█████████████████████████████████████████████████▏ | 750/1189 [1:06:32<14:23, 1.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▏ | 750/1189 [1:06:32<14:23, 1.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▎ | 751/1189 [1:06:37<22:00, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▎ | 751/1189 [1:06:37<22:00, 3.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▎ | 752/1189 [1:06:42<26:40, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▎ | 752/1189 [1:06:42<26:40, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.2307, 'learning_rate': 1.9201741654571844e-05, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▎ | 752/1189 [1:06:42<26:40, 3.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▍ | 753/1189 [1:06:47<29:46, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▍ | 753/1189 [1:06:47<29:46, 4.10s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:06:53<31:42, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:06:53<31:42, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.0733, 'learning_rate': 1.911465892597968e-05, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:06:53<31:42, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:06:53<31:42, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.279, 'learning_rate': 1.90711175616836e-05, 'epoch': 0.63} 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:06:53<31:42, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 63%|█████████████████████████████████████████████████▍ | 754/1189 [1:06:53<31:42, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▌ | 756/1189 [1:07:03<33:58, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▌ | 756/1189 [1:07:03<33:58, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▋ | 757/1189 [1:07:08<34:29, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▋ | 757/1189 [1:07:08<34:29, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.1397, 'learning_rate': 1.8984034833091435e-05, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▋ | 757/1189 [1:07:08<34:29, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▋ | 758/1189 [1:07:12<34:43, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▋ | 758/1189 [1:07:12<34:43, 4.83s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▊ | 759/1189 [1:07:17<34:53, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▊ | 759/1189 [1:07:17<34:53, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.1564, 'learning_rate': 1.8896952104499276e-05, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▊ | 759/1189 [1:07:17<34:53, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▊ | 760/1189 [1:07:22<34:56, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▊ | 760/1189 [1:07:22<34:56, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▊ | 760/1189 [1:07:22<34:56, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▉ | 761/1189 [1:07:27<34:42, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▉ | 761/1189 [1:07:27<34:42, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▉ | 762/1189 [1:07:32<34:36, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|█████████████████████████████████████████████████▉ | 762/1189 [1:07:32<34:36, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.1269, 'learning_rate': 1.8766328011611033e-05, 'epoch': 0.64} 64%|█████████████████████████████████████████████████▉ | 762/1189 [1:07:32<34:36, 4.86s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████ | 763/1189 [1:07:37<34:21, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████ | 763/1189 [1:07:37<34:21, 4.84s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████ | 764/1189 [1:07:42<34:05, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████ | 764/1189 [1:07:42<34:05, 4.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.057, 'learning_rate': 1.8679245283018867e-05, 'epoch': 0.64} 64%|██████████████████████████████████████████████████▏ | 765/1189 [1:07:46<33:53, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████▏ | 765/1189 [1:07:46<33:53, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.2914, 'learning_rate': 1.8635703918722787e-05, 'epoch': 0.64} 64%|██████████████████████████████████████████████████▏ | 765/1189 [1:07:46<33:53, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████▎ | 766/1189 [1:07:51<33:36, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 64%|██████████████████████████████████████████████████▎ | 766/1189 [1:07:51<33:36, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▎ | 767/1189 [1:07:56<33:18, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▎ | 767/1189 [1:07:56<33:18, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.1764, 'learning_rate': 1.8548621190130624e-05, 'epoch': 0.64} 65%|██████████████████████████████████████████████████▍ | 768/1189 [1:08:00<33:08, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▍ | 768/1189 [1:08:00<33:08, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 3.9162, 'learning_rate': 1.8505079825834544e-05, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:05<32:46, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:05<32:46, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.1707, 'learning_rate': 1.8461538461538465e-05, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:05<32:46, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:05<32:46, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.3203, 'learning_rate': 1.8417997097242378e-05, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:05<32:46, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▍ | 769/1189 [1:08:05<32:46, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▌ | 771/1189 [1:08:14<32:27, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▌ | 771/1189 [1:08:14<32:27, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▌ | 771/1189 [1:08:14<32:27, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▋ | 772/1189 [1:08:19<32:14, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▋ | 772/1189 [1:08:19<32:14, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▋ | 773/1189 [1:08:23<31:56, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▋ | 773/1189 [1:08:23<31:56, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.0481, 'learning_rate': 1.8287373004354136e-05, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▋ | 773/1189 [1:08:23<31:56, 4.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▊ | 774/1189 [1:08:28<31:29, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▊ | 774/1189 [1:08:28<31:29, 4.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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] 2022-03-01 09:27:28,255 >> 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] 2022-03-01 09:27:28,255 >> 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': 4.1995, 'learning_rate': 1.8200290275761976e-05, 'epoch': 0.65} [WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▉ | 776/1189 [1:08:37<31:04, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▉ | 776/1189 [1:08:37<31:04, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▉ | 776/1189 [1:08:37<31:04, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▉ | 776/1189 [1:08:37<31:04, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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': 4.1521, 'learning_rate': 1.811320754716981e-05, 'epoch': 0.65} 65%|██████████████████████████████████████████████████▉ | 776/1189 [1:08:37<31:04, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|██████████████████████████████████████████████████▉ | 776/1189 [1:08:37<31:04, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|███████████████████████████████████████████████████ | 778/1189 [1:08:45<30:21, 4.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|███████████████████████████████████████████████████ | 778/1189 [1:08:45<30:21, 4.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 65%|███████████████████████████████████████████████████ | 778/1189 [1:08:45<30:21, 4.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████ | 779/1189 [1:08:50<29:50, 4.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:27:28,255 >> 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] 2022-03-01 09:29:47,601 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:27:28,255 >> 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] 2022-03-01 09:29:47,601 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:27:28,255 >> 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': 4.2847, 'learning_rate': 1.7982583454281567e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▏ | 781/1189 [1:08:58<29:14, 4.30s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▏ | 781/1189 [1:08:58<29:14, 4.30s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.052, 'learning_rate': 1.7939042089985487e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▎ | 782/1189 [1:09:02<29:04, 4.29s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▎ | 782/1189 [1:09:02<29:04, 4.29s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.1232, 'learning_rate': 1.7895500725689408e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▎ | 783/1189 [1:09:07<28:40, 4.24s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▎ | 783/1189 [1:09:07<28:40, 4.24s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 3.9496, 'learning_rate': 1.7851959361393325e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▍ | 784/1189 [1:09:11<28:06, 4.16s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▍ | 784/1189 [1:09:11<28:06, 4.16s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.2887, 'learning_rate': 1.780841799709724e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▍ | 785/1189 [1:09:14<27:39, 4.11s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▍ | 785/1189 [1:09:14<27:39, 4.11s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.3544, 'learning_rate': 1.7764876632801162e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▌ | 786/1189 [1:09:18<27:02, 4.02s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▌ | 786/1189 [1:09:18<27:02, 4.02s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.0901, 'learning_rate': 1.772133526850508e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▋ | 787/1189 [1:09:22<26:26, 3.95s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▋ | 787/1189 [1:09:22<26:26, 3.95s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.3868, 'learning_rate': 1.7677793904209e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▋ | 788/1189 [1:09:26<25:47, 3.86s/it]g-point operations will not be computed-01 09:27:28,255 >> 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. 66%|███████████████████████████████████████████████████▋ | 788/1189 [1:09:26<25:47, 3.86s/it]g-point operations will not be computed-01 09:27:28,255 >> 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': 4.0689, 'learning_rate': 1.763425253991292e-05, 'epoch': 0.66} 66%|███████████████████████████████████████████████████▊ | 789/1189 [1:09:29<25:09, 3.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:24,781 >> 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. 66%|███████████████████████████████████████████████████▊ | 789/1189 [1:09:29<25:09, 3.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:24,781 >> 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. 66%|███████████████████████████████████████████████████▊ | 790/1189 [1:09:33<24:31, 3.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:24,781 >> 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. 66%|███████████████████████████████████████████████████▊ | 790/1189 [1:09:33<24:31, 3.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:24,781 >> 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. {'loss': 3.9722, 'learning_rate': 1.7547169811320753e-05, 'epoch': 0.66} 67%|███████████████████████████████████████████████████▉ | 791/1189 [1:09:36<23:35, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:24,781 >> 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. 67%|███████████████████████████████████████████████████▉ | 791/1189 [1:09:36<23:35, 3.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:24,781 >> 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] 2022-03-01 09:30:32,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:24,781 >> 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] 2022-03-01 09:30:32,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:24,781 >> 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. {'loss': 4.4479, 'learning_rate': 1.7460087082728593e-05, 'epoch': 0.67} [WARNING|modeling_utils.py:388] 2022-03-01 09:30:32,807 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:24,781 >> 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. 67%|████████████████████████████████████████████████████ | 793/1189 [1:09:42<21:28, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:09:42<21:28, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:09:45<20:12, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:09:45<20:12, 3.07s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:40,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:40,670 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:42,784 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:44,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:44,663 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:46,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:46,345 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:47,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:47,773 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:49,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:49,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:30:49,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:01<19:00, 2.94s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:01<19:00, 2.94s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:01<19:00, 2.94s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 802/1189 [1:10:06<23:13, 3.60s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 802/1189 [1:10:06<23:13, 3.60s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████▌ | 802/1189 [1:10:06<23:13, 3.60s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:12<26:08, 4.06s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:12<26:08, 4.06s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:12<26:08, 4.06s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:17<27:57, 4.36s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:17<27:57, 4.36s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:17<27:57, 4.36s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:22<29:07, 4.55s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:22<29:07, 4.55s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:22<29:07, 4.55s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:22<29:07, 4.55s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1982, 'learning_rate': 1.6850507982583453e-05, 'epoch': 0.68} 68%|████████████████████████████████████████████████████▊ | 805/1189 [1:10:22<29:07, 4.55s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:22<29:07, 4.55s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:32<30:27, 4.78s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:32<30:27, 4.78s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:37<30:42, 4.84s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:37<30:42, 4.84s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0565, 'learning_rate': 1.6763425253991294e-05, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████ | 808/1189 [1:10:37<30:42, 4.84s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:41<30:44, 4.85s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:41<30:44, 4.85s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▏ | 810/1189 [1:10:46<30:46, 4.87s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▏ | 810/1189 [1:10:46<30:46, 4.87s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0345, 'learning_rate': 1.667634252539913e-05, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████▏ | 810/1189 [1:10:46<30:46, 4.87s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:51<30:36, 4.86s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:51<30:36, 4.86s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:51<30:36, 4.86s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:56<30:23, 4.84s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:56<30:23, 