diff --git "a/wandb/run-20220228_185039-2l3jouo4/files/output.log" "b/wandb/run-20220228_185039-2l3jouo4/files/output.log" --- "a/wandb/run-20220228_185039-2l3jouo4/files/output.log" +++ "b/wandb/run-20220228_185039-2l3jouo4/files/output.log" @@ -2562,3 +2562,443 @@ [INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. [INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +02/28/2022 20:12:38 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20220228_185039-2l3jouo4/run-2l3jouo4.wandb']. This may take a bit of time if the files are large. +[INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|feature_extraction_utils.py:324] 2022-02-28 20:11:06,749 >> Configuration saved in ./checkpoint-500/preprocessor_config.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 501/594 [1:22:38<7:13:46, 279.86s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 501/594 [1:22:38<7:13:46, 279.86s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 501/594 [1:22:38<7:13:46, 279.86s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████���████████████████████ | 501/594 [1:22:38<7:13:46, 279.86s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████ | 501/594 [1:22:38<7:13:46, 279.86s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▏ | 502/594 [1:22:48<5:05:19, 199.13s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▏ | 502/594 [1:22:48<5:05:19, 199.13s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▏ | 502/594 [1:22:48<5:05:19, 199.13s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▏ | 502/594 [1:22:48<5:05:19, 199.13s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▎ | 503/594 [1:22:59<3:36:16, 142.60s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▎ | 503/594 [1:22:59<3:36:16, 142.60s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1053, 'learning_rate': 1e-05, 'epoch': 0.85} + 85%|████████████████████████████████████████████████████████████████▎ | 503/594 [1:22:59<3:36:16, 142.60s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████���████████████████████████████████▎ | 503/594 [1:22:59<3:36:16, 142.60s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▎ | 503/594 [1:22:59<3:36:16, 142.60s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▍ | 504/594 [1:23:10<2:34:25, 102.95s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▍ | 504/594 [1:23:10<2:34:25, 102.95s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▍ | 504/594 [1:23:10<2:34:25, 102.95s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████▍ | 504/594 [1:23:10<2:34:25, 102.95s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 505/594 [1:23:20<1:51:27, 75.14s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 505/594 [1:23:20<1:51:27, 75.14s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1617, 'learning_rate': 9.787234042553192e-06, 'epoch': 0.85} + 85%|█████████████████████████████████████████████████████████████████▍ | 505/594 [1:23:20<1:51:27, 75.14s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████��██████████████████████████████████████████████████████▍ | 505/594 [1:23:20<1:51:27, 75.14s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▍ | 505/594 [1:23:20<1:51:27, 75.14s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1643, 'learning_rate': 9.574468085106385e-06, 'epoch': 0.85} + 85%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.158, 'learning_rate': 9.46808510638298e-06, 'epoch': 0.85} + 85%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████▌ | 506/594 [1:23:30<1:21:44, 55.73s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▋ | 509/594 [1:24:01<36:30, 25.77s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▋ | 509/594 [1:24:01<36:30, 25.77s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0941, 'learning_rate': 9.361702127659576e-06, 'epoch': 0.86} + 86%|███████████████████████████████████████████████████████████████████▋ | 509/594 [1:24:01<36:30, 25.77s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▋ | 509/594 [1:24:01<36:30, 25.77s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 510/594 [1:24:11<29:26, 21.03s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 510/594 [1:24:11<29:26, 21.03s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.17, 'learning_rate': 9.255319148936171e-06, 'epoch': 0.86} + 86%|███████████████████████████████████████████████████████████████████▊ | 510/594 [1:24:11<29:26, 21.03s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 510/594 [1:24:11<29:26, 21.03s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▊ | 510/594 [1:24:11<29:26, 21.03s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1385, 'learning_rate': 9.042553191489362e-06, 'epoch': 0.86} + 86%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████▉ | 511/594 [1:24:21<24:29, 17.70s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▏ | 513/594 [1:24:40<18:26, 13.66s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▏ | 513/594 [1:24:40<18:26, 13.66s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1332, 'learning_rate': 8.936170212765958e-06, 'epoch': 0.86} + 86%|██████████████████████████���█████████████████████████████████████████▏ | 513/594 [1:24:40<18:26, 13.66s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▏ | 513/594 [1:24:40<18:26, 13.66s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▏ | 513/594 [1:24:40<18:26, 13.66s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 