diff --git "a/training.log" "b/training.log" --- "a/training.log" +++ "b/training.log" @@ -1,5 +1,5 @@ -05/07/2023 10:33:39 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 2distributed training: True, 16-bits training: True -05/07/2023 10:33:39 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( +05/22/2023 13:20:20 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 2distributed training: True, 16-bits training: True +05/22/2023 13:20:20 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( _n_gpu=2, adafactor=False, adam_beta1=0.9, @@ -38,7 +38,7 @@ full_determinism=False, generation_config=None, generation_max_length=225, generation_num_beams=None, -gradient_accumulation_steps=2, +gradient_accumulation_steps=8, gradient_checkpointing=True, greater_is_better=False, group_by_length=False, @@ -52,25 +52,25 @@ include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, -learning_rate=1e-05, +learning_rate=1.75e-05, length_column_name=input_length, load_best_model_at_end=True, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, -logging_dir=./runs/May07_10-33-38_crimv3mgpu025, +logging_dir=./runs/May22_13-20-19_crimv3mgpu016, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=25, logging_strategy=steps, lr_scheduler_type=linear, max_grad_norm=1.0, -max_steps=5000, +max_steps=-1, metric_for_best_model=wer, mp_parameters=, no_cuda=False, -num_train_epochs=3.0, +num_train_epochs=30.0, optim=adamw_hf, optim_args=None, output_dir=./, @@ -109,11 +109,11 @@ use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, -warmup_steps=500, +warmup_steps=4000, weight_decay=0.0, xpu_backend=None, ) -05/07/2023 10:33:39 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( +05/22/2023 13:20:20 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( _n_gpu=2, adafactor=False, adam_beta1=0.9, @@ -152,7 +152,7 @@ full_determinism=False, generation_config=None, generation_max_length=225, generation_num_beams=None, -gradient_accumulation_steps=2, +gradient_accumulation_steps=8, gradient_checkpointing=True, greater_is_better=False, group_by_length=False, @@ -166,25 +166,25 @@ include_inputs_for_metrics=False, jit_mode_eval=False, label_names=None, label_smoothing_factor=0.0, -learning_rate=1e-05, +learning_rate=1.75e-05, length_column_name=input_length, load_best_model_at_end=True, local_rank=0, log_level=passive, log_level_replica=warning, log_on_each_node=True, -logging_dir=./runs/May07_10-33-38_crimv3mgpu025, +logging_dir=./runs/May22_13-20-19_crimv3mgpu016, logging_first_step=False, logging_nan_inf_filter=True, logging_steps=25, logging_strategy=steps, lr_scheduler_type=linear, max_grad_norm=1.0, -max_steps=5000, +max_steps=-1, metric_for_best_model=wer, mp_parameters=, no_cuda=False, -num_train_epochs=3.0, +num_train_epochs=30.0, optim=adamw_hf, optim_args=None, output_dir=./, @@ -223,12 +223,12 @@ use_ipex=False, use_legacy_prediction_loop=False, use_mps_device=False, warmup_ratio=0.0, -warmup_steps=500, +warmup_steps=4000, weight_decay=0.0, xpu_backend=None, ) -[INFO|configuration_utils.py:669] 2023-05-07 10:33:51,873 >> loading configuration file config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/config.json -[INFO|configuration_utils.py:725] 2023-05-07 10:33:51,887 >> Model config WhisperConfig { +[INFO|configuration_utils.py:669] 2023-05-22 13:20:37,583 >> loading configuration file config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/config.json +[INFO|configuration_utils.py:725] 2023-05-22 13:20:37,651 >> Model config WhisperConfig { "_name_or_path": "openai/whisper-small", "activation_dropout": 0.0, "activation_function": "gelu", @@ -380,8 +380,8 @@ xpu_backend=None, "vocab_size": 51865 } -[INFO|feature_extraction_utils.py:469] 2023-05-07 10:33:52,076 >> loading configuration file preprocessor_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/preprocessor_config.json -[INFO|feature_extraction_utils.py:511] 2023-05-07 10:33:52,082 >> Feature extractor WhisperFeatureExtractor { +[INFO|feature_extraction_utils.py:469] 2023-05-22 13:20:37,926 >> loading configuration file preprocessor_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/preprocessor_config.json +[INFO|feature_extraction_utils.py:511] 2023-05-22 13:20:37,955 >> Feature extractor WhisperFeatureExtractor { "chunk_length": 30, "feature_extractor_type": "WhisperFeatureExtractor", "feature_size": 80, @@ -396,15 +396,15 @@ xpu_backend=None, "sampling_rate": 16000 } -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file vocab.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/vocab.json -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file tokenizer.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/tokenizer.json -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file merges.txt from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/merges.txt -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file normalizer.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/normalizer.json -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file added_tokens.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/added_tokens.json -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file special_tokens_map.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/special_tokens_map.json -[INFO|tokenization_utils_base.py:1810] 2023-05-07 10:33:52,291 >> loading file tokenizer_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/tokenizer_config.json -[INFO|modeling_utils.py:2542] 2023-05-07 10:33:52,385 >> loading weights file pytorch_model.bin from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/pytorch_model.bin -[INFO|configuration_utils.py:577] 2023-05-07 10:33:52,963 >> Generate config GenerationConfig { +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file vocab.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/vocab.json +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file tokenizer.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/tokenizer.json +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file merges.txt from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/merges.txt +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file normalizer.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/normalizer.json +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file added_tokens.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/added_tokens.json +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file special_tokens_map.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/special_tokens_map.json +[INFO|tokenization_utils_base.py:1810] 2023-05-22 13:20:38,269 >> loading file tokenizer_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/tokenizer_config.json +[INFO|modeling_utils.py:2542] 2023-05-22 13:20:38,651 >> loading weights file pytorch_model.bin from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/pytorch_model.bin +[INFO|configuration_utils.py:577] 2023-05-22 13:20:47,050 >> Generate config GenerationConfig { "_from_model_config": true, "begin_suppress_tokens": [ 220, @@ -419,12 +419,12 @@ xpu_backend=None, "use_cache": false } -[INFO|modeling_utils.py:3211] 2023-05-07 10:33:55,474 >> All model checkpoint weights were used when initializing WhisperForConditionalGeneration. +[INFO|modeling_utils.py:3211] 2023-05-22 13:20:49,666 >> All model checkpoint weights were used when initializing WhisperForConditionalGeneration. -[INFO|modeling_utils.py:3219] 2023-05-07 10:33:55,474 >> All the weights of WhisperForConditionalGeneration were initialized from the model checkpoint at openai/whisper-small. +[INFO|modeling_utils.py:3219] 2023-05-22 13:20:49,666 >> All the weights of WhisperForConditionalGeneration were initialized from the model checkpoint at openai/whisper-small. If your task is similar to the task the model of the checkpoint was trained on, you can already use WhisperForConditionalGeneration for predictions without further training. -[INFO|configuration_utils.py:539] 2023-05-07 10:33:55,680 >> loading configuration file generation_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/generation_config.json -[INFO|configuration_utils.py:577] 2023-05-07 10:33:55,681 >> Generate config GenerationConfig { +[INFO|configuration_utils.py:539] 2023-05-22 13:20:50,330 >> loading configuration file generation_config.json from cache at /home/local/QCRI/dizham/.cache/huggingface/hub/models--openai--whisper-small/snapshots/f6744499d1eba717bcf4d6be735e3d386ffb60ad/generation_config.json +[INFO|configuration_utils.py:577] 2023-05-22 13:20:50,331 >> Generate config GenerationConfig { "begin_suppress_tokens": [ 220, 50257 @@ -646,13 +646,13 @@ If your task is similar to the task the model of the checkpoint was trained on, "transformers_version": "4.29.0.dev0" } -[INFO|feature_extraction_utils.py:369] 2023-05-07 10:33:56,907 >> Feature extractor saved in ./preprocessor_config.json -[INFO|tokenization_utils_base.py:2181] 2023-05-07 10:33:56,915 >> tokenizer config file saved in ./tokenizer_config.json -[INFO|tokenization_utils_base.py:2188] 2023-05-07 10:33:56,922 >> Special tokens file saved in ./special_tokens_map.json -[INFO|configuration_utils.py:458] 2023-05-07 10:33:57,075 >> Configuration saved in ./config.json -[INFO|image_processing_utils.py:307] 2023-05-07 10:33:57,075 >> loading configuration file ./preprocessor_config.json -[INFO|feature_extraction_utils.py:467] 2023-05-07 10:33:57,084 >> loading configuration file ./preprocessor_config.json -[INFO|feature_extraction_utils.py:511] 2023-05-07 10:33:57,085 >> Feature extractor WhisperFeatureExtractor { +[INFO|feature_extraction_utils.py:369] 2023-05-22 13:20:52,959 >> Feature extractor saved in ./preprocessor_config.json +[INFO|tokenization_utils_base.py:2181] 2023-05-22 13:20:52,962 >> tokenizer config file saved in ./tokenizer_config.json +[INFO|tokenization_utils_base.py:2188] 2023-05-22 13:20:52,965 >> Special tokens file saved in ./special_tokens_map.json +[INFO|configuration_utils.py:458] 2023-05-22 13:20:53,103 >> Configuration saved in ./config.json +[INFO|image_processing_utils.py:307] 2023-05-22 13:20:53,104 >> loading configuration file ./preprocessor_config.json +[INFO|feature_extraction_utils.py:467] 2023-05-22 13:20:53,134 >> loading configuration file ./preprocessor_config.json +[INFO|feature_extraction_utils.py:511] 2023-05-22 13:20:53,135 >> Feature extractor WhisperFeatureExtractor { "chunk_length": 30, "feature_extractor_type": "WhisperFeatureExtractor", "feature_size": 80, @@ -667,461 +667,145 @@ If your task is similar to the task the model of the checkpoint was trained on, "sampling_rate": 16000 } -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file vocab.json -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file tokenizer.json -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file merges.txt -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file normalizer.json -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file added_tokens.json -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file special_tokens_map.json -[INFO|tokenization_utils_base.py:1808] 2023-05-07 10:33:57,086 >> loading file tokenizer_config.json -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|startoftranscript|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|en|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|zh|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|de|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|es|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|ru|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|ko|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|fr|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|ja|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|pt|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|tr|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|pl|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|ca|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|nl|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|ar|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|sv|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|it|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|id|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|hi|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|fi|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,149 >> Adding <|vi|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|he|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|uk|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|el|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|ms|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|cs|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|ro|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|da|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|hu|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|ta|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|no|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|th|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|ur|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|hr|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|bg|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|lt|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|la|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|mi|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|ml|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|cy|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|sk|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|te|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|fa|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|lv|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|bn|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|sr|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|az|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|sl|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|kn|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|et|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|mk|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|br|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|eu|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|is|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|hy|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|ne|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|mn|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|bs|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|kk|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|sq|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|sw|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|gl|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,150 >> Adding <|mr|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|pa|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|si|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|km|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|sn|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|yo|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|so|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|af|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|oc|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|ka|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|be|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|tg|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|sd|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|gu|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|am|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|yi|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|lo|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|uz|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|fo|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|ht|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|ps|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|tk|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|nn|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|mt|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|sa|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|lb|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|my|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|bo|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|tl|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|mg|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|as|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|tt|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|haw|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|ln|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|ha|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|ba|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|jw|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|su|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|translate|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|transcribe|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|startoflm|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,151 >> Adding <|startofprev|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,152 >> Adding <|nocaptions|> to the vocabulary -[INFO|tokenization_utils.py:426] 2023-05-07 10:33:57,152 >> Adding <|notimestamps|> to the vocabulary +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file vocab.json +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file tokenizer.json +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file