4.84s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:10:56<30:23, 4.84s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▎ | 813/1189 [1:11:01<30:01, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▎ | 813/1189 [1:11:01<30:01, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:05<29:54, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:05<29:54, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4523, 'learning_rate': 1.6502177068214805e-05, 'epoch': 0.68} 68%|█████████████████████████████████████████████████████▍ | 814/1189 [1:11:05<29:54, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:10<29:51, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:10<29:51, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:10<29:51, 4.79s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:15<29:36, 4.76s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:15<29:36, 4.76s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:20<29:20, 4.73s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:20<29:20, 4.73s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0953, 'learning_rate': 1.6371552975326563e-05, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▋ | 818/1189 [1:11:24<29:10, 4.72s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:24<29:10, 4.72s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0001, 'learning_rate': 1.6328011611030476e-05, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▋ | 818/1189 [1:11:24<29:10, 4.72s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:29<28:58, 4.70s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:29<28:58, 4.70s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:29<28:58, 4.70s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▊ | 820/1189 [1:11:34<28:49, 4.69s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████▊ | 820/1189 [1:11:34<28:49, 4.69s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:38<28:39, 4.67s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:38<28:39, 4.67s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1797, 'learning_rate': 1.6197387518142237e-05, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▉ | 822/1189 [1:11:43<28:21, 4.64s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:43<28:21, 4.64s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9392, 'learning_rate': 1.6153846153846154e-05, 'epoch': 0.69} 69%|█████████████████████████████████████████████████████▉ | 822/1189 [1:11:43<28:21, 4.64s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:47<28:11, 4.62s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:47<28:11, 4.62s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:47<28:11, 4.62s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:52<28:02, 4.61s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:52<28:02, 4.61s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:57<27:55, 4.60s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:11:57<27:55, 4.60s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1203, 'learning_rate': 1.6023222060957908e-05, 'epoch': 0.69} 69%|██████████████████████████████████████████████████████▏ | 826/1189 [1:12:01<27:38, 4.57s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:01<27:38, 4.57s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4287, 'learning_rate': 1.5979680696661828e-05, 'epoch': 0.69} 70%|██████████████████████████████████████████████████████▎ | 827/1189 [1:12:05<27:16, 4.52s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████▎ | 827/1189 [1:12:05<27:16, 4.52s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1276, 'learning_rate': 1.593613933236575e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▎ | 828/1189 [1:12:10<26:54, 4.47s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:10<26:54, 4.47s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2576, 'learning_rate': 1.5892597968069665e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▍ | 829/1189 [1:12:14<26:37, 4.44s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:14<26:37, 4.44s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0118, 'learning_rate': 1.5849056603773586e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▍ | 829/1189 [1:12:14<26:37, 4.44s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:18<26:20, 4.40s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:18<26:20, 4.40s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:23<26:09, 4.38s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:23<26:09, 4.38s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1189, 'learning_rate': 1.5761973875181423e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▌ | 832/1189 [1:12:27<25:57, 4.36s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:27<25:57, 4.36s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1439, 'learning_rate': 1.571843251088534e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▋ | 833/1189 [1:12:31<25:40, 4.33s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:31<25:40, 4.33s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9951, 'learning_rate': 1.567489114658926e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▋ | 834/1189 [1:12:35<25:10, 4.25s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:35<25:10, 4.25s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2016, 'learning_rate': 1.563134978229318e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▊ | 835/1189 [1:12:40<24:57, 4.23s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:40<24:57, 4.23s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2312, 'learning_rate': 1.5587808417997097e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▊ | 836/1189 [1:12:44<24:26, 4.16s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:44<24:26, 4.16s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3068, 'learning_rate': 1.5544267053701017e-05, 'epoch': 0.7} 70%|██████████████████████████████████████████████████████▊ | 836/1189 [1:12:44<24:26, 4.16s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:48<24:02, 4.10s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:48<24:02, 4.10s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:48<24:02, 4.10s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:51<23:34, 4.03s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:51<23:34, 4.03s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:51<23:34, 4.03s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:55<22:59, 3.94s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:55<22:59, 3.94s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:55<22:59, 3.94s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:59<22:28, 3.86s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:59<22:28, 3.86s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:12:59<22:28, 3.86s/it]g-point operations will not be computed-01 09:30:37,099 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:02<21:46, 3.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:33:57,747 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:02<21:46, 3.75s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:33:57,747 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:06<20:53, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:33:57,747 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:06<20:53, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:33:57,747 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:06<20:53, 3.61s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:33:57,747 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:09<19:47, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:09<19:47, 3.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:11<18:37, 3.24s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:07,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:07,676 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:10,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:12,123 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:12,123 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:13,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:13,985 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9351, 'learning_rate': 1.502177068214804e-05, 'epoch': 0.71} [WARNING|modeling_utils.py:388] 2022-03-01 09:34:15,514 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:15,514 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:17,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:17,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:34:17,350 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:29<17:08, 3.04s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:29<17:08, 3.04s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:29<17:08, 3.04s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:34<20:36, 3.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:34<20:36, 3.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:34<20:36, 3.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▉ | 853/1189 [1:13:39<23:00, 4.11s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▉ | 853/1189 [1:13:39<23:00, 4.11s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████▉ | 853/1189 [1:13:39<23:00, 4.11s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:44<24:21, 4.36s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:44<24:21, 4.36s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:49<25:24, 4.56s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:49<25:24, 4.56s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1274, 'learning_rate': 1.4716981132075472e-05, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████ | 855/1189 [1:13:49<25:24, 4.56s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:54<25:59, 4.68s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:54<25:59, 4.68s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:59<26:16, 4.75s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:59<26:16, 4.75s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1611, 'learning_rate': 1.462989840348331e-05, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████▏ | 857/1189 [1:13:59<26:16, 4.75s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:59<26:16, 4.75s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.987, 'learning_rate': 1.4586357039187228e-05, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████▏ | 857/1189 [1:13:59<26:16, 4.75s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:13:59<26:16, 4.75s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:09<26:40, 4.85s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:09<26:40, 4.85s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:14<26:49, 4.89s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:14<26:49, 4.89s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1824, 'learning_rate': 1.4499274310595066e-05, 'epoch': 0.72} 72%|████████████████████████████████████████████████████████▍ | 860/1189 [1:14:14<26:49, 4.89s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:19<26:37, 4.87s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:19<26:37, 4.87s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:24<26:24, 4.85s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:24<26:24, 4.85s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2457, 'learning_rate': 1.4412191582002904e-05, 'epoch': 0.72} 73%|████████████████████████████████████████████████████████▌ | 863/1189 [1:14:29<26:17, 4.84s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:29<26:17, 4.84s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2206, 'learning_rate': 1.4368650217706822e-05, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████▌ | 863/1189 [1:14:29<26:17, 4.84s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:33<26:11, 4.84s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:33<26:11, 4.84s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:33<26:11, 4.84s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:38<26:03, 4.83s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:38<26:03, 4.83s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▊ | 866/1189 [1:14:43<25:48, 4.79s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▊ | 866/1189 [1:14:43<25:48, 4.79s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0894, 'learning_rate': 1.4238026124818578e-05, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████▊ | 866/1189 [1:14:43<25:48, 4.79s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████▊ | 866/1189 [1:14:43<25:48, 4.79s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0147, 'learning_rate': 1.4194484760522498e-05, 'epoch': 0.73} 73%|████████████████████████████████████████████████████████▊ | 866/1189 [1:14:43<25:48, 4.79s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:52<25:10, 4.71s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:52<25:10, 4.71s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1724, 'learning_rate': 1.4150943396226415e-05, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████ | 869/1189 [1:14:57<24:55, 4.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:14:57<24:55, 4.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2902, 'learning_rate': 1.4107402031930334e-05, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████ | 870/1189 [1:15:01<24:49, 4.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:01<24:49, 4.67s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8653, 'learning_rate': 1.4063860667634254e-05, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 871/1189 [1:15:06<24:32, 4.63s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:06<24:32, 4.63s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8608, 'learning_rate': 1.402031930333817e-05, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:10<24:18, 4.60s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:10<24:18, 4.60s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0124, 'learning_rate': 1.397677793904209e-05, 'epoch': 0.73} 73%|█████████████████████████████████████████████████████████▏ | 872/1189 [1:15:10<24:18, 4.60s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▎ | 873/1189 [1:15:15<24:19, 4.62s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████▎ | 873/1189 [1:15:15<24:19, 4.62s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:20<24:03, 4.58s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:20<24:03, 4.58s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be 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': 1.3889695210449928e-05, 'epoch': 0.73} 74%|█████████████████████████████████████████████████████████▍ | 875/1189 [1:15:24<23:43, 4.53s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:24<23:43, 4.53s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1595, 'learning_rate': 1.3846153846153847e-05, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▍ | 876/1189 [1:15:28<23:26, 4.49s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:28<23:26, 4.49s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:36:26,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:36:26,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9706, 'learning_rate': 1.3759071117561684e-05, 'epoch': 0.74} [WARNING|modeling_utils.py:388] 2022-03-01 09:36:26,429 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 1.3671988388969521e-05, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▋ | 880/1189 [1:15:46<22:25, 4.36s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:46<22:25, 4.36s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3128, 'learning_rate': 1.362844702467344e-05, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▊ | 881/1189 [1:15:50<22:08, 4.31s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:50<22:08, 4.31s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9761, 'learning_rate': 1.358490566037736e-05, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▊ | 882/1189 [1:15:54<21:54, 4.28s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:54<21:54, 4.28s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2406, 'learning_rate': 1.3541364296081277e-05, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▉ | 883/1189 [1:15:58<21:37, 4.24s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:15:58<21:37, 4.24s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1138, 'learning_rate': 1.3497822931785197e-05, 'epoch': 0.74} 74%|█████████████████████████████████████████████████████████▉ | 884/1189 [1:16:02<21:17, 4.19s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:02<21:17, 4.19s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1666, 'learning_rate': 1.3454281567489116e-05, 'epoch': 0.74} 74%|██████████████████████████████████████████████████████████ | 885/1189 [1:16:06<20:51, 4.12s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:06<20:51, 4.12s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0527, 'learning_rate': 1.3410740203193032e-05, 'epoch': 0.74} 75%|██████████████████████████████████████████████████████████ | 886/1189 [1:16:10<20:33, 4.07s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:10<20:33, 4.07s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1166, 'learning_rate': 1.3367198838896953e-05, 'epoch': 0.74} 75%|██████████████████████████████████████████████████████████▏ | 887/1189 [1:16:14<20:11, 4.01s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:14<20:11, 4.01s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3572, 'learning_rate': 1.3323657474600871e-05, 'epoch': 0.75} 75%|██████████████████████████████████████████████████████████▏ | 887/1189 [1:16:14<20:11, 4.01s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:18<19:46, 3.94s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:18<19:46, 3.94s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:18<19:46, 3.94s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▎ | 889/1189 [1:16:22<19:18, 3.86s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:18,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:18,769 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3323, 'learning_rate': 1.3193033381712627e-05, 'epoch': 0.75} 75%|██████████████████████████████████████████████████████████▍ | 891/1189 [1:16:28<18:03, 3.64s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:28<18:03, 3.64s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3149, 'learning_rate': 1.3149492017416547e-05, 'epoch': 0.75} 75%|██████████████████████████████████████████████████████████▍ | 891/1189 [1:16:28<18:03, 3.64s/it]g-point operations will not be computed-01 09:34:03,778 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▌ | 892/1189 [1:16:32<17:10, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████▌ | 892/1189 [1:16:32<17:10, 3.