514/594 [1:24:50<16:42, 12.53s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 514/594 [1:24:50<16:42, 12.53s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 514/594 [1:24:50<16:42, 12.53s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 514/594 [1:24:50<16:42, 12.53s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▎ | 514/594 [1:24:50<16:42, 12.53s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▍ | 515/594 [1:25:00<15:22, 11.68s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▍ | 515/594 [1:25:00<15:22, 11.68s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▍ | 515/594 [1:25:00<15:22, 11.68s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▍ | 515/594 [1:25:00<15:22, 11.68s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▋ | 516/594 [1:25:09<14:19, 11.02s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▋ | 516/594 [1:25:09<14:19, 11.02s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1385, 'learning_rate': 8.617021276595746e-06, 'epoch': 0.87} + 87%|████████████████████████████████████████████████████████████████████▋ | 516/594 [1:25:09<14:19, 11.02s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▋ | 516/594 [1:25:09<14:19, 11.02s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▊ | 517/594 [1:25:19<13:30, 10.52s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▊ | 517/594 [1:25:19<13:30, 10.52s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1791, 'learning_rate': 8.510638297872341e-06, 'epoch': 0.87} + 87%|████████████████████████████████████████████████████████████████████▊ | 517/594 [1:25:19<13:30, 10.52s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████▊ | 517/594 [1:25:19<13:30, 10.52s/it]onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + onfig.jsonner.py:560] 2022-02-28 19:57:54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2385, 'learning_rate': 8.404255319148937e-06, 'epoch': 0.87} +[WARNING|modeling_utils.py:388] 2022-02-28 20:16:13,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:16:13,515 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████ | 519/594 [1:25:37<12:22, 9.89s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████ | 519/594 [1:25:37<12:22, 9.89s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0488, 'learning_rate': 8.297872340425532e-06, 'epoch': 0.87} + 87%|█████████████████████████████████████████████████████████████████████ | 519/594 [1:25:37<12:22, 9.89s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████ | 519/594 [1:25:37<12:22, 9.89s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1701, 'learning_rate': 8.191489361702128e-06, 'epoch': 0.87} + 88%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1984, 'learning_rate': 8.085106382978723e-06, 'epoch': 0.88} + 88%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▏ | 520/594 [1:25:46<11:56, 9.68s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 522/594 [1:26:05<11:15, 9.39s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 522/594 [1:26:05<11:15, 9.39s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 522/594 [1:26:05<11:15, 9.39s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▍ | 522/594 [1:26:05<11:15, 9.39s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▌ | 523/594 [1:26:14<11:00, 9.31s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▌ | 523/594 [1:26:14<11:00, 9.31s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0696, 'learning_rate': 7.872340425531916e-06, 'epoch': 0.88} + 88%|█████████████████████████████████████████████████████████████████████▌ | 523/594 [1:26:14<11:00, 9.31s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▌ | 523/594 [1:26:14<11:00, 9.31s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▌ | 523/594 [1:26:14<11:00, 9.31s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▋ | 524/594 [1:26:23<10:44, 9.21s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:17:08,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:17:08,082 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▊ | 525/594 [1:26:32<10:37, 9.24s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▊ | 525/594 [1:26:32<10:37, 9.24s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0892, 'learning_rate': 7.659574468085107e-06, 'epoch': 0.88} + 88%|█████████████████████████████████████████████████████████████████████▊ | 525/594 [1:26:32<10:37, 9.24s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|█████████████████████████████████████████████████████████████████████▊ | 525/594 [1:26:32<10:37, 9.24s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.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 computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.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 computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0812, 'learning_rate': 7.553191489361703e-06, 'epoch': 0.88} + g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.