merges.txt +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file normalizer.json +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file added_tokens.json +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file special_tokens_map.json +[INFO|tokenization_utils_base.py:1808] 2023-05-22 13:20:53,136 >> loading file tokenizer_config.json +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,201 >> Adding <|startoftranscript|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,201 >> Adding <|en|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|zh|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|de|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|es|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ru|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ko|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|fr|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ja|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|pt|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|tr|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|pl|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ca|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|nl|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ar|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|sv|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|it|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|id|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|hi|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|fi|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|vi|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|he|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|uk|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|el|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ms|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|cs|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ro|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|da|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|hu|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ta|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|no|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|th|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ur|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|hr|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|bg|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|lt|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|la|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|mi|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|ml|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|cy|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|sk|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,202 >> Adding <|te|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|fa|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|lv|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|bn|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sr|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|az|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sl|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|kn|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|et|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|mk|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|br|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|eu|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|is|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|hy|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ne|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|mn|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|bs|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|kk|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sq|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sw|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|gl|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|mr|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|pa|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|si|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|km|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sn|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|yo|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|so|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|af|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|oc|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ka|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|be|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|tg|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|sd|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|gu|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|am|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|yi|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|lo|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|uz|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|fo|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ht|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,203 >> Adding <|ps|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|tk|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|nn|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|mt|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|sa|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|lb|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|my|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|bo|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|tl|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|mg|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|as|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|tt|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|haw|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|ln|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|ha|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|ba|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|jw|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|su|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|translate|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|transcribe|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|startoflm|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|startofprev|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|nocaptions|> to the vocabulary +[INFO|tokenization_utils.py:426] 2023-05-22 13:20:53,204 >> Adding <|notimestamps|> to the vocabulary /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/./ is already a clone of https://huggingface.co/danielizham/whisper-small-ar. Make sure you pull the latest changes with `repo.git_pull()`. -05/07/2023 10:34:00 - WARNING - huggingface_hub.repository - /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/./ is already a clone of https://huggingface.co/danielizham/whisper-small-ar. Make sure you pull the latest changes with `repo.git_pull()`. -[INFO|trainer.py:565] 2023-05-07 10:34:02,856 >> max_steps is given, it will override any value given in num_train_epochs -[INFO|trainer.py:622] 2023-05-07 10:34:02,856 >> Using cuda_amp half precision backend -/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/optimization.py:407: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning - warnings.warn( -[INFO|trainer.py:1771] 2023-05-07 10:34:02,869 >> ***** Running training ***** -[INFO|trainer.py:1772] 2023-05-07 10:34:02,869 >> Num examples = 640,000 -[INFO|trainer.py:1773] 2023-05-07 10:34:02,869 >> Num Epochs = 9,223,372,036,854,775,807 -[INFO|trainer.py:1774] 2023-05-07 10:34:02,870 >> Instantaneous batch size per device = 32 -[INFO|trainer.py:1775] 2023-05-07 10:34:02,870 >> Total train batch size (w. parallel, distributed & accumulation) = 128 -[INFO|trainer.py:1776] 2023-05-07 10:34:02,870 >> Gradient Accumulation steps = 2 -[INFO|trainer.py:1777] 2023-05-07 10:34:02,870 >> Total optimization steps = 5,000 -[INFO|trainer.py:1778] 2023-05-07 10:34:02,871 >> Number of trainable parameters = 241,734,912 -[INFO|integrations.py:720] 2023-05-07 10:34:02,872 >> Automatic Weights & Biases logging enabled, to disable set os.environ["WANDB_DISABLED"] = "true" -wandb: Currently logged in as: danielizham. Use `wandb login --relogin` to force relogin -wandb: Tracking run with wandb version 0.15.2 -wandb: Run data is saved locally in /home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/wandb/run-20230507_103405-9zf5xxpu -wandb: Run `wandb offline` to turn off syncing. -wandb: Syncing run fast-feather-2 -wandb: ⭐️ View project at https://wandb.ai/danielizham/huggingface -wandb: 🚀 View run at https://wandb.ai/danielizham/huggingface/runs/9zf5xxpu - 0%| | 0/5000 [00:00 + main() + File "/home/local/QCRI/dizham/kanari/whisper/whisper-small-ar/run_speech_recognition_seq2seq_streaming.py", line 560, in main + trainer = Seq2SeqTrainer( + File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer_seq2seq.py", line 56, in __init__ + super().__init__( + File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 551, in __init__ + self.init_git_repo(at_init=True) + File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/transformers/trainer.py", line 3516, in init_git_repo + self.repo.git_pull() + File "/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/huggingface_hub/repository.py", line 990, in git_pull + raise EnvironmentError(exc.stderr) +OSError: error: cannot pull with rebase: You have unstaged changes. +error: please commit or stash them. - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.37it/s] Reading metadata...: 10438it [00:00, 28290.14it/s] -[INFO|trainer_utils.py:693] 2023-05-07 10:35:32,760 >> The following columns in the training set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message. -/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector. - warnings.warn('Was asked to gather along dimension 0, but all ' - 0%| | 1/5000 [01:47<148:38:46, 107.05s/it] 0%| | 2/5000 [02:14<83:36:35, 60.22s/it] 0%| | 3/5000 [02:41<62:42:18, 45.17s/it] 0%| | 4/5000 [03:10<53:25:35, 38.50s/it] 0%| | 5/5000 [03:40<49:28:00, 35.65s/it] 0%| | 6/5000 [04:08<45:33:39, 32.84s/it] 0%| | 7/5000 [04:35<42:56:31, 30.96s/it] 0%| | 8/5000 [05:02<41:32:10, 29.95s/it] 0%| | 9/5000 [05:30<40:27:17, 29.18s/it] 0%| | 10/5000 [05:59<40:15:31, 29.04s/it] 0%| | 11/5000 [06:25<39:17:47, 28.36s/it] 0%| | 12/5000 [06:54<39:16:28, 28.35s/it] 0%| | 13/5000 [07:22<39:09:18, 28.27s/it] 0%| | 14/5000 [07:50<39:02:25, 28.19s/it] 0%| | 15/5000 [08:17<38:33:57, 27.85s/it] 0%| | 16/5000 [08:45<38:35:55, 27.88s/it] 0%| | 17/5000 [09:13<38:32:36, 27.85s/it] 0%| | 18/5000 [09:40<38:19:57, 27.70s/it] 0%| | 19/5000 [10:10<39:17:48, 28.40s/it] 0%| | 20/5000 [10:37<38:47:34, 28.04s/it] 0%| | 21/5000 [11:04<38:25:49, 27.79s/it] 0%| | 22/5000 [11:33<38:42:41, 28.00s/it] 0%| | 23/5000 [12:01<38:38:51, 27.95s/it] 0%| | 24/5000 [12:28<38:28:42, 27.84s/it] 0%| | 25/5000 [12:57<38:59:22, 28.21s/it] 0%| | 25/5000 [12:57<38:59:22, 28.21s/it] 1%| | 26/5000 [13:24<38:30:52, 27.88s/it] 1%| | 27/5000 [13:52<38:13:36, 27.67s/it] 1%| | 28/5000 [14:20<38:19:33, 27.75s/it] 1%| | 29/5000 [14:47<38:05:23, 27.58s/it] 1%| | 30/5000 [15:14<38:00:17, 27.53s/it] 1%| | 31/5000 [15:42<38:12:38, 27.68s/it] 1%| | 32/5000 [16:09<37:58:26, 27.52s/it] 1%| | 33/5000 [16:36<37:47:47, 27.39s/it] 1%| | 34/5000 [17:07<38:52:40, 28.18s/it] 1%| | 35/5000 [17:33<38:19:00, 27.78s/it] 1%| | 36/5000 [18:01<38:02:35, 27.59s/it] 1%| | 37/5000 [18:30<38:40:53, 28.06s/it] 1%| | 38/5000 [18:57<38:17:23, 27.78s/it] 1%| | 39/5000 [19:24<38:09:39, 27.69s/it] 1%| | 40/5000 [19:54<38:59:07, 28.30s/it] 1%| | 41/5000 [20:21<38:36:11, 28.02s/it] 1%| | 42/5000 [20:50<38:40:08, 28.08s/it] 1%| | 43/5000 [21:17<38:33:12, 28.00s/it] 1%| | 44/5000 [21:44<38:03:57, 27.65s/it] 1%| | 45/5000 [22:13<38:24:59, 27.91s/it] 1%| | 46/5000 [22:40<38:11:21, 27.75s/it] 1%| | 47/5000 [23:10<38:55:38, 28.29s/it] 1%| | 48/5000 [23:37<38:24:02, 27.92s/it] 1%| | 49/5000 [24:03<37:46:25, 27.47s/it] 1%| | 50/5000 [24:31<38:04:45, 27.69s/it] 1%| | 50/5000 [24:31<38:04:45, 27.69s/it] 1%| | 51/5000 [24:59<38:02:43, 27.68s/it] 1%| | 52/5000 [25:26<37:51:48, 27.55s/it] 1%| | 53/5000 [25:55<38:16:50, 27.86s/it] 1%| | 54/5000 [26:22<38:10:08, 27.78s/it] 1%| | 55/5000 [26:50<37:59:21, 27.66s/it] 1%| | 56/5000 [27:18<38:09:00, 27.78s/it] 1%| | 57/5000 [27:45<37:51:24, 27.57s/it] 1%| | 58/5000 [28:12<37:39:30, 27.43s/it] 1%| | 59/5000 [28:42<38:33:05, 28.09s/it] 1%| | 60/5000 [29:09<38:09:46, 27.81s/it] 1%| | 61/5000 [29:36<38:01:21, 27.71s/it] 1%| | 62/5000 [30:05<38:26:25, 28.02s/it] 1%|▏ | 63/5000 [30:32<38:07:36, 27.80s/it] 1%|▏ | 64/5000 [30:59<37:48:53, 27.58s/it] 1%|▏ | 65/5000 [31:29<38:48:09, 28.31s/it] 1%|▏ | 66/5000 [31:57<38:25:18, 28.03s/it] 1%|▏ | 67/5000 [32:26<38:52:41, 28.37s/it] 1%|▏ | 68/5000 [32:54<38:41:09, 28.24s/it] 1%|▏ | 69/5000 [33:21<38:15:10, 27.93s/it] 1%|▏ | 70/5000 [33:49<38:07:26, 27.84s/it] 1%|▏ | 71/5000 [34:16<37:59:11, 27.74s/it] 1%|▏ | 72/5000 [34:47<39:02:11, 28.52s/it] 1%|▏ | 73/5000 [35:15<38:48:31, 28.36s/it] 1%|▏ | 74/5000 [35:42<38:24:24, 28.07s/it] 2%|▏ | 75/5000 [36:10<38:12:36, 27.93s/it] 2%|▏ | 75/5000 [36:10<38:12:36, 27.93s/it] 2%|▏ | 76/5000 [36:42<40:02:06, 29.27s/it] 2%|▏ | 77/5000 [37:09<39:13:52, 28.69s/it] 2%|▏ | 78/5000 [37:37<38:50:12, 28.41s/it] 2%|▏ | 79/5000 [38:06<39:05:12, 28.59s/it] 2%|▏ | 80/5000 [38:33<38:20:59, 28.06s/it] 2%|▏ | 81/5000 [39:01<38:30:04, 28.18s/it] 2%|▏ | 82/5000 [39:29<38:05:29, 27.88s/it] 2%|▏ | 83/5000 [39:56<37:52:05, 27.73s/it] 2%|▏ | 84/5000 [40:23<37:34:58, 27.52s/it] 2%|▏ | 85/5000 [40:51<37:40:57, 27.60s/it] 2%|▏ | 86/5000 [41:18<37:44:37, 27.65s/it] 2%|▏ | 87/5000 [41:46<37:36:43, 27.56s/it] 2%|▏ | 88/5000 [42:14<37:44:37, 27.66s/it] 2%|▏ | 89/5000 [42:42<37:51:35, 27.75s/it] 2%|▏ | 90/5000 [43:09<37:41:54, 27.64s/it] 2%|▏ | 91/5000 [43:37<37:50:15, 27.75s/it] 2%|▏ | 92/5000 [44:05<38:00:27, 27.88s/it] 2%|▏ | 93/5000 [44:32<37:38:09, 27.61s/it] 2%|▏ | 94/5000 [45:00<37:35:56, 27.59s/it] 2%|▏ | 95/5000 [45:27<37:35:42, 27.59s/it] 2%|▏ | 96/5000 [45:55<37:24:43, 27.46s/it] 2%|▏ | 97/5000 [46:23<37:39:21, 27.65s/it] 2%|▏ | 98/5000 [46:50<37:38:40, 27.65s/it] 2%|▏ | 99/5000 [47:18<37:32:18, 27.57s/it] 2%|▏ | 100/5000 [47:46<37:40:02, 27.67s/it] 2%|▏ | 100/5000 [47:46<37:40:02, 27.67s/it] 2%|▏ | 101/5000 [48:13<37:44:47, 27.74s/it] 2%|▏ | 102/5000 [48:41<37:29:30, 27.56s/it] 2%|▏ | 103/5000 [49:09<37:45:09, 27.75s/it] 2%|▏ | 104/5000 [49:36<37:34:21, 27.63s/it] 2%|▏ | 105/5000 [50:03<37:25:22, 27.52s/it] 2%|▏ | 106/5000 [50:31<37:25:13, 27.53s/it] 2%|▏ | 107/5000 [50:58<37:16:28, 27.42s/it] 2%|▏ | 108/5000 [51:25<37:13:39, 27.40s/it] 2%|▏ | 109/5000 [51:53<37:18:48, 27.46s/it] 2%|▏ | 110/5000 [52:20<37:12:04, 27.39s/it] 2%|▏ | 111/5000 [52:48<37:11:35, 27.39s/it] 2%|▏ | 112/5000 [53:15<37:19:40, 27.49s/it] 2%|▏ | 113/5000 [53:43<37:14:35, 27.44s/it] 2%|▏ | 114/5000 [54:10<37:06:26, 27.34s/it] 2%|▏ | 115/5000 [54:37<37:12:39, 27.42s/it] 2%|▏ | 116/5000 [55:06<37:30:46, 27.65s/it] 2%|▏ | 117/5000 [55:33<37:33:08, 27.69s/it] 2%|▏ | 118/5000 [56:01<37:25:22, 27.60s/it] 2%|▏ | 119/5000 [56:29<37:37:17, 27.75s/it] 2%|▏ | 120/5000 [56:56<37:25:52, 27.61s/it] 2%|▏ | 121/5000 [57:24<37:19:37, 27.54s/it] 2%|▏ | 122/5000 [57:53<38:07:24, 28.14s/it] 2%|▏ | 123/5000 [58:20<37:47:02, 27.89s/it] 2%|▏ | 124/5000 [58:48<37:31:04, 27.70s/it] 2%|▎ | 125/5000 [59:17<37:59:12, 28.05s/it] 2%|▎ | 125/5000 [59:17<37:59:12, 28.05s/it] 3%|▎ | 126/5000 [59:43<37:15:16, 27.52s/it] 3%|▎ | 127/5000 [1:00:08<36:26:56, 26.93s/it] 3%|▎ | 128/5000 [1:00:37<36:56:46, 27.30s/it] 3%|▎ | 129/5000 [1:01:03<36:45:18, 27.16s/it] 3%|▎ | 130/5000 [1:01:30<36:26:39, 26.94s/it] 3%|▎ | 131/5000 [1:01:57<36:38:18, 27.09s/it] 3%|▎ | 132/5000 [1:02:25<37:00:00, 27.36s/it] 3%|▎ | 133/5000 [1:02:52<36:50:32, 27.25s/it] 3%|▎ | 134/5000 [1:03:20<36:51:47, 27.27s/it] 3%|▎ | 135/5000 [1:03:50<38:00:00, 28.12s/it] 3%|▎ | 136/5000 [1:04:17<37:37:28, 27.85s/it] 3%|▎ | 137/5000 [1:04:44<37:24:28, 27.69s/it] 3%|▎ | 138/5000 [1:05:13<37:57:48, 28.11s/it] 3%|▎ | 139/5000 [1:05:41<37:35:32, 27.84s/it] 3%|▎ | 140/5000 [1:06:08<37:17:24, 27.62s/it] 3%|▎ | 141/5000 [1:06:35<37:22:03, 27.69s/it] 3%|▎ | 142/5000 [1:07:03<37:12:38, 27.57s/it] 3%|▎ | 143/5000 [1:07:30<37:00:17, 27.43s/it] 3%|▎ | 144/5000 [1:07:58<37:20:26, 27.68s/it] 3%|▎ | 145/5000 [1:08:26<37:18:01, 27.66s/it] 3%|▎ | 146/5000 [1:08:53<37:10:30, 27.57s/it] 3%|▎ | 147/5000 [1:09:24<38:26:43, 28.52s/it] 3%|▎ | 148/5000 [1:09:51<37:53:31, 28.11s/it] 3%|▎ | 149/5000 [1:10:18<37:34:47, 27.89s/it] 3%|▎ | 150/5000 [1:10:46<37:32:21, 27.86s/it] 3%|▎ | 150/5000 [1:10:46<37:32:21, 27.86s/it] 3%|▎ | 151/5000 [1:11:14<37:20:59, 27.73s/it] 3%|▎ | 152/5000 [1:11:41<37:11:01, 27.61s/it] 3%|▎ | 153/5000 [1:12:11<38:05:01, 28.29s/it] 3%|▎ | 154/5000 [1:12:38<37:41:38, 28.00s/it] 3%|▎ | 155/5000 [1:13:05<37:14:21, 27.67s/it] 3%|▎ | 156/5000 [1:13:34<37:40:15, 28.00s/it] 3%|▎ | 157/5000 [1:14:01<37:22:01, 27.78s/it] 3%|▎ | 158/5000 [1:14:28<37:08:30, 27.61s/it] 3%|▎ | 159/5000 [1:14:56<37:18:52, 27.75s/it] 3%|▎ | 160/5000 [1:15:10<31:43:49, 23.60s/it] 3%|▎ | 161/5000 [1:15:21<26:35:31, 19.78s/it] 3%|▎ | 162/5000 [1:15:32<23:01:15, 17.13s/it] 3%|▎ | 163/5000 [1:15:43<20:26:07, 15.21s/it]{'loss': 0.9879, 'learning_rate': 4.6000000000000004e-07, 'epoch': 0.01} -{'loss': 0.8962, 'learning_rate': 9.600000000000001e-07, 'epoch': 0.01} -{'loss': 0.6006, 'learning_rate': 1.46e-06, 'epoch': 0.01} -{'loss': 0.4218, 'learning_rate': 1.9600000000000003e-06, 'epoch': 0.02} -{'loss': 0.4419, 'learning_rate': 2.46e-06, 'epoch': 0.03} -{'loss': 0.4007, 'learning_rate': 2.96e-06, 'epoch': 0.