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:34<16:06, 3.26s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:30,562 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:30,562 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:32,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:32,933 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:35,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:35,092 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:37,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:37,007 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:38,724 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:38,724 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:40,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:40,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:42,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:37:42,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3779, 'learning_rate': 1.2757619738751814e-05, 'epoch': 0.76} [WARNING|modeling_utils.py:388] 2022-03-01 09:37:42,003 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:54<14:42, 3.06s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:54<14:42, 3.06s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:59<17:43, 3.70s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:16:59<17:43, 3.70s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2128, 'learning_rate': 1.2670537010159652e-05, 'epoch': 0.76} 76%|███████████████████████████████████████████████████████████▏ | 902/1189 [1:16:59<17:43, 3.70s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:04<19:48, 4.16s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:04<19:48, 4.16s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:09<20:58, 4.41s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:09<20:58, 4.41s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2009, 'learning_rate': 1.258345428156749e-05, 'epoch': 0.76} 76%|███████████████████████████████████████████████████████████▎ | 904/1189 [1:17:09<20:58, 4.41s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:15<21:53, 4.63s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:15<21:53, 4.63s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:20<22:29, 4.77s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:20<22:29, 4.77s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2604, 'learning_rate': 1.2496371552975326e-05, 'epoch': 0.76} 76%|███████████████████████████████████████████████████████████▍ | 906/1189 [1:17:20<22:29, 4.77s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:25<22:52, 4.87s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:25<22:52, 4.87s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:30<22:59, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:30<22:59, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.475, 'learning_rate': 1.2409288824383165e-05, 'epoch': 0.76} 76%|███████████████████████████████████████████████████████████▋ | 909/1189 [1:17:35<22:55, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:35<22:55, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1919, 'learning_rate': 1.2365747460087082e-05, 'epoch': 0.76} 77%|███████████████████████████████████████████████████████████▋ | 910/1189 [1:17:40<22:52, 4.92s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:40<22:52, 4.92s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3414, 'learning_rate': 1.2322206095791002e-05, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▊ | 911/1189 [1:17:45<22:44, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:45<22:44, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0319, 'learning_rate': 1.227866473149492e-05, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▊ | 911/1189 [1:17:45<22:44, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:45<22:44, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:45<22:44, 4.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0561, 'learning_rate': 1.223512336719884e-05, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▉ | 913/1189 [1:17:54<22:29, 4.89s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:54<22:29, 4.89s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1455, 'learning_rate': 1.2191582002902758e-05, 'epoch': 0.77} 77%|███████████████████████████████████████████████████████████▉ | 914/1189 [1:17:59<22:18, 4.87s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:17:59<22:18, 4.87s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1583, 'learning_rate': 1.2148040638606676e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████ | 915/1189 [1:18:04<22:04, 4.83s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:04<22:04, 4.83s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 1.2104499274310596e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████ | 916/1189 [1:18:09<21:50, 4.80s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:09<21:50, 4.80s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.108, 'learning_rate': 1.2060957910014513e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▏ | 917/1189 [1:18:13<21:33, 4.75s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:13<21:33, 4.75s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1194, 'learning_rate': 1.2017416545718432e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▏ | 918/1189 [1:18:18<21:21, 4.73s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:18<21:21, 4.73s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0818, 'learning_rate': 1.1973875181422352e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▎ | 919/1189 [1:18:23<21:12, 4.71s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:23<21:12, 4.71s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3585, 'learning_rate': 1.193033381712627e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▎ | 919/1189 [1:18:23<21:12, 4.71s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:23<21:12, 4.71s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:23<21:12, 4.71s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2281, 'learning_rate': 1.188679245283019e-05, 'epoch': 0.77} 77%|████████████████████████████████████████████████████████████▍ | 921/1189 [1:18:32<20:49, 4.66s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:32<20:49, 4.66s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0967, 'learning_rate': 1.1843251088534108e-05, 'epoch': 0.77} 78%|████████████████████████████████████████████████████████████▍ | 922/1189 [1:18:36<20:41, 4.65s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:36<20:41, 4.65s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2058, 'learning_rate': 1.1799709724238026e-05, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▌ | 923/1189 [1:18:41<20:24, 4.60s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:41<20:24, 4.60s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0207, 'learning_rate': 1.1756168359941945e-05, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▌ | 923/1189 [1:18:41<20:24, 4.60s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:45<20:16, 4.59s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:45<20:16, 4.59s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:50<20:02, 4.55s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:50<20:02, 4.55s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9778, 'learning_rate': 1.1669085631349782e-05, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▋ | 926/1189 [1:18:54<19:48, 4.52s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:54<19:48, 4.52s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0005, 'learning_rate': 1.1625544267053702e-05, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▊ | 927/1189 [1:18:59<19:36, 4.49s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:18:59<19:36, 4.49s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 1.158200290275762e-05, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▉ | 928/1189 [1:19:03<19:25, 4.47s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▉ | 928/1189 [1:19:03<19:25, 4.47s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.223, 'learning_rate': 1.153846153846154e-05, 'epoch': 0.78} 78%|████████████████████████████████████████████████████████████▉ | 929/1189 [1:19:08<19:10, 4.42s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████▉ | 929/1189 [1:19:08<19:10, 4.42s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0355, 'learning_rate': 1.1494920174165458e-05, 'epoch': 0.78} 78%|█████████████████████████████████████████████████████████████ | 930/1189 [1:19:12<19:00, 4.40s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████ | 930/1189 [1:19:12<19:00, 4.40s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9679, 'learning_rate': 1.1451378809869375e-05, 'epoch': 0.78} 78%|█████████████████████████████████████████████████████████████ | 931/1189 [1:19:16<18:47, 4.37s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:16<18:47, 4.37s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2022, 'learning_rate': 1.1407837445573295e-05, 'epoch': 0.78} 78%|█████████████████████████████████████████████████████████████ | 931/1189 [1:19:16<18:47, 4.37s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:20<18:35, 4.34s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:20<18:35, 4.34s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:20<18:35, 4.34s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:25<18:21, 4.30s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:25<18:21, 4.30s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:25<18:21, 4.30s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:29<18:05, 4.26s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:29<18:05, 4.26s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:29<18:05, 4.26s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:33<17:47, 4.20s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:33<17:47, 4.20s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:33<17:47, 4.20s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:37<17:31, 4.16s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:37<17:31, 4.16s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:37<17:31, 4.16s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:41<17:08, 4.08s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:41<17:08, 4.08s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:41<17:08, 4.08s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:45<16:44, 4.00s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:45<16:44, 4.00s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:45<16:44, 4.00s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:48<16:18, 3.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:48<16:18, 3.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:48<16:18, 3.91s/it]g-point operations will not be computed-01 09:37:26,660 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:52<15:47, 3.81s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:55<15:14, 3.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:55<15:14, 3.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.997, 'learning_rate': 1.0972423802612483e-05, 'epoch': 0.79} 79%|█████████████████████████████████████████████████████████████▋ | 941/1189 [1:19:55<15:14, 3.69s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:19:59<14:36, 3.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:40:55,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:40:55,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0163, 'learning_rate': 1.088534107402032e-05, 'epoch': 0.79} [WARNING|modeling_utils.py:388] 2022-03-01 09:40:55,173 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:47,376 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:04<12:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:04<12:59, 3.