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 computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████ | 527/594 [1:26:49<10:02, 8.99s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████ | 527/594 [1:26:49<10:02, 8.99s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:17:34,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:17:34,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:17:34,791 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▏ | 528/594 [1:26:58<09:46, 8.88s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████��███▏ | 528/594 [1:26:58<09:46, 8.88s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:17:45,409 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▎ | 529/594 [1:27:06<09:27, 8.73s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▎ | 529/594 [1:27:06<09:27, 8.73s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.056, 'learning_rate': 7.234042553191491e-06, 'epoch': 0.89} + 89%|██████████████████████████████████████████████████████████████████████▎ | 529/594 [1:27:06<09:27, 8.73s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▎ | 529/594 [1:27:06<09:27, 8.73s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▍ | 530/594 [1:27:15<09:13, 8.66s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▍ | 530/594 [1:27:15<09:13, 8.66s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0824, 'learning_rate': 7.127659574468085e-06, 'epoch': 0.89} + 89%|██████████████████████████████████████████████████████████████████████▍ | 530/594 [1:27:15<09:13, 8.66s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████���██████████████████████████████████▍ | 530/594 [1:27:15<09:13, 8.66s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▌ | 531/594 [1:27:23<08:59, 8.57s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▌ | 531/594 [1:27:23<08:59, 8.57s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0396, 'learning_rate': 7.021276595744682e-06, 'epoch': 0.89} + 89%|██████████████████████████████████████████████████████████████████████▌ | 531/594 [1:27:23<08:59, 8.57s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▌ | 531/594 [1:27:23<08:59, 8.57s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▊ | 532/594 [1:27:32<08:48, 8.52s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▊ | 532/594 [1:27:32<08:48, 8.52s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2931, 'learning_rate': 6.914893617021278e-06, 'epoch': 0.89} + 90%|██████████████████████████████████████████████████████████████████████▊ | 532/594 [1:27:32<08:48, 8.52s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▊ | 532/594 [1:27:32<08:48, 8.52s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▉ | 533/594 [1:27:40<08:32, 8.40s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▉ | 533/594 [1:27:40<08:32, 8.40s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1061, 'learning_rate': 6.808510638297873e-06, 'epoch': 0.9} + 90%|██████████████████████████████████████████████████████████████████████▉ | 533/594 [1:27:40<08:32, 8.40s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|██████████████████████████████████████████████████████████████████████▉ | 533/594 [1:27:40<08:32, 8.40s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████ | 534/594 [1:27:48<08:18, 8.30s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████ | 534/594 [1:27:48<08:18, 8.30s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.124, 'learning_rate': 6.702127659574469e-06, 'epoch': 0.9} + 90%|███████████████████████████████████████████████████████████████████████ | 534/594 [1:27:48<08:18, 8.30s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████ | 534/594 [1:27:48<08:18, 8.30s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████��� | 535/594 [1:27:56<08:03, 8.19s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▏ | 535/594 [1:27:56<08:03, 8.19s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.149, 'learning_rate': 6.595744680851064e-06, 'epoch': 0.9} + 90%|███████████████████████████████████████████████████████████████████████▏ | 535/594 [1:27:56<08:03, 8.19s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▏ | 535/594 [1:27:56<08:03, 8.19s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▎ | 536/594 [1:28:04<07:46, 8.05s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▎ | 536/594 [1:28:04<07:46, 8.05s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.0031, 'learning_rate': 6.48936170212766e-06, 'epoch': 0.9} + 90%|███████████████████████████████████████████████████████████████████████▎ | 536/594 [1:28:04<07:46, 8.05s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▎ | 536/594 [1:28:04<07:46, 8.05s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▍ | 537/594 [1:28:11<07:30, 7.91s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▍ | 537/594 [1:28:11<07:30, 7.91s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.2344, 'learning_rate': 6.382978723404256e-06, 'epoch': 0.9} +[WARNING|modeling_utils.py:388] 2022-02-28 20:18:57,735 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:18:57,735 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▌ | 538/594 [1:28:19<07:14, 7.77s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▌ | 538/594 [1:28:19<07:14, 7.77s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▌ | 538/594 [1:28:19<07:14, 7.77s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▌ | 538/594 [1:28:19<07:14, 7.77s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▌ | 538/594 [1:28:19<07:14, 7.77s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▋ | 539/594 [1:28:26<06:56, 7.58s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:10,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:10,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:10,214 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▊ | 540/594 [1:28:33<06:38, 