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.54it/s] - Reading metadata...: 15060it [00:00, 40107.89it/s] - Reading metadata...: 23919it [00:01, 14960.32it/s] Reading metadata...: 28043it [00:01, 18033.45it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:01, 1.15s/it] Reading metadata...: 10438it [00:01, 8535.33it/s] - 3%|▎ | 164/5000 [1:17:12<50:13:58, 37.39s/it] 3%|▎ | 165/5000 [1:17:40<46:30:54, 34.63s/it] 3%|▎ | 166/5000 [1:18:08<43:58:06, 32.74s/it] 3%|▎ | 167/5000 [1:18:37<42:17:46, 31.51s/it] 3%|▎ | 168/5000 [1:19:04<40:32:14, 30.20s/it] 3%|▎ | 169/5000 [1:19:33<39:51:03, 29.70s/it] 3%|▎ | 170/5000 [1:20:02<39:30:40, 29.45s/it] 3%|▎ | 171/5000 [1:20:31<39:30:47, 29.46s/it] 3%|▎ | 172/5000 [1:20:59<39:02:18, 29.11s/it] 3%|▎ | 173/5000 [1:21:27<38:19:55, 28.59s/it] 3%|▎ | 174/5000 [1:21:55<38:12:08, 28.50s/it] 4%|▎ | 175/5000 [1:22:25<38:42:56, 28.89s/it] 4%|▎ | 175/5000 [1:22:25<38:42:56, 28.89s/it] 4%|▎ | 176/5000 [1:22:52<37:55:34, 28.30s/it] 4%|▎ | 177/5000 [1:23:20<37:58:12, 28.34s/it] 4%|▎ | 178/5000 [1:23:48<37:52:23, 28.28s/it] 4%|▎ | 179/5000 [1:24:16<37:46:36, 28.21s/it] 4%|▎ | 180/5000 [1:24:44<37:33:35, 28.05s/it] 4%|▎ | 181/5000 [1:25:11<37:14:38, 27.82s/it] 4%|▎ | 182/5000 [1:25:44<39:19:43, 29.39s/it] 4%|▎ | 183/5000 [1:26:13<38:47:39, 28.99s/it] 4%|▎ | 184/5000 [1:26:40<38:00:33, 28.41s/it] 4%|▎ | 185/5000 [1:27:08<38:09:17, 28.53s/it] 4%|▎ | 186/5000 [1:27:37<38:02:08, 28.44s/it] 4%|▎ | 187/5000 [1:28:04<37:29:01, 28.04s/it] 4%|▍ | 188/5000 [1:28:33<37:47:02, 28.27s/it] 4%|▍ | 189/5000 [1:29:00<37:39:52, 28.18s/it] 4%|▍ | 190/5000 [1:29:28<37:13:28, 27.86s/it] 4%|▍ | 191/5000 [1:29:56<37:29:50, 28.07s/it] 4%|▍ | 192/5000 [1:30:26<38:20:14, 28.71s/it] 4%|▍ | 193/5000 [1:30:54<37:43:33, 28.25s/it] 4%|▍ | 194/5000 [1:31:23<38:01:21, 28.48s/it] 4%|▍ | 195/5000 [1:31:51<38:09:37, 28.59s/it] 4%|▍ | 196/5000 [1:32:19<37:38:58, 28.21s/it] 4%|▍ | 197/5000 [1:32:48<37:55:29, 28.43s/it] 4%|▍ | 198/5000 [1:33:15<37:25:58, 28.06s/it] 4%|▍ | 199/5000 [1:33:41<36:50:43, 27.63s/it] 4%|▍ | 200/5000 [1:34:15<39:11:58, 29.40s/it] 4%|▍ | 200/5000 [1:34:15<39:11:58, 29.40s/it] 4%|▍ | 201/5000 [1:34:44<38:50:49, 29.14s/it] 4%|▍ | 202/5000 [1:35:11<38:06:09, 28.59s/it] 4%|▍ | 203/5000 [1:35:39<37:59:39, 28.51s/it] 4%|▍ | 204/5000 [1:36:07<37:39:47, 28.27s/it] 4%|▍ | 205/5000 [1:36:34<37:18:41, 28.01s/it] 4%|▍ | 206/5000 [1:37:03<37:22:26, 28.07s/it] 4%|▍ | 207/5000 [1:37:31<37:39:51, 28.29s/it] 4%|▍ | 208/5000 [1:37:58<36:56:51, 27.76s/it] 4%|▍ | 209/5000 [1:38:26<37:06:54, 27.89s/it] 4%|▍ | 210/5000 [1:38:54<36:58:07, 27.78s/it] 4%|▍ | 211/5000 [1:39:21<36:51:24, 27.71s/it] 4%|▍ | 212/5000 [1:39:48<36:25:39, 27.39s/it] 4%|▍ | 213/5000 [1:40:14<36:06:47, 27.16s/it] 4%|▍ | 214/5000 [1:40:43<36:31:19, 27.47s/it] 4%|▍ | 215/5000 [1:41:10<36:30:44, 27.47s/it] 4%|▍ | 216/5000 [1:41:39<37:02:43, 27.88s/it] 4%|▍ | 217/5000 [1:42:08<37:27:08, 28.19s/it] 4%|▍ | 218/5000 [1:42:35<37:12:10, 28.01s/it] 4%|▍ | 219/5000 [1:43:04<37:27:18, 28.20s/it] 4%|▍ | 220/5000 [1:43:32<37:32:49, 28.28s/it] 4%|▍ | 221/5000 [1:44:00<37:14:15, 28.05s/it] 4%|▍ | 222/5000 [1:44:29<37:34:23, 28.31s/it] 4%|▍ | 223/5000 [1:44:56<37:10:20, 28.01s/it] 4%|▍ | 224/5000 [1:45:23<36:46:48, 27.72s/it] 4%|▍ | 225/5000 [1:45:53<37:34:07, 28.32s/it] 4%|▍ | 225/5000 [1:45:53<37:34:07, 28.32s/it] 5%|▍ | 226/5000 [1:46:20<37:01:08, 27.92s/it] 5%|▍ | 227/5000 [1:46:47<36:45:13, 27.72s/it] 5%|▍ | 228/5000 [1:47:16<37:12:24, 28.07s/it] 5%|▍ | 229/5000 [1:47:45<37:36:57, 28.38s/it] 5%|▍ | 230/5000 [1:48:12<37:03:13, 27.97s/it] 5%|▍ | 231/5000 [1:48:40<37:09:03, 28.04s/it] 5%|▍ | 232/5000 [1:49:09<37:18:54, 28.17s/it] 5%|▍ | 233/5000 [1:49:36<37:00:35, 27.95s/it] 5%|▍ | 234/5000 [1:50:05<37:20:39, 28.21s/it] 5%|▍ | 235/5000 [1:50:33<37:08:04, 28.06s/it] 5%|▍ | 236/5000 [1:51:00<36:46:12, 27.79s/it] 5%|▍ | 237/5000 [1:51:28<37:02:06, 27.99s/it] 5%|▍ | 238/5000 [1:51:57<37:14:26, 28.15s/it] 5%|▍ | 239/5000 [1:52:26<37:23:32, 28.27s/it] 5%|▍ | 240/5000 [1:52:53<36:58:16, 27.96s/it] 5%|▍ | 241/5000 [1:53:22<37:17:08, 28.21s/it] 5%|▍ | 242/5000 [1:53:50<37:23:16, 28.29s/it] 5%|▍ | 243/5000 [1:54:18<37:04:50, 28.06s/it] 5%|▍ | 244/5000 [1:54:46<37:20:31, 28.27s/it] 5%|▍ | 245/5000 [1:55:15<37:34:31, 28.45s/it] 5%|▍ | 246/5000 [1:55:43<37:08:49, 28.13s/it] 5%|▍ | 247/5000 [1:56:11<37:22:29, 28.31s/it] 5%|▍ | 248/5000 [1:56:40<37:33:11, 28.45s/it] 5%|▍ | 249/5000 [1:57:07<37:05:48, 28.11s/it] 5%|▌ | 250/5000 [1:57:37<37:49:09, 28.66s/it] 5%|▌ | 250/5000 [1:57:37<37:49:09, 28.66s/it] 5%|▌ | 251/5000 [1:58:06<37:46:16, 28.63s/it] 5%|▌ | 252/5000 [1:58:33<37:13:53, 28.23s/it] 5%|▌ | 253/5000 [1:59:01<37:12:43, 28.22s/it] 5%|▌ | 254/5000 [1:59:30<37:21:10, 28.33s/it] 5%|▌ | 255/5000 [1:59:57<36:56:09, 28.02s/it] 5%|▌ | 256/5000 [2:00:26<37:17:02, 28.29s/it] 5%|▌ | 257/5000 [2:00:56<37:42:29, 28.62s/it] 5%|▌ | 258/5000 [2:01:22<36:40:47, 27.85s/it] 5%|▌ | 259/5000 [2:01:50<36:50:29, 27.97s/it] 5%|▌ | 260/5000 [2:02:19<37:11:52, 28.25s/it] 5%|▌ | 261/5000 [2:02:46<36:45:24, 27.92s/it] 5%|▌ | 262/5000 [2:03:15<37:08:28, 28.22s/it] 5%|▌ | 263/5000 [2:03:43<36:55:19, 28.06s/it] 5%|▌ | 264/5000 [2:04:11<36:57:37, 28.09s/it] 5%|▌ | 265/5000 [2:04:38<36:37:24, 27.84s/it] 5%|▌ | 266/5000 [2:05:09<38:02:09, 28.92s/it] 5%|▌ | 267/5000 [2:05:38<37:58:42, 28.89s/it] 5%|▌ | 268/5000 [2:06:06<37:22:13, 28.43s/it] 5%|▌ | 269/5000 [2:06:33<36:50:00, 28.03s/it] 5%|▌ | 270/5000 [2:07:02<37:30:20, 28.55s/it] 5%|▌ | 271/5000 [2:07:29<36:42:57, 27.95s/it] 5%|▌ | 272/5000 [2:07:56<36:14:44, 27.60s/it] 5%|▌ | 273/5000 [2:08:25<37:00:39, 28.19s/it] 5%|▌ | 274/5000 [2:08:53<36:42:42, 27.97s/it] 6%|▌ | 275/5000 [2:09:20<36:22:53, 27.72s/it] 6%|▌ | 275/5000 [2:09:20<36:22:53, 27.72s/it] 6%|▌ | 276/5000 [2:09:50<37:23:24, 28.49s/it] 6%|▌ | 277/5000 [2:10:18<36:54:46, 28.14s/it] 6%|▌ | 278/5000 [2:10:46<37:06:12, 28.29s/it] 6%|▌ | 279/5000 [2:11:15<37:16:37, 28.43s/it] 6%|▌ | 280/5000 [2:11:43<37:06:44, 28.31s/it] 6%|▌ | 281/5000 [2:12:10<36:43:23, 28.02s/it] 6%|▌ | 282/5000 [2:12:39<36:56:56, 28.19s/it] 6%|▌ | 283/5000 [2:13:07<37:01:41, 28.26s/it] 6%|▌ | 284/5000 [2:13:33<36:08:17, 27.59s/it] 6%|▌ | 285/5000 [2:14:01<36:14:21, 27.67s/it] 6%|▌ | 286/5000 [2:14:30<36:32:41, 27.91s/it] 6%|▌ | 287/5000 [2:14:57<36:20:12, 27.76s/it] 6%|▌ | 288/5000 [2:15:28<37:40:15, 28.78s/it] 6%|▌ | 289/5000 [2:15:57<37:40:20, 28.79s/it] 6%|▌ | 290/5000 [2:16:24<37:05:20, 28.35s/it] 6%|▌ | 291/5000 [2:16:52<36:35:38, 27.98s/it] 6%|▌ | 292/5000 [2:17:21<37:08:29, 28.40s/it] 6%|▌ | 293/5000 [2:17:48<36:35:56, 27.99s/it] 6%|▌ | 294/5000 [2:18:15<36:15:07, 27.73s/it] 6%|▌ | 295/5000 [2:18:45<37:01:27, 28.33s/it] 6%|▌ | 296/5000 [2:19:12<36:38:26, 28.04s/it] 6%|▌ | 297/5000 [2:19:39<36:10:13, 27.69s/it] 6%|▌ | 298/5000 [2:20:09<37:13:08, 28.50s/it] 6%|▌ | 299/5000 [2:20:36<36:26:30, 27.91s/it] 6%|▌ | 300/5000 [2:21:03<36:04:12, 27.63s/it] 6%|▌ | 300/5000 [2:21:03<36:04:12, 27.63s/it] 6%|▌ | 301/5000 [2:21:32<36:29:21, 27.96s/it] 6%|▌ | 302/5000 [2:22:01<36:54:28, 28.28s/it] 6%|▌ | 303/5000 [2:22:28<36:31:45, 28.00s/it] 6%|▌ | 304/5000 [2:22:57<36:51:38, 28.26s/it] 6%|▌ | 305/5000 [2:23:24<36:23:09, 27.90s/it] 6%|▌ | 306/5000 [2:23:51<36:07:02, 27.70s/it] 6%|▌ | 307/5000 [2:24:20<36:39:50, 28.12s/it] 6%|▌ | 308/5000 [2:24:49<36:59:57, 28.39s/it] 6%|▌ | 309/5000 [2:25:17<36:34:23, 28.07s/it] 6%|▌ | 310/5000 [2:25:44<36:21:42, 27.91s/it] 6%|▌ | 311/5000 [2:26:12<36:30:16, 28.03s/it] 6%|▌ | 312/5000 [2:26:40<36:08:38, 27.76s/it] 6%|▋ | 313/5000 [2:27:10<37:11:11, 28.56s/it] 6%|▋ | 314/5000 [2:27:37<36:34:51, 28.10s/it] 6%|▋ | 315/5000 [2:28:04<36:11:05, 27.80s/it] 6%|▋ | 316/5000 [2:28:33<36:35:48, 28.13s/it] 6%|▋ | 317/5000 [2:29:00<36:12:26, 27.83s/it] 6%|▋ | 318/5000 [2:29:27<35:56:52, 27.64s/it] 6%|▋ | 319/5000 [2:29:56<36:27:25, 28.04s/it] 6%|▋ | 320/5000 [2:30:24<36:15:39, 27.89s/it] 6%|▋ | 321/5000 [2:30:51<35:57:36, 27.67s/it] 6%|▋ | 322/5000 [2:31:20<36:38:12, 28.19s/it] 6%|▋ | 323/5000 [2:31:43<34:18:17, 26.41s/it] 6%|▋ | 324/5000 [2:31:54<28:14:37, 21.74s/it] 6%|▋ | 325/5000 [2:32:04<23:59:08, 18.47s/it] 6%|▋ | 325/5000 [2:32:04<23:59:08, 18.47s/it] 7%|▋ | 326/5000 [2:32:15<21:01:36, 16.20s/it] 7%|▋ | 327/5000 [2:32:23<17:43:56, 13.66s/it]{'loss': 0.3592, 'learning_rate': 3.46e-06, 'epoch': 1.0} -{'loss': 0.3448, 'learning_rate': 3.96e-06, 'epoch': 1.01} -{'loss': 0.3673, 'learning_rate': 4.4600000000000005e-06, 'epoch': 1.01} -{'loss': 0.273, 'learning_rate': 4.960000000000001e-06, 'epoch': 1.02} -{'loss': 0.3088, 'learning_rate': 5.460000000000001e-06, 'epoch': 1.02} -{'loss': 0.302, 'learning_rate': 5.9600000000000005e-06, 'epoch': 1.03} -{'loss': 0.2583, 'learning_rate': 6.460000000000001e-06, 'epoch': 1.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:01, 1.09s/it] - Reading metadata...: 15098it [00:01, 17551.49it/s] - Reading metadata...: 23979it [00:02, 8389.85it/s]  Reading metadata...: 28043it [00:02, 9574.58it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:03, 3.94s/it] Reading metadata...: 10438it [00:04, 2601.71it/s] - 7%|▋ | 328/5000 [2:34:24<59:27:28, 45.82s/it] 7%|▋ | 329/5000 [2:34:54<53:18:07, 41.08s/it] 7%|▋ | 330/5000 [2:35:21<47:58:08, 36.98s/it] 7%|▋ | 331/5000 [2:35:51<45:08:09, 34.80s/it] 7%|▋ | 332/5000 [2:36:21<43:09:15, 33.28s/it] 7%|▋ | 333/5000 [2:36:51<41:49:05, 32.26s/it] 7%|▋ | 334/5000 [2:37:18<39:53:29, 30.78s/it] 7%|▋ | 335/5000 [2:37:49<39:56:07, 30.82s/it] 7%|▋ | 336/5000 [2:38:19<39:47:55, 30.72s/it] 7%|▋ | 337/5000 [2:38:49<39:19:14, 30.36s/it] 7%|▋ | 338/5000 [2:39:16<38:05:12, 29.41s/it] 7%|▋ | 339/5000 [2:39:46<38:06:08, 29.43s/it] 7%|▋ | 340/5000 [2:40:23<41:17:39, 31.90s/it] 7%|▋ | 341/5000 [2:40:53<40:16:40, 31.12s/it] 7%|▋ | 342/5000 [2:41:20<38:45:32, 29.96s/it] 7%|▋ | 343/5000 [2:41:49<38:35:57, 29.84s/it] 7%|▋ | 344/5000 [2:42:19<38:26:12, 29.72s/it] 7%|▋ | 345/5000 [2:42:46<37:37:18, 29.10s/it] 7%|▋ | 346/5000 [2:43:25<41:28:39, 32.08s/it] 7%|▋ | 347/5000 [2:43:53<39:32:15, 30.59s/it] 7%|▋ | 348/5000 [2:44:20<38:24:11, 29.72s/it] 7%|▋ | 349/5000 [2:44:50<38:33:23, 29.84s/it] 7%|▋ | 350/5000 [2:45:20<38:18:16, 29.66s/it] 7%|▋ | 350/5000 [2:45:20<38:18:16, 29.66s/it] 7%|▋ | 351/5000 [2:45:47<37:25:43, 28.98s/it] 7%|▋ | 352/5000 [2:46:24<40:39:26, 31.49s/it] 7%|▋ | 353/5000 [2:46:52<39:00:37, 30.22s/it] 7%|▋ | 354/5000 [2:47:19<37:50:13, 29.32s/it] 7%|▋ | 355/5000 [2:47:50<38:39:55, 29.97s/it] 7%|▋ | 356/5000 [2:48:18<37:44:03, 29.25s/it] 7%|▋ | 357/5000 [2:48:45<36:53:44, 28.61s/it] 7%|▋ | 358/5000 [2:49:16<37:57:20, 29.44s/it] 7%|▋ | 359/5000 [2:49:44<37:07:42, 28.80s/it] 7%|▋ | 360/5000 [2:50:11<36:34:52, 28.38s/it] 7%|▋ | 361/5000 [2:50:41<37:16:38, 28.93s/it] 7%|▋ | 362/5000 [2:51:08<36:25:25, 28.27s/it] 7%|▋ | 363/5000 [2:51:35<36:03:10, 27.99s/it] 7%|▋ | 364/5000 [2:52:08<37:57:49, 29.48s/it] 7%|▋ | 365/5000 [2:52:36<37:09:38, 28.86s/it] 7%|▋ | 366/5000 [2:53:03<36:26:23, 28.31s/it] 7%|▋ | 367/5000 [2:53:33<37:20:10, 29.01s/it] 7%|▋ | 368/5000 [2:54:00<36:21:56, 28.26s/it] 7%|▋ | 369/5000 [2:54:29<36:32:11, 28.40s/it] 7%|▋ | 370/5000 [2:54:58<36:49:06, 28.63s/it] 7%|▋ | 371/5000 [2:55:25<36:14:47, 28.19s/it] 7%|▋ | 372/5000 [2:55:56<37:19:36, 29.04s/it] 7%|▋ | 373/5000 [2:56:23<36:34:38, 28.46s/it] 7%|▋ | 374/5000 [2:56:51<36:29:03, 28.39s/it] 8%|▊ | 375/5000 [2:57:26<38:44:36, 30.16s/it] 8%|▊ | 375/5000 [2:57:26<38:44:36, 30.16s/it] 8%|▊ | 376/5000 [2:57:53<37:34:56, 29.26s/it] 8%|▊ | 377/5000 [2:58:23<37:52:08, 29.49s/it] 8%|▊ | 378/5000 [2:58:53<37:59:17, 29.59s/it] 8%|▊ | 379/5000 [2:59:20<37:09:54, 28.95s/it] 8%|▊ | 380/5000 [2:59:52<38:14:13, 29.80s/it] 8%|▊ | 381/5000 [3:00:19<37:18:02, 29.07s/it] 8%|▊ | 382/5000 [3:00:46<36:33:53, 28.50s/it] 8%|▊ | 383/5000 [3:01:19<38:02:05, 29.66s/it] 8%|▊ | 384/5000 [3:01:46<37:05:06, 28.92s/it] 8%|▊ | 385/5000 [3:02:13<36:29:52, 28.47s/it] 8%|▊ | 386/5000 [3:02:44<37:20:51, 29.14s/it] 8%|▊ | 387/5000 [3:03:11<36:28:43, 28.47s/it] 8%|▊ | 388/5000 [3:03:37<35:26:14, 27.66s/it] 8%|▊ | 389/5000 [3:04:08<36:38:24, 28.61s/it] 8%|▊ | 390/5000 [3:04:35<36:09:31, 28.24s/it] 8%|▊ | 391/5000 [3:05:02<35:46:46, 27.95s/it] 8%|▊ | 392/5000 [3:05:32<36:24:56, 28.45s/it] 8%|▊ | 393/5000 [3:05:59<35:54:14, 28.06s/it] 8%|▊ | 394/5000 [3:06:29<36:30:25, 28.53s/it] 8%|▊ | 395/5000 [3:07:02<38:23:21, 30.01s/it] 8%|▊ | 396/5000 [3:07:29<37:17:38, 29.16s/it] 8%|▊ | 397/5000 [3:07:59<37:24:48, 29.26s/it] 8%|▊ | 398/5000 [3:08:26<36:38:14, 28.66s/it] 8%|▊ | 399/5000 [3:08:58<37:48:56, 29.59s/it] 8%|▊ | 400/5000 [3:09:27<37:45:36, 29.55s/it] 8%|▊ | 400/5000 [3:09:27<37:45:36, 29.55s/it] 8%|▊ | 401/5000 [3:09:54<36:51:22, 28.85s/it] 8%|▊ | 402/5000 [3:10:24<37:14:45, 29.16s/it] 8%|▊ | 403/5000 [3:10:55<37:40:44, 29.51s/it] 8%|▊ | 404/5000 [3:11:22<36:45:44, 28.80s/it] 8%|▊ | 405/5000 [3:11:51<37:01:17, 29.00s/it] 8%|▊ | 406/5000 [3:12:26<39:06:48, 30.65s/it] 8%|▊ | 407/5000 [3:12:53<37:47:58, 29.63s/it] 8%|▊ | 408/5000 [3:13:22<37:42:58, 29.57s/it] 8%|▊ | 409/5000 [3:13:52<37:40:01, 29.54s/it] 8%|▊ | 410/5000 [3:14:19<36:46:57, 28.85s/it] 8%|▊ | 411/5000 [3:14:52<38:10:48, 29.95s/it] 8%|▊ | 412/5000 [3:15:20<37:36:03, 29.50s/it] 8%|▊ | 413/5000 [3:15:50<37:35:51, 29.51s/it] 8%|▊ | 414/5000 [3:16:16<36:32:40, 28.69s/it] 8%|▊ | 415/5000 [3:16:46<36:43:34, 28.84s/it] 8%|▊ | 416/5000 [3:17:15<37:01:20, 29.08s/it] 8%|▊ | 417/5000 [3:17:42<36:02:01, 28.30s/it] 8%|▊ | 418/5000 [3:18:11<36:23:04, 28.59s/it] 8%|▊ | 419/5000 [3:18:40<36:35:37, 28.76s/it] 8%|▊ | 420/5000 [3:19:07<35:55:13, 28.23s/it] 8%|▊ | 421/5000 [3:19:37<36:31:35, 28.72s/it] 8%|▊ | 422/5000 [3:20:06<36:44:24, 28.89s/it] 8%|▊ | 423/5000 [3:20:34<36:09:13, 28.44s/it] 8%|▊ | 424/5000 [3:21:03<36:39:46, 28.84s/it] 8%|▊ | 425/5000 [3:21:33<36:52:00, 29.01s/it] 8%|▊ | 425/5000 [3:21:33<36:52:00, 29.01s/it] 9%|▊ | 426/5000 [3:22:00<36:05:51, 28.41s/it] 9%|▊ | 427/5000 [3:22:30<36:43:01, 28.90s/it] 9%|▊ | 428/5000 [3:22:59<36:49:08, 28.99s/it] 9%|▊ | 429/5000 [3:23:26<36:07:18, 28.45s/it] 9%|▊ | 430/5000 [3:23:58<37:29:11, 29.53s/it] 9%|▊ | 431/5000 [3:24:26<36:36:32, 28.84s/it] 9%|▊ | 432/5000 [3:24:53<35:57:34, 28.34s/it] 9%|▊ | 433/5000 [3:25:25<37:21:31, 29.45s/it] 9%|▊ | 434/5000 [3:25:52<36:34:29, 28.84s/it] 9%|▊ | 435/5000 [3:26:19<35:56:08, 28.34s/it] 9%|▊ | 436/5000 [3:26:50<36:42:42, 28.96s/it] 9%|▊ | 437/5000 [3:27:20<37:05:57, 29.27s/it] 9%|▉ | 438/5000 [3:27:47<36:12:53, 28.58s/it] 9%|▉ | 439/5000 [3:28:17<36:41:46, 28.96s/it] 9%|▉ | 440/5000 [3:28:46<36:55:46, 29.15s/it] 9%|▉ | 441/5000 [3:29:13<36:09:48, 28.56s/it] 9%|▉ | 442/5000 [3:29:43<36:28:07, 28.80s/it] 9%|▉ | 443/5000 [3:30:12<36:43:21, 29.01s/it] 9%|▉ | 444/5000 [3:30:42<36:55:59, 29.18s/it] 9%|▉ | 445/5000 [3:31:09<36:02:45, 28.49s/it] 9%|▉ | 446/5000 [3:31:40<37:05:25, 29.32s/it] 9%|▉ | 447/5000 [3:32:07<36:13:45, 28.65s/it] 9%|▉ | 448/5000 [3:32:34<35:38:07, 28.18s/it] 9%|▉ | 449/5000 [3:33:05<36:30:32, 28.88s/it] 9%|▉ | 450/5000 [3:33:32<35:54:20, 28.41s/it] 9%|▉ | 450/5000 [3:33:32<35:54:20, 28.41s/it] 9%|▉ | 451/5000 [3:33:59<35:22:36, 28.00s/it] 9%|▉ | 452/5000 [3:34:31<36:52:54, 29.19s/it] 9%|▉ | 453/5000 [3:34:58<36:06:32, 28.59s/it] 9%|▉ | 454/5000 [3:35:25<35:30:53, 28.12s/it] 9%|▉ | 455/5000 [3:35:57<37:00:03, 29.31s/it] 9%|▉ | 456/5000 [3:36:24<36:06:07, 28.60s/it] 9%|▉ | 457/5000 [3:36:51<35:17:38, 27.97s/it] 9%|▉ | 458/5000 [3:37:17<34:37:21, 27.44s/it] 9%|▉ | 459/5000 [3:37:49<36:31:38, 28.96s/it] 9%|▉ | 460/5000 [3:38:17<35:49:57, 28.41s/it] 9%|▉ | 461/5000 [3:38:44<35:16:34, 27.98s/it] 9%|▉ | 462/5000 [3:39:14<36:11:48, 28.71s/it] 9%|▉ | 463/5000 [3:39:41<35:42:23, 28.33s/it] 9%|▉ | 464/5000 [3:40:08<35:02:57, 27.82s/it] 9%|▉ | 465/5000 [3:40:40<36:28:00, 28.95s/it] 9%|▉ | 466/5000 [3:41:07<35:48:57, 28.44s/it] 9%|▉ | 467/5000 [3:41:34<35:21:06, 28.08s/it] 9%|▉ | 468/5000 [3:42:06<36:39:29, 29.12s/it] 9%|▉ | 469/5000 [3:42:33<36:00:39, 28.61s/it] 9%|▉ | 470/5000 [3:43:00<35:25:08, 28.15s/it] 9%|▉ | 471/5000 [3:43:32<36:57:59, 29.38s/it] 9%|▉ | 472/5000 [3:43:59<36:04:29, 28.68s/it] 9%|▉ | 473/5000 [3:44:27<35:39:16, 28.35s/it] 9%|▉ | 474/5000 [3:44:57<36:23:20, 28.94s/it] 10%|▉ | 475/5000 [3:45:25<35:46:58, 28.47s/it] 10%|▉ | 475/5000 [3:45:25<35:46:58, 28.47s/it] 10%|▉ | 476/5000 [3:45:52<35:21:38, 28.14s/it] 10%|▉ | 477/5000 [3:46:28<38:13:45, 30.43s/it] 10%|▉ | 478/5000 [3:46:55<37:06:11, 29.54s/it] 10%|▉ | 479/5000 [3:47:21<35:39:21, 28.39s/it] 10%|▉ | 480/5000 [3:47:49<35:32:51, 28.31s/it] 10%|▉ | 481/5000 [3:48:16<34:57:24, 27.85s/it] 10%|▉ | 482/5000 [3:48:43<34:46:50, 27.71s/it] 10%|▉ | 483/5000 [3:49:16<36:38:31, 29.20s/it] 10%|▉ | 484/5000 [3:49:43<35:54:50, 28.63s/it] 10%|▉ | 485/5000 [3:50:10<35:19:14, 28.16s/it] 10%|▉ | 486/5000 [3:50:43<36:49:28, 29.37s/it] 10%|▉ | 487/5000 [3:50:57<31:01:29, 24.75s/it] 10%|▉ | 488/5000 [3:51:07<25:45:30, 20.55s/it] 10%|▉ | 489/5000 [3:51:18<22:05:59, 17.64s/it] 10%|▉ | 490/5000 [3:51:29<19:35:34, 15.64s/it]{'loss': 0.2545, 'learning_rate': 6.96e-06, 'epoch': 2.0} -{'loss': 0.2599, 'learning_rate': 7.4600000000000006e-06, 'epoch': 2.01} -{'loss': 0.2464, 'learning_rate': 7.960000000000002e-06, 'epoch': 2.01} -{'loss': 0.1981, 'learning_rate': 8.46e-06, 'epoch': 2.02} -{'loss': 0.2316, 'learning_rate': 8.96e-06, 'epoch': 2.02} -{'loss': 0.2077, 'learning_rate': 9.460000000000001e-06, 'epoch': 2.