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:07<12:08, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:07<12:08, 2.99s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:02,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:02,716 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:04,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:04,759 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:06,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:06,523 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:09,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:09,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1115, 'learning_rate': 1.0580551523947752e-05, 'epoch': 0.8} [WARNING|modeling_utils.py:388] 2022-03-01 09:41:09,781 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:15,113 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:41:15,113 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:27<14:19, 3.62s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:27<14:19, 3.62s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2221, 'learning_rate': 1.0493468795355589e-05, 'epoch': 0.8} 80%|██████████████████████████████████████████████████████████████▍ | 952/1189 [1:20:27<14:19, 3.62s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:32<16:01, 4.08s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:32<16:01, 4.08s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:32<16:01, 4.08s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:37<17:04, 4.36s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:37<17:04, 4.36s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:37<17:04, 4.36s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▋ | 955/1189 [1:20:42<17:52, 4.58s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▋ | 955/1189 [1:20:42<17:52, 4.58s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▋ | 955/1189 [1:20:42<17:52, 4.58s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:47<18:25, 4.74s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:47<18:25, 4.74s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:47<18:25, 4.74s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:52<18:37, 4.82s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:52<18:37, 4.82s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:57<18:44, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:20:57<18:44, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0216, 'learning_rate': 1.02322206095791e-05, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████▊ | 958/1189 [1:20:57<18:44, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:02<18:40, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:02<18:40, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:02<18:40, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 960/1189 [1:21:07<18:43, 4.91s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 960/1189 [1:21:07<18:43, 4.91s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 960/1189 [1:21:07<18:43, 4.91s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 960/1189 [1:21:07<18:43, 4.91s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0515, 'learning_rate': 1.0101596516690856e-05, 'epoch': 0.81} 81%|██████████████████████████████████████████████████████████████▉ | 960/1189 [1:21:07<18:43, 4.91s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████▉ | 960/1189 [1:21:07<18:43, 4.91s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████ | 962/1189 [1:21:16<18:24, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████ | 962/1189 [1:21:16<18:24, 4.87s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:21<18:15, 4.85s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:21<18:15, 4.85s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.948, 'learning_rate': 1.0014513788098695e-05, 'epoch': 0.81} 81%|███████████████████████████████████████████████████████████████▏ | 963/1189 [1:21:21<18:15, 4.85s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:26<18:05, 4.83s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:26<18:05, 4.83s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:26<18:05, 4.83s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:31<17:57, 4.81s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:31<17:57, 4.81s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▎ | 966/1189 [1:21:36<17:47, 4.79s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▎ | 966/1189 [1:21:36<17:47, 4.79s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9826, 'learning_rate': 9.88388969521045e-06, 'epoch': 0.81} 81%|███████████████████████████████████████████████████████████████▍ | 967/1189 [1:21:40<17:40, 4.78s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:40<17:40, 4.78s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1475, 'learning_rate': 9.840348330914369e-06, 'epoch': 0.81} 81%|███████████████████████████████████████████████████████████████▍ | 967/1189 [1:21:40<17:40, 4.78s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:45<17:30, 4.75s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:45<17:30, 4.75s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:45<17:30, 4.75s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:50<17:20, 4.73s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:50<17:20, 4.73s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▋ | 970/1189 [1:21:54<17:12, 4.72s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████▋ | 970/1189 [1:21:54<17:12, 4.72s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0959, 'learning_rate': 9.709724238026126e-06, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▋ | 971/1189 [1:21:59<17:02, 4.69s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:21:59<17:02, 4.69s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.961, 'learning_rate': 9.666182873730043e-06, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▋ | 971/1189 [1:21:59<17:02, 4.69s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:04<16:48, 4.65s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:04<16:48, 4.65s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:08<16:35, 4.61s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:08<16:35, 4.61s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1277, 'learning_rate': 9.579100145137882e-06, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▉ | 974/1189 [1:22:13<16:28, 4.60s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:13<16:28, 4.60s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0237, 'learning_rate': 9.5355587808418e-06, 'epoch': 0.82} 82%|███████████████████████████████████████████████████████████████▉ | 974/1189 [1:22:13<16:28, 4.60s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:13<16:28, 4.60s/it]g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1151, 'learning_rate': 9.492017416545717e-06, 'epoch': 0.82} g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1315, 'learning_rate': 9.448476052249638e-06, 'epoch': 0.82} g-point operations will not be computed-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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-01 09:40:59,282 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:26<15:57, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▏ | 978/1189 [1:22:30<15:42, 4.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▏ | 978/1189 [1:22:30<15:42, 4.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1165, 'learning_rate': 9.361393323657475e-06, 'epoch': 0.82} 82%|████████████████████████████████████████████████████████████████▏ | 978/1189 [1:22:30<15:42, 4.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:35<15:29, 4.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:35<15:29, 4.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:35<15:29, 4.43s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:21,995 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:39<15:15, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:39<15:15, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:43<15:04, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:43:41,216 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:43:41,216 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2319, 'learning_rate': 9.18722786647315e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▍ | 983/1189 [1:22:52<14:38, 4.27s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:52<14:38, 4.27s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0098, 'learning_rate': 9.143686502177068e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▌ | 984/1189 [1:22:56<14:21, 4.20s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:22:56<14:21, 4.20s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2086, 'learning_rate': 9.100145137880988e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▌ | 985/1189 [1:23:00<14:03, 4.13s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:00<14:03, 4.13s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9627, 'learning_rate': 9.056603773584905e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▋ | 986/1189 [1:23:04<13:43, 4.05s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:04<13:43, 4.05s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0762, 'learning_rate': 9.013062409288825e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▋ | 987/1189 [1:23:07<13:24, 3.98s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:07<13:24, 3.98s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 8.969521044992744e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▊ | 988/1189 [1:23:11<13:01, 3.89s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:11<13:01, 3.89s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 8.925979680696662e-06, 'epoch': 0.83} 83%|████████████████████████████████████████████████████████████████▊ | 988/1189 [1:23:11<13:01, 3.89s/it]g-point operations will not be computed-01 09:43:34,899 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▉ | 989/1189 [1:23:15<12:37, 3.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:18<12:13, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:18<12:13, 3.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1577, 'learning_rate': 8.8388969521045e-06, 'epoch': 0.83} 83%|█████████████████████████████████████████████████████████████████ | 991/1189 [1:23:21<11:47, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:21<11:47, 3.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:44:18,233 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 09:44:18,233 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0552, 'learning_rate': 8.751814223512337e-06, 'epoch': 0.83} 84%|█████████████████████████████████████████████████████████████████▏ | 993/1189 [1:23:28<10:56, 3.35s/it]g-point operations will not be computed-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:28<10:56, 3.35s/it]g-point operations will not be computed-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8965, 'learning_rate': 8.708272859216255e-06, 'epoch': 0.83} 84%|█████████████████████████████████████████████████████████████████▏ | 993/1189 [1:23:28<10:56, 3.35s/it]g-point operations will not be computed-01 09:44:10,121 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:31<10:26, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:25,613 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:31<10:26, 3.21s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:25,613 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▎ | 995/1189 [1:23:33<09:45, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:28,064 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▎ | 995/1189 [1:23:33<09:45, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:28,064 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:35<09:00, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:30,154 >> 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. 84%|█████████████████████████████████████████████████████████████████▎ | 996/1189 [1:23:35<09:00, 2.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:30,154 >> 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. 84%|█████████████████████████████████████████████████████████████████▍ | 997/1189 [1:23:37<08:10, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:32,067 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████▍ | 997/1189 [1:23:37<08:10, 2.55s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:32,067 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:23:39<07:24, 2.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:33,674 >> 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%|█████████████████████████████████████████████████████████████████▍ | 998/1189 [1:23:39<07:24, 2.33s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:33,674 >> 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%|████████████████████████████████████████████████████████████████▊ | 1000/1189 [1:23:43<06:19, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:35,090 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████▊ | 1000/1189 [1:23:43<06:19, 2.01s/it][WARNING|modeling_utils.py:388] 2022-03-01 09:44:35,090 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-01 09:44:36,378 >> Num examples = 2642 | 1000/1189 [1:23:43<06:19, 2.01s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-01 09:44:36,378 >> Num examples = 2642 | 1000/1189 [1:23:43<06:19, 2.01s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|trainer.py:2366] 2022-03-01 09:44:36,378 >> Num examples = 2642 | 1000/1189 [1:23:43<06:19, 2.01s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 1%|█▏ | 3/221 [00:05<07:14, 1.99s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<08:43, 2.41s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<09:25, 2.62s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [00:14<10:08, 2.83s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<11:09, 3.13s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<10:55, 3.08s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 4%|███▍ | 9/221 [00:24<10:45, 3.05s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|███▋ | 10/221 [00:28<11:43, 3.33s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [00:32<12:39, 3.61s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 5%|████▍ | 12/221 [00:35<11:49, 3.39s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [00:38<11:22, 3.28s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<11:30, 3.33s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [00:46<12:53, 3.75s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [00:51<13:50, 4.05s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<13:13, 3.89s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [00:58<12:58, 3.84s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<12:22, 3.68s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<11:46, 3.51s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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<11:01, 3.31s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▏ | 22/221 [01:11<10:44, 3.24s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 10%|████████▌ | 23/221 [01:14<10:33, 3.20s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|████████▉ | 24/221 [01:18<11:04, 3.37s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 11%|█████████▎ | 25/221 [01:22<11:35, 3.55s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [01:25<11:50, 3.64s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [01:28<10:46, 3.33s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 13%|██████████▍ | 28/221 [01:32<11:19, 3.52s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [01:36<12:04, 3.77s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [01:39<11:13, 3.52s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 14%|███████████▌ | 31/221 [01:42<10:13, 3.23s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [01:45<10:08, 3.22s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 15%|████████████▏ | 33/221 [01:49<10:38, 3.40s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [01:52<10:47, 3.46s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|████████████▉ | 35/221 [01:56<10:23, 3.35s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 16%|█████████████▎ | 36/221 [01:59<10:15, 3.33s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [02:03<11:02, 3.60s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [02:06<10:23, 3.41s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▍ | 39/221 [02:10<10:36, 3.50s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 18%|██████████████▊ | 40/221 [02:13<10:00, 3.32s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [02:16<10:15, 3.42s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 19%|███████████████▌ | 42/221 [02:21<11:16, 3.78s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [02:24<10:48, 3.64s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▎ | 44/221 [02:29<11:41, 3.96s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 20%|████████████████▋ | 45/221 [02:34<12:13, 4.17s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████ | 46/221 [02:38<12:07, 4.16s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 21%|█████████████████▍ | 47/221 [02:42<11:52, 4.09s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 22%|█████████████████▊ | 48/221 [02:46<11:44, 4.08s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [02:49<11:23, 3.97s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [02:53<11:22, 3.99s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 23%|██████████████████▉ | 51/221 [02:57<10:42, 3.78s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▎ | 52/221 [03:00<09:59, 3.55s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 24%|███████████████████▋ | 53/221 [03:03<09:26, 3.37s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [03:06<09:40, 3.47s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▍ | 55/221 [03:10<09:45, 3.53s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 25%|████████████████████▊ | 56/221 [03:15<10:30, 3.82s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▏ | 57/221 [03:19<10:35, 3.87s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 26%|█████████████████████▌ | 58/221 [03:22<10:10, 3.74s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [03:25<09:37, 3.56s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 27%|██████████████████████▎ | 60/221 [03:28<08:47, 3.27s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [03:31<08:58, 3.37s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 28%|███████████████████████ | 62/221 [03:35<08:45, 3.30s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [03:38<08:51, 