7.38s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▊ | 540/594 [1:28:33<06:38, 7.38s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:18,503 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▉ | 541/594 [1:28:39<06:16, 7.10s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|███████████████████████████████████████████████████████████████████████▉ | 541/594 [1:28:39<06:16, 7.10s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.151, 'learning_rate': 5.957446808510638e-06, 'epoch': 0.91} + 91%|███████████████████████████████████████████████████████████████████████▉ | 541/594 [1:28:39<06:16, 7.10s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:26,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:26,237 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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': 4.1377, 'learning_rate': 5.851063829787235e-06, 'epoch': 0.91} +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:30,659 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:30,659 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▏ | 543/594 [1:28:51<05:32, 6.52s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▏ | 543/594 [1:28:51<05:32, 6.52s/it]g-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:35,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument in `SpeechEncoderDecoderModel.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:35,995 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed54,583 >> The following columns in the evaluation set don't have a corresponding argument 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%|████████████████████████████████████████████████████████████████████████▎ | 544/594 [1:28:56<05:05, 6.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▎ | 544/594 [1:28:56<05:05, 6.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████▎ | 544/594 [1:28:56<05:05, 6.12s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:41,993 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:44,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:44,191 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:46,165 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:48,108 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:48,108 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:49,852 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:51,617 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:51,617 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:54,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:54,701 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:56,030 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:57,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:57,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:58,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:19:58,948 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:20:04,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:20:04,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:20:04,521 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▎ | 551/594 [1:29:29<04:07, 5.75s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▎ | 551/594 [1:29:29<04:07, 5.75s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▎ | 551/594 [1:29:29<04:07, 5.75s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████���████████████████████▎ | 551/594 [1:29:29<04:07, 5.75s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▎ | 551/594 [1:29:29<04:07, 5.75s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▍ | 552/594 [1:29:39<04:56, 7.07s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▍ | 552/594 [1:29:39<04:56, 7.07s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▍ | 552/594 [1:29:39<04:56, 7.07s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▍ | 552/594 [1:29:39<04:56, 7.07s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▍ | 552/594 [1:29:39<04:56, 7.07s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 553/594 [1:29:49<05:26, 7.96s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 553/594 [1:29:49<05:26, 7.96s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 553/594 [1:29:49<05:26, 7.96s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 553/594 [1:29:49<05:26, 7.96s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▌ | 553/594 [1:29:49<05:26, 7.96s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▋ | 554/594 [1:29:59<05:43, 8.58s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▋ | 554/594 [1:29:59<05:43, 8.58s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▋ | 554/594 [1:29:59<05:43, 8.58s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▋ | 554/594 [1:29:59<05:43, 8.58s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▊ | 555/594 [1:30:09<05:49, 8.97s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▊ | 555/594 [1:30:09<05:49, 8.97s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.0749, 'learning_rate': 4.468085106382979e-06, 'epoch': 0.93} + 93%|█████████████████████████████████████████████████████████████████████████▊ | 555/594 [1:30:09<05:49, 8.97s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▊ | 555/594 [1:30:09<05:49, 8.97s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▉ | 556/594 [1:30:19<05:50, 9.23s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▉ | 556/594 [1:30:19<05:50, 9.23s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.106, 