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:02, 2.22s/it] - Reading metadata...: 15016it [00:02, 9088.72it/s] - Reading metadata...: 23848it [00:02, 13351.04it/s] Reading metadata...: 28043it [00:02, 10627.78it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:01, 1.89s/it] Reading metadata...: 10438it [00:01, 5308.23it/s] - 10%|▉ | 491/5000 [3:53:06<49:59:47, 39.92s/it] 10%|▉ | 492/5000 [3:53:34<45:28:45, 36.32s/it] 10%|▉ | 493/5000 [3:54:01<42:16:20, 33.77s/it] 10%|▉ | 494/5000 [3:54:30<40:29:47, 32.35s/it] 10%|▉ | 495/5000 [3:54:58<38:41:25, 30.92s/it] 10%|▉ | 496/5000 [3:55:26<37:40:40, 30.12s/it] 10%|▉ | 497/5000 [3:55:57<37:50:39, 30.26s/it] 10%|▉ | 498/5000 [3:56:25<36:55:39, 29.53s/it] 10%|▉ | 499/5000 [3:56:53<36:39:25, 29.32s/it] 10%|█ | 500/5000 [3:57:20<35:45:29, 28.61s/it] 10%|█ | 500/5000 [3:57:20<35:45:29, 28.61s/it] 10%|█ | 501/5000 [3:57:50<36:10:29, 28.95s/it] 10%|█ | 502/5000 [3:58:17<35:22:32, 28.31s/it] 10%|█ | 503/5000 [3:58:44<34:59:39, 28.01s/it] 10%|█ | 504/5000 [3:59:13<35:18:43, 28.27s/it] 10%|█ | 505/5000 [3:59:41<35:07:06, 28.13s/it] 10%|█ | 506/5000 [4:00:09<35:10:42, 28.18s/it] 10%|█ | 507/5000 [4:00:37<35:09:58, 28.18s/it] 10%|█ | 508/5000 [4:01:05<34:52:29, 27.95s/it] 10%|█ | 509/5000 [4:01:33<34:57:53, 28.03s/it] 10%|█ | 510/5000 [4:02:01<34:58:48, 28.05s/it] 10%|█ | 511/5000 [4:02:28<34:36:24, 27.75s/it] 10%|█ | 512/5000 [4:02:57<34:56:20, 28.03s/it] 10%|█ | 513/5000 [4:03:25<34:47:39, 27.92s/it] 10%|█ | 514/5000 [4:03:52<34:30:48, 27.70s/it] 10%|█ | 515/5000 [4:04:19<34:25:26, 27.63s/it] 10%|█ | 516/5000 [4:04:47<34:17:59, 27.54s/it] 10%|█ | 517/5000 [4:05:14<34:12:29, 27.47s/it] 10%|█ | 518/5000 [4:05:41<34:10:29, 27.45s/it] 10%|█ | 519/5000 [4:06:09<34:24:54, 27.65s/it] 10%|█ | 520/5000 [4:06:36<34:07:13, 27.42s/it] 10%|█ | 521/5000 [4:07:08<35:46:29, 28.75s/it] 10%|█ | 522/5000 [4:07:36<35:18:23, 28.38s/it] 10%|█ | 523/5000 [4:08:03<34:47:17, 27.97s/it] 10%|█ | 524/5000 [4:08:32<35:23:31, 28.47s/it] 10%|█ | 525/5000 [4:09:00<34:54:55, 28.09s/it] 10%|█ | 525/5000 [4:09:00<34:54:55, 28.09s/it] 11%|█ | 526/5000 [4:09:25<33:59:55, 27.36s/it] 11%|█ | 527/5000 [4:09:51<33:27:38, 26.93s/it] 11%|█ | 528/5000 [4:10:19<33:45:53, 27.18s/it] 11%|█ | 529/5000 [4:10:46<33:44:51, 27.17s/it] 11%|█ | 530/5000 [4:11:15<34:14:15, 27.57s/it] 11%|█ | 531/5000 [4:11:42<34:10:56, 27.54s/it] 11%|█ | 532/5000 [4:12:09<34:01:11, 27.41s/it] 11%|█ | 533/5000 [4:12:38<34:34:56, 27.87s/it] 11%|█ | 534/5000 [4:13:06<34:35:00, 27.88s/it] 11%|█ | 535/5000 [4:13:33<34:18:03, 27.66s/it] 11%|█ | 536/5000 [4:14:01<34:30:46, 27.83s/it] 11%|█ | 537/5000 [4:14:29<34:28:24, 27.81s/it] 11%|█ | 538/5000 [4:14:57<34:24:07, 27.76s/it] 11%|█ | 539/5000 [4:15:24<34:11:36, 27.59s/it] 11%|█ | 540/5000 [4:15:51<34:07:40, 27.55s/it] 11%|█ | 541/5000 [4:16:20<34:33:30, 27.90s/it] 11%|█ | 542/5000 [4:16:47<34:20:33, 27.73s/it] 11%|█ | 543/5000 [4:17:15<34:24:08, 27.79s/it] 11%|█ | 544/5000 [4:17:43<34:25:59, 27.82s/it] 11%|█ | 545/5000 [4:18:10<34:09:36, 27.60s/it] 11%|█ | 546/5000 [4:18:38<34:19:04, 27.74s/it] 11%|█ | 547/5000 [4:19:06<34:21:15, 27.77s/it] 11%|█ | 548/5000 [4:19:34<34:13:57, 27.68s/it] 11%|█ | 549/5000 [4:20:03<34:45:28, 28.11s/it] 11%|█ | 550/5000 [4:20:30<34:27:46, 27.88s/it] 11%|█ | 550/5000 [4:20:30<34:27:46, 27.88s/it] 11%|█ | 551/5000 [4:20:57<34:11:41, 27.67s/it] 11%|█ | 552/5000 [4:21:26<34:33:00, 27.96s/it] 11%|█ | 553/5000 [4:21:53<34:17:24, 27.76s/it] 11%|█ | 554/5000 [4:22:21<34:08:34, 27.65s/it] 11%|█ | 555/5000 [4:22:49<34:26:50, 27.90s/it] 11%|█ | 556/5000 [4:23:17<34:28:07, 27.92s/it] 11%|█ | 557/5000 [4:23:44<34:10:44, 27.69s/it] 11%|█ | 558/5000 [4:24:12<34:00:19, 27.56s/it] 11%|█ | 559/5000 [4:24:40<34:23:16, 27.88s/it] 11%|█ | 560/5000 [4:25:08<34:11:49, 27.73s/it] 11%|█ | 561/5000 [4:25:36<34:17:53, 27.82s/it] 11%|█ | 562/5000 [4:26:04<34:35:00, 28.05s/it] 11%|█▏ | 563/5000 [4:26:31<33:58:17, 27.56s/it] 11%|█▏ | 564/5000 [4:26:58<34:00:51, 27.60s/it] 11%|█▏ | 565/5000 [4:27:26<34:07:16, 27.70s/it] 11%|█▏ | 566/5000 [4:27:54<34:20:15, 27.88s/it] 11%|█▏ | 567/5000 [4:28:22<34:03:53, 27.66s/it] 11%|█▏ | 568/5000 [4:28:50<34:09:43, 27.75s/it] 11%|█▏ | 569/5000 [4:29:17<34:10:34, 27.77s/it] 11%|█▏ | 570/5000 [4:29:45<33:56:18, 27.58s/it] 11%|█▏ | 571/5000 [4:30:13<34:10:09, 27.77s/it] 11%|█▏ | 572/5000 [4:30:41<34:11:42, 27.80s/it] 11%|█▏ | 573/5000 [4:31:08<33:58:26, 27.63s/it] 11%|█▏ | 574/5000 [4:31:36<34:02:43, 27.69s/it] 12%|█▏ | 575/5000 [4:32:04<34:05:04, 27.73s/it] 12%|█▏ | 575/5000 [4:32:04<34:05:04, 27.73s/it] 12%|█▏ | 576/5000 [4:32:31<33:53:20, 27.58s/it] 12%|█▏ | 577/5000 [4:32:58<33:43:16, 27.45s/it] 12%|█▏ | 578/5000 [4:33:25<33:25:33, 27.21s/it] 12%|█▏ | 579/5000 [4:33:52<33:22:58, 27.18s/it] 12%|█▏ | 580/5000 [4:34:19<33:30:08, 27.29s/it] 12%|█▏ | 581/5000 [4:34:47<33:40:18, 27.43s/it] 12%|█▏ | 582/5000 [4:35:14<33:32:07, 27.33s/it] 12%|█▏ | 583/5000 [4:35:42<33:55:35, 27.65s/it] 12%|█▏ | 584/5000 [4:36:10<33:48:17, 27.56s/it] 12%|█▏ | 585/5000 [4:36:37<33:41:31, 27.47s/it] 12%|█▏ | 586/5000 [4:37:05<33:56:36, 27.68s/it] 12%|█▏ | 587/5000 [4:37:33<33:58:42, 27.72s/it] 12%|█▏ | 588/5000 [4:38:00<33:51:26, 27.63s/it] 12%|█▏ | 589/5000 [4:38:29<34:04:58, 27.82s/it] 12%|█▏ | 590/5000 [4:38:56<34:03:34, 27.80s/it] 12%|█▏ | 591/5000 [4:39:24<33:57:32, 27.73s/it] 12%|█▏ | 592/5000 [4:39:51<33:42:24, 27.53s/it] 12%|█▏ | 593/5000 [4:40:19<33:58:36, 27.76s/it] 12%|█▏ | 594/5000 [4:40:47<34:02:31, 27.81s/it] 12%|█▏ | 595/5000 [4:41:15<33:51:44, 27.67s/it] 12%|█▏ | 596/5000 [4:41:42<33:39:13, 27.51s/it] 12%|█▏ | 597/5000 [4:42:10<33:58:56, 27.78s/it] 12%|█▏ | 598/5000 [4:42:37<33:42:46, 27.57s/it] 12%|█▏ | 599/5000 [4:43:04<33:30:34, 27.41s/it] 12%|█▏ | 600/5000 [4:43:33<34:06:44, 27.91s/it] 12%|█▏ | 600/5000 [4:43:33<34:06:44, 27.91s/it] 12%|█▏ | 601/5000 [4:44:01<33:53:07, 27.73s/it] 12%|█▏ | 602/5000 [4:44:28<33:41:18, 27.58s/it] 12%|█▏ | 603/5000 [4:44:59<35:04:30, 28.72s/it] 12%|█▏ | 604/5000 [4:45:27<34:38:09, 28.36s/it] 12%|█▏ | 605/5000 [4:45:55<34:34:59, 28.33s/it] 12%|█▏ | 606/5000 [4:46:23<34:20:01, 28.13s/it] 12%|█▏ | 607/5000 [4:46:51<34:20:45, 28.15s/it] 12%|█▏ | 608/5000 [4:47:18<34:01:48, 27.89s/it] 12%|█▏ | 609/5000 [4:47:46<34:00:57, 27.89s/it] 12%|█▏ | 610/5000 [4:48:14<34:06:23, 27.97s/it] 12%|█▏ | 611/5000 [4:48:41<33:49:16, 27.74s/it] 12%|█▏ | 612/5000 [4:49:10<34:06:46, 27.99s/it] 12%|█▏ | 613/5000 [4:49:38<34:00:04, 27.90s/it] 12%|█▏ | 614/5000 [4:50:05<33:43:00, 27.67s/it] 12%|█▏ | 615/5000 [4:50:32<33:37:13, 27.60s/it] 12%|█▏ | 616/5000 [4:51:00<33:39:36, 27.64s/it] 12%|█▏ | 617/5000 [4:51:27<33:30:54, 27.53s/it] 12%|█▏ | 618/5000 [4:51:55<33:23:37, 27.43s/it] 12%|█▏ | 619/5000 [4:52:23<33:51:14, 27.82s/it] 12%|█▏ | 620/5000 [4:52:50<33:32:09, 27.56s/it] 12%|█▏ | 621/5000 [4:53:17<33:20:34, 27.41s/it] 12%|█▏ | 622/5000 [4:53:45<33:35:22, 27.62s/it] 12%|█▏ | 623/5000 [4:54:13<33:30:25, 27.56s/it] 12%|█▏ | 624/5000 [4:54:40<33:11:34, 27.31s/it] 12%|█▎ | 625/5000 [4:55:08<33:43:52, 27.76s/it] 12%|█▎ | 625/5000 [4:55:08<33:43:52, 27.76s/it] 13%|█▎ | 626/5000 [4:55:36<33:33:46, 27.62s/it] 13%|█▎ | 627/5000 [4:56:03<33:23:47, 27.49s/it] 13%|█▎ | 628/5000 [4:56:32<33:50:09, 27.86s/it] 13%|█▎ | 629/5000 [4:57:00<33:54:49, 27.93s/it] 13%|█▎ | 630/5000 [4:57:27<33:38:47, 27.72s/it] 13%|█▎ | 631/5000 [4:57:55<33:41:28, 27.76s/it] 13%|█▎ | 632/5000 [4:58:22<33:38:57, 27.73s/it] 13%|█▎ | 633/5000 [4:58:49<33:19:08, 27.47s/it] 13%|█▎ | 634/5000 [4:59:17<33:30:40, 27.63s/it] 13%|█▎ | 635/5000 [4:59:44<33:21:27, 27.51s/it] 13%|█▎ | 636/5000 [5:00:12<33:16:18, 27.45s/it] 13%|█▎ | 637/5000 [5:00:40<33:31:57, 27.67s/it] 13%|█▎ | 638/5000 [5:01:08<33:39:37, 27.78s/it] 13%|█▎ | 639/5000 [5:01:35<33:26:38, 27.61s/it] 13%|█▎ | 640/5000 [5:02:04<34:00:57, 28.09s/it] 13%|█▎ | 641/5000 [5:02:32<33:44:56, 27.87s/it] 13%|█▎ | 642/5000 [5:02:59<33:29:59, 27.67s/it] 13%|█▎ | 643/5000 [5:03:28<33:47:23, 27.92s/it] 13%|█▎ | 644/5000 [5:03:54<33:15:04, 27.48s/it] 13%|█▎ | 645/5000 [5:04:21<33:01:41, 27.30s/it] 13%|█▎ | 646/5000 [5:04:48<32:48:05, 27.12s/it] 13%|█▎ | 647/5000 [5:05:16<33:09:03, 27.42s/it] 13%|█▎ | 648/5000 [5:05:43<32:59:56, 27.30s/it] 13%|█▎ | 649/5000 [5:06:12<33:44:52, 27.92s/it] 13%|█▎ | 650/5000 [5:06:34<31:39:01, 26.19s/it] 13%|█▎ | 650/5000 [5:06:34<31:39:01, 26.19s/it] 13%|█▎ | 651/5000 [5:06:45<26:03:56, 21.58s/it] 13%|█▎ | 652/5000 [5:06:56<22:15:49, 18.43s/it] 13%|█▎ | 653/5000 [5:07:07<19:32:01, 16.18s/it] 13%|█▎ | 654/5000 [5:07:15<16:27:10, 13.63s/it]{'loss': 0.1836, 'learning_rate': 9.960000000000001e-06, 'epoch': 3.0} -{'loss': 0.2001, 'learning_rate': 9.94888888888889e-06, 'epoch': 3.01} -{'loss': 0.1875, 'learning_rate': 9.893333333333334e-06, 'epoch': 3.01} -{'loss': 0.15, 'learning_rate': 9.837777777777778e-06, 'epoch': 3.02} -{'loss': 0.1534, 'learning_rate': 9.782222222222222e-06, 'epoch': 3.02} -{'loss': 0.1565, 'learning_rate': 9.726666666666668e-06, 'epoch': 3.03} -{'loss': 0.1266, 'learning_rate': 9.671111111111112e-06, 'epoch': 3.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.40it/s] - Reading metadata...: 13887it [00:00, 35502.94it/s] - Reading metadata...: 22056it [00:00, 29691.65it/s] Reading metadata...: 28043it [00:00, 31651.18it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.34it/s] Reading metadata...: 10438it [00:00, 28332.17it/s] - 13%|█▎ | 655/5000 [5:08:52<46:55:10, 38.87s/it] 13%|█▎ | 656/5000 [5:09:21<43:01:04, 35.65s/it] 13%|█▎ | 657/5000 [5:09:48<39:53:00, 33.06s/it] 13%|█▎ | 658/5000 [5:10:16<38:12:56, 31.69s/it] 13%|█▎ | 659/5000 [5:10:45<37:11:39, 30.85s/it] 13%|█▎ | 660/5000 [5:11:13<36:08:48, 29.98s/it] 13%|█▎ | 661/5000 [5:11:40<35:07:56, 29.15s/it] 13%|█▎ | 662/5000 [5:12:08<34:35:15, 28.70s/it] 13%|█▎ | 663/5000 [5:12:36<34:21:00, 28.51s/it] 13%|█▎ | 664/5000 [5:13:04<34:13:30, 28.42s/it] 13%|█▎ | 665/5000 [5:13:31<33:46:38, 28.05s/it] 13%|█▎ | 666/5000 [5:14:00<34:02:21, 28.27s/it] 13%|█▎ | 667/5000 [5:14:28<33:49:20, 28.10s/it] 13%|█▎ | 668/5000 [5:14:56<34:02:05, 28.28s/it] 13%|█▎ | 669/5000 [5:15:24<33:41:22, 28.00s/it] 13%|█▎ | 670/5000 [5:15:52<33:34:18, 27.91s/it] 13%|█▎ | 671/5000 [5:16:20<33:35:14, 27.93s/it] 13%|█▎ | 672/5000 [5:16:47<33:18:26, 27.70s/it] 13%|█▎ | 673/5000 [5:17:17<34:06:49, 28.38s/it] 13%|█▎ | 674/5000 [5:17:44<33:41:46, 28.04s/it] 14%|█▎ | 675/5000 [5:18:11<33:22:09, 27.78s/it] 14%|█▎ | 675/5000 [5:18:11<33:22:09, 27.78s/it] 14%|█▎ | 676/5000 [5:18:39<33:28:46, 27.87s/it] 14%|█▎ | 677/5000 [5:19:06<33:03:48, 27.53s/it] 14%|█▎ | 678/5000 [5:19:32<32:31:54, 27.10s/it] 14%|█▎ | 679/5000 [5:20:00<32:46:53, 27.31s/it] 14%|█▎ | 680/5000 [5:20:26<32:28:07, 27.06s/it] 14%|█▎ | 681/5000 [5:20:53<32:23:40, 27.00s/it] 14%|█▎ | 682/5000 [5:21:21<32:45:28, 27.31s/it] 14%|█▎ | 683/5000 [5:21:48<32:40:09, 27.24s/it] 14%|█▎ | 684/5000 [5:22:16<32:41:46, 27.27s/it] 14%|█▎ | 685/5000 [5:22:44<33:11:01, 27.69s/it] 14%|█▎ | 686/5000 [5:23:12<33:07:35, 27.64s/it] 14%|█▎ | 687/5000 [5:23:39<32:59:00, 27.53s/it] 14%|█▍ | 688/5000 [5:24:08<33:19:27, 27.82s/it] 14%|█▍ | 689/5000 [5:24:34<32:52:08, 27.45s/it] 14%|█▍ | 690/5000 [5:25:02<32:50:17, 27.43s/it] 14%|█▍ | 691/5000 [5:25:29<32:47:05, 27.39s/it] 14%|█▍ | 692/5000 [5:25:55<32:30:49, 27.17s/it] 14%|█▍ | 693/5000 [5:26:22<32:24:10, 27.08s/it] 14%|█▍ | 694/5000 [5:26:50<32:34:11, 27.23s/it] 14%|█▍ | 695/5000 [5:27:17<32:33:06, 27.22s/it] 14%|█▍ | 696/5000 [5:27:45<32:48:17, 27.44s/it] 14%|█▍ | 697/5000 [5:28:13<33:02:45, 27.65s/it] 14%|█▍ | 698/5000 [5:28:40<32:49:27, 27.47s/it] 14%|█▍ | 699/5000 [5:29:08<32:58:14, 27.60s/it] 14%|█▍ | 700/5000 [5:29:36<32:52:54, 27.53s/it] 14%|█▍ | 700/5000 [5:29:36<32:52:54, 27.53s/it] 14%|█▍ | 701/5000 [5:30:03<32:59:06, 27.62s/it] 14%|█▍ | 702/5000 [5:30:31<33:01:56, 27.67s/it] 14%|█▍ | 703/5000 [5:30:58<32:42:15, 27.40s/it] 14%|█▍ | 704/5000 [5:31:27<33:14:49, 27.86s/it] 14%|█▍ | 705/5000 [5:31:55<33:10:53, 27.81s/it] 14%|█▍ | 706/5000 [5:32:22<33:01:40, 27.69s/it] 14%|█▍ | 707/5000 [5:32:51<33:27:50, 28.06s/it] 14%|█▍ | 708/5000 [5:33:18<33:11:38, 27.84s/it] 14%|█▍ | 709/5000 [5:33:45<32:58:58, 27.67s/it] 14%|█▍ | 710/5000 [5:34:14<33:20:25, 27.98s/it] 14%|█▍ | 711/5000 [5:34:41<33:03:46, 27.75s/it] 14%|█▍ | 712/5000 [5:35:09<32:58:54, 27.69s/it] 14%|█▍ | 713/5000 [5:35:38<33:29:44, 28.13s/it] 14%|█▍ | 714/5000 [5:36:05<33:12:27, 27.89s/it] 14%|█▍ | 715/5000 [5:36:33<33:01:30, 27.75s/it] 14%|█▍ | 716/5000 [5:37:05<34:30:24, 29.00s/it] 14%|█▍ | 717/5000 [5:37:32<33:45:23, 28.37s/it] 14%|█▍ | 718/5000 [5:37:59<33:22:11, 28.06s/it] 14%|█▍ | 719/5000 [5:38:29<34:12:47, 28.77s/it] 14%|█▍ | 720/5000 [5:38:57<33:39:21, 28.31s/it] 14%|█▍ | 721/5000 [5:39:25<33:32:35, 28.22s/it] 14%|█▍ | 722/5000 [5:39:53<33:33:52, 28.25s/it] 14%|█▍ | 723/5000 [5:40:20<33:12:43, 27.96s/it] 14%|█▍ | 724/5000 [5:40:48<33:17:00, 28.02s/it] 14%|█▍ | 725/5000 [5:41:16<32:59:03, 27.78s/it] 14%|█▍ | 725/5000 [5:41:16<32:59:03, 27.78s/it] 15%|█▍ | 726/5000 [5:41:43<32:57:34, 27.76s/it] 15%|█▍ | 727/5000 [5:42:11<32:46:32, 27.61s/it] 15%|█▍ | 728/5000 [5:42:38<32:38:55, 27.51s/it] 15%|█▍ | 729/5000 [5:43:06<32:51:03, 27.69s/it] 15%|█▍ | 730/5000 [5:43:34<33:03:15, 27.87s/it] 15%|█▍ | 731/5000 [5:44:02<32:55:06, 27.76s/it] 15%|█▍ | 732/5000 [5:44:30<33:04:30, 27.90s/it] 15%|█▍ | 733/5000 [5:44:58<33:12:34, 28.02s/it] 15%|█▍ | 734/5000 [5:45:26<32:58:22, 27.83s/it] 15%|█▍ | 735/5000 [5:45:54<33:00:14, 27.86s/it] 15%|█▍ | 736/5000 [5:46:21<32:58:52, 27.85s/it] 15%|█▍ | 737/5000 [5:46:49<32:46:49, 27.68s/it] 15%|█▍ | 738/5000 [5:47:16<32:45:39, 27.67s/it] 15%|█▍ | 739/5000 [5:47:45<32:58:14, 27.86s/it] 15%|█▍ | 740/5000 [5:48:12<32:53:57, 27.80s/it] 15%|█▍ | 741/5000 [5:48:40<32:41:30, 27.63s/it] 15%|█▍ | 742/5000 [5:49:13<34:39:06, 29.30s/it] 15%|█▍ | 743/5000 [5:49:42<34:44:37, 29.38s/it] 15%|█▍ | 744/5000 [5:50:09<33:50:56, 28.63s/it] 15%|█▍ | 745/5000 [5:50:38<33:44:17, 28.54s/it] 15%|█▍ | 746/5000 [5:51:06<33:31:41, 28.37s/it] 15%|█▍ | 747/5000 [5:51:32<32:53:41, 27.84s/it] 15%|█▍ | 748/5000 [5:52:00<33:01:45, 27.96s/it] 15%|█▍ | 749/5000 [5:52:28<32:45:54, 27.75s/it] 15%|█▌ | 750/5000 [5:52:55<32:38:30, 27.65s/it] 15%|█▌ | 750/5000 [5:52:55<32:38:30, 27.65s/it] 15%|█▌ | 751/5000 [5:53:23<32:35:57, 27.62s/it] 15%|█▌ | 752/5000 [5:53:51<32:57:59, 27.94s/it] 15%|█▌ | 753/5000 [5:54:19<32:43:21, 27.74s/it] 15%|█▌ | 754/5000 [5:54:47<32:54:30, 27.90s/it] 15%|█▌ | 755/5000 [5:55:15<33:06:21, 28.08s/it] 15%|█▌ | 756/5000 [5:55:43<32:51:02, 27.87s/it] 15%|█▌ | 757/5000 [5:56:11<33:07:55, 28.11s/it] 15%|█▌ | 758/5000 [5:56:39<32:52:04, 27.89s/it] 15%|█▌ | 759/5000 [5:57:06<32:39:43, 27.73s/it] 15%|█▌ | 760/5000 [5:57:35<33:04:22, 28.08s/it] 15%|█▌ | 761/5000 [5:58:02<32:47:53, 27.85s/it] 15%|█▌ | 762/5000 [5:58:30<32:35:13, 27.68s/it] 15%|█▌ | 763/5000 [5:58:57<32:38:01, 27.73s/it] 15%|█▌ | 764/5000 [5:59:26<32:49:59, 27.90s/it] 15%|█▌ | 765/5000 [5:59:53<32:36:02, 27.71s/it] 15%|█▌ | 766/5000 [6:00:21<32:48:05, 27.89s/it] 15%|█▌ | 767/5000 [6:00:49<32:45:08, 27.85s/it] 15%|█▌ | 768/5000 [6:01:17<32:36:36, 27.74s/it] 15%|█▌ | 769/5000 [6:01:45<32:40:26, 27.80s/it] 15%|█▌ | 770/5000 [6:02:13<32:48:40, 27.92s/it] 15%|█▌ | 771/5000 [6:02:41<32:46:30, 27.90s/it] 15%|█▌ | 772/5000 [6:03:08<32:28:53, 27.66s/it] 15%|█▌ | 773/5000 [6:03:36<32:52:36, 28.00s/it] 15%|█▌ | 774/5000 [6:04:04<32:33:05, 27.73s/it] 16%|█▌ | 775/5000 [6:04:31<32:25:51, 27.63s/it] 16%|█▌ | 775/5000 [6:04:31<32:25:51, 27.63s/it] 16%|█▌ | 776/5000 [6:04:58<32:20:50, 27.57s/it] 16%|█▌ | 777/5000 [6:05:25<32:09:51, 27.42s/it] 16%|█▌ | 778/5000 [6:05:53<32:08:01, 27.40s/it] 16%|█▌ | 779/5000 [6:06:26<34:05:05, 29.07s/it] 16%|█▌ | 780/5000 [6:06:53<33:26:32, 28.53s/it] 16%|█▌ | 781/5000 [6:07:21<33:04:20, 28.22s/it] 16%|█▌ | 782/5000 [6:07:49<33:15:12, 28.38s/it] 16%|█▌ | 783/5000 [6:08:16<32:46:58, 27.99s/it] 16%|█▌ | 784/5000 [6:08:44<32:28:10, 27.73s/it] 16%|█▌ | 785/5000 [6:09:11<32:19:03, 27.60s/it] 16%|█▌ | 786/5000 [6:09:40<32:53:14, 28.10s/it] 16%|█▌ | 787/5000 [6:10:07<32:31:51, 27.80s/it] 16%|█▌ | 788/5000 [6:10:34<32:07:03, 27.45s/it] 16%|█▌ | 789/5000 [6:11:02<32:30:34, 27.79s/it] 16%|█▌ | 790/5000 [6:11:30<32:23:16, 27.70s/it] 16%|█▌ | 791/5000 [6:11:57<32:15:07, 27.59s/it] 16%|█▌ | 792/5000 [6:12:26<32:45:02, 28.02s/it] 16%|█▌ | 793/5000 [6:12:54<32:33:00, 27.85s/it] 16%|█▌ | 794/5000 [6:13:20<32:04:35, 27.45s/it] 16%|█▌ | 795/5000 [6:13:48<32:20:21, 27.69s/it] 16%|█▌ | 796/5000 [6:14:16<32:08:30, 27.52s/it] 16%|█▌ | 797/5000 [6:14:42<31:54:08, 27.33s/it] 16%|█▌ | 798/5000 [6:15:11<32:25:26, 27.78s/it] 16%|█▌ | 799/5000 [6:15:38<32:07:25, 27.53s/it] 16%|█▌ | 800/5000 [6:16:05<31:52:14, 27.32s/it] 16%|█▌ | 800/5000 [6:16:05<31:52:14, 27.32s/it] 16%|█▌ | 801/5000 [6:16:35<32:43:39, 28.06s/it] 16%|█▌ | 802/5000 [6:17:01<32:07:25, 27.55s/it] 16%|█▌ | 803/5000 [6:17:29<32:04:13, 27.51s/it] 16%|█▌ | 804/5000 [6:17:58<32:39:16, 28.02s/it] 16%|█▌ | 805/5000 [6:18:25<32:30:30, 27.90s/it] 16%|█▌ | 806/5000 [6:18:53<32:15:14, 27.69s/it] 16%|█▌ | 807/5000 [6:19:20<32:07:52, 27.59s/it] 16%|█▌ | 808/5000 [6:19:47<31:59:21, 27.47s/it] 16%|█▌ | 809/5000 [6:20:14<31:49:52, 27.34s/it] 16%|█▌ | 810/5000 [6:20:42<32:03:25, 27.54s/it] 16%|█▌ | 811/5000 [6:21:10<31:57:46, 27.47s/it] 16%|█▌ | 812/5000 [6:21:37<31:55:38, 27.44s/it] 16%|█▋ | 813/5000 [6:22:05<32:09:12, 27.65s/it] 16%|█▋ | 814/5000 [6:22:19<27:24:16, 23.57s/it] 16%|█▋ | 815/5000 [6:22:30<22:57:38, 19.75s/it] 16%|█▋ | 816/5000 [6:22:41<19:50:24, 17.07s/it] 16%|█▋ | 817/5000 [6:22:52<17:40:15, 15.21s/it]{'loss': 0.1249, 'learning_rate': 9.615555555555558e-06, 'epoch': 4.0} -{'loss': 0.1291, 'learning_rate': 9.56e-06, 'epoch': 4.01} -{'loss': 0.1197, 'learning_rate': 9.504444444444446e-06, 'epoch': 4.01} -{'loss': 0.0921, 'learning_rate': 9.44888888888889e-06, 'epoch': 4.02} -{'loss': 0.1023, 'learning_rate': 9.393333333333334e-06, 'epoch': 4.02} -{'loss': 0.0962, 'learning_rate': 9.33777777777778e-06, 'epoch': 4.