3.36s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [03:41<08:47, 3.36s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 29%|████████████████████████ | 65/221 [03:45<08:42, 3.35s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [03:48<08:46, 3.40s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 30%|████████████████████████▊ | 67/221 [03:51<08:08, 3.17s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▏ | 68/221 [03:55<08:49, 3.46s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 31%|█████████████████████████▌ | 69/221 [03:58<08:29, 3.35s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:01<08:25, 3.35s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 32%|██████████████████████████▎ | 71/221 [04:05<08:12, 3.29s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:07<07:44, 3.12s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:11<08:03, 3.27s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:14<07:58, 3.26s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:17<07:50, 3.23s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:20<07:44, 3.20s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 35%|████████████████████████████▌ | 77/221 [04:24<07:39, 3.19s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:27<07:48, 3.27s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:30<07:30, 3.17s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:33<07:30, 3.19s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:37<07:54, 3.39s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:41<08:25, 3.63s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|██████████████████████████████▊ | 83/221 [04:46<08:50, 3.85s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 38%|███████████████████████████████▏ | 84/221 [04:50<08:52, 3.89s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [04:54<09:13, 4.07s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 39%|███████████████████████████████▉ | 86/221 [04:58<08:54, 3.96s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:02<09:13, 4.13s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 40%|████████████████████████████████▋ | 88/221 [05:06<08:36, 3.89s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:09<08:08, 3.70s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▍ | 90/221 [05:13<08:06, 3.72s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 41%|█████████████████████████████████▊ | 91/221 [05:17<08:20, 3.85s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:21<08:35, 3.99s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:25<08:39, 4.06s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:29<08:24, 3.97s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:33<08:22, 3.99s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:37<08:08, 3.91s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:41<08:20, 4.03s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:45<08:06, 3.95s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 45%|████████████████████████████████████▋ | 99/221 [05:48<07:20, 3.61s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [05:51<07:18, 3.62s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████ | 101/221 [05:55<06:59, 3.49s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 46%|█████████████████████████████████████▍ | 102/221 [05:58<06:35, 3.32s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:01<06:52, 3.50s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:05<07:06, 3.64s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▍ | 105/221 [06:10<07:29, 3.87s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 48%|██████████████████████████████████████▊ | 106/221 [06:14<07:28, 3.90s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:17<06:58, 3.67s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:21<07:16, 3.86s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:25<07:16, 3.90s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▎ | 110/221 [06:29<06:52, 3.72s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 50%|████████████████████████████████████████▋ | 111/221 [06:32<06:33, 3.58s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 51%|█████████████████████████████████████████ | 112/221 [06:36<06:36, 3.64s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:39<06:34, 3.65s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 52%|█████████████████████████████████████████▊ | 114/221 [06:43<06:19, 3.54s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:46<06:14, 3.53s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:49<05:59, 3.42s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 53%|██████████████████████████████████████████▉ | 117/221 [06:53<05:52, 3.39s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [06:56<06:01, 3.51s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 54%|███████████████████████████████████████████▌ | 119/221 [07:01<06:22, 3.75s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:05<06:35, 3.92s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 55%|████████████████████████████████████████████▎ | 121/221 [07:09<06:21, 3.81s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:11<05:38, 3.42s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:13<05:06, 3.12s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 56%|█████████████████████████████████████████████▍ | 124/221 [07:17<05:03, 3.12s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:20<05:20, 3.34s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:23<05:01, 3.17s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:26<04:49, 3.08s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 58%|██████████████████████████████████████████████▉ | 128/221 [07:29<04:33, 2.94s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:32<04:52, 3.18s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:35<04:37, 3.05s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 59%|████████████████████████████████████████████████ | 131/221 [07:39<04:51, 3.23s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:41<04:30, 3.04s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 60%|████████████████████████████████████████████████▋ | 133/221 [07:45<04:31, 3.08s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:47<04:20, 2.99s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 61%|█████████████████████████████████████████████████▍ | 135/221 [07:51<04:24, 3.07s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [07:54<04:38, 3.28s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▏ | 137/221 [07:58<04:42, 3.36s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 62%|██████████████████████████████████████████████████▌ | 138/221 [08:02<04:52, 3.52s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|██████████████████████████████████████████████████▉ | 139/221 [08:06<04:54, 3.59s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 63%|███████████████████████████████████████████████████▎ | 140/221 [08:08<04:24, 3.26s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 64%|███████████████████████████████████████████████████▋ | 141/221 [08:11<04:21, 3.27s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [08:14<04:11, 3.18s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▍ | 143/221 [08:17<03:49, 2.94s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 65%|████████████████████████████████████████████████████▊ | 144/221 [08:21<04:06, 3.20s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 66%|█████████████████████████████████████████████████████▏ | 145/221 [08:24<04:00, 3.16s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [08:27<04:09, 3.33s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|█████████████████████████████████████████████████████▉ | 147/221 [08:30<03:53, 3.16s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [08:33<03:54, 3.21s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 67%|██████████████████████████████████████████████████████▌ | 149/221 [08:37<03:53, 3.25s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|██████████████████████████████████████████████████████▉ | 150/221 [08:40<03:48, 3.22s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 68%|███████████████████████████████████████████████████████▎ | 151/221 [08:44<03:56, 3.38s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|███████████████████████████████████████████████████████▋ | 152/221 [08:47<03:49, 3.33s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 69%|████████████████████████████████████████████████████████ | 153/221 [08:50<03:41, 3.25s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [08:53<03:41, 3.31s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 70%|████████████████████████████████████████████████████████▊ | 155/221 [08:57<03:41, 3.35s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [09:00<03:41, 3.40s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▌ | 157/221 [09:03<03:24, 3.19s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 71%|█████████████████████████████████████████████████████████▉ | 158/221 [09:08<03:47, 3.62s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [09:11<03:46, 3.65s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [09:15<03:50, 3.78s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████ | 161/221 [09:20<03:54, 3.90s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 73%|███████████████████████████████████████████████████████████▍ | 162/221 [09:24<03:51, 3.93s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|███████████████████████████████████████████████████████████▋ | 163/221 [09:28<03:55, 4.06s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 74%|████████████████████████████████████████████████████████████ | 164/221 [09:33<04:00, 4.21s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 75%|████████████████████████████████████████████████████████████▍ | 165/221 [09:36<03:45, 4.03s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [09:39<03:26, 3.76s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▏ | 167/221 [09:43<03:18, 3.68s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▌ | 168/221 [09:46<03:04, 3.48s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 76%|█████████████████████████████████████████████████████████████▉ | 169/221 [09:50<03:06, 3.59s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▎ | 170/221 [09:54<03:06, 3.66s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 77%|██████████████████████████████████████████████████████████████▋ | 171/221 [09:57<03:02, 3.65s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [10:00<02:53, 3.55s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 78%|███████████████████████████████████████████████████████████████▍ | 173/221 [10:04<02:49, 3.52s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|███████████████████████████████████████████████████████████████▊ | 174/221 [10:07<02:40, 3.41s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 79%|████████████████████████████████████████████████████████████████▏ | 175/221 [10:10<02:32, 3.32s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▌ | 176/221 [10:14<02:37, 3.49s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 80%|████████████████████████████████████████████████████████████████▊ | 177/221 [10:17<02:26, 3.32s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▏ | 178/221 [10:21<02:29, 3.47s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▌ | 179/221 [10:24<02:23, 3.41s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 81%|█████████████████████████████████████████████████████████████████▉ | 180/221 [10:28<02:29, 3.65s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▎ | 181/221 [10:32<02:29, 3.74s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 82%|██████████████████████████████████████████████████████████████████▋ | 182/221 [10:36<02:25, 3.73s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████ | 183/221 [10:40<02:28, 3.91s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 83%|███████████████████████████████████████████████████████████████████▍ | 184/221 [10:44<02:22, 3.86s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|███████████████████████████████████████████████████████████████████▊ | 185/221 [10:47<02:12, 3.68s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 84%|████████████████████████████████████████████████████████████████████▏ | 186/221 [10:52<02:16, 3.90s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▌ | 187/221 [10:55<02:08, 3.77s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 85%|████████████████████████████████████████████████████████████████████▉ | 188/221 [10:59<02:07, 3.87s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▎ | 189/221 [11:03<02:05, 3.93s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|█████████████████████████████████████████████████████████████████████▋ | 190/221 [11:08<02:06, 4.09s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 86%|██████████████████████████████████████████████████████████████████████ | 191/221 [11:12<02:07, 4.25s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▎ | 192/221 [11:17<02:03, 4.27s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 87%|██████████████████████████████████████████████████████████████████████▋ | 193/221 [11:20<01:51, 3.97s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████ | 194/221 [11:23<01:40, 3.73s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████████▍ | 195/221 [11:26<01:31, 3.53s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [11:30<01:26, 3.46s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 89%|████████████████████████████████████████████████████████████████████████▏ | 197/221 [11:32<01:18, 3.26s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [11:37<01:21, 3.55s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|████████████████████████████████████████████████████████████████████████▉ | 199/221 [11:41<01:23, 3.81s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 90%|█████████████████████████████████████████████████████████████████████████▎ | 200/221 [11:44<01:17, 3.69s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 91%|█████████████████████████████████████████████████████████████████████████▋ | 201/221 [11:48<01:11, 3.58s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [11:51<01:04, 3.37s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▍ | 203/221 [11:54<01:02, 3.45s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████████▊ | 204/221 [11:59<01:03, 3.75s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [12:04<01:05, 4.08s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████████▌ | 206/221 [12:08<01:03, 4.22s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|███████████████████████████████████████████████████████████████████████████▊ | 207/221 [12:11<00:55, 3.98s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████████▏ | 208/221 [12:15<00:50, 3.91s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [12:19<00:44, 3.72s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [12:23<00:41, 3.81s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████████▎ | 211/221 [12:27<00:39, 3.99s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [12:31<00:35, 3.91s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [12:34<00:29, 3.64s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▍ | 214/221 [12:37<00:25, 3.61s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 97%|██████████████████████████████████████████████████████████████████████████████▊ | 215/221 [12:41<00:22, 3.78s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▏ | 216/221 [12:45<00:19, 3.87s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 98%|███████████████████████████████████████████████████████████████████████████████▌ | 217/221 [12:49<00:15, 3.90s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|███████████████████████████████████████████████████████████████████████████████▉ | 218/221 [12:53<00:11, 3.88s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 99%|████████████████████████████████████████████████████████████████████████████████▎| 219/221 [12:57<00:07, 3.87s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [13:02<00:04, 4.07s/it][INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-01 09:57:43,373 >> Configuration saved in ./checkpoint-1000/config.json [INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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] 2022-03-01 09:57:43,373 >> Configuration saved in ./checkpoint-1000/config.json [INFO|trainer.