'learning_rate': 4.361702127659575e-06, 'epoch': 0.93} + 94%|█████████████████████████████████████████████████████████████████████████▉ | 556/594 [1:30:19<05:50, 9.23s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████▉ | 556/594 [1:30:19<05:50, 9.23s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 557/594 [1:30:28<05:47, 9.40s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 557/594 [1:30:28<05:47, 9.40s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.1974, 'learning_rate': 4.255319148936171e-06, 'epoch': 0.94} + 94%|█████████████████████████████��████████████████████████████████████████████ | 557/594 [1:30:28<05:47, 9.40s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 557/594 [1:30:28<05:47, 9.40s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████ | 557/594 [1:30:28<05:47, 9.40s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.0609, 'learning_rate': 4.042553191489362e-06, 'epoch': 0.94} + 94%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▏ | 558/594 [1:30:38<05:42, 9.52s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▍ | 560/594 [1:30:57<05:24, 9.55s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▍ | 560/594 [1:30:57<05:24, 9.55s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.1074, 'learning_rate': 3.936170212765958e-06, 'epoch': 0.94} + 94%|██████████████████████████████████████████████████████████████████████████▍ | 560/594 [1:30:57<05:24, 9.55s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▍ | 560/594 [1:30:57<05:24, 9.55s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 561/594 [1:31:07<05:15, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 561/594 [1:31:07<05:15, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.4338, 'learning_rate': 3.8297872340425535e-06, 'epoch': 0.94} + 94%|██████████████████████████████████████████████████████████████████████████▌ | 561/594 [1:31:07<05:15, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▌ | 561/594 [1:31:07<05:15, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 562/594 [1:31:17<05:06, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 562/594 [1:31:17<05:06, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.041, 'learning_rate': 3.723404255319149e-06, 'epoch': 0.94} + 95%|██████████████████████████████████████████████████████████████████████████▋ | 562/594 [1:31:17<05:06, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▋ | 562/594 [1:31:17<05:06, 9.56s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 563/594 [1:31:26<04:53, 9.47s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 563/594 [1:31:26<04:53, 9.47s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 3.6170212765957453e-06, 'epoch': 0.95} + 95%|██████████████████████████████████████████████████████████████████████████▉ | 563/594 [1:31:26<04:53, 9.47s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 563/594 [1:31:26<04:53, 9.47s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████▉ | 563/594 [1:31:26<04:53, 9.47s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 564/594 [1:31:35<04:41, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 564/594 [1:31:35<04:41, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 564/594 [1:31:35<04:41, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 564/594 [1:31:35<04:41, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████ | 564/594 [1:31:35<04:41, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 565/594 [1:31:44<04:32, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 565/594 [1:31:44<04:32, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 565/594 [1:31:44<04:32, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▏ | 565/594 [1:31:44<04:32, 9.39s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.0428, 'learning_rate': 3.297872340425532e-06, 'epoch': 0.95} + 95%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.1384, 'learning_rate': 3.191489361702128e-06, 'epoch': 0.95} + 95%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▎ | 566/594 [1:31:54<04:20, 9.30s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 568/594 [1:32:12<03:58, 9.19s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 568/594 [1:32:12<03:58, 9.19s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.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': 3.0851063829787237e-06, 'epoch': 0.96} + 96%|███████████████████████████████████████████████████████████████████████████▌ | 568/594 [1:32:12<03:58, 9.19s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 568/594 [1:32:12<03:58, 9.19s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 568/594 [1:32:12<03:58, 9.19s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▌ | 568/594 [1:32:12<03:58, 9.19s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 3.9581, 'learning_rate': 2.978723404255319e-06, 'epoch': 0.96} +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:06,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:06,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:06,229 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 570/594 [1:32:30<03:37, 9.08s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 570/594 [1:32:30<03:37, 9.08s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 570/594 [1:32:30<03:37, 9.08s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 570/594 [1:32:30<03:37, 9.08s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▊ | 570/594 [1:32:30<03:37, 9.08s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▉ | 571/594 [1:32:38<03:27, 9.