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.99it/s] - Reading metadata...: 14292it [00:00, 31622.25it/s] - Reading metadata...: 22699it [00:01, 14675.60it/s] Reading metadata...: 28043it [00:01, 17791.47it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.06it/s] Reading metadata...: 10438it [00:00, 26121.88it/s] - 16%|█▋ | 818/5000 [6:24:21<43:33:27, 37.50s/it] 16%|█▋ | 819/5000 [6:24:49<40:08:37, 34.57s/it] 16%|█▋ | 820/5000 [6:25:18<38:07:25, 32.83s/it] 16%|█▋ | 821/5000 [6:25:46<36:30:50, 31.46s/it] 16%|█▋ | 822/5000 [6:26:13<35:08:17, 30.28s/it] 16%|█▋ | 823/5000 [6:26:42<34:24:28, 29.65s/it] 16%|█▋ | 824/5000 [6:27:10<33:50:30, 29.17s/it] 16%|█▋ | 825/5000 [6:27:37<33:16:40, 28.69s/it] 16%|█▋ | 825/5000 [6:27:37<33:16:40, 28.69s/it] 17%|█▋ | 826/5000 [6:28:05<32:50:08, 28.32s/it] 17%|█▋ | 827/5000 [6:28:32<32:31:20, 28.06s/it] 17%|█▋ | 828/5000 [6:29:00<32:32:50, 28.08s/it] 17%|█▋ | 829/5000 [6:29:29<32:47:49, 28.31s/it] 17%|█▋ | 830/5000 [6:29:56<32:25:57, 28.00s/it] 17%|█▋ | 831/5000 [6:30:24<32:08:03, 27.75s/it] 17%|█▋ | 832/5000 [6:30:52<32:21:38, 27.95s/it] 17%|█▋ | 833/5000 [6:31:20<32:30:00, 28.08s/it] 17%|█▋ | 834/5000 [6:31:48<32:28:06, 28.06s/it] 17%|█▋ | 835/5000 [6:32:15<32:08:23, 27.78s/it] 17%|█▋ | 836/5000 [6:32:44<32:21:13, 27.97s/it] 17%|█▋ | 837/5000 [6:33:12<32:27:14, 28.06s/it] 17%|█▋ | 838/5000 [6:33:39<32:08:25, 27.80s/it] 17%|█▋ | 839/5000 [6:34:07<31:57:33, 27.65s/it] 17%|█▋ | 840/5000 [6:34:34<31:59:22, 27.68s/it] 17%|█▋ | 841/5000 [6:35:02<31:51:45, 27.58s/it] 17%|█▋ | 842/5000 [6:35:29<31:43:14, 27.46s/it] 17%|█▋ | 843/5000 [6:35:57<31:59:44, 27.71s/it] 17%|█▋ | 844/5000 [6:36:24<31:45:32, 27.51s/it] 17%|█▋ | 845/5000 [6:36:53<32:03:23, 27.77s/it] 17%|█▋ | 846/5000 [6:37:21<32:12:27, 27.91s/it] 17%|█▋ | 847/5000 [6:37:48<31:57:26, 27.70s/it] 17%|█▋ | 848/5000 [6:38:17<32:13:27, 27.94s/it] 17%|█▋ | 849/5000 [6:38:45<32:12:00, 27.93s/it] 17%|█▋ | 850/5000 [6:39:12<31:58:48, 27.74s/it] 17%|█▋ | 850/5000 [6:39:12<31:58:48, 27.74s/it] 17%|█▋ | 851/5000 [6:39:41<32:35:02, 28.27s/it] 17%|█▋ | 852/5000 [6:40:08<32:03:50, 27.83s/it] 17%|█▋ | 853/5000 [6:40:34<31:21:02, 27.22s/it] 17%|█▋ | 854/5000 [6:41:05<32:35:05, 28.29s/it] 17%|█▋ | 855/5000 [6:41:32<32:20:09, 28.08s/it] 17%|█▋ | 856/5000 [6:42:00<32:05:24, 27.88s/it] 17%|█▋ | 857/5000 [6:42:27<32:00:54, 27.82s/it] 17%|█▋ | 858/5000 [6:42:55<31:53:36, 27.72s/it] 17%|█▋ | 859/5000 [6:43:21<31:21:33, 27.26s/it] 17%|█▋ | 860/5000 [6:43:48<31:23:22, 27.30s/it] 17%|█▋ | 861/5000 [6:44:16<31:33:14, 27.44s/it] 17%|█▋ | 862/5000 [6:44:44<31:32:29, 27.44s/it] 17%|█▋ | 863/5000 [6:45:11<31:36:02, 27.50s/it] 17%|█▋ | 864/5000 [6:45:39<31:47:27, 27.67s/it] 17%|█▋ | 865/5000 [6:46:08<32:02:32, 27.90s/it] 17%|█▋ | 866/5000 [6:46:35<31:48:54, 27.71s/it] 17%|█▋ | 867/5000 [6:47:02<31:40:50, 27.59s/it] 17%|█▋ | 868/5000 [6:47:30<31:44:43, 27.66s/it] 17%|█▋ | 869/5000 [6:47:58<31:40:10, 27.60s/it] 17%|█▋ | 870/5000 [6:48:26<31:54:41, 27.82s/it] 17%|█▋ | 871/5000 [6:48:53<31:45:34, 27.69s/it] 17%|█▋ | 872/5000 [6:49:21<31:40:09, 27.62s/it] 17%|█▋ | 873/5000 [6:49:49<31:45:19, 27.70s/it] 17%|█▋ | 874/5000 [6:50:17<31:49:11, 27.76s/it] 18%|█▊ | 875/5000 [6:50:44<31:43:20, 27.68s/it] 18%|█▊ | 875/5000 [6:50:44<31:43:20, 27.68s/it] 18%|█▊ | 876/5000 [6:51:13<32:09:20, 28.07s/it] 18%|█▊ | 877/5000 [6:51:40<31:49:58, 27.79s/it] 18%|█▊ | 878/5000 [6:52:06<31:12:07, 27.25s/it] 18%|█▊ | 879/5000 [6:52:34<31:26:38, 27.47s/it] 18%|█▊ | 880/5000 [6:53:02<31:30:05, 27.53s/it] 18%|█▊ | 881/5000 [6:53:29<31:17:53, 27.35s/it] 18%|█▊ | 882/5000 [6:53:56<31:20:37, 27.40s/it] 18%|█▊ | 883/5000 [6:54:24<31:28:55, 27.53s/it] 18%|█▊ | 884/5000 [6:54:51<31:18:44, 27.39s/it] 18%|█▊ | 885/5000 [6:55:23<32:58:05, 28.84s/it] 18%|█▊ | 886/5000 [6:55:51<32:40:29, 28.59s/it] 18%|█▊ | 887/5000 [6:56:19<32:10:38, 28.16s/it] 18%|█▊ | 888/5000 [6:56:49<33:03:36, 28.94s/it] 18%|█▊ | 889/5000 [6:57:19<33:11:19, 29.06s/it] 18%|█▊ | 890/5000 [6:57:45<32:08:10, 28.15s/it] 18%|█▊ | 891/5000 [6:58:13<32:16:37, 28.28s/it] 18%|█▊ | 892/5000 [6:58:41<32:05:31, 28.12s/it] 18%|█▊ | 893/5000 [6:59:09<32:09:33, 28.19s/it] 18%|█▊ | 894/5000 [6:59:37<31:48:05, 27.88s/it] 18%|█▊ | 895/5000 [7:00:05<32:07:41, 28.18s/it] 18%|█▊ | 896/5000 [7:00:34<32:11:07, 28.23s/it] 18%|█▊ | 897/5000 [7:01:01<31:56:09, 28.02s/it] 18%|█▊ | 898/5000 [7:01:30<32:00:27, 28.09s/it] 18%|█▊ | 899/5000 [7:01:58<32:05:52, 28.18s/it] 18%|█▊ | 900/5000 [7:02:26<31:53:22, 28.00s/it] 18%|█▊ | 900/5000 [7:02:26<31:53:22, 28.00s/it] 18%|█▊ | 901/5000 [7:02:52<31:29:30, 27.66s/it] 18%|█▊ | 902/5000 [7:03:21<31:37:07, 27.78s/it] 18%|█▊ | 903/5000 [7:03:48<31:31:29, 27.70s/it] 18%|█▊ | 904/5000 [7:04:16<31:41:15, 27.85s/it] 18%|█▊ | 905/5000 [7:04:44<31:44:15, 27.90s/it] 18%|█▊ | 906/5000 [7:05:12<31:35:45, 27.78s/it] 18%|█▊ | 907/5000 [7:05:40<31:39:21, 27.84s/it] 18%|█▊ | 908/5000 [7:06:08<31:47:10, 27.96s/it] 18%|█▊ | 909/5000 [7:06:35<31:33:15, 27.77s/it] 18%|█▊ | 910/5000 [7:07:03<31:30:04, 27.73s/it] 18%|█▊ | 911/5000 [7:07:31<31:42:06, 27.91s/it] 18%|█▊ | 912/5000 [7:07:58<31:25:28, 27.67s/it] 18%|█▊ | 913/5000 [7:08:26<31:26:02, 27.69s/it] 18%|█▊ | 914/5000 [7:08:54<31:35:53, 27.84s/it] 18%|█▊ | 915/5000 [7:09:22<31:29:30, 27.75s/it] 18%|█▊ | 916/5000 [7:09:50<31:38:49, 27.90s/it] 18%|█▊ | 917/5000 [7:10:19<31:52:19, 28.10s/it] 18%|█▊ | 918/5000 [7:10:46<31:43:08, 27.97s/it] 18%|█▊ | 919/5000 [7:11:14<31:30:55, 27.80s/it] 18%|█▊ | 920/5000 [7:11:42<31:36:39, 27.89s/it] 18%|█▊ | 921/5000 [7:12:09<31:25:04, 27.73s/it] 18%|█▊ | 922/5000 [7:12:36<31:15:20, 27.59s/it] 18%|█▊ | 923/5000 [7:13:04<31:07:13, 27.48s/it] 18%|█▊ | 924/5000 [7:13:33<31:44:03, 28.03s/it] 18%|█▊ | 925/5000 [7:14:00<31:27:54, 27.80s/it] 18%|█▊ | 925/5000 [7:14:00<31:27:54, 27.80s/it] 19%|█▊ | 926/5000 [7:14:26<30:55:29, 27.33s/it] 19%|█▊ | 927/5000 [7:14:54<30:58:35, 27.38s/it] 19%|█▊ | 928/5000 [7:15:21<30:50:12, 27.26s/it] 19%|█▊ | 929/5000 [7:15:48<30:41:11, 27.14s/it] 19%|█▊ | 930/5000 [7:16:17<31:25:56, 27.80s/it] 19%|█▊ | 931/5000 [7:16:44<31:11:50, 27.60s/it] 19%|█▊ | 932/5000 [7:17:12<31:18:34, 27.71s/it] 19%|█▊ | 933/5000 [7:17:40<31:26:23, 27.83s/it] 19%|█▊ | 934/5000 [7:18:08<31:23:55, 27.80s/it] 19%|█▊ | 935/5000 [7:18:35<31:02:04, 27.48s/it] 19%|█▊ | 936/5000 [7:19:03<31:07:14, 27.57s/it] 19%|█▊ | 937/5000 [7:19:30<31:10:13, 27.62s/it] 19%|█▉ | 938/5000 [7:19:58<31:00:48, 27.49s/it] 19%|█▉ | 939/5000 [7:20:26<31:23:30, 27.83s/it] 19%|█▉ | 940/5000 [7:20:54<31:18:10, 27.76s/it] 19%|█▉ | 941/5000 [7:21:21<31:06:46, 27.59s/it] 19%|█▉ | 942/5000 [7:21:48<30:58:47, 27.48s/it] 19%|█▉ | 943/5000 [7:22:16<31:00:08, 27.51s/it] 19%|█▉ | 944/5000 [7:22:43<30:50:49, 27.38s/it] 19%|█▉ | 945/5000 [7:23:10<30:45:47, 27.31s/it] 19%|█▉ | 946/5000 [7:23:39<31:26:24, 27.92s/it] 19%|█▉ | 947/5000 [7:24:06<30:59:01, 27.52s/it] 19%|█▉ | 948/5000 [7:24:31<30:12:57, 26.85s/it] 19%|█▉ | 949/5000 [7:24:59<30:28:04, 27.08s/it] 19%|█▉ | 950/5000 [7:25:24<29:51:57, 26.55s/it] 19%|█▉ | 950/5000 [7:25:24<29:51:57, 26.55s/it] 19%|█▉ | 951/5000 [7:25:51<29:49:11, 26.51s/it] 19%|█▉ | 952/5000 [7:26:20<30:39:01, 27.26s/it] 19%|█▉ | 953/5000 [7:26:47<30:39:02, 27.27s/it] 19%|█▉ | 954/5000 [7:27:14<30:39:54, 27.28s/it] 19%|█▉ | 955/5000 [7:27:43<31:09:52, 27.74s/it] 19%|█▉ | 956/5000 [7:28:10<31:05:19, 27.68s/it] 19%|█▉ | 957/5000 [7:28:38<30:52:26, 27.49s/it] 19%|█▉ | 958/5000 [7:29:05<30:49:08, 27.45s/it] 19%|█▉ | 959/5000 [7:29:33<30:53:05, 27.51s/it] 19%|█▉ | 960/5000 [7:30:00<30:47:34, 27.44s/it] 19%|█▉ | 961/5000 [7:30:28<31:11:15, 27.80s/it] 19%|█▉ | 962/5000 [7:30:56<31:08:37, 27.77s/it] 19%|█▉ | 963/5000 [7:31:24<31:04:05, 27.71s/it] 19%|█▉ | 964/5000 [7:31:51<30:49:39, 27.50s/it] 19%|█▉ | 965/5000 [7:32:18<30:54:27, 27.58s/it] 19%|█▉ | 966/5000 [7:32:46<30:45:21, 27.45s/it] 19%|█▉ | 967/5000 [7:33:14<31:04:40, 27.74s/it] 19%|█▉ | 968/5000 [7:33:40<30:26:48, 27.18s/it] 19%|█▉ | 969/5000 [7:34:07<30:28:54, 27.22s/it] 19%|█▉ | 970/5000 [7:34:36<30:57:28, 27.65s/it] 19%|█▉ | 971/5000 [7:35:03<30:50:45, 27.56s/it] 19%|█▉ | 972/5000 [7:35:31<30:50:11, 27.56s/it] 19%|█▉ | 973/5000 [7:35:59<31:02:30, 27.75s/it] 19%|█▉ | 974/5000 [7:36:27<31:11:27, 27.89s/it] 20%|█▉ | 975/5000 [7:36:55<31:02:52, 27.77s/it] 20%|█▉ | 975/5000 [7:36:55<31:02:52, 27.77s/it] 20%|█▉ | 976/5000 [7:37:23<31:13:46, 27.94s/it] 20%|█▉ | 977/5000 [7:37:45<29:17:09, 26.21s/it] 20%|█▉ | 978/5000 [7:37:56<24:09:31, 21.62s/it] 20%|█▉ | 979/5000 [7:38:07<20:32:29, 18.39s/it] 20%|█▉ | 980/5000 [7:38:18<17:59:55, 16.12s/it] 20%|█▉ | 981/5000 [7:38:26<15:15:07, 13.66s/it]{'loss': 0.0803, 'learning_rate': 9.282222222222222e-06, 'epoch': 5.0} -{'loss': 0.0877, 'learning_rate': 9.226666666666668e-06, 'epoch': 5.01} -{'loss': 0.0812, 'learning_rate': 9.171111111111112e-06, 'epoch': 5.01} -{'loss': 0.0639, 'learning_rate': 9.115555555555556e-06, 'epoch': 5.02} -{'loss': 0.0615, 'learning_rate': 9.060000000000001e-06, 'epoch': 5.02} -{'loss': 0.07, 'learning_rate': 9.004444444444445e-06, 'epoch': 5.03} -{'loss': 0.053, 'learning_rate': 8.94888888888889e-06, 'epoch': 5.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.05it/s] - Reading metadata...: 14689it [00:00, 33229.49it/s] - Reading metadata...: 23329it [00:00, 27403.88it/s] Reading metadata...: 28043it [00:01, 28001.93it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.80it/s] Reading metadata...: 10438it [00:00, 24569.38it/s] - 20%|█▉ | 982/5000 [7:40:08<44:59:17, 40.31s/it] 20%|█▉ | 983/5000 [7:40:39<41:48:40, 37.47s/it] 20%|█▉ | 984/5000 [7:41:06<38:21:27, 34.38s/it] 20%|█▉ | 985/5000 [7:41:35<36:19:09, 32.57s/it] 20%|█▉ | 986/5000 [7:42:03<34:54:32, 31.31s/it] 20%|█▉ | 987/5000 [7:42:31<33:49:17, 30.34s/it] 20%|█▉ | 988/5000 [7:42:58<32:48:35, 29.44s/it] 20%|█▉ | 989/5000 [7:43:27<32:34:34, 29.24s/it] 20%|█▉ | 990/5000 [7:43:55<32:09:24, 28.87s/it] 20%|█▉ | 991/5000 [7:44:22<31:31:59, 28.32s/it] 20%|█▉ | 992/5000 [7:44:50<31:14:19, 28.06s/it] 20%|█▉ | 993/5000 [7:45:18<31:13:43, 28.06s/it] 20%|█▉ | 994/5000 [7:45:46<31:25:23, 28.24s/it] 20%|█▉ | 995/5000 [7:46:15<31:30:11, 28.32s/it] 20%|█▉ | 996/5000 [7:46:42<31:11:18, 28.04s/it] 20%|█▉ | 997/5000 [7:47:14<32:27:39, 29.19s/it] 20%|█▉ | 998/5000 [7:47:43<32:18:30, 29.06s/it] 20%|█▉ | 999/5000 [7:48:10<31:41:54, 28.52s/it] 20%|██ | 1000/5000 [7:48:38<31:29:41, 28.35s/it] 20%|██ | 1000/5000 [7:48:38<31:29:41, 28.35s/it][INFO|trainer.py:3138] 2023-05-07 18:22:49,172 >> ***** Running Evaluation ***** -[INFO|trainer.py:3142] 2023-05-07 18:22:49,172 >> Num examples: Unknown -[INFO|trainer.py:3143] 2023-05-07 18:22:49,172 >> Batch size = 64 -{'loss': 0.0519, 'learning_rate': 8.893333333333333e-06, 'epoch': 6.0} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:02, 2.58s/it] Reading metadata...: 10440it [00:02, 3954.23it/s] -[INFO|trainer_utils.py:693] 2023-05-07 18:23:04,305 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message. - 20%|██ | 1000/5000 [8:26:06<31:29:41, 28.35s/it][INFO|trainer.py:2877] 2023-05-07 19:00:17,386 >> Saving model checkpoint to ./checkpoint-1000 -[INFO|configuration_utils.py:458] 2023-05-07 19:00:17,393 >> Configuration saved in ./checkpoint-1000/config.json -[INFO|configuration_utils.py:364] 2023-05-07 19:00:17,398 >> Configuration saved in ./checkpoint-1000/generation_config.json -[INFO|modeling_utils.py:1855] 2023-05-07 19:00:20,753 >> Model weights saved in ./checkpoint-1000/pytorch_model.bin -[INFO|feature_extraction_utils.py:369] 2023-05-07 19:00:20,758 >> Feature extractor saved in ./checkpoint-1000/preprocessor_config.json -[INFO|feature_extraction_utils.py:369] 2023-05-07 19:00:30,115 >> Feature extractor saved in ./preprocessor_config.json -Adding files tracked by Git LFS: ['wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb', 'wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb']. This may take a bit of time if the files are large. -{'eval_loss': 0.43405279517173767, 'eval_wer': 54.25600000000001, 'eval_runtime': 2248.2056, 'eval_samples_per_second': 4.644, 'eval_steps_per_second': 0.073, 'epoch': 6.0} -05/07/2023 19:00:40 - WARNING - huggingface_hub.repository - Adding files tracked by Git LFS: ['wandb/run-20230506_113337-ysywp688/run-ysywp688.wandb', 'wandb/run-20230507_103405-9zf5xxpu/run-9zf5xxpu.wandb']. This may take a bit of time if the files are large. -/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector. - warnings.warn('Was asked to gather along dimension 0, but all ' - 20%|██ | 1001/5000 [8:27:07<791:34:47, 712.60s/it] 20%|██ | 1002/5000 [8:27:35<563:11:28, 507.13s/it] 20%|██ | 1003/5000 [8:28:04<403:46:05, 363.66s/it] 20%|██ | 1004/5000 [8:28:32<291:54:08, 262.98s/it] 20%|██ | 1005/5000 [8:28:59<213:24:18, 192.30s/it] 20%|██ | 1006/5000 [8:29:28<158:59:55, 143.31s/it] 20%|██ | 1007/5000 [8:29:56<120:19:03, 108.48s/it] 20%|██ | 1008/5000 [8:30:23<93:12:59, 84.06s/it] 20%|██ | 1009/5000 [8:30:52<74:58:34, 67.63s/it] 20%|██ | 1010/5000 [8:31:19<61:38:34, 55.62s/it] 20%|██ | 1011/5000 [8:31:46<51:49:30, 46.77s/it] 20%|██ | 1012/5000 [8:32:20<47:34:07, 42.94s/it] 20%|██ | 1013/5000 [8:32:46<42:11:11, 38.09s/it] 20%|██ | 1014/5000 [8:33:14<38:34:08, 34.83s/it] 20%|██ | 1015/5000 [8:33:43<36:51:23, 33.30s/it] 20%|██ | 1016/5000 [8:34:11<34:51:19, 31.50s/it] 20%|██ | 1017/5000 [8:34:38<33:26:52, 30.23s/it] 20%|██ | 1018/5000 [8:35:07<32:57:16, 29.79s/it] 20%|██ | 1019/5000 [8:35:34<32:09:41, 29.08s/it] 20%|██ | 1020/5000 [8:36:01<31:28:13, 28.47s/it] 20%|██ | 1021/5000 [8:36:29<31:22:00, 28.38s/it] 20%|██ | 1022/5000 [8:36:56<30:53:33, 27.96s/it] 20%|██ | 1023/5000 [8:37:25<31:00:06, 28.06s/it] 20%|██ | 1024/5000 [8:37:52<30:54:36, 27.99s/it] 20%|██ | 1025/5000 [8:38:20<30:36:36, 27.72s/it] 20%|██ | 1025/5000 [8:38:20<30:36:36, 27.72s/it] 21%|██ | 1026/5000 [8:38:52<32:15:09, 29.22s/it] 21%|██ | 1027/5000 [8:39:20<31:39:01, 28.68s/it] 21%|██ | 1028/5000 [8:39:49<31:48:02, 28.82s/it] 21%|██ | 1029/5000 [8:40:17<31:30:25, 28.56s/it] 21%|██ | 1030/5000 [8:40:44<31:02:35, 28.15s/it] 21%|██ | 1031/5000 [8:41:12<30:58:22, 28.09s/it] 21%|██ | 1032/5000 [8:41:40<31:03:55, 28.18s/it] 21%|██ | 1033/5000 [8:42:08<30:48:01, 27.95s/it] 21%|██ | 1034/5000 [8:42:37<31:18:07, 28.41s/it] 21%|██ | 1035/5000 [8:43:04<30:48:47, 27.98s/it] 21%|██ | 1036/5000 [8:43:31<30:34:22, 27.77s/it] 21%|██ | 1037/5000 [8:44:01<31:08:55, 28.30s/it] 21%|██ | 1038/5000 [8:44:28<30:52:59, 28.06s/it] 21%|██ | 1039/5000 [8:44:55<30:22:36, 27.61s/it] 21%|██ | 1040/5000 [8:45:24<30:47:47, 28.00s/it] 21%|██ | 1041/5000 [8:45:51<30:35:37, 27.82s/it] 21%|██ | 1042/5000 [8:46:19<30:27:20, 27.70s/it] 21%|██ | 1043/5000 [8:46:48<30:51:34, 28.08s/it] 21%|██ | 1044/5000 [8:47:15<30:37:28, 27.87s/it] 21%|██ | 1045/5000 [8:47:43<30:27:59, 27.73s/it] 21%|██ | 1046/5000 [8:48:13<31:16:19, 28.47s/it] 21%|██ | 1047/5000 [8:48:40<30:57:09, 28.19s/it] 21%|██ | 1048/5000 [8:49:08<30:57:21, 28.20s/it] 21%|██ | 1049/5000 [8:49:36<30:47:50, 28.06s/it] 21%|██ | 1050/5000 [8:50:03<30:27:46, 27.76s/it] 21%|██ | 1050/5000 [8:50:03<30:27:46, 27.76s/it] 21%|██ | 1051/5000 [8:50:31<30:35:30, 27.89s/it] 21%|██ | 1052/5000 [8:50:59<30:23:13, 27.71s/it] 21%|██ | 1053/5000 [8:51:26<30:20:08, 27.67s/it] 21%|██ | 1054/5000 [8:51:55<30:40:01, 27.98s/it] 21%|██ | 1055/5000 [8:52:22<30:26:27, 27.78s/it] 21%|██ | 1056/5000 [8:52:51<30:35:40, 27.93s/it] 21%|██ | 1057/5000 [8:53:19<30:49:56, 28.15s/it] 21%|██ | 1058/5000 [8:53:47<30:32:42, 27.90s/it] 21%|██ | 1059/5000 [8:54:15<30:49:41, 28.16s/it] 21%|██ | 1060/5000 [8:54:44<30:49:17, 28.16s/it] 21%|██ | 1061/5000 [8:55:11<30:35:19, 27.96s/it] 21%|██ | 1062/5000 [8:55:39<30:31:43, 27.91s/it] 21%|██▏ | 1063/5000 [8:56:07<30:35:45, 27.98s/it] 21%|██▏ | 1064/5000 [8:56:34<30:18:02, 27.71s/it] 21%|██▏ | 1065/5000 [8:57:02<30:22:09, 27.78s/it] 21%|██▏ | 1066/5000 [8:57:30<30:19:09, 27.75s/it] 21%|██▏ | 1067/5000 [8:57:58<30:32:30, 27.96s/it] 21%|██▏ | 1068/5000 [8:58:26<30:22:01, 27.80s/it] 21%|██▏ | 1069/5000 [8:58:53<30:23:43, 27.84s/it] 21%|██▏ | 1070/5000 [8:59:22<30:30:16, 27.94s/it] 21%|██▏ | 1071/5000 [8:59:49<30:15:17, 27.72s/it] 21%|██▏ | 1072/5000 [9:00:17<30:25:31, 27.88s/it] 21%|██▏ | 1073/5000 [9:00:45<30:29:45, 27.96s/it] 21%|██▏ | 1074/5000 [9:01:12<30:10:29, 27.67s/it] 22%|██▏ | 1075/5000 [9:01:40<30:19:39, 27.82s/it] 22%|██▏ | 1075/5000 [9:01:40<30:19:39, 27.82s/it] 22%|██▏ | 1076/5000 [9:02:09<30:31:41, 28.01s/it] 22%|██▏ | 1077/5000 [9:02:36<30:21:10, 27.85s/it] 22%|██▏ | 1078/5000 [9:03:10<32:09:28, 29.52s/it] 22%|██▏ | 1079/5000 [9:03:38<31:35:39, 29.01s/it] 22%|██▏ | 1080/5000 [9:04:05<31:02:48, 28.51s/it] 22%|██▏ | 1081/5000 [9:04:34<31:04:38, 28.55s/it] 22%|██▏ | 1082/5000 [9:05:01<30:49:32, 28.32s/it] 22%|██▏ | 1083/5000 [9:05:29<30:27:31, 27.99s/it] 22%|██▏ | 1084/5000 [9:05:57<30:35:11, 28.12s/it] 22%|██▏ | 1085/5000 [9:06:24<30:16:06, 27.83s/it] 22%|██▏ | 1086/5000 [9:06:51<30:05:13, 27.67s/it] 22%|██▏ | 1087/5000 [9:07:19<30:12:16, 27.79s/it] 22%|██▏ | 1088/5000 [9:07:47<29:59:56, 27.61s/it] 22%|██▏ | 1089/5000 [9:08:14<29:53:36, 27.52s/it] 22%|██▏ | 1090/5000 [9:08:42<30:12:33, 27.81s/it] 22%|██▏ | 1091/5000 [9:09:11<30:22:11, 27.97s/it] 22%|██▏ | 1092/5000 [9:09:38<30:04:13, 27.70s/it] 22%|██▏ | 1093/5000 [9:10:07<30:23:16, 28.00s/it] 22%|██▏ | 1094/5000 [9:10:35<30:28:50, 28.09s/it] 22%|██▏ | 1095/5000 [9:11:02<30:13:00, 27.86s/it] 22%|██▏ | 1096/5000 [9:11:30<30:06:49, 27.77s/it] 22%|██▏ | 1097/5000 [9:11:57<29:52:09, 27.55s/it] 22%|██▏ | 1098/5000 [9:12:24<29:39:33, 27.36s/it] 22%|██▏ | 1099/5000 [9:12:51<29:28:49, 27.21s/it] 22%|██▏ | 1100/5000 [9:13:19<29:59:10, 27.68s/it] 22%|██▏ | 1100/5000 [9:13:19<29:59:10, 27.68s/it] 22%|██▏ | 1101/5000 [9:13:47<29:51:50, 27.57s/it] 22%|██▏ | 1102/5000 [9:14:14<29:47:06, 27.51s/it] 22%|██▏ | 1103/5000 [9:14:44<30:29:52, 28.17s/it] 22%|██▏ | 1104/5000 [9:15:11<30:10:21, 27.88s/it] 22%|██▏ | 1105/5000 [9:15:38<29:59:50, 27.73s/it] 22%|██▏ | 1106/5000 [9:16:07<30:17:25, 28.00s/it] 22%|██▏ | 1107/5000 [9:16:34<29:53:47, 27.65s/it] 22%|���█▏ | 1108/5000 [9:17:01<29:46:04, 27.53s/it] 22%|██▏ | 1109/5000 [9:17:30<30:16:16, 28.01s/it] 22%|██▏ | 1110/5000 [9:17:56<29:32:50, 27.34s/it] 22%|██▏ | 1111/5000 [9:18:22<29:10:58, 27.01s/it] 22%|██▏ | 1112/5000 [9:18:49<29:11:25, 27.03s/it] 22%|██▏ | 1113/5000 [9:19:21<30:44:52, 28.48s/it] 22%|██▏ | 1114/5000 [9:19:48<30:21:43, 28.13s/it] 22%|██▏ | 1115/5000 [9:20:16<30:03:12, 27.85s/it] 22%|██▏ | 1116/5000 [9:20:44<30:16:39, 28.06s/it] 22%|██▏ | 1117/5000 [9:21:11<29:59:08, 27.80s/it] 22%|██▏ | 1118/5000 [9:21:39<29:47:14, 27.62s/it] 22%|██▏ | 1119/5000 [9:22:08<30:25:13, 28.22s/it] 22%|██▏ | 1120/5000 [9:22:35<30:04:44, 27.91s/it] 22%|██▏ | 1121/5000 [9:23:03<29:55:42, 27.78s/it] 22%|██▏ | 1122/5000 [9:23:31<30:02:09, 27.88s/it] 22%|██▏ | 1123/5000 [9:23:59<29:54:51, 27.78s/it] 22%|██▏ | 1124/5000 [9:24:26<29:46:03, 27.65s/it] 22%|██▎ | 1125/5000 [9:24:55<30:10:55, 28.04s/it] 22%|██▎ | 1125/5000 [9:24:55<30:10:55, 28.04s/it] 23%|██▎ | 1126/5000 [9:25:22<29:51:53, 27.75s/it] 23%|██▎ | 1127/5000 [9:25:49<29:45:21, 27.66s/it] 23%|██▎ | 1128/5000 [9:26:20<30:44:37, 28.58s/it] 23%|██▎ | 1129/5000 [9:26:47<30:10:15, 28.06s/it] 23%|██▎ | 1130/5000 [9:27:14<29:55:46, 27.84s/it] 23%|██▎ | 1131/5000 [9:27:44<30:27:45, 28.34s/it] 23%|██▎ | 1132/5000 [9:28:11<30:09:16, 28.07s/it] 23%|██▎ | 1133/5000 [9:28:39<29:54:37, 27.85s/it] 23%|██▎ | 1134/5000 [9:29:07<30:12:17, 28.13s/it] 23%|██▎ | 1135/5000 [9:29:35<29:55:13, 27.87s/it] 23%|██▎ | 1136/5000 [9:30:02<29:43:08, 27.69s/it] 23%|██▎ | 1137/5000 [9:30:31<30:11:03, 28.13s/it] 23%|██▎ | 1138/5000 [9:30:58<29:51:31, 27.83s/it] 23%|██▎ | 1139/5000 [9:31:25<29:39:25, 27.65s/it] 23%|██▎ | 1140/5000 [9:31:55<30:11:51, 28.16s/it] 23%|██▎ | 1141/5000 [9:32:08<25:33:16, 23.84s/it] 23%|██▎ | 1142/5000 [9:32:19<21:24:24, 19.98s/it] 23%|██▎ | 1143/5000 [9:32:30<18:27:07, 17.22s/it] 23%|██▎ | 1144/5000 [9:32:41<16:23:31, 15.30s/it]{'loss': 0.0512, 'learning_rate': 8.83777777777778e-06, 'epoch': 6.01} -{'loss': 0.048, 'learning_rate': 8.782222222222223e-06, 'epoch': 6.01} -{'loss': 0.034, 'learning_rate': 8.726666666666667e-06, 'epoch': 6.02} -{'loss': 0.0415, 'learning_rate': 8.671111111111113e-06, 'epoch': 6.02} -{'loss': 0.0402, 'learning_rate': 8.615555555555555e-06, 'epoch': 6.