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/01/2022 09:57:43 - INFO - datasets.metric - Removing /home/sanchit_huggingface_co/.cache/huggingface/metrics/wer/default/default_experiment-1-0.arrow [INFO|feature_extraction_utils.py:324] 2022-03-01 09:57:48,359 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:57:48,359 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:57:48,359 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:57:48,359 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-03-01 09:57:48,359 >> Configuration saved in ./checkpoint-1000/preprocessor_config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:00<14:26:26, 276.52s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:00<14:26:26, 276.52s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:00<14:26:26, 276.52s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:05<10:08:16, 195.17s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:05<10:08:16, 195.17s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:10<7:08:23, 138.19s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:10<7:08:23, 138.19s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1036, 'learning_rate': 8.272859216255443e-06, 'epoch': 0.84} 84%|██████████████████████████████████████████████████████████████▍ | 1003/1189 [1:39:10<7:08:23, 138.19s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:15<5:03:02, 98.28s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:15<5:03:02, 98.28s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:20<3:35:43, 70.34s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:20<3:35:43, 70.34s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2296, 'learning_rate': 8.185776487663281e-06, 'epoch': 0.84} 85%|███████████████████████████████████████████████████████████████▍ | 1005/1189 [1:39:20<3:35:43, 70.34s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:26<2:34:55, 50.80s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:26<2:34:55, 50.80s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:31<1:52:35, 37.12s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:31<1:52:35, 37.12s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0667, 'learning_rate': 8.098693759071119e-06, 'epoch': 0.85} 85%|███████████████████████████████████████████████████████████████▌ | 1007/1189 [1:39:31<1:52:35, 37.12s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:36<1:22:59, 27.51s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:36<1:22:59, 27.51s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:41<1:02:23, 20.80s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:41<1:02:23, 20.80s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0827, 'learning_rate': 8.011611030478954e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▍ | 1010/1189 [1:39:46<48:00, 16.09s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:46<48:00, 16.09s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0883, 'learning_rate': 7.968069666182874e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▍ | 1011/1189 [1:39:51<37:52, 12.77s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:51<37:52, 12.77s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0383, 'learning_rate': 7.924528301886793e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▍ | 1011/1189 [1:39:51<37:52, 12.77s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:56<30:43, 10.42s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:39:56<30:43, 10.42s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:01<25:40, 8.75s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:01<25:40, 8.75s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.999, 'learning_rate': 7.83744557329463e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▋ | 1014/1189 [1:40:06<22:09, 7.60s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:06<22:09, 7.60s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0975, 'learning_rate': 7.793904208998549e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▋ | 1015/1189 [1:40:11<19:38, 6.77s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:11<19:38, 6.77s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1168, 'learning_rate': 7.750362844702469e-06, 'epoch': 0.85} 85%|█████████████████████████████████████████████████████████████████▊ | 1016/1189 [1:40:16<17:51, 6.20s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▊ | 1016/1189 [1:40:16<17:51, 6.20s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2072, 'learning_rate': 7.706821480406386e-06, 'epoch': 0.85} 86%|█████████████████████████████████████████████████████████████████▊ | 1017/1189 [1:40:21<16:40, 5.82s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:21<16:40, 5.82s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0171, 'learning_rate': 7.663280116110304e-06, 'epoch': 0.85} 86%|█████████████████████████████████████████████████████████████████▊ | 1017/1189 [1:40:21<16:40, 5.82s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:25<15:43, 5.52s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:25<15:43, 5.52s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.277, 'learning_rate': 7.6197387518142245e-06, 'epoch': 0.86} 86%|█████████████████████████████████████████████████████████████████▉ | 1019/1189 [1:40:30<15:00, 5.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:30<15:00, 5.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2476, 'learning_rate': 7.576197387518142e-06, 'epoch': 0.86} 86%|█████████████████████████████████████████████████████████████████▉ | 1019/1189 [1:40:30<15:00, 5.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:30<15:00, 5.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:30<15:00, 5.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9786, 'learning_rate': 7.53265602322206e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████ | 1021/1189 [1:40:40<14:17, 5.10s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:40<14:17, 5.10s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0455, 'learning_rate': 7.48911465892598e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▏ | 1022/1189 [1:40:45<13:59, 5.02s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:45<13:59, 5.02s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.3022, 'learning_rate': 7.445573294629898e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▏ | 1023/1189 [1:40:50<13:44, 4.97s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:50<13:44, 4.97s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2723, 'learning_rate': 7.402031930333817e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▎ | 1024/1189 [1:40:55<13:34, 4.94s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:55<13:34, 4.94s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9124, 'learning_rate': 7.358490566037736e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▍ | 1025/1189 [1:40:59<13:15, 4.85s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:40:59<13:15, 4.85s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0956, 'learning_rate': 7.314949201741655e-06, 'epoch': 0.86} 86%|██████████████████████████████████████████████████████████████████▍ | 1025/1189 [1:40:59<13:15, 4.85s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:04<12:54, 4.75s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:04<12:54, 4.75s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:04<12:54, 4.75s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:08<12:40, 4.69s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:08<12:40, 4.69s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:08<12:40, 4.69s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:13<12:27, 4.64s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:13<12:27, 4.64s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:13<12:27, 4.64s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:17<12:13, 4.58s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:17<12:13, 4.58s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:17<12:13, 4.58s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:22<12:01, 4.53s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:22<12:01, 4.53s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:22<12:01, 4.53s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:26<11:46, 4.47s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:26<11:46, 4.47s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:30<11:32, 4.41s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:30<11:32, 4.41s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0364, 'learning_rate': 7.010159651669085e-06, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▉ | 1033/1189 [1:41:35<11:22, 4.37s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:35<11:22, 4.37s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.091, 'learning_rate': 6.966618287373005e-06, 'epoch': 0.87} 87%|██████████████████████████████████████████████████████████████████▉ | 1034/1189 [1:41:39<11:05, 4.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:39<11:05, 4.30s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9847, 'learning_rate': 6.923076923076923e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1035/1189 [1:41:43<10:47, 4.20s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:43<10:47, 4.20s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9737, 'learning_rate': 6.879535558780842e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████ | 1036/1189 [1:41:47<10:32, 4.13s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:47<10:32, 4.13s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 3.9495, 'learning_rate': 6.8359941944847605e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▏ | 1037/1189 [1:41:50<10:15, 4.05s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:50<10:15, 4.05s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0117, 'learning_rate': 6.79245283018868e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▏ | 1038/1189 [1:41:54<10:02, 3.99s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:54<10:02, 3.99s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.3146, 'learning_rate': 6.7489114658925985e-06, 'epoch': 0.87} 87%|███████████████████████████████████████████████████████████████████▏ | 1038/1189 [1:41:54<10:02, 3.99s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:58<09:45, 3.91s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:58<09:45, 3.91s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:41:58<09:45, 3.91s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:42:02<09:29, 3.82s/it]config.jsoner.py:560] 2022-03-01 09:44:36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:02:58,823 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed36,376 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:02:58,823 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed36,376 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2033, 'learning_rate': 6.618287373004354e-06, 'epoch': 0.88} [WARNING|modeling_utils.py:388] 2022-03-01 10:02:58,823 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:42:08<08:49, 3.60s/it]g-point operations will not be computed36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:42:08<08:49, 3.60s/it]g-point operations will not be computed36,376 >> The following columns in the evaluation set don't have a corresponding argument 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 [1:42:08<08:49, 3.60s/it]g-point operations will not be computed36,376 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▌ | 1043/1189 [1:42:12<08:22, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:03:06,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▌ | 1043/1189 [1:42:12<08:22, 3.44s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:03:06,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 88%|███████████████████████████████████████████████████████████████████▌ | 1044/1189 [1:42:14<07:51, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:14<07:51, 3.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:17<07:14, 3.02s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:12,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:12,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:14,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:14,703 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1117, 'learning_rate': 6.3570391872278665e-06, 'epoch': 0.88} [WARNING|modeling_utils.py:388] 2022-03-01 10:03:16,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:16,469 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:18,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:18,021 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:19,875 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:19,875 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:03:19,875 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:32<07:09, 3.12s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:32<07:09, 3.12s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:32<07:09, 3.12s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:37<08:31, 3.73s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:37<08:31, 3.73s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:37<08:31, 3.73s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:42<09:24, 4.15s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:42<09:24, 4.15s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:42<09:24, 4.15s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:47<09:59, 4.44s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:47<09:59, 4.44s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:47<09:59, 4.44s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:47<09:59, 4.44s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1773, 'learning_rate': 6.008708272859216e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▎ | 1054/1189 [1:42:47<09:59, 4.44s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:47<09:59, 4.44s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:57<10:26, 4.71s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:42:57<10:26, 4.71s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:02<10:34, 4.81s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:02<10:34, 4.81s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2032, 'learning_rate': 5.921625544267054e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▍ | 1057/1189 [1:43:02<10:34, 4.81s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████▌ | 1058/1189 [1:43:07<10:35, 4.85s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████▌ | 1058/1189 [1:43:07<10:35, 4.85s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:12<10:33, 4.88s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:12<10:33, 4.88s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.193, 'learning_rate': 5.834542815674891e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▋ | 1060/1189 [1:43:17<10:31, 4.90s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:17<10:31, 4.90s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1571, 'learning_rate': 5.79100145137881e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▋ | 1060/1189 [1:43:17<10:31, 4.90s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:22<10:23, 4.87s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:22<10:23, 4.87s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:27<10:16, 4.86s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:27<10:16, 4.86s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0113, 'learning_rate': 5.703918722786648e-06, 'epoch': 0.89} 89%|████████████████████████████████████████████████████████████████████▊ | 1062/1189 [1:43:27<10:16, 4.86s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:32<10:10, 4.84s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:32<10:10, 4.84s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:32<10:10, 4.84s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:36<10:01, 4.81s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:36<10:01, 4.81s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:41<09:54, 4.79s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:41<09:54, 4.79s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8992, 'learning_rate': 