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▉ | 571/594 [1:32:38<03:27, 9.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▉ | 571/594 [1:32:38<03:27, 9.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████████████████████████████▉ | 571/594 [1:32:38<03:27, 9.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 572/594 [1:32:47<03:16, 8.94s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 572/594 [1:32:47<03:16, 8.94s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.1715, 'learning_rate': 2.6595744680851065e-06, 'epoch': 0.96} + 96%|████████████████████████████████████████████████████████████████████████████ | 572/594 [1:32:47<03:16, 8.94s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 572/594 [1:32:47<03:16, 8.94s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████���███████ | 572/594 [1:32:47<03:16, 8.94s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████ | 572/594 [1:32:47<03:16, 8.94s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.2385, 'learning_rate': 2.553191489361702e-06, 'epoch': 0.96} +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:41,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:41,323 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. + g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.1462, 'learning_rate': 2.446808510638298e-06, 'epoch': 0.97} +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:49,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:49,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:23:49,922 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍ | 575/594 [1:33:14<02:49, 8.90s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍ | 575/594 [1:33:14<02:49, 8.90s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍ | 575/594 [1:33:14<02:49, 8.90s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍ | 575/594 [1:33:14<02:49, 8.90s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▍ | 575/594 [1:33:14<02:49, 8.90s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌ | 576/594 [1:33:22<02:38, 8.80s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌ | 576/594 [1:33:22<02:38, 8.80s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌ | 576/594 [1:33:22<02:38, 8.80s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌ | 576/594 [1:33:22<02:38, 8.80s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▌ | 576/594 [1:33:22<02:38, 8.80s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████��█████████████████████████▋ | 577/594 [1:33:31<02:27, 8.69s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▋ | 577/594 [1:33:31<02:27, 8.69s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▋ | 577/594 [1:33:31<02:27, 8.69s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▋ | 577/594 [1:33:31<02:27, 8.69s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▋ | 577/594 [1:33:31<02:27, 8.69s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▊ | 578/594 [1:33:39<02:17, 8.62s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▊ | 578/594 [1:33:39<02:17, 8.62s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▊ | 578/594 [1:33:39<02:17, 8.62s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|████████████████████████████████████████████████████████████████████████████▊ | 578/594 [1:33:39<02:17, 8.62s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████ | 579/594 [1:33:48<02:08, 8.55s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████ | 579/594 [1:33:48<02:08, 8.55s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:24:32,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:24:32,712 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▏ | 580/594 [1:33:56<01:58, 8.46s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▏ | 580/594 [1:33:56<01:58, 8.46s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.2692, 'learning_rate': 1.8085106382978727e-06, 'epoch': 0.98} + 98%|█████████████████████████████████████████████████████████████████████████████▏ | 580/594 [1:33:56<01:58, 8.46s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▏ | 580/594 [1:33:56<01:58, 8.46s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▎ | 581/594 [1:34:04<01:48, 8.32s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▎ | 581/594 [1:34:04<01:48, 8.32s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.3664, 'learning_rate': 1.7021276595744682e-06, 'epoch': 0.98} + 98%|█████████████████████████████████████████████████████████████████████████████▎ | 581/594 [1:34:04<01:48, 8.32s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▎ | 581/594 [1:34:04<01:48, 8.32s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▎ | 581/594 [1:34:04<01:48, 8.32s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▍ | 582/594 [1:34:12<01:37, 8.16s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▍ | 582/594 [1:34:12<01:37, 8.16s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▍ | 582/594 [1:34:12<01:37, 8.16s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▍ | 582/594 [1:34:12<01:37, 8.16s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▍ | 582/594 [1:34:12<01:37, 8.16s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▌ | 583/594 [1:34:19<01:27, 8.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▌ | 583/594 [1:34:19<01:27, 8.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▌ | 583/594 [1:34:19<01:27, 8.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▌ | 583/594 [1:34:19<01:27, 8.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▌ | 583/594 [1:34:19<01:27, 8.00s/it]g-point operations will not be computed-28 20:19:38,544 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▋ | 584/594 [1:34:27<01:18, 7.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▋ | 584/594 [1:34:27<01:18, 7.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▋ | 584/594 [1:34:27<01:18, 7.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▋ | 584/594 [1:34:27<01:18, 7.81s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▊ | 585/594 [1:34:34<01:08, 7.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▊ | 585/594 [1:34:34<01:08, 7.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▊ | 585/594 [1:34:34<01:08, 7.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|█████████████████████████████████████████████████████████████████████████████▊ | 585/594 [1:34:34<01:08, 7.59s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:21,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:21,288 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:25,937 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:25,937 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████████ | 587/594 [1:34:46<00:48, 6.94s/it]g-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████████ | 587/594 [1:34:46<00:48, 6.94s/it]g-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:31,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:31,800 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████████▏| 588/594 [1:34:52<00:39, 6.59s/it]g-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:35,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:35,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:35,889 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:09,472 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████████▎| 589/594 [1:34:57<00:30, 6.18s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:39,706 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:42,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:39,706 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:42,038 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:39,706 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|███████████████████████████████████████████████████��██████████████████████████▍| 590/594 [1:35:02<00:23, 5.77s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:44,344 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:46,388 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:44,344 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:46,388 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:44,344 >> Could not estimate the number of tokens of the input, floating-point operations will not 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%|██████████████████████████████████████████████████████████████████████████████▌| 591/594 [1:35:06<00:15, 5.29s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:48,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:50,261 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:48,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:50,261 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:48,416 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +100%|██████████████████████████████████████████████████████████████████████████████▋| 592/594 [1:35:10<00:09, 4.83s/it][WARNING|modeling_utils.py:388] 2022-02-28 20:25:52,075 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +100%|██████████████████████████████████████████████████████████████████████████████▊| 593/594 [1:35:13<00:04, 4.35s/it]g-point operations will not be computed-28 20:25:52,075 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +100%|██████████████████████████████████████████████████████████████████████████████▊| 593/594 [1:35:13<00:04, 4.35s/it]g-point operations will not be computed-28 20:25:52,075 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:56,492 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:55,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[WARNING|modeling_utils.py:388] 2022-02-28 20:25:56,492 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed-28 20:25:55,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +{'loss': 4.4907, 'learning_rate': 3.1914893617021275e-07, 'epoch': 1.0} +[INFO|trainer.py:2114] 2022-02-28 20:25:57,230 >> Saving model checkpoint to ./=)███| 594/594 [1:35:16<00:00, 3.88s/it][INFO|trainer.py:1492] 2022-02-28 20:25:57,228 >> 5,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|trainer.py:2114] 2022-02-28 20:26:13,677 >> Saving model checkpoint to ./ ./pytorch_model.bin:16<00:00, 3.88s/it][INFO|trainer.py:1492] 2022-02-28 20:25:57,228 >> 5,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message. +[INFO|modeling_utils.py:1081] 2022-02-28 20:26:29,910 >> Model weights saved in ./pytorch_model.bin:16<00:00, 3.88s/it][INFO|trainer.py:1492] 2022-02-28 20:25:57,228 >> 5,181 >> Could not estimate the number of tokens of the input, floating-point operations will not be computed.forward` and have been ignored: input_length. If input_length are not expected by `SpeechEncoderDecoderModel.forward`, you can safely ignore this message.