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.05it/s] - Reading metadata...: 14652it [00:01, 19129.68it/s] - Reading metadata...: 23270it [00:01, 13633.81it/s] Reading metadata...: 28043it [00:01, 14523.88it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.19it/s] Reading metadata...: 10438it [00:00, 11491.98it/s] - 23%|██▎ | 1145/5000 [9:34:08<39:27:24, 36.85s/it] 23%|██▎ | 1146/5000 [9:34:36<36:36:12, 34.19s/it] 23%|██▎ | 1147/5000 [9:35:04<34:35:24, 32.32s/it] 23%|██▎ | 1148/5000 [9:35:33<33:24:02, 31.22s/it] 23%|██▎ | 1149/5000 [9:36:00<32:12:01, 30.10s/it] 23%|██▎ | 1150/5000 [9:36:28<31:22:23, 29.34s/it] 23%|██▎ | 1150/5000 [9:36:28<31:22:23, 29.34s/it] 23%|██▎ | 1151/5000 [9:36:56<30:57:29, 28.96s/it] 23%|██▎ | 1152/5000 [9:37:25<31:06:31, 29.10s/it] 23%|██▎ | 1153/5000 [9:37:54<30:52:06, 28.89s/it] 23%|██▎ | 1154/5000 [9:38:21<30:24:52, 28.47s/it] 23%|██▎ | 1155/5000 [9:38:49<30:20:14, 28.40s/it] 23%|██▎ | 1156/5000 [9:39:18<30:20:51, 28.42s/it] 23%|██▎ | 1157/5000 [9:39:45<30:01:50, 28.13s/it] 23%|██▎ | 1158/5000 [9:40:17<31:17:11, 29.32s/it] 23%|██▎ | 1159/5000 [9:40:46<31:04:33, 29.13s/it] 23%|██▎ | 1160/5000 [9:41:14<30:47:06, 28.86s/it] 23%|██▎ | 1161/5000 [9:41:42<30:31:23, 28.62s/it] 23%|██▎ | 1162/5000 [9:42:09<30:00:08, 28.14s/it] 23%|██▎ | 1163/5000 [9:42:38<30:07:34, 28.27s/it] 23%|██▎ | 1164/5000 [9:43:07<30:22:38, 28.51s/it] 23%|██▎ | 1165/5000 [9:43:34<29:54:41, 28.08s/it] 23%|██▎ | 1166/5000 [9:44:03<29:59:17, 28.16s/it] 23%|██▎ | 1167/5000 [9:44:30<29:46:29, 27.96s/it] 23%|██▎ | 1168/5000 [9:44:57<29:33:03, 27.76s/it] 23%|██▎ | 1169/5000 [9:45:26<29:42:04, 27.91s/it] 23%|██▎ | 1170/5000 [9:45:54<29:43:32, 27.94s/it] 23%|██▎ | 1171/5000 [9:46:21<29:24:42, 27.65s/it] 23%|██▎ | 1172/5000 [9:46:48<29:28:19, 27.72s/it] 23%|██▎ | 1173/5000 [9:47:16<29:26:16, 27.69s/it] 23%|██▎ | 1174/5000 [9:47:44<29:21:08, 27.62s/it] 24%|██▎ | 1175/5000 [9:48:12<29:43:46, 27.98s/it] 24%|██▎ | 1175/5000 [9:48:12<29:43:46, 27.98s/it] 24%|██▎ | 1176/5000 [9:48:40<29:35:28, 27.86s/it] 24%|██▎ | 1177/5000 [9:49:07<29:24:07, 27.69s/it] 24%|██▎ | 1178/5000 [9:49:37<30:00:47, 28.27s/it] 24%|██▎ | 1179/5000 [9:50:04<29:40:06, 27.95s/it] 24%|██▎ | 1180/5000 [9:50:31<29:28:19, 27.77s/it] 24%|██▎ | 1181/5000 [9:51:00<29:45:25, 28.05s/it] 24%|██▎ | 1182/5000 [9:51:27<29:27:17, 27.77s/it] 24%|██▎ | 1183/5000 [9:51:55<29:18:55, 27.65s/it] 24%|██▎ | 1184/5000 [9:52:22<29:17:14, 27.63s/it] 24%|██▎ | 1185/5000 [9:52:51<29:35:04, 27.92s/it] 24%|██▎ | 1186/5000 [9:53:18<29:12:33, 27.57s/it] 24%|██▎ | 1187/5000 [9:53:46<29:28:17, 27.83s/it] 24%|██▍ | 1188/5000 [9:54:14<29:28:42, 27.84s/it] 24%|██▍ | 1189/5000 [9:54:41<29:19:26, 27.70s/it] 24%|██▍ | 1190/5000 [9:55:09<29:21:17, 27.74s/it] 24%|██▍ | 1191/5000 [9:55:36<29:16:01, 27.66s/it] 24%|██▍ | 1192/5000 [9:56:05<29:27:45, 27.85s/it] 24%|██▍ | 1193/5000 [9:56:32<29:21:57, 27.77s/it] 24%|██▍ | 1194/5000 [9:57:00<29:12:55, 27.63s/it] 24%|██▍ | 1195/5000 [9:57:28<29:26:52, 27.86s/it] 24%|██▍ | 1196/5000 [9:57:55<29:17:25, 27.72s/it] 24%|██▍ | 1197/5000 [9:58:28<30:39:41, 29.02s/it] 24%|██▍ | 1198/5000 [9:58:55<30:08:15, 28.54s/it] 24%|██▍ | 1199/5000 [9:59:22<29:47:08, 28.21s/it] 24%|██▍ | 1200/5000 [9:59:51<29:47:38, 28.23s/it] 24%|██▍ | 1200/5000 [9:59:51<29:47:38, 28.23s/it] 24%|██▍ | 1201/5000 [10:00:19<29:50:16, 28.27s/it] 24%|██▍ | 1202/5000 [10:00:46<29:28:02, 27.93s/it] 24%|██▍ | 1203/5000 [10:01:16<30:07:10, 28.56s/it] 24%|██▍ | 1204/5000 [10:01:44<29:44:04, 28.20s/it] 24%|██▍ | 1205/5000 [10:02:10<29:11:59, 27.70s/it] 24%|██▍ | 1206/5000 [10:02:39<29:31:12, 28.01s/it] 24%|██▍ | 1207/5000 [10:03:06<29:21:01, 27.86s/it] 24%|██▍ | 1208/5000 [10:03:34<29:12:16, 27.73s/it] 24%|██▍ | 1209/5000 [10:04:02<29:14:38, 27.77s/it] 24%|██▍ | 1210/5000 [10:04:29<29:15:48, 27.80s/it] 24%|██▍ | 1211/5000 [10:04:57<29:09:36, 27.71s/it] 24%|██▍ | 1212/5000 [10:05:25<29:14:42, 27.79s/it] 24%|██▍ | 1213/5000 [10:05:54<29:29:44, 28.04s/it] 24%|██▍ | 1214/5000 [10:06:21<29:14:43, 27.81s/it] 24%|██▍ | 1215/5000 [10:06:49<29:27:37, 28.02s/it] 24%|██▍ | 1216/5000 [10:07:17<29:20:27, 27.91s/it] 24%|██▍ | 1217/5000 [10:07:44<29:05:54, 27.69s/it] 24%|██▍ | 1218/5000 [10:08:13<29:28:06, 28.05s/it] 24%|██▍ | 1219/5000 [10:08:42<29:37:11, 28.20s/it] 24%|██▍ | 1220/5000 [10:09:10<29:38:02, 28.22s/it] 24%|██▍ | 1221/5000 [10:09:37<29:23:29, 28.00s/it] 24%|██▍ | 1222/5000 [10:10:05<29:17:45, 27.92s/it] 24%|██▍ | 1223/5000 [10:10:34<29:29:06, 28.10s/it] 24%|██▍ | 1224/5000 [10:11:01<29:19:05, 27.95s/it] 24%|██▍ | 1225/5000 [10:11:33<30:38:14, 29.22s/it] 24%|██▍ | 1225/5000 [10:11:33<30:38:14, 29.22s/it] 25%|██▍ | 1226/5000 [10:12:06<31:41:12, 30.23s/it] 25%|██▍ | 1227/5000 [10:12:33<30:48:50, 29.40s/it] 25%|██▍ | 1228/5000 [10:13:02<30:26:55, 29.06s/it] 25%|██▍ | 1229/5000 [10:13:29<30:01:58, 28.67s/it] 25%|██▍ | 1230/5000 [10:13:57<29:40:08, 28.33s/it] 25%|██▍ | 1231/5000 [10:14:26<29:43:02, 28.38s/it] 25%|██▍ | 1232/5000 [10:14:54<29:44:59, 28.42s/it] 25%|██▍ | 1233/5000 [10:15:22<29:28:20, 28.17s/it] 25%|██▍ | 1234/5000 [10:15:50<29:33:45, 28.26s/it] 25%|██▍ | 1235/5000 [10:16:18<29:25:23, 28.13s/it] 25%|██▍ | 1236/5000 [10:16:45<29:09:52, 27.89s/it] 25%|██▍ | 1237/5000 [10:17:14<29:28:07, 28.19s/it] 25%|██▍ | 1238/5000 [10:17:43<29:34:26, 28.30s/it] 25%|██▍ | 1239/5000 [10:18:10<29:20:32, 28.09s/it] 25%|██▍ | 1240/5000 [10:18:38<29:15:22, 28.01s/it] 25%|██▍ | 1241/5000 [10:19:07<29:26:21, 28.19s/it] 25%|██▍ | 1242/5000 [10:19:34<29:11:01, 27.96s/it] 25%|██▍ | 1243/5000 [10:20:02<29:14:14, 28.02s/it] 25%|██▍ | 1244/5000 [10:20:32<29:41:58, 28.47s/it] 25%|██▍ | 1245/5000 [10:21:00<29:39:22, 28.43s/it] 25%|██▍ | 1246/5000 [10:21:28<29:18:40, 28.11s/it] 25%|██▍ | 1247/5000 [10:21:56<29:20:01, 28.14s/it] 25%|██▍ | 1248/5000 [10:22:24<29:23:37, 28.20s/it] 25%|██▍ | 1249/5000 [10:22:52<29:08:23, 27.97s/it] 25%|██▌ | 1250/5000 [10:23:19<28:54:41, 27.75s/it] 25%|██▌ | 1250/5000 [10:23:19<28:54:41, 27.75s/it] 25%|██▌ | 1251/5000 [10:23:47<29:01:29, 27.87s/it] 25%|██▌ | 1252/5000 [10:24:14<28:50:15, 27.70s/it] 25%|██▌ | 1253/5000 [10:24:41<28:39:31, 27.53s/it] 25%|██▌ | 1254/5000 [10:25:10<29:06:11, 27.97s/it] 25%|██▌ | 1255/5000 [10:25:38<28:52:51, 27.76s/it] 25%|██▌ | 1256/5000 [10:26:05<28:41:32, 27.59s/it] 25%|██▌ | 1257/5000 [10:26:34<29:16:45, 28.16s/it] 25%|██▌ | 1258/5000 [10:27:02<29:00:11, 27.90s/it] 25%|██▌ | 1259/5000 [10:27:34<30:29:19, 29.34s/it] 25%|██▌ | 1260/5000 [10:28:03<30:23:14, 29.25s/it] 25%|██▌ | 1261/5000 [10:28:32<30:06:56, 29.00s/it] 25%|██▌ | 1262/5000 [10:28:59<29:33:12, 28.46s/it] 25%|██▌ | 1263/5000 [10:29:28<29:37:23, 28.54s/it] 25%|██▌ | 1264/5000 [10:29:56<29:31:45, 28.45s/it] 25%|██▌ | 1265/5000 [10:30:23<29:09:47, 28.11s/it] 25%|██▌ | 1266/5000 [10:30:53<29:31:51, 28.47s/it] 25%|██▌ | 1267/5000 [10:31:20<29:17:45, 28.25s/it] 25%|██▌ | 1268/5000 [10:31:48<29:01:45, 28.00s/it] 25%|██▌ | 1269/5000 [10:32:19<29:57:39, 28.91s/it] 25%|██▌ | 1270/5000 [10:32:47<29:37:03, 28.59s/it] 25%|██▌ | 1271/5000 [10:33:14<29:16:45, 28.27s/it] 25%|██▌ | 1272/5000 [10:33:41<28:57:17, 27.96s/it] 25%|██▌ | 1273/5000 [10:34:11<29:25:01, 28.41s/it] 25%|██▌ | 1274/5000 [10:34:38<29:04:30, 28.09s/it] 26%|██▌ | 1275/5000 [10:35:05<28:48:22, 27.84s/it] 26%|██▌ | 1275/5000 [10:35:05<28:48:22, 27.84s/it] 26%|██▌ | 1276/5000 [10:35:35<29:21:57, 28.39s/it] 26%|██▌ | 1277/5000 [10:36:02<29:00:15, 28.05s/it] 26%|██▌ | 1278/5000 [10:36:29<28:42:16, 27.76s/it] 26%|██▌ | 1279/5000 [10:37:01<29:54:01, 28.93s/it] 26%|██▌ | 1280/5000 [10:37:28<29:21:26, 28.41s/it] 26%|██▌ | 1281/5000 [10:37:56<28:59:06, 28.06s/it] 26%|██▌ | 1282/5000 [10:38:24<28:58:21, 28.05s/it] 26%|██▌ | 1283/5000 [10:38:52<29:02:29, 28.13s/it] 26%|██▌ | 1284/5000 [10:39:19<28:46:09, 27.87s/it] 26%|██▌ | 1285/5000 [10:39:46<28:25:42, 27.55s/it] 26%|██▌ | 1286/5000 [10:40:14<28:31:23, 27.65s/it] 26%|██▌ | 1287/5000 [10:40:41<28:24:06, 27.54s/it] 26%|██▌ | 1288/5000 [10:41:11<28:59:54, 28.12s/it] 26%|██▌ | 1289/5000 [10:41:38<28:53:49, 28.03s/it] 26%|██▌ | 1290/5000 [10:42:06<28:38:34, 27.79s/it] 26%|██▌ | 1291/5000 [10:42:34<28:48:10, 27.96s/it] 26%|██▌ | 1292/5000 [10:43:02<28:48:21, 27.97s/it] 26%|██▌ | 1293/5000 [10:43:29<28:36:59, 27.79s/it] 26%|██▌ | 1294/5000 [10:43:58<28:51:53, 28.04s/it] 26%|██▌ | 1295/5000 [10:44:25<28:38:48, 27.84s/it] 26%|██▌ | 1296/5000 [10:44:53<28:29:34, 27.69s/it] 26%|██▌ | 1297/5000 [10:45:22<28:57:55, 28.16s/it] 26%|██▌ | 1298/5000 [10:45:49<28:43:09, 27.93s/it] 26%|██▌ | 1299/5000 [10:46:17<28:38:13, 27.86s/it] 26%|██▌ | 1300/5000 [10:46:45<28:46:40, 28.00s/it] 26%|██▌ | 1300/5000 [10:46:45<28:46:40, 28.00s/it] 26%|██▌ | 1301/5000 [10:47:12<28:29:08, 27.72s/it] 26%|██▌ | 1302/5000 [10:47:40<28:18:07, 27.55s/it] 26%|██▌ | 1303/5000 [10:48:09<28:49:19, 28.07s/it] 26%|██▌ | 1304/5000 [10:48:31<27:00:51, 26.31s/it] 26%|██▌ | 1305/5000 [10:48:42<22:15:13, 21.68s/it] 26%|██▌ | 1306/5000 [10:48:53<18:52:30, 18.39s/it] 26%|██▌ | 1307/5000 [10:49:04<16:33:11, 16.14s/it] 26%|██▌ | 1308/5000 [10:49:12<14:02:21, 13.69s/it]{'loss': 0.0321, 'learning_rate': 8.560000000000001e-06, 'epoch': 7.0} -{'loss': 0.0312, 'learning_rate': 8.504444444444445e-06, 'epoch': 7.01} -{'loss': 0.0309, 'learning_rate': 8.448888888888889e-06, 'epoch': 7.01} -{'loss': 0.0235, 'learning_rate': 8.393333333333335e-06, 'epoch': 7.02} -{'loss': 0.0225, 'learning_rate': 8.337777777777777e-06, 'epoch': 7.02} -{'loss': 0.0255, 'learning_rate': 8.282222222222223e-06, 'epoch': 7.03} -{'loss': 0.0221, 'learning_rate': 8.226666666666667e-06, 'epoch': 7.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.02it/s] - Reading metadata...: 15160it [00:01, 19331.91it/s] - Reading metadata...: 24077it [00:01, 19421.87it/s] Reading metadata...: 28043it [00:01, 17982.36it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.02it/s] Reading metadata...: 10438it [00:00, 26165.49it/s] - 26%|██▌ | 1309/5000 [10:50:51<40:30:13, 39.51s/it] 26%|██▌ | 1310/5000 [10:51:19<36:51:28, 35.96s/it] 26%|██▌ | 1311/5000 [10:51:46<34:15:18, 33.43s/it] 26%|██▌ | 1312/5000 [10:52:15<32:48:56, 32.03s/it] 26%|██▋ | 1313/5000 [10:52:44<31:42:44, 30.96s/it] 26%|██▋ | 1314/5000 [10:53:12<30:44:16, 30.02s/it] 26%|██▋ | 1315/5000 [10:53:38<29:47:00, 29.10s/it] 26%|██▋ | 1316/5000 [10:54:07<29:30:34, 28.84s/it] 26%|██▋ | 1317/5000 [10:54:35<29:23:11, 28.72s/it] 26%|██▋ | 1318/5000 [10:55:02<28:47:46, 28.15s/it] 26%|██▋ | 1319/5000 [10:55:29<28:34:03, 27.94s/it] 26%|██▋ | 1320/5000 [10:55:57<28:19:25, 27.71s/it] 26%|██▋ | 1321/5000 [10:56:24<28:13:39, 27.62s/it] 26%|██▋ | 1322/5000 [10:56:52<28:27:31, 27.86s/it] 26%|██▋ | 1323/5000 [10:57:20<28:20:03, 27.74s/it] 26%|██▋ | 1324/5000 [10:57:48<28:34:52, 27.99s/it] 26%|██▋ | 1325/5000 [10:58:18<29:02:53, 28.46s/it] 26%|██▋ | 1325/5000 [10:58:18<29:02:53, 28.46s/it] 27%|██▋ | 1326/5000 [10:58:45<28:42:25, 28.13s/it] 27%|██▋ | 1327/5000 [10:59:14<28:55:53, 28.36s/it] 27%|██▋ | 1328/5000 [10:59:42<28:36:24, 28.05s/it] 27%|██▋ | 1329/5000 [11:00:09<28:20:46, 27.80s/it] 27%|██▋ | 1330/5000 [11:00:37<28:19:44, 27.79s/it] 27%|██▋ | 1331/5000 [11:01:04<28:12:05, 27.67s/it] 27%|██▋ | 1332/5000 [11:01:31<27:58:19, 27.45s/it] 27%|██▋ | 1333/5000 [11:02:00<28:22:16, 27.85s/it] 27%|██▋ | 1334/5000 [11:02:27<28:12:17, 27.70s/it] 27%|██▋ | 1335/5000 [11:02:54<28:02:03, 27.54s/it] 27%|██▋ | 1336/5000 [11:03:23<28:19:08, 27.82s/it] 27%|██▋ | 1337/5000 [11:03:50<28:14:55, 27.76s/it] 27%|██▋ | 1338/5000 [11:04:18<28:08:07, 27.66s/it] 27%|██▋ | 1339/5000 [11:04:46<28:27:51, 27.99s/it] 27%|██▋ | 1340/5000 [11:05:14<28:17:34, 27.83s/it] 27%|██▋ | 1341/5000 [11:05:41<28:04:00, 27.61s/it] 27%|██▋ | 1342/5000 [11:06:11<28:41:41, 28.24s/it] 27%|██▋ | 1343/5000 [11:06:37<28:07:48, 27.69s/it] 27%|██▋ | 1344/5000 [11:07:04<27:55:34, 27.50s/it] 27%|██▋ | 1345/5000 [11:07:33<28:16:45, 27.85s/it] 27%|██▋ | 1346/5000 [11:08:00<28:10:19, 27.76s/it] 27%|██▋ | 1347/5000 [11:08:28<27:58:30, 27.57s/it] 27%|██▋ | 1348/5000 [11:08:57<28:30:17, 28.10s/it] 27%|██▋ | 1349/5000 [11:09:24<28:12:24, 27.81s/it] 27%|██▋ | 1350/5000 [11:09:55<29:06:48, 28.71s/it] 27%|██▋ | 1350/5000 [11:09:55<29:06:48, 28.71s/it] 27%|██▋ | 1351/5000 [11:10:24<29:08:35, 28.75s/it] 27%|██▋ | 1352/5000 [11:10:51<28:39:20, 28.28s/it] 27%|██▋ | 1353/5000 [11:11:24<29:59:24, 29.60s/it] 27%|██▋ | 1354/5000 [11:11:51<29:19:51, 28.96s/it] 27%|██▋ | 1355/5000 [11:12:18<28:48:42, 28.46s/it] 27%|██▋ | 1356/5000 [11:12:46<28:43:07, 28.37s/it] 27%|██▋ | 1357/5000 [11:13:14<28:23:55, 28.06s/it] 27%|██▋ | 1358/5000 [11:13:41<28:15:04, 27.93s/it] 27%|██▋ | 1359/5000 [11:14:09<28:17:31, 27.97s/it] 27%|██▋ | 1360/5000 [11:14:37<28:05:50, 27.79s/it] 27%|██▋ | 1361/5000 [11:15:05<28:16:14, 27.97s/it] 27%|██▋ | 1362/5000 [11:15:33<28:04:12, 27.78s/it] 27%|██▋ | 1363/5000 [11:16:00<27:57:20, 27.67s/it] 27%|██▋ | 1364/5000 [11:16:29<28:24:49, 28.13s/it] 27%|██▋ | 1365/5000 [11:16:56<28:03:22, 27.79s/it] 27%|██▋ | 1366/5000 [11:17:23<27:53:22, 27.63s/it] 27%|██▋ | 1367/5000 [11:17:52<28:03:10, 27.80s/it] 27%|██▋ | 1368/5000 [11:18:18<27:42:37, 27.47s/it] 27%|██▋ | 1369/5000 [11:18:45<27:30:31, 27.27s/it] 27%|██▋ | 1370/5000 [11:19:15<28:13:04, 27.98s/it] 27%|██▋ | 1371/5000 [11:19:42<27:57:43, 27.74s/it] 27%|██▋ | 1372/5000 [11:20:08<27:32:56, 27.34s/it] 27%|██▋ | 1373/5000 [11:20:38<28:06:40, 27.90s/it] 27%|██▋ | 1374/5000 [11:21:05<27:52:56, 27.68s/it] 28%|██▊ | 1375/5000 [11:21:33<28:04:21, 27.88s/it] 28%|██▊ | 1375/5000 [11:21:33<28:04:21, 27.88s/it] 28%|██▊ | 1376/5000 [11:22:01<28:08:49, 27.96s/it] 28%|██▊ | 1377/5000 [11:22:29<27:59:07, 27.81s/it] 28%|██▊ | 1378/5000 [11:22:57<28:08:09, 27.96s/it] 28%|██▊ | 1379/5000 [11:23:24<27:54:55, 27.75s/it] 28%|██▊ | 1380/5000 [11:23:52<27:58:23, 27.82s/it] 28%|██▊ | 1381/5000 [11:24:20<28:04:00, 27.92s/it] 28%|██▊ | 1382/5000 [11:24:47<27:48:29, 27.67s/it] 28%|██▊ | 1383/5000 [11:25:15<27:44:58, 27.62s/it] 28%|██▊ | 1384/5000 [11:25:42<27:26:25, 27.32s/it] 28%|██▊ | 1385/5000 [11:26:09<27:23:13, 27.27s/it] 28%|██▊ | 1386/5000 [11:26:37<27:44:26, 27.63s/it] 28%|██▊ | 1387/5000 [11:27:05<27:50:53, 27.75s/it] 28%|██▊ | 1388/5000 [11:27:32<27:35:04, 27.49s/it] 28%|██▊ | 1389/5000 [11:28:00<27:46:04, 27.68s/it] 28%|██▊ | 1390/5000 [11:28:29<27:59:32, 27.91s/it] 28%|██▊ | 1391/5000 [11:28:56<27:47:18, 27.72s/it] 28%|██▊ | 1392/5000 [11:29:24<27:54:20, 27.84s/it] 28%|██▊ | 1393/5000 [11:29:52<27:55:22, 27.87s/it] 28%|██▊ | 1394/5000 [11:30:21<28:13:02, 28.17s/it] 28%|██▊ | 1395/5000 [11:30:48<27:51:33, 27.82s/it] 28%|██▊ | 1396/5000 [11:31:16<27:58:08, 27.94s/it] 28%|██▊ | 1397/5000 [11:31:45<28:12:19, 28.18s/it] 28%|██▊ | 1398/5000 [11:32:12<27:57:18, 27.94s/it] 28%|██▊ | 1399/5000 [11:32:41<28:02:08, 28.03s/it] 28%|██▊ | 1400/5000 [11:33:09<28:05:10, 28.09s/it] 28%|██▊ | 1400/5000 [11:33:09<28:05:10, 28.09s/it] 28%|██▊ | 1401/5000 [11:33:36<27:53:26, 27.90s/it] 28%|██▊ | 1402/5000 [11:34:05<28:02:49, 28.06s/it] 28%|██▊ | 1403/5000 [11:34:33<28:06:52, 28.14s/it] 28%|██▊ | 1404/5000 [11:35:01<27:55:53, 27.96s/it] 28%|██▊ | 1405/5000 [11:35:29<28:01:31, 28.06s/it] 28%|██▊ | 1406/5000 [11:35:57<28:04:24, 28.12s/it] 28%|██▊ | 1407/5000 [11:36:24<27:51:24, 27.91s/it] 28%|██▊ | 1408/5000 [11:36:52<27:49:08, 27.88s/it] 28%|██▊ | 1409/5000 [11:37:21<28:01:06, 28.09s/it] 28%|██▊ | 1410/5000 [11:37:49<27:53:02, 27.96s/it] 28%|██▊ | 1411/5000 [11:38:18<28:12:46, 28.30s/it] 28%|██▊ | 1412/5000 [11:38:45<27:53:21, 27.98s/it] 28%|██▊ | 1413/5000 [11:39:12<27:34:11, 27.67s/it] 28%|██▊ | 1414/5000 [11:39:41<28:00:46, 28.12s/it] 28%|██▊ | 1415/5000 [11:40:08<27:41:46, 27.81s/it] 28%|██▊ | 1416/5000 [11:40:35<27:26:29, 27.56s/it] 28%|██▊ | 1417/5000 [11:41:03<27:28:07, 27.60s/it] 28%|██▊ | 1418/5000 [11:41:31<27:36:52, 27.75s/it] 28%|██▊ | 1419/5000 [11:41:58<27:30:02, 27.65s/it] 28%|██▊ | 1420/5000 [11:42:27<27:40:21, 27.83s/it] 28%|██▊ | 1421/5000 [11:42:55<27:45:15, 27.92s/it] 28%|██▊ | 1422/5000 [11:43:22<27:34:57, 27.75s/it] 28%|██▊ | 1423/5000 [11:43:50<27:44:26, 27.92s/it] 28%|██▊ | 1424/5000 [11:44:18<27:42:26, 27.89s/it] 28%|██▊ | 1425/5000 [11:44:46<27:43:38, 27.92s/it] 28%|██▊ | 1425/5000 [11:44:46<27:43:38, 27.92s/it] 29%|██▊ | 1426/5000 [11:45:14<27:33:33, 27.76s/it] 29%|██▊ | 1427/5000 [11:45:43<27:55:02, 28.13s/it] 29%|██▊ | 1428/5000 [11:46:10<27:38:56, 27.87s/it] 29%|██▊ | 1429/5000 [11:46:37<27:22:36, 27.60s/it] 29%|██▊ | 1430/5000 [11:47:05<27:38:14, 27.87s/it] 29%|██▊ | 1431/5000 [11:47:32<27:24:41, 27.65s/it] 29%|██▊ | 1432/5000 [11:48:00<27:15:12, 27.50s/it] 29%|██▊ | 1433/5000 [11:48:32<28:37:24, 28.89s/it] 29%|██▊ | 1434/5000 [11:48:59<28:09:46, 28.43s/it] 29%|██▊ | 1435/5000 [11:49:26<27:50:08, 28.11s/it] 29%|██▊ | 1436/5000 [11:49:55<27:58:10, 28.25s/it] 29%|██▊ | 1437/5000 [11:50:22<27:38:38, 27.93s/it] 29%|██▉ | 1438/5000 [11:50:49<27:26:56, 27.74s/it] 29%|██▉ | 1439/5000 [11:51:17<27:18:33, 27.61s/it] 29%|██▉ | 1440/5000 [11:51:47<28:03:57, 28.38s/it] 29%|██▉ | 1441/5000 [11:52:14<27:49:17, 28.14s/it] 29%|██▉ | 1442/5000 [11:52:42<27:39:29, 27.98s/it] 29%|██▉ | 1443/5000 [11:53:11<27:51:56, 28.20s/it] 29%|██▉ | 1444/5000 [11:53:38<27:39:04, 27.99s/it] 29%|██▉ | 1445/5000 [11:54:05<27:18:37, 27.66s/it] 29%|██▉ | 1446/5000 [11:54:35<28:01:38, 28.39s/it] 29%|██▉ | 1447/5000 [11:55:02<27:38:57, 28.02s/it] 29%|██▉ | 1448/5000 [11:55:30<27:21:35, 27.73s/it] 29%|██▉ | 1449/5000 [11:55:59<27:53:39, 28.28s/it] 29%|██▉ | 1450/5000 [11:56:27<27:40:17, 28.06s/it] 29%|██▉ | 1450/5000 [11:56:27<27:40:17, 28.06s/it] 29%|██▉ | 1451/5000 [11:56:54<27:26:28, 27.84s/it] 29%|██▉ | 1452/5000 [11:57:23<27:48:44, 28.22s/it] 29%|██▉ | 1453/5000 [11:57:50<27:30:27, 27.92s/it] 29%|██▉ | 1454/5000 [11:58:16<26:58:29, 27.39s/it] 29%|██▉ | 1455/5000 [11:58:46<27:28:33, 27.90s/it] 29%|██▉ | 1456/5000 [11:59:13<27:13:41, 27.66s/it] 29%|██▉ | 1457/5000 [11:59:40<27:05:51, 27.53s/it] 29%|██▉ | 1458/5000 [12:00:09<27:32:16, 27.99s/it] 29%|██▉ | 1459/5000 [12:00:36<27:17:05, 27.74s/it] 29%|██▉ | 1460/5000 [12:01:04<27:11:50, 27.66s/it] 29%|██▉ | 1461/5000 [12:01:32<27:30:47, 27.99s/it] 29%|██▉ | 1462/5000 [12:02:00<27:19:06, 27.80s/it] 29%|██▉ | 1463/5000 [12:02:27<27:11:13, 27.67s/it] 29%|██▉ | 1464/5000 [12:02:57<27:43:10, 28.22s/it] 29%|██▉ | 1465/5000 [12:03:24<27:28:50, 27.99s/it] 29%|██▉ | 1466/5000 [12:03:51<27:17:06, 27.79s/it] 29%|██▉ | 1467/5000 [12:04:21<27:47:06, 28.31s/it] 29%|██▉ | 1468/5000 [12:04:35<23:32:33, 24.00s/it] 29%|██▉ | 1469/5000 [12:04:45<19:37:47, 20.01s/it] 29%|██▉ | 1470/5000 [12:04:56<16:57:46, 17.30s/it] 29%|██▉ | 1471/5000 [12:05:07<15:02:59, 15.35s/it]{'loss': 0.0189, 'learning_rate': 8.171111111111113e-06, 'epoch': 8.0} -{'loss': 0.0201, 'learning_rate': 8.115555555555557e-06, 'epoch': 8.01} -{'loss': 0.0182, 'learning_rate': 8.06e-06, 'epoch': 8.01} -{'loss': 0.013, 'learning_rate': 8.004444444444445e-06, 'epoch': 8.02} -{'loss': 0.0148, 'learning_rate': 7.948888888888889e-06, 'epoch': 8.02} -{'loss': 0.016, 'learning_rate': 7.893333333333335e-06, 'epoch': 8.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.09it/s] - Reading metadata...: 14729it [00:01, 19892.17it/s] - Reading metadata...: 23393it [00:02, 12147.21it/s] Reading metadata...: 28043it [00:02, 13424.59it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.07it/s] Reading metadata...: 10438it [00:00, 26428.08it/s] - 29%|██▉ | 1472/5000 [12:06:37<36:46:56, 37.53s/it] 29%|██▉ | 1473/5000 [12:07:05<34:05:45, 34.80s/it] 29%|██▉ | 1474/5000 [12:07:33<32:09:36, 32.83s/it] 30%|██▉ | 1475/5000 [12:08:01<30:35:51, 31.25s/it] 30%|██▉ | 1475/5000 [12:08:01<30:35:51, 31.25s/it] 30%|██▉ | 1476/5000 [12:08:27<29:14:42, 29.88s/it] 30%|██▉ | 1477/5000 [12:08:56<28:45:55, 29.39s/it] 30%|██▉ | 1478/5000 [12:09:24<28:32:11, 29.17s/it] 30%|██▉ | 1479/5000 [12:09:53<28:20:02, 28.97s/it] 30%|██▉ | 1480/5000 [12:10:21<28:00:31, 28.65s/it] 30%|██▉ | 1481/5000 [12:10:48<27:27:23, 28.09s/it] 30%|██▉ | 1482/5000 [12:11:16<27:26:09, 28.08s/it] 30%|██▉ | 1483/5000 [12:11:44<27:37:15, 28.27s/it] 30%|██▉ | 1484/5000 [12:12:12<27:25:44, 28.08s/it] 30%|██▉ | 1485/5000 [12:12:40<27:27:43, 28.13s/it] 30%|██▉ | 1486/5000 [12:13:08<27:29:56, 28.17s/it] 30%|██▉ | 1487/5000 [12:13:37<27:34:55, 28.27s/it] 30%|██▉ | 1488/5000 [12:14:05<27:37:15, 28.31s/it] 30%|██▉ | 1489/5000 [12:14:33<27:21:52, 28.06s/it] 30%|██▉ | 1490/5000 [12:15:06<28:46:38, 29.52s/it] 30%|██▉ | 1491/5000 [12:15:35<28:49:28, 29.57s/it] 30%|██▉ | 1492/5000 [12:16:03<28:10:52, 28.92s/it] 30%|██▉ | 1493/5000 [12:16:31<28:03:07, 28.80s/it] 30%|██▉ | 1494/5000 [12:17:00<27:58:07, 28.72s/it] 30%|██▉ | 1495/5000 [12:17:27<27:30:58, 28.26s/it] 30%|██▉ | 1496/5000 [12:17:56<27:39:50, 28.42s/it] 30%|██▉ | 1497/5000 [12:18:24<27:28:43, 28.24s/it] 30%|██▉ | 1498/5000 [12:18:51<27:10:42, 27.94s/it] 30%|██▉ | 1499/5000 [12:19:20<27:21:26, 28.13s/it] 30%|███ | 1500/5000 [12:19:47<27:11:41, 27.97s/it] 30%|███ | 1500/5000 [12:19:47<27:11:41, 27.97s/it] 30%|███ | 1501/5000 [12:20:15<27:01:40, 27.81s/it] 30%|███ | 1502/5000 [12:20:43<27:12:26, 28.00s/it] 30%|███ | 1503/5000 [12:21:11<27:04:51, 27.88s/it] 30%|███ | 1504/5000 [12:21:38<26:58:32, 27.78s/it] 30%|███ | 1505/5000 [12:22:07<27:24:25, 28.23s/it] 30%|███ | 1506/5000 [12:22:35<27:07:09, 27.94s/it] 30%|███ | 1507/5000 [12:23:02<26:52:11, 27.69s/it] 30%|███ | 1508/5000 [12:23:30<27:08:51, 27.99s/it] 30%|███ | 1509/5000 [12:23:59<27:13:40, 28.08s/it] 30%|███ | 1510/5000 [12:24:26<27:06:58, 27.97s/it] 30%|███ | 1511/5000 [12:24:55<27:21:39, 28.23s/it] 30%|███ | 1512/5000 [12:25:24<27:23:35, 28.27s/it] 30%|███ | 1513/5000 [12:25:50<26:56:58, 27.82s/it] 30%|███ | 1514/5000 [12:26:19<27:08:41, 28.03s/it] 30%|███ | 1515/5000 [12:26:47<27:14:18, 28.14s/it] 30%|███ | 1516/5000 [12:27:14<26:55:57, 27.83s/it] 30%|███ | 1517/5000 [12:27:43<27:07:38, 28.04s/it] 30%|███ | 1518/5000 [12:28:11<27:02:39, 27.96s/it] 30%|███ | 1519/5000 [12:28:38<26:54:32, 27.83s/it] 30%|███ | 1520/5000 [12:29:06<26:44:12, 27.66s/it] 30%|███ | 1521/5000 [12:29:33<26:39:53, 27.59s/it] 30%|███ | 1522/5000 [12:30:03<27:21:36, 28.32s/it] 30%|███ | 1523/5000 [12:30:31<27:07:24, 28.08s/it] 30%|███ | 1524/5000 [12:31:04<28:34:47, 29.60s/it] 30%|███ | 1525/5000 [12:31:31<27:52:56, 28.89s/it] 30%|███ | 1525/5000 [12:31:31<27:52:56, 28.89s/it] 31%|███ | 1526/5000 [12:31:57<27:01:16, 28.00s/it] 31%|███ | 1527/5000 [12:32:25<27:06:31, 28.10s/it] 31%|███ | 1528/5000 [12:32:53<26:54:47, 27.91s/it] 31%|███ | 1529/5000 [12:33:20<26:42:00, 27.69s/it] 31%|███ | 1530/5000 [12:33:49<26:59:04, 28.00s/it] 31%|███ | 1531/5000 [12:34:16<26:44:41, 27.75s/it] 31%|███ | 1532/5000 [12:34:43<26:36:35, 27.62s/it] 31%|███ | 1533/5000 [12:35:12<27:00:56, 28.05s/it] 31%|███ | 1534/5000 [12:35:39<26:46:28, 27.81s/it] 31%|███ | 1535/5000 [12:36:06<26:34:27, 27.61s/it] 31%|███ | 1536/5000 [12:36:35<26:47:15, 27.84s/it] 31%|███ | 1537/5000 [12:37:03<26:48:11, 27.86s/it] 31%|███ | 1538/5000 [12:37:30<26:33:13, 27.61s/it] 31%|███ | 1539/5000 [12:37:58<26:36:55, 27.68s/it] 31%|███ | 1540/5000 [12:38:26<26:50:03, 27.92s/it] 31%|███ | 1541/5000 [12:38:54<26:41:16, 27.78s/it] 31%|███ | 1542/5000 [12:39:27<28:19:05, 29.48s/it] 31%|███ | 1543/5000 [12:39:55<27:53:20, 29.04s/it] 31%|███ | 1544/5000 [12:40:22<27:22:52, 28.52s/it] 31%|███ | 1545/5000 [12:40:52<27:50:04, 29.00s/it] 31%|███ | 1546/5000 [12:41:21<27:36:28, 28.77s/it] 31%|███ | 1547/5000 [12:41:49<27:32:42, 28.72s/it] 31%|███ | 1548/5000 [12:42:17<27:12:32, 28.38s/it] 31%|███ | 1549/5000 [12:42:45<27:06:36, 28.28s/it] 31%|███ | 1550/5000 [12:43:13<27:03:45, 28.24s/it] 31%|███ | 1550/5000 [12:43:13<27:03:45, 28.24s/it] 31%|███ | 1551/5000 [12:43:40<26:46:01, 27.94s/it] 31%|███ | 1552/5000 [12:44:09<26:51:27, 28.04s/it] 31%|███ | 1553/5000 [12:44:36<26:46:02, 27.96s/it] 31%|███ | 1554/5000 [12:45:04<26:33:26, 27.74s/it] 31%|███ | 1555/5000 [12:45:31<26:30:35, 27.70s/it] 31%|███ | 1556/5000 [12:46:00<26:48:06, 28.02s/it] 31%|███ | 1557/5000 [12:46:27<26:37:19, 27.84s/it] 31%|███ | 1558/5000 [12:46:56<26:44:03, 27.96s/it] 31%|███ | 1559/5000 [12:47:24<26:44:24, 27.98s/it] 31%|███ | 1560/5000 [12:47:51<26:32:17, 27.77s/it] 31%|███ | 1561/5000 [12:48:19<26:35:55, 27.84s/it] 31%|███ | 1562/5000 [12:48:47<26:45:43, 28.02s/it] 31%|███▏ | 1563/5000 [12:49:15<26:36:00, 27.86s/it] 31%|███▏ | 1564/5000 [12:49:43<26:47:23, 28.07s/it] 31%|███▏ | 1565/5000 [12:50:11<26:30:26, 27.78s/it] 31%|███▏ | 1566/5000 [12:50:37<26:06:30, 27.37s/it] 31%|███▏ | 1567/5000 [12:51:05<26:15:14, 27.53s/it] 31%|███▏ | 1568/5000 [12:51:33<26:32:55, 27.85s/it] 31%|███▏ | 1569/5000 [12:52:01<26:22:45, 27.68s/it] 31%|███▏ | 1570/5000 [12:52:29<26:29:00, 27.80s/it] 31%|███▏ | 1571/5000 [12:52:57<26:42:31, 28.04s/it] 31%|███▏ | 1572/5000 [12:53:26<26:44:39, 28.09s/it] 31%|███▏ | 1573/5000 [12:53:53<26:33:34, 27.90s/it] 31%|███▏ | 1574/5000 [12:54:23<26:59:56, 28.37s/it] 32%|███▏ | 1575/5000 [12:54:51<26:59:30, 28.37s/it] 32%|███▏ | 1575/5000 [12:54:51<26:59:30, 28.37s/it] 32%|███▏ | 1576/5000 [12:55:18<26:38:35, 28.01s/it] 32%|███▏ | 1577/5000 [12:55:45<26:17:00, 27.64s/it] 32%|███▏ | 1578/5000 [12:56:13<26:30:11, 27.88s/it] 32%|███▏ | 1579/5000 [12:56:40<26:16:59, 27.66s/it] 32%|███▏ | 1580/5000 [12:57:07<26:06:31, 27.48s/it] 32%|███▏ | 1581/5000 [12:57:37<26:43:35, 28.14s/it] 32%|███▏ | 1582/5000 [12:58:04<26:24:12, 27.81s/it] 32%|███▏ | 1583/5000 [12:58:31<26:08:29, 27.54s/it] 32%|███▏ | 1584/5000 [12:59:00<26:33:22, 27.99s/it] 32%|███▏ | 1585/5000 [12:59:27<26:14:21, 27.66s/it] 32%|███▏ | 1586/5000 [12:59:55<26:17:01, 27.72s/it] 32%|███▏ | 1587/5000 [13:00:27<27:34:23, 29.08s/it] 32%|███▏ | 1588/5000 [13:00:55<27:15:15, 28.76s/it] 32%|███▏ | 1589/5000 [13:01:23<26:51:00, 28.34s/it] 32%|███▏ | 1590/5000 [13:01:51<26:58:44, 28.48s/it] 32%|███▏ | 1591/5000 [13:02:19<26:52:04, 28.37s/it] 32%|███▏ | 1592/5000 [13:02:47<26:29:16, 27.98s/it] 32%|███▏ | 1593/5000 [13:03:15<26:30:34, 28.01s/it] 32%|███▏ | 1594/5000 [13:03:43<26:33:39, 28.07s/it] 32%|███▏ | 1595/5000 [13:04:10<26:21:22, 27.87s/it] 32%|███▏ | 1596/5000 [13:04:38<26:27:24, 27.98s/it] 32%|███▏ | 1597/5000 [13:05:06<26:24:36, 27.94s/it] 32%|███▏ | 1598/5000 [13:05:34<26:16:14, 27.80s/it] 32%|███▏ | 1599/5000 [13:06:01<26:09:28, 27.69s/it] 32%|███▏ | 1600/5000 [13:06:30<26:27:03, 28.01s/it] 32%|███▏ | 1600/5000 [13:06:30<26:27:03, 28.01s/it] 32%|███▏ | 1601/5000 [13:06:56<26:00:03, 27.54s/it] 32%|███▏ | 1602/5000 [13:07:24<25:56:00, 27.48s/it] 32%|███▏ | 1603/5000 [13:07:53<26:30:08, 28.09s/it] 32%|███▏ | 1604/5000 [13:08:21<26:18:15, 27.88s/it] 32%|███▏ | 1605/5000 [13:08:47<25:57:29, 27.53s/it] 32%|███▏ | 1606/5000 [13:09:17<26:27:58, 28.07s/it] 32%|███▏ | 1607/5000 [13:09:44<26:12:10, 27.80s/it] 32%|███▏ | 1608/5000 [13:10:11<26:03:09, 27.65s/it] 32%|███▏ | 1609/5000 [13:10:39<26:07:40, 27.74s/it] 32%|███▏ | 1610/5000 [13:11:07<26:05:11, 27.70s/it] 32%|███▏ | 1611/5000 [13:11:34<25:53:08, 27.50s/it] 32%|███▏ | 1612/5000 [13:12:02<26:08:36, 27.78s/it] 32%|███▏ | 1613/5000 [13:12:30<26:17:08, 27.94s/it] 32%|███▏ | 1614/5000 [13:12:58<26:06:32, 27.76s/it] 32%|███▏ | 1615/5000 [13:13:26<26:15:27, 27.93s/it] 32%|███▏ | 1616/5000 [13:13:54<26:07:22, 27.79s/it] 32%|███▏ | 1617/5000 [13:14:21<25:58:13, 27.64s/it] 32%|███▏ | 1618/5000 [13:14:49<26:12:17, 27.89s/it] 32%|███▏ | 1619/5000 [13:15:18<26:19:24, 28.03s/it] 32%|███▏ | 1620/5000 [13:15:45<26:06:14, 27.80s/it] 32%|███▏ | 1621/5000 [13:16:15<26:36:44, 28.35s/it] 32%|███▏ | 1622/5000 [13:16:42<26:20:53, 28.08s/it] 32%|███▏ | 1623/5000 [13:17:09<26:08:41, 27.87s/it] 32%|███▏ | 1624/5000 [13:17:39<26:33:00, 28.31s/it] 32%|███▎ | 1625/5000 [13:18:05<26:04:53, 27.82s/it] 32%|███▎ | 1625/5000 [13:18:05<26:04:53, 27.82s/it] 33%|███▎ | 1626/5000 [13:18:32<25:39:43, 27.38s/it] 33%|███▎ | 1627/5000 [13:19:00<25:57:00, 27.70s/it] 33%|███▎ | 1628/5000 [13:19:28<26:02:38, 27.80s/it] 33%|███▎ | 1629/5000 [13:19:56<25:55:25, 27.68s/it] 33%|███▎ | 1630/5000 [13:20:25<26:13:16, 28.01s/it] 33%|███▎ | 1631/5000 [13:20:47<24:36:03, 26.29s/it] 33%|███▎ | 1632/5000 [13:20:58<20:14:27, 21.64s/it] 33%|███▎ | 1633/5000 [13:21:09<17:14:14, 18.43s/it] 33%|███▎ | 1634/5000 [13:21:19<15:06:12, 16.15s/it] 33%|███▎ | 1635/5000 [13:21:27<12:44:04, 13.62s/it]{'loss': 0.0138, 'learning_rate': 7.837777777777779e-06, 'epoch': 9.0} -{'loss': 0.0132, 'learning_rate': 7.782222222222223e-06, 'epoch': 9.01} -{'loss': 0.0128, 'learning_rate': 7.726666666666667e-06, 'epoch': 9.01} -{'loss': 0.0096, 'learning_rate': 7.67111111111111e-06, 'epoch': 9.02} -{'loss': 0.0085, 'learning_rate': 7.6155555555555564e-06, 'epoch': 9.02} -{'loss': 0.0093, 'learning_rate': 7.5600000000000005e-06, 'epoch': 9.03} -{'loss': 0.0108, 'learning_rate': 7.504444444444445e-06, 'epoch': 9.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.09it/s] - Reading metadata...: 14297it [00:01, 19335.87it/s] - Reading metadata...: 22707it [00:01, 13626.53it/s] Reading metadata...: 28043it [00:01, 14883.39it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.31it/s] Reading metadata...: 10438it [00:00, 27803.36it/s] - 33%|███▎ | 1636/5000 [13:23:09<37:25:31, 40.05s/it] 33%|███▎ | 1637/5000 [13:23:37<34:06:50, 36.52s/it] 33%|███▎ | 1638/5000 [13:24:04<31:28:36, 33.71s/it] 33%|███▎ | 1639/5000 [13:24:33<29:57:34, 32.09s/it] 33%|███▎ | 1640/5000 [13:25:01<28:52:57, 30.95s/it] 33%|███▎ | 1641/5000 [13:25:29<28:05:03, 30.10s/it] 33%|███▎ | 1642/5000 [13:25:56<27:21:45, 29.33s/it] 33%|███▎ | 1643/5000 [13:26:24<26:57:20, 28.91s/it] 33%|███▎ | 1644/5000 [13:26:53<26:45:01, 28.70s/it] 33%|███▎ | 1645/5000 [13:27:20<26:29:16, 28.42s/it] 33%|███▎ | 1646/5000 [13:27:48<26:09:44, 28.08s/it] 33%|███▎ | 1647/5000 [13:28:16<26:17:17, 28.22s/it] 33%|███▎ | 1648/5000 [13:28:44<26:07:09, 28.05s/it] 33%|███▎ | 1649/5000 [13:29:11<25:50:31, 27.76s/it] 33%|███▎ | 1650/5000 [13:29:38<25:39:58, 27.58s/it] 33%|███▎ | 1650/5000 [13:29:38<25:39:58, 27.58s/it] 33%|███▎ | 1651/5000 [13:30:05<25:34:33, 27.49s/it] 33%|███▎ | 1652/5000 [13:30:33<25:44:02, 27.67s/it] 33%|███▎ | 1653/5000 [13:31:01<25:33:44, 27.49s/it] 33%|███▎ | 1654/5000 [13:31:30<25:57:38, 27.93s/it] 33%|███▎ | 1655/5000 [13:31:57<25:45:05, 27.71s/it] 33%|███▎ | 1656/5000 [13:32:24<25:32:51, 27.50s/it] 33%|███▎ | 1657/5000 [13:32:52<25:47:19, 27.77s/it] 33%|███▎ | 1658/5000 [13:33:20<25:52:06, 27.87s/it] 33%|███▎ | 1659/5000 [13:33:47<25:39:52, 27.65s/it] 33%|███▎ | 1660/5000 [13:34:16<25:53:40, 27.91s/it] 33%|███▎ | 1661/5000 [13:34:43<25:42:34, 27.72s/it] 33%|███▎ | 1662/5000 [13:35:10<25:32:21, 27.54s/it] 33%|███▎ | 1663/5000 [13:35:38<25:30:18, 27.52s/it] 33%|███▎ | 1664/5000 [13:36:05<25:22:15, 27.38s/it] 33%|███▎ | 1665/5000 [13:36:31<25:09:22, 27.16s/it] 33%|███▎ | 1666/5000 [13:37:01<25:44:47, 27.80s/it] 33%|███▎ | 1667/5000 [13:37:28<25:32:31, 27.59s/it] 33%|███▎ | 1668/5000 [13:37:54<25:08:43, 27.17s/it] 33%|███▎ | 1669/5000 [13:38:23<25:31:37, 27.59s/it] 33%|███▎ | 1670/5000 [13:38:50<25:21:33, 27.42s/it] 33%|███▎ | 1671/5000 [13:39:16<25:09:14, 27.20s/it] 33%|███▎ | 1672/5000 [13:39:45<25:38:28, 27.74s/it] 33%|███▎ | 1673/5000 [13:40:12<25:15:14, 27.33s/it] 33%|███▎ | 1674/5000 [13:40:38<25:03:16, 27.12s/it] 34%|███▎ | 1675/5000 [13:41:06<25:19:32, 27.42s/it] 34%|███▎ | 1675/5000 [13:41:06<25:19:32, 27.42s/it] 34%|███▎ | 1676/5000 [13:41:33<25:12:57, 27.31s/it] 34%|███▎ | 1677/5000 [13:42:02<25:31:21, 27.65s/it] 34%|███▎ | 1678/5000 [13:42:30<25:30:24, 27.64s/it] 34%|███▎ | 1679/5000 [13:42:56<25:13:08, 27.34s/it] 34%|███▎ | 1680/5000 [13:43:25<25:45:10, 27.92s/it] 34%|███▎ | 1681/5000 [13:43:53<25:37:04, 27.79s/it] 34%|███▎ | 1682/5000 [13:44:21<25:43:44, 27.92s/it] 34%|███▎ | 1683/5000 [13:44:49<25:40:16, 27.86s/it] 34%|███▎ | 1684/5000 [13:45:16<25:27:47, 27.64s/it] 34%|███▎ | 1685/5000 [13:45:44<25:32:00, 27.73s/it] 34%|███▎ | 1686/5000 [13:46:12<25:29:49, 27.70s/it] 34%|███▎ | 1687/5000 [13:46:38<25:15:57, 27.45s/it] 34%|███▍ | 1688/5000 [13:47:07<25:26:03, 27.65s/it] 34%|███▍ | 1689/5000 [13:47:33<25:11:11, 27.38s/it] 34%|███▍ | 1690/5000 [13:48:01<25:09:34, 27.36s/it] 34%|███▍ | 1691/5000 [13:48:29<25:24:40, 27.65s/it] 34%|███▍ | 1692/5000 [13:48:56<25:16:12, 27.50s/it] 34%|███▍ | 1693/5000 [13:49:23<25:01:04, 27.23s/it] 34%|███▍ | 1694/5000 [13:49:51<25:22:41, 27.64s/it] 34%|███▍ | 1695/5000 [13:50:18<25:14:46, 27.50s/it] 34%|███▍ | 1696/5000 [13:50:46<25:10:07, 27.42s/it] 34%|███▍ | 1697/5000 [13:51:14<25:29:33, 27.78s/it] 34%|███▍ | 1698/5000 [13:51:41<25:18:17, 27.59s/it] 34%|███▍ | 1699/5000 [13:52:08<25:06:27, 27.38s/it] 34%|███▍ | 1700/5000 [13:52:38<25:50:17, 28.19s/it] 34%|███▍ | 1700/5000 [13:52:38<25:50:17, 28.19s/it] 34%|███▍ | 1701/5000 [13:53:04<25:13:16, 27.52s/it] 34%|███▍ | 1702/5000 [13:53:33<25:30:11, 27.84s/it] 34%|███▍ | 1703/5000 [13:54:01<25:37:22, 27.98s/it] 34%|███▍ | 1704/5000 [13:54:29<25:27:40, 27.81s/it] 34%|███▍ | 1705/5000 [13:54:57<25:42:19, 28.08s/it] 34%|███▍ | 1706/5000 [13:55:25<25:33:51, 27.94s/it] 34%|███▍ | 1707/5000 [13:55:53<25:33:44, 27.95s/it] 34%|███▍ | 1708/5000 [13:56:21<25:37:52, 28.03s/it] 34%|███▍ | 1709/5000 [13:56:48<25:20:10, 27.72s/it] 34%|███▍ | 1710/5000 [13:57:16<25:28:39, 27.88s/it] 34%|███▍ | 1711/5000 [13:57:44<25:21:54, 27.76s/it] 34%|███▍ | 1712/5000 [13:58:12<25:18:23, 27.71s/it] 34%|███▍ | 1713/5000 [13:58:40<25:30:41, 27.94s/it] 34%|███▍ | 1714/5000 [13:59:08<25:29:34, 27.93s/it] 34%|███▍ | 1715/5000 [13:59:35<25:15:18, 27.68s/it] 34%|███▍ | 1716/5000 [14:00:05<25:47:17, 28.27s/it] 34%|███▍ | 1717/5000 [14:00:34<25:57:15, 28.46s/it] 34%|███▍ | 1718/5000 [14:01:01<25:41:12, 28.18s/it] 34%|███▍ | 1719/5000 [14:01:30<25:45:47, 28.27s/it] 34%|███▍ | 1720/5000 [14:01:57<25:36:59, 28.12s/it] 34%|███▍ | 1721/5000 [14:02:30<26:45:27, 29.38s/it] 34%|███▍ | 1722/5000 [14:02:57<26:07:19, 28.69s/it] 34%|███▍ | 1723/5000 [14:03:29<27:06:41, 29.78s/it] 34%|███▍ | 1724/5000 [14:03:58<26:45:27, 29.40s/it] 34%|███▍ | 1725/5000 [14:04:25<26:15:06, 28.86s/it] 34%|███▍ | 1725/5000 [14:04:25<26:15:06, 28.86s/it] 35%|███▍ | 1726/5000 [14:04:53<25:57:25, 28.54s/it] 35%|███▍ | 1727/5000 [14:05:21<25:53:10, 28.47s/it] 35%|███▍ | 1728/5000 [14:05:49<25:34:32, 28.14s/it] 35%|███▍ | 1729/5000 [14:06:17<25:44:27, 28.33s/it] 35%|███▍ | 1730/5000 [14:06:46<25:41:59, 28.29s/it] 35%|███▍ | 1731/5000 [14:07:13<25:24:43, 27.99s/it] 35%|███▍ | 1732/5000 [14:07:41<25:34:15, 28.17s/it] 35%|███▍ | 1733/5000 [14:08:10<25:33:06, 28.16s/it] 35%|███▍ | 1734/5000 [14:08:37<25:20:07, 27.93s/it] 35%|███▍ | 1735/5000 [14:09:05<25:20:19, 27.94s/it] 35%|███▍ | 1736/5000 [14:09:33<25:25:28, 28.04s/it] 35%|███▍ | 1737/5000 [14:10:01<25:12:55, 27.82s/it] 35%|███▍ | 1738/5000 [14:10:30<25:42:46, 28.38s/it] 35%|███▍ | 1739/5000 [14:10:58<25:27:33, 28.11s/it] 35%|███▍ | 1740/5000 [14:11:25<25:16:29, 27.91s/it] 35%|███▍ | 1741/5000 [14:11:54<25:34:43, 28.26s/it] 35%|███▍ | 1742/5000 [14:12:21<25:15:11, 27.90s/it] 35%|███▍ | 1743/5000 [14:12:48<25:03:08, 27.69s/it] 35%|███▍ | 1744/5000 [14:13:17<25:16:42, 27.95s/it] 35%|███▍ | 1745/5000 [14:13:45<25:22:19, 28.06s/it] 35%|███▍ | 1746/5000 [14:14:13<25:08:41, 27.82s/it] 35%|███▍ | 1747/5000 [14:14:41<25:19:52, 28.03s/it] 35%|███▍ | 1748/5000 [14:15:08<25:05:57, 27.79s/it] 35%|███▍ | 1749/5000 [14:15:36<25:00:19, 27.69s/it] 35%|███▌ | 1750/5000 [14:16:09<26:21:11, 29.19s/it] 35%|███▌ | 1750/5000 [14:16:09<26:21:11, 29.19s/it] 35%|███▌ | 1751/5000 [14:16:39<26:42:55, 29.60s/it] 35%|███▌ | 1752/5000 [14:17:07<26:22:37, 29.24s/it] 35%|███▌ | 1753/5000 [14:17:34<25:45:51, 28.57s/it] 35%|███▌ | 1754/5000 [14:18:03<25:46:47, 28.59s/it] 35%|███▌ | 1755/5000 [14:18:31<25:26:59, 28.23s/it] 35%|███▌ | 1756/5000 [14:18:58<25:07:45, 27.89s/it] 35%|███▌ | 1757/5000 [14:19:27<25:31:09, 28.33s/it] 35%|███▌ | 1758/5000 [14:19:54<25:15:10, 28.04s/it] 35%|███▌ | 1759/5000 [14:20:21<24:59:00, 27.75s/it] 35%|███▌ | 1760/5000 [14:20:51<25:21:43, 28.18s/it] 35%|███▌ | 1761/5000 [14:21:18<25:06:13, 27.90s/it] 35%|███▌ | 1762/5000 [14:21:45<24:53:38, 27.68s/it] 35%|███▌ | 1763/5000 [14:22:19<26:32:47, 29.52s/it] 35%|███▌ | 1764/5000 [14:22:46<25:54:14, 28.82s/it] 35%|███▌ | 1765/5000 [14:23:13<25:23:46, 28.26s/it] 35%|███▌ | 1766/5000 [14:23:40<25:07:10, 27.96s/it] 35%|███▌ | 1767/5000 [14:24:09<25:19:26, 28.20s/it] 35%|███▌ | 1768/5000 [14:24:36<25:06:20, 27.96s/it] 35%|███▌ | 1769/5000 [14:25:03<24:50:11, 27.67s/it] 35%|███▌ | 1770/5000 [14:25:33<25:17:01, 28.18s/it] 35%|███▌ | 1771/5000 [14:26:00<24:59:39, 27.87s/it] 35%|███▌ | 1772/5000 [14:26:27<24:53:26, 27.76s/it] 35%|███▌ | 1773/5000 [14:26:56<25:13:41, 28.14s/it] 35%|███▌ | 1774/5000 [14:27:24<24:58:53, 27.88s/it] 36%|███▌ | 1775/5000 [14:27:51<24:48:36, 27.69s/it] 36%|███▌ | 1775/5000 [14:27:51<24:48:36, 27.69s/it] 36%|███▌ | 1776/5000 [14:28:19<24:56:20, 27.85s/it] 36%|███▌ | 1777/5000 [14:28:47<24:51:23, 27.76s/it] 36%|███▌ | 1778/5000 [14:29:14<24:42:01, 27.60s/it] 36%|███▌ | 1779/5000 [14:29:42<24:53:03, 27.81s/it] 36%|███▌ | 1780/5000 [14:30:10<24:48:58, 27.74s/it] 36%|███▌ | 1781/5000 [14:30:37<24:40:13, 27.59s/it] 36%|███▌ | 1782/5000 [14:31:07<25:12:30, 28.20s/it] 36%|███▌ | 1783/5000 [14:31:34<25:00:34, 27.99s/it] 36%|███▌ | 1784/5000 [14:32:02<24:50:43, 27.81s/it] 36%|███▌ | 1785/5000 [14:32:31<25:21:21, 28.39s/it] 36%|███▌ | 1786/5000 [14:32:59<25:05:46, 28.11s/it] 36%|███▌ | 1787/5000 [14:33:26<24:48:35, 27.80s/it] 36%|███▌ | 1788/5000 [14:33:54<24:49:08, 27.82s/it] 36%|███▌ | 1789/5000 [14:34:21<24:41:28, 27.68s/it] 36%|███▌ | 1790/5000 [14:34:48<24:32:55, 27.53s/it] 36%|███▌ | 1791/5000 [14:35:17<24:59:21, 28.03s/it] 36%|███▌ | 1792/5000 [14:35:45<24:48:49, 27.85s/it] 36%|███▌ | 1793/5000 [14:36:12<24:30:17, 27.51s/it] 36%|███▌ | 1794/5000 [14:36:41<24:54:35, 27.97s/it] 36%|███▌ | 1795/5000 [14:36:54<21:05:37, 23.69s/it] 36%|███▌ | 1796/5000 [14:37:05<17:37:54, 19.81s/it] 36%|███▌ | 1797/5000 [14:37:16<15:14:25, 17.13s/it] 36%|███▌ | 1798/5000 [14:37:27<13:32:16, 15.22s/it]{'loss': 0.0086, 'learning_rate': 7.44888888888889e-06, 'epoch': 10.0} -{'loss': 0.0085, 'learning_rate': 7.393333333333333e-06, 'epoch': 10.01} -{'loss': 0.0087, 'learning_rate': 7.337777777777778e-06, 'epoch': 10.01} -{'loss': 0.006, 'learning_rate': 7.282222222222222e-06, 'epoch': 10.02} -{'loss': 0.0064, 'learning_rate': 7.226666666666667e-06, 'epoch': 10.02} -{'loss': 0.0072, 'learning_rate': 7.171111111111112e-06, 'epoch': 10.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.19it/s] - Reading metadata...: 15185it [00:00, 22097.72it/s] - Reading metadata...: 24117it [00:01, 15316.75it/s] Reading metadata...: 28043it [00:01, 15924.27it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.26it/s] Reading metadata...: 10438it [00:00, 12100.29it/s] - 36%|███▌ | 1799/5000 [14:39:04<35:31:12, 39.95s/it] 36%|███▌ | 1800/5000 [14:39:33<32:23:23, 36.44s/it] 36%|███▌ | 1800/5000 [14:39:33<32:23:23, 36.44s/it] 36%|███▌ | 1801/5000 [14:40:01<30:07:58, 33.91s/it] 36%|███▌ | 1802/5000 [14:40:29<28:37:19, 32.22s/it] 36%|███▌ | 1803/5000 [14:40:56<27:13:59, 30.67s/it] 36%|███▌ | 1804/5000 [14:41:25<26:41:19, 30.06s/it] 36%|███▌ | 1805/5000 [14:41:52<26:05:36, 29.40s/it] 36%|███▌ | 1806/5000 [14:42:20<25:31:20, 28.77s/it] 36%|███▌ | 1807/5000 [14:42:48<25:20:18, 28.57s/it] 36%|███▌ | 1808/5000 [14:43:15<24:55:49, 28.12s/it] 36%|███▌ | 1809/5000 [14:43:43<24:54:39, 28.10s/it] 36%|███▌ | 1810/5000 [14:44:16<26:11:14, 29.55s/it] 36%|███▌ | 1811/5000 [14:44:43<25:37:31, 28.93s/it] 36%|███▌ | 1812/5000 [14:45:12<25:37:11, 28.93s/it] 36%|███▋ | 1813/5000 [14:45:41<25:31:39, 28.84s/it] 36%|███▋ | 1814/5000 [14:46:09<25:20:29, 28.63s/it] 36%|███▋ | 1815/5000 [14:46:37<25:07:30, 28.40s/it] 36%|███▋ | 1816/5000 [14:47:05<24:53:54, 28.15s/it] 36%|███▋ | 1817/5000 [14:47:32<24:45:59, 28.01s/it] 36%|███▋ | 1818/5000 [14:48:01<24:51:11, 28.12s/it] 36%|███▋ | 1819/5000 [14:48:28<24:40:39, 27.93s/it] 36%|███▋ | 1820/5000 [14:48:57<24:54:24, 28.20s/it] 36%|███▋ | 1821/5000 [14:49:25<24:52:56, 28.18s/it] 36%|███▋ | 1822/5000 [14:49:52<24:35:39, 27.86s/it] 36%|███▋ | 1823/5000 [14:50:20<24:37:45, 27.91s/it] 36%|███▋ | 1824/5000 [14:50:48<24:39:31, 27.95s/it] 36%|███▋ | 1825/5000 [14:51:15<24:28:15, 27.75s/it] 36%|███▋ | 1825/5000 [14:51:16<24:28:15, 27.75s/it] 37%|███▋ | 1826/5000 [14:51:44<24:45:45, 28.09s/it] 37%|███▋ | 1827/5000 [14:52:13<24:48:43, 28.15s/it] 37%|███▋ | 1828/5000 [14:52:40<24:32:10, 27.85s/it] 37%|███▋ | 1829/5000 [14:53:09<24:45:40, 28.11s/it] 37%|███▋ | 1830/5000 [14:53:35<24:20:58, 27.65s/it] 37%|███▋ | 1831/5000 [14:54:02<24:12:02, 27.49s/it] 37%|███▋ | 1832/5000 [14:54:31<24:38:40, 28.01s/it] 37%|███▋ | 1833/5000 [14:54:58<24:14:57, 27.56s/it] 37%|███▋ | 1834/5000 [14:55:25<24:03:56, 27.36s/it] 37%|███▋ | 1835/5000 [14:55:53<24:10:50, 27.50s/it] 37%|███▋ | 1836/5000 [14:56:20<24:14:11, 27.58s/it] 37%|███▋ | 1837/5000 [14:56:48<24:09:05, 27.49s/it] 37%|███▋ | 1838/5000 [14:57:16<24:17:08, 27.65s/it] 37%|███▋ | 1839/5000 [14:57:44<24:25:02, 27.81s/it] 37%|███▋ | 1840/5000 [14:58:11<24:18:52, 27.70s/it] 37%|███▋ | 1841/5000 [14:58:39<24:19:25, 27.72s/it] 37%|███▋ | 1842/5000 [14:59:07<24:26:37, 27.86s/it] 37%|███▋ | 1843/5000 [14:59:34<24:02:28, 27.41s/it] 37%|███▋ | 1844/5000 [15:00:02<24:08:51, 27.54s/it] 37%|███▋ | 1845/5000 [15:00:29<24:12:56, 27.63s/it] 37%|███▋ | 1846/5000 [15:00:59<24:39:11, 28.14s/it] 37%|███▋ | 1847/5000 [15:01:25<24:13:52, 27.67s/it] 37%|███▋ | 1848/5000 [15:01:52<24:03:48, 27.48s/it] 37%|███▋ | 1849/5000 [15:02:21<24:26:37, 27.93s/it] 37%|███▋ | 1850/5000 [15:02:48<24:08:51, 27.60s/it] 37%|███▋ | 1850/5000 [15:02:48<24:08:51, 27.60s/it] 37%|███▋ | 1851/5000 [15:03:16<24:18:32, 27.79s/it] 37%|███▋ | 1852/5000 [15:03:44<24:17:52, 27.79s/it] 37%|███▋ | 1853/5000 [15:04:11<23:58:03, 27.42s/it] 37%|███▋ | 1854/5000 [15:04:42<25:01:11, 28.63s/it] 37%|███▋ | 1855/5000 [15:05:10<24:48:46, 28.40s/it] 37%|███▋ | 1856/5000 [15:05:37<24:30:29, 28.06s/it] 37%|███▋ | 1857/5000 [15:06:07<24:49:58, 28.44s/it] 37%|███▋ | 1858/5000 [15:06:34<24:31:44, 28.10s/it] 37%|███▋ | 1859/5000 [15:07:01<24:12:28, 27.75s/it] 37%|███▋ | 1860/5000 [15:07:30<24:31:36, 28.12s/it] 37%|███▋ | 1861/5000 [15:07:57<24:20:04, 27.91s/it] 37%|███▋ | 1862/5000 [15:08:25<24:10:41, 27.74s/it] 37%|███▋ | 1863/5000 [15:08:53<24:25:45, 28.04s/it] 37%|███▋ | 1864/5000 [15:09:21<24:25:20, 28.04s/it] 37%|███▋ | 1865/5000 [15:09:49<24:11:48, 27.79s/it] 37%|███▋ | 1866/5000 [15:10:16<24:07:50, 27.72s/it] 37%|███▋ | 1867/5000 [15:10:44<24:08:44, 27.74s/it] 37%|███▋ | 1868/5000 [15:11:11<23:50:26, 27.40s/it] 37%|███▋ | 1869/5000 [15:11:40<24:19:09, 27.96s/it] 37%|███▋ | 1870/5000 [15:12:07<24:05:39, 27.71s/it] 37%|███▋ | 1871/5000 [15:12:34<23:57:34, 27.57s/it] 37%|███▋ | 1872/5000 [15:13:03<24:15:18, 27.92s/it] 37%|███▋ | 1873/5000 [15:13:35<25:25:58, 29.28s/it] 37%|███▋ | 1874/5000 [15:14:04<25:09:04, 28.97s/it] 38%|███▊ | 1875/5000 [15:14:31<24:36:48, 28.35s/it] 38%|███▊ | 1875/5000 [15:14:31<24:36:48, 28.35s/it] 38%|███▊ | 1876/5000 [15:14:59<24:32:58, 28.29s/it] 38%|███▊ | 1877/5000 [15:15:27<24:31:43, 28.28s/it] 38%|███▊ | 1878/5000 [15:15:54<24:18:21, 28.03s/it] 38%|███▊ | 1879/5000 [15:16:27<25:23:08, 29.28s/it] 38%|███▊ | 1880/5000 [15:16:55<25:07:16, 28.99s/it] 38%|███▊ | 1881/5000 [15:17:22<24:42:22, 28.52s/it] 38%|███▊ | 1882/5000 [15:17:51<24:43:18, 28.54s/it] 38%|███▊ | 1883/5000 [15:18:19<24:43:19, 28.55s/it] 38%|███▊ | 1884/5000 [15:18:47<24:27:07, 28.25s/it] 38%|███▊ | 1885/5000 [15:19:15<24:29:34, 28.31s/it] 38%|███▊ | 1886/5000 [15:19:44<24:30:25, 28.33s/it] 38%|███▊ | 1887/5000 [15:20:11<24:14:05, 28.03s/it] 38%|███▊ | 1888/5000 [15:20:39<24:18:14, 28.12s/it] 38%|███▊ | 1889/5000 [15:21:07<24:14:50, 28.06s/it] 38%|███▊ | 1890/5000 [15:21:35<24:06:48, 27.91s/it] 38%|███▊ | 1891/5000 [15:22:04<24:17:57, 28.14s/it] 38%|███▊ | 1892/5000 [15:22:32<24:26:48, 28.32s/it] 38%|███▊ | 1893/5000 [15:23:00<24:09:43, 28.00s/it] 38%|███▊ | 1894/5000 [15:23:28<24:15:09, 28.11s/it] 38%|███▊ | 1895/5000 [15:23:57<24:22:03, 28.25s/it] 38%|███▊ | 1896/5000 [15:24:24<24:04:27, 27.92s/it] 38%|███▊ | 1897/5000 [15:24:52<24:07:46, 27.99s/it] 38%|███▊ | 1898/5000 [15:25:20<24:12:01, 28.09s/it] 38%|███▊ | 1899/5000 [15:25:48<24:12:41, 28.11s/it] 38%|███▊ | 1900/5000 [15:26:16<24:03:23, 27.94s/it] 38%|███▊ | 1900/5000 [15:26:16<24:03:23, 27.94s/it] 38%|███▊ | 1901/5000 [15:26:44<24:03:15, 27.94s/it] 38%|███▊ | 1902/5000 [15:27:12<24:05:04, 27.99s/it] 38%|███▊ | 1903/5000 [15:27:39<23:54:36, 27.79s/it] 38%|███▊ | 1904/5000 [15:28:06<23:42:02, 27.56s/it] 38%|███▊ | 1905/5000 [15:28:38<24:41:45, 28.73s/it] 38%|███▊ | 1906/5000 [15:29:04<24:08:42, 28.09s/it] 38%|███▊ | 1907/5000 [15:29:32<23:55:44, 27.85s/it] 38%|███▊ | 1908/5000 [15:30:01<24:18:45, 28.31s/it] 38%|███▊ | 1909/5000 [15:30:28<24:02:18, 28.00s/it] 38%|███▊ | 1910/5000 [15:30:55<23:47:19, 27.72s/it] 38%|███▊ | 1911/5000 [15:31:30<25:29:01, 29.70s/it] 38%|███▊ | 1912/5000 [15:31:57<24:54:20, 29.04s/it] 38%|███▊ | 1913/5000 [15:32:26<24:46:17, 28.89s/it] 38%|███▊ | 1914/5000 [15:32:54<24:40:57, 28.79s/it] 38%|███▊ | 1915/5000 [15:33:23<24:33:13, 28.65s/it] 38%|███▊ | 1916/5000 [15:33:50<24:14:18, 28.29s/it] 38%|███▊ | 1917/5000 [15:34:18<24:12:28, 28.27s/it] 38%|███▊ | 1918/5000 [15:34:47<24:11:54, 28.27s/it] 38%|███▊ | 1919/5000 [15:35:14<23:57:00, 27.98s/it] 38%|███▊ | 1920/5000 [15:35:42<24:04:11, 28.13s/it] 38%|███▊ | 1921/5000 [15:36:11<24:07:01, 28.20s/it] 38%|███▊ | 1922/5000 [15:36:38<23:55:02, 27.97s/it] 38%|███▊ | 1923/5000 [15:37:07<24:04:12, 28.16s/it] 38%|███▊ | 1924/5000 [15:37:35<24:05:39, 28.20s/it] 38%|███▊ | 1925/5000 [15:38:02<23:49:05, 27.88s/it] 38%|███▊ | 1925/5000 [15:38:02<23:49:05, 27.88s/it] 39%|███▊ | 1926/5000 [15:38:30<23:41:10, 27.74s/it] 39%|███▊ | 1927/5000 [15:38:58<23:57:47, 28.07s/it] 39%|███▊ | 1928/5000 [15:39:26<23:43:48, 27.81s/it] 39%|███▊ | 1929/5000 [15:39:53<23:36:07, 27.67s/it] 39%|███▊ | 1930/5000 [15:40:22<23:57:46, 28.10s/it] 39%|███▊ | 1931/5000 [15:40:50<23:48:12, 27.92s/it] 39%|███▊ | 1932/5000 [15:41:17<23:36:02, 27.69s/it] 39%|███▊ | 1933/5000 [15:41:46<23:56:01, 28.09s/it] 39%|███▊ | 1934/5000 [15:42:13<23:42:50, 27.84s/it] 39%|███▊ | 1935/5000 [15:42:40<23:24:27, 27.49s/it] 39%|███▊ | 1936/5000 [15:43:08<23:35:31, 27.72s/it] 39%|███▊ | 1937/5000 [15:43:36<23:42:08, 27.86s/it] 39%|███▉ | 1938/5000 [15:44:04<23:35:47, 27.74s/it] 39%|███▉ | 1939/5000 [15:44:32<23:42:19, 27.88s/it] 39%|███▉ | 1940/5000 [15:45:00<23:43:14, 27.91s/it] 39%|███▉ | 1941/5000 [15:45:27<23:30:02, 27.66s/it] 39%|███▉ | 1942/5000 [15:45:55<23:42:36, 27.91s/it] 39%|███▉ | 1943/5000 [15:46:24<23:48:55, 28.05s/it] 39%|███▉ | 1944/5000 [15:46:51<23:40:41, 27.89s/it] 39%|███▉ | 1945/5000 [15:47:20<23:50:14, 28.09s/it] 39%|███▉ | 1946/5000 [15:47:48<23:52:55, 28.15s/it] 39%|███▉ | 1947/5000 [15:48:15<23:31:55, 27.75s/it] 39%|███▉ | 1948/5000 [15:48:47<24:44:37, 29.19s/it] 39%|███▉ | 1949/5000 [15:49:15<24:14:04, 28.60s/it] 39%|███▉ | 1950/5000 [15:49:42<23:58:06, 28.29s/it] 39%|███▉ | 1950/5000 [15:49:42<23:58:06, 28.29s/it] 39%|███▉ | 1951/5000 [15:50:10<23:56:41, 28.27s/it] 39%|███▉ | 1952/5000 [15:50:37<23:27:30, 27.71s/it] 39%|███▉ | 1953/5000 [15:51:04<23:20:49, 27.58s/it] 39%|███▉ | 1954/5000 [15:51:33<23:33:34, 27.84s/it] 39%|███▉ | 1955/5000 [15:52:00<23:31:36, 27.81s/it] 39%|███▉ | 1956/5000 [15:52:28<23:27:02, 27.73s/it] 39%|███▉ | 1957/5000 [15:52:57<23:48:47, 28.17s/it] 39%|███▉ | 1958/5000 [15:53:19<22:17:09, 26.37s/it] 39%|███▉ | 1959/5000 [15:53:30<18:20:33, 21.71s/it] 39%|███▉ | 1960/5000 [15:53:41<15:34:09, 18.44s/it] 39%|███▉ | 1961/5000 [15:53:52<13:37:41, 16.14s/it] 39%|███▉ | 1962/5000 [15:54:00<11:31:58, 13.67s/it]{'loss': 0.0063, 'learning_rate': 7.115555555555557e-06, 'epoch': 11.0} -{'loss': 0.006, 'learning_rate': 7.06e-06, 'epoch': 11.01} -{'loss': 0.006, 'learning_rate': 7.004444444444445e-06, 'epoch': 11.01} -{'loss': 0.0053, 'learning_rate': 6.948888888888889e-06, 'epoch': 11.02} -{'loss': 0.0044, 'learning_rate': 6.893333333333334e-06, 'epoch': 11.02} -{'loss': 0.0045, 'learning_rate': 6.837777777777779e-06, 'epoch': 11.03} -{'loss': 0.0051, 'learning_rate': 6.782222222222222e-06, 'epoch': 11.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.18it/s] - Reading metadata...: 14228it [00:00, 20577.69it/s] - Reading metadata...: 22597it [00:02, 10604.53it/s] Reading metadata...: 28043it [00:02, 12606.30it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.55it/s] Reading metadata...: 10438it [00:00, 22408.00it/s] - 39%|███▉ | 1963/5000 [15:55:49<35:48:04, 42.44s/it] 39%|███▉ | 1964/5000 [15:56:18<32:14:09, 38.22s/it] 39%|███▉ | 1965/5000 [15:56:45<29:34:02, 35.07s/it] 39%|███▉ | 1966/5000 [15:57:13<27:49:21, 33.01s/it] 39%|███▉ | 1967/5000 [15:57:42<26:33:25, 31.52s/it] 39%|███▉ | 1968/5000 [15:58:09<25:31:00, 30.30s/it] 39%|███▉ | 1969/5000 [15:58:35<24:25:58, 29.02s/it] 39%|███▉ | 1970/5000 [15:59:02<23:58:24, 28.48s/it] 39%|███▉ | 1971/5000 [15:59:30<23:54:33, 28.42s/it] 39%|███▉ | 1972/5000 [15:59:59<23:56:40, 28.47s/it] 39%|███▉ | 1973/5000 [16:00:26<23:39:18, 28.13s/it] 39%|███▉ | 1974/5000 [16:00:55<23:40:04, 28.16s/it] 40%|███▉ | 1975/5000 [16:01:23<23:43:18, 28.23s/it] 40%|███▉ | 1975/5000 [16:01:23<23:43:18, 28.23s/it] 40%|███▉ | 1976/5000 [16:01:50<23:18:54, 27.76s/it] 40%|███▉ | 1977/5000 [16:02:15<22:48:42, 27.17s/it] 40%|███▉ | 1978/5000 [16:02:44<23:09:22, 27.59s/it] 40%|███▉ | 1979/5000 [16:03:12<23:16:07, 27.73s/it] 40%|███▉ | 1980/5000 [16:03:40<23:11:08, 27.64s/it] 40%|███▉ | 1981/5000 [16:04:10<23:51:34, 28.45s/it] 40%|███▉ | 1982/5000 [16:04:37<23:28:46, 28.01s/it] 40%|███▉ | 1983/5000 [16:05:03<22:58:47, 27.42s/it] 40%|███▉ | 1984/5000 [16:05:31<23:10:05, 27.65s/it] 40%|███▉ | 1985/5000 [16:05:59<23:17:24, 27.81s/it] 40%|███▉ | 1986/5000 [16:06:27<23:10:17, 27.68s/it] 40%|███▉ | 1987/5000 [16:06:55<23:13:45, 27.76s/it] 40%|███▉ | 1988/5000 [16:07:21<22:49:43, 27.29s/it] 40%|███▉ | 1989/5000 [16:07:47<22:30:02, 26.90s/it] 40%|███▉ | 1990/5000 [16:08:17<23:12:12, 27.75s/it] 40%|███▉ | 1991/5000 [16:08:44<23:01:36, 27.55s/it] 40%|███▉ | 1992/5000 [16:09:11<22:56:53, 27.46s/it] 40%|███▉ | 1993/5000 [16:09:44<24:18:04, 29.09s/it] 40%|███▉ | 1994/5000 [16:10:11<23:50:07, 28.55s/it] 40%|███▉ | 1995/5000 [16:10:38<23:32:28, 28.20s/it] 40%|███▉ | 1996/5000 [16:11:07<23:34:32, 28.25s/it] 40%|███▉ | 1997/5000 [16:11:34<23:14:15, 27.86s/it] 40%|███▉ | 1998/5000 [16:12:01<22:57:58, 27.54s/it] 40%|███▉ | 1999/5000 [16:12:28<22:50:43, 27.41s/it] 40%|████ | 2000/5000 [16:12:55<22:45:51, 27.32s/it] 40%|████ | 2000/5000 [16:12:55<22:45