5.573294629898403e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████ | 1066/1189 [1:43:46<09:46, 4.77s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:46<09:46, 4.77s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0046, 'learning_rate': 5.529753265602323e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████ | 1066/1189 [1:43:46<09:46, 4.77s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:50<09:37, 4.74s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:50<09:37, 4.74s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:55<09:31, 4.72s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:43:55<09:31, 4.72s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0333, 'learning_rate': 5.44267053701016e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▏ | 1069/1189 [1:44:00<09:22, 4.69s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:00<09:22, 4.69s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0606, 'learning_rate': 5.3991291727140785e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▏ | 1069/1189 [1:44:00<09:22, 4.69s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:04<09:16, 4.68s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:04<09:16, 4.68s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:04<09:16, 4.68s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:09<09:07, 4.64s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:09<09:07, 4.64s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:14<09:01, 4.63s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:14<09:01, 4.63s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0718, 'learning_rate': 5.268505079825834e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▍ | 1073/1189 [1:44:18<08:53, 4.60s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:18<08:53, 4.60s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8236, 'learning_rate': 5.224963715529754e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▌ | 1074/1189 [1:44:23<08:47, 4.59s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:23<08:47, 4.59s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9818, 'learning_rate': 5.181422351233672e-06, 'epoch': 0.9} 90%|█████████████████████████████████████████████████████████████████████▌ | 1074/1189 [1:44:23<08:47, 4.59s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:27<08:40, 4.56s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:27<08:40, 4.56s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:32<08:32, 4.53s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:32<08:32, 4.53s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0444, 'learning_rate': 5.094339622641509e-06, 'epoch': 0.9} 91%|█████████████████████████████████████████████████████████████████████▋ | 1077/1189 [1:44:36<08:23, 4.49s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:36<08:23, 4.49s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4012, 'learning_rate': 5.050798258345428e-06, 'epoch': 0.91} 91%|█████████████████████████████████████████████████████████████████████▊ | 1078/1189 [1:44:40<08:13, 4.45s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:40<08:13, 4.45s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1033, 'learning_rate': 5.007256894049347e-06, 'epoch': 0.91} 91%|█████████████████████████████████████████████████████████████████████▉ | 1079/1189 [1:44:45<08:03, 4.39s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████▉ | 1079/1189 [1:44:45<08:03, 4.39s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1105, 'learning_rate': 4.963715529753266e-06, 'epoch': 0.91} 91%|█████████████████████████████████████████████████████████████████████▉ | 1080/1189 [1:44:49<07:55, 4.36s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:49<07:55, 4.36s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:05:46,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:05:46,838 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2026, 'learning_rate': 4.876632801161103e-06, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████ | 1082/1189 [1:44:57<07:39, 4.29s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:44:57<07:39, 4.29s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1863, 'learning_rate': 4.833091436865022e-06, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████▏ | 1083/1189 [1:45:02<07:30, 4.25s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:02<07:30, 4.25s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0533, 'learning_rate': 4.789550072568941e-06, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████▏ | 1084/1189 [1:45:06<07:20, 4.19s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:06<07:20, 4.19s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0973, 'learning_rate': 4.746008708272859e-06, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████▎ | 1085/1189 [1:45:10<07:08, 4.12s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:10<07:08, 4.12s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1554, 'learning_rate': 4.702467343976778e-06, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████▎ | 1086/1189 [1:45:13<06:55, 4.03s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:13<06:55, 4.03s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0183, 'learning_rate': 4.658925979680697e-06, 'epoch': 0.91} 91%|██████████████████████████████████████████████████████████████████████▍ | 1087/1189 [1:45:17<06:42, 3.94s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:17<06:42, 3.94s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1119, 'learning_rate': 4.615384615384616e-06, 'epoch': 0.91} 92%|██████████████████████████████████████████████████████████████████████▍ | 1088/1189 [1:45:21<06:29, 3.86s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:21<06:29, 3.86s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:17,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:17,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0389, 'learning_rate': 4.5283018867924524e-06, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-03-01 10:06:17,936 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:28<06:01, 3.65s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:28<06:01, 3.65s/it]g-point operations will not be computed-01 10:03:09,318 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:31<05:42, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:31<05:42, 3.49s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:34<05:24, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:34<05:24, 3.34s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:30,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:30,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0949, 'learning_rate': 4.354136429608128e-06, 'epoch': 0.92} [WARNING|modeling_utils.py:388] 2022-03-01 10:06:30,232 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:26,052 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:39<04:44, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:34,053 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:39<04:44, 3.00s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:34,053 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:41<04:22, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:36,243 >> 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. 92%|██████████████████████████████████████████████████████████████████████▉ | 1095/1189 [1:45:41<04:22, 2.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:36,243 >> 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. 92%|██████████████████████████████████████████████████████████████████████▉ | 1096/1189 [1:45:44<03:59, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:38,209 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|██████████████████████████████████████████████████████████████████████▉ | 1096/1189 [1:45:44<03:59, 2.58s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:38,209 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 92%|███████████████████████████████████████████████████████████████████████ | 1097/1189 [1:45:45<03:36, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:39,927 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:45<03:36, 2.36s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:39,927 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4235, 'learning_rate': 4.136429608127721e-06, 'epoch': 0.92} 92%|███████████████████████████████████████████████████████████████████████▏ | 1099/1189 [1:45:48<02:52, 1.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:41,444 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:45:50<02:48, 1.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▏ | 1100/1189 [1:45:50<02:48, 1.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2408, 'learning_rate': 4.049346879535559e-06, 'epoch': 0.92} 93%|███████████████████████████████████████████████████████████████████████▏ | 1100/1189 [1:45:50<02:48, 1.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▏ | 1100/1189 [1:45:50<02:48, 1.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1101/1189 [1:45:56<04:21, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1101/1189 [1:45:56<04:21, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1101/1189 [1:45:56<04:21, 2.97s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1102/1189 [1:46:01<05:17, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1102/1189 [1:46:01<05:17, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▎ | 1102/1189 [1:46:01<05:17, 3.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:06<05:51, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:06<05:51, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1103/1189 [1:46:06<05:51, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1104/1189 [1:46:11<06:12, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1104/1189 [1:46:11<06:12, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▍ | 1104/1189 [1:46:11<06:12, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1105/1189 [1:46:16<06:26, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1105/1189 [1:46:16<06:26, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1106/1189 [1:46:21<06:31, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▌ | 1106/1189 [1:46:21<06:31, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9154, 'learning_rate': 3.788098693759071e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▌ | 1106/1189 [1:46:21<06:31, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1107/1189 [1:46:26<06:33, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1107/1189 [1:46:26<06:33, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▋ | 1107/1189 [1:46:26<06:33, 4.79s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:46:31<06:30, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:46:31<06:30, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:46:31<06:30, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:46:31<06:30, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1533, 'learning_rate': 3.6574746008708277e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:46:31<06:30, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▊ | 1108/1189 [1:46:31<06:30, 4.82s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1110/1189 [1:46:41<06:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1110/1189 [1:46:41<06:27, 4.90s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1111/1189 [1:46:46<06:21, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 93%|███████████████████████████████████████████████████████████████████████▉ | 1111/1189 [1:46:46<06:21, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0455, 'learning_rate': 3.570391872278665e-06, 'epoch': 0.93} 93%|███████████████████████████████████████████████████████████████████████▉ | 1111/1189 [1:46:46<06:21, 4.89s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1112/1189 [1:46:51<06:14, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1112/1189 [1:46:51<06:14, 4.87s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1113/1189 [1:46:56<06:08, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████ | 1113/1189 [1:46:56<06:08, 4.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1454, 'learning_rate': 3.4833091436865024e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▏ | 1114/1189 [1:47:00<06:00, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▏ | 1114/1189 [1:47:00<06:00, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8138, 'learning_rate': 3.439767779390421e-06, 'epoch': 0.94} [WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1425, 'learning_rate': 3.39622641509434e-06, 'epoch': 0.94} [WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1116/1189 [1:47:10<05:44, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1116/1189 [1:47:10<05:44, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1116/1189 [1:47:10<05:44, 4.72s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1117/1189 [1:47:14<05:38, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▎ | 1117/1189 [1:47:14<05:38, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:19<05:30, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▍ | 1118/1189 [1:47:19<05:30, 4.66s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9879, 'learning_rate': 3.2656023222060957e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▍ | 1119/1189 [1:47:23<05:23, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▍ | 1119/1189 [1:47:23<05:23, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.8181, 'learning_rate': 3.2220609579100147e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▍ | 1119/1189 [1:47:23<05:23, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1120/1189 [1:47:28<05:17, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1120/1189 [1:47:28<05:17, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1120/1189 [1:47:28<05:17, 4.59s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1121/1189 [1:47:32<05:09, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▌ | 1121/1189 [1:47:32<05:09, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1122/1189 [1:47:37<05:03, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1122/1189 [1:47:37<05:03, 4.52s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2224, 'learning_rate': 3.0914368650217704e-06, 'epoch': 0.94} 94%|████████████████████████████████████████████████████████████████████████▋ | 1123/1189 [1:47:41<04:57, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 94%|████████████████████████████████████████████████████████████████████████▋ | 1123/1189 [1:47:41<04:57, 4.51s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9595, 'learning_rate': 3.0478955007256894e-06, 'epoch': 0.94} 95%|████████████████████████████████████████████████████████████████████████▊ | 1124/1189 [1:47:46<04:50, 4.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▊ | 1124/1189 [1:47:46<04:50, 4.47s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1257, 'learning_rate': 3.004354136429608e-06, 'epoch': 0.94} 95%|████████████████████████████████████████████████████████████████████████▊ | 1125/1189 [1:47:50<04:44, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▊ | 1125/1189 [1:47:50<04:44, 4.45s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3169, 'learning_rate': 2.960812772133527e-06, 'epoch': 0.95} 95%|████████████████████████████████████████████████████████████████████████▉ | 1126/1189 [1:47:54<04:38, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▉ | 1126/1189 [1:47:54<04:38, 4.42s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1508, 'learning_rate': 2.9172714078374455e-06, 'epoch': 0.95} 95%|████████████████████████████████████████████████████████████████████████▉ | 1127/1189 [1:47:59<04:31, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|████████████████████████████████████████████████████████████████████████▉ | 1127/1189 [1:47:59<04:31, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2589, 'learning_rate': 2.8737300435413645e-06, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████ | 1128/1189 [1:48:03<04:25, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████ | 1128/1189 [1:48:03<04:25, 4.35s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0514, 'learning_rate': 2.830188679245283e-06, 'epoch': 0.95} [WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1067, 'learning_rate': 2.7866473149492017e-06, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▏ | 1130/1189 [1:48:11<04:12, 4.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▏ | 1130/1189 [1:48:11<04:12, 4.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1904, 'learning_rate': 2.7431059506531207e-06, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▏ | 1130/1189 [1:48:11<04:12, 4.28s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▏ | 1131/1189 [1:48:15<04:06, 4.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▏ | 1131/1189 [1:48:15<04:06, 4.25s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▎ | 1132/1189 [1:48:20<04:00, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▎ | 1132/1189 [1:48:20<04:00, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.939, 'learning_rate': 2.6560232220609582e-06, 'epoch': 0.95} 95%|█████████████████████████████████████████████████████████████████████████▎ | 1132/1189 [1:48:20<04:00, 4.23s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▎ | 1133/1189 [1:48:24<03:53, 4.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▎ | 1133/1189 [1:48:24<03:53, 4.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▎ | 1133/1189 [1:48:24<03:53, 4.17s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▍ | 1134/1189 [1:48:28<03:47, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▍ | 1134/1189 [1:48:28<03:47, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▍ | 1134/1189 [1:48:28<03:47, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▌ | 1135/1189 [1:48:32<03:40, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▌ | 1135/1189 [1:48:32<03:40, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 95%|█████████████████████████████████████████████████████████████████████████▌ | 1135/1189 [1:48:32<03:40, 4.08s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1136/1189 [1:48:36<03:33, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1136/1189 [1:48:36<03:33, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▌ | 1136/1189 [1:48:36<03:33, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1137/1189 [1:48:39<03:24, 3.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1137/1189 [1:48:39<03:24, 3.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1137/1189 [1:48:39<03:24, 3.94s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1138/1189 [1:48:43<03:16, 3.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▋ | 1138/1189 [1:48:43<03:16, 3.85s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:40,212 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:40,212 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:40,212 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 96%|█████████████████████████████████████████████████████████████████████████▊ | 1140/1189 [1:48:50<02:57, 3.62s/it]g-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:46,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:46,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3512, 'learning_rate': 2.2641509433962262e-06, 'epoch': 0.96} [WARNING|modeling_utils.py:388] 2022-03-01 10:09:46,588 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:49,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:52,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:09:52,242 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:06:42,785 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2587, 'learning_rate': 2.177068214804064e-06, 'epoch': 0.96} 96%|██████████████████████████████████████████████████████████████████████████ | 1144/1189 [1:49:01<02:12, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:09:56,025 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:01<02:12, 2.95s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:09:56,025 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:03<02:01, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:09:58,235 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:03<02:01, 2.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:09:58,235 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 1146/1189 [1:49:06<01:50, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 1146/1189 [1:49:06<01:50, 2.57s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:00,252 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▎ | 1147/1189 [1:49:07<01:39, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:02,073 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▎ | 1147/1189 [1:49:07<01:39, 2.37s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:02,073 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▎ | 1148/1189 [1:49:09<01:29, 2.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:03,701 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▎ | 1148/1189 [1:49:09<01:29, 2.18s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:03,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▍ | 1150/1189 [1:49:13<01:14, 1.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▍ | 1150/1189 [1:49:13<01:14, 1.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 1.872278664731495e-06, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▍ | 1150/1189 [1:49:13<01:14, 1.92s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:18<01:53, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:18<01:53, 2.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:23<02:14, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:23<02:14, 3.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9277, 'learning_rate': 1.7851959361393324e-06, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▋ | 1153/1189 [1:49:28<02:25, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:28<02:25, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9927, 'learning_rate': 1.7416545718432512e-06, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▋ | 1153/1189 [1:49:28<02:25, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:28<02:25, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9426, 'learning_rate': 1.69811320754717e-06, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▋ | 1153/1189 [1:49:28<02:25, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:28<02:25, 4.04s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:38<02:33, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:38<02:33, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:43<02:32, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:43<02:32, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1312, 'learning_rate': 1.6110304789550073e-06, 'epoch': 0.97} 97%|██████████████████████████████████████████████████████████████████████████▊ | 1156/1189 [1:49:43<02:32, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:48<02:31, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:48<02:31, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:48<02:31, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1158/1189 [1:49:53<02:28, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 1158/1189 [1:49:53<02:28, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:58<02:23, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:49:58<02:23, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9514, 'learning_rate': 1.4804063860667635e-06, 'epoch': 0.97} 97%|███████████████████████████████████████████████████████████████████████████ | 1159/1189 [1:49:58<02:23, 4.80s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:02<02:18, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:02<02:18, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:02<02:18, 4.78s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:07<02:13, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:07<02:13, 4.77s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:12<02:07, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:12<02:07, 4.73s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1842, 'learning_rate': 1.3497822931785196e-06, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▎ | 1163/1189 [1:50:16<02:02, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 1163/1189 [1:50:16<02:02, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2224, 'learning_rate': 1.3062409288824384e-06, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▎ | 1163/1189 [1:50:16<02:02, 4.71s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:21<01:57, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:21<01:57, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:21<01:57, 4.70s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:26<01:52, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:26<01:52, 4.68s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:30<01:46, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:30<01:46, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.19, 'learning_rate': 1.1756168359941945e-06, 'epoch': 0.98} 98%|███████████████████████████████████████████████████████████████████████████▌ | 1166/1189 [1:50:30<01:46, 4.64s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:35<01:41, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:35<01:41, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:35<01:41, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:40<01:37, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:40<01:37, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:40<01:37, 4.63s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:44<01:31, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:44<01:31, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:44<01:31, 4.60s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:49<01:26, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:49<01:26, 4.56s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 1171/1189 [1:50:53<01:21, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 1171/1189 [1:50:53<01:21, 4.53s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0634, 'learning_rate': 9.57910014513788e-07, 'epoch': 0.98} 99%|███████████████████████████████████████████████████████████████████████████▉ | 1172/1189 [1:50:57<01:16, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:50:57<01:16, 4.50s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9348, 'learning_rate': 9.143686502177069e-07, 'epoch': 0.99} [WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1515, 'learning_rate': 8.708272859216256e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████ | 1174/1189 [1:51:06<01:05, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:06<01:05, 4.38s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0434, 'learning_rate': 8.272859216255443e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████ | 1175/1189 [1:51:10<01:00, 4.32s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:10<01:00, 4.32s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9705, 'learning_rate': 7.837445573294631e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▏| 1176/1189 [1:51:14<00:55, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:14<00:55, 4.27s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0213, 'learning_rate': 7.402031930333817e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▏| 1177/1189 [1:51:18<00:50, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:18<00:50, 4.20s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.149, 'learning_rate': 6.966618287373004e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▎| 1178/1189 [1:51:22<00:45, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:22<00:45, 4.13s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.4807, 'learning_rate': 6.531204644412192e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▎| 1179/1189 [1:51:26<00:40, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:26<00:40, 4.05s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 3.9835, 'learning_rate': 6.095791001451379e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▍| 1180/1189 [1:51:30<00:35, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:30<00:35, 3.98s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.1959, 'learning_rate': 5.660377358490566e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▍| 1181/1189 [1:51:34<00:31, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:34<00:31, 3.88s/it][WARNING|modeling_utils.py:388] 2022-03-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:30,686 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:30,686 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.0851, 'learning_rate': 4.78955007256894e-07, 'epoch': 0.99} 99%|████████████████████████████████████████████████████████████████████████████▌| 1183/1189 [1:51:40<00:21, 3.54s/it]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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 [1:51:40<00:21, 3.54s/it]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:36,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:36,566 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:39,054 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:41,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:41,270 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:43,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:43,162 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:44,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [WARNING|modeling_utils.py:388] 2022-03-01 10:12:44,762 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.2001, 'learning_rate': 2.6124818577648767e-07, 'epoch': 1.0} [INFO|configuration_utils.py:438] 2022-03-01 10:12:46,207 >> Configuration saved in ./config.json51:52<00:00, 5.65s/it]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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] 2022-03-01 10:12:46,207 >> Configuration saved in ./config.json51:52<00:00, 5.65s/it]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. {'loss': 4.3516, 'learning_rate': 1.741654571843251e-07, 'epoch': 1.0} [INFO|configuration_utils.py:438] 2022-03-01 10:13:02,686 >> Configuration saved in ./config.jsoncessor_config.jsons/it]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not 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] 2022-03-01 10:13:18,949 >> Configuration saved in ./preprocessor_config.jsons/it]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 33%|███▋ | 11.8M/35.4M [00:01<00:02, 12.2MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 84%|█████████▏ | 29.7M/35.4M [00:02<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|███████████| 35.4M/35.4M [00:18<00:00, 16.1MB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/01/2022 10:17:22 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 100%|████████████| 35.4M/35.4M [02:29<00:00, 169kB/s]g-point operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|modelcard.py:460] 2022-03-01 10:17:25,983 >> Dropping the following result as it does not have all the necessary fields:t operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 51%|█████▋ | 18.1M/35.4M [00:01<00:00, 18.9MB/s]ields:t operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 51%|█████▋ | 18.1M/35.4M [00:01<00:00, 18.9MB/s]ields:t operations will not be computed-01 10:10:05,048 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. 03/01/2022 10:17:33 - WARNING - huggingface_hub.repository - To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-search Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 51%|█████▋ | 18.1M/35.4M [00:01<00:00, 18.9MB/s]To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-searchimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 51%|█████▋ | 18.1M/35.4M [00:01<00:00, 18.9MB/s]To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-searchimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. Upload file wandb/run-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 51%|█████▋ | 18.1M/35.4M [00:01<00:00, 18.9MB/s]To https://huggingface.co/sanchit-gandhi/wav2vec2-gpt2-wandb-grid-searchimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. ***** train metrics ***** epoch = 1.0 train_loss = 4.2422 train_runtime = 1:51:54.55 train_samples = 28538 train_samples_per_second = 4.25 train_steps_per_second = 0.177 [INFO|trainer.py:2366] 2022-03-01 10:17:36,185 >> 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 ./ | 2/221 [00:03<05:30, 1.51s/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] 2022-03-01 10:33:25,938 >> Model weights saved in ./pytorch_model.bin:03<05:30, 1.51s/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-20220301_082052-1y1by2yf/run-1y1by2yf.wandb: 0%| | 32.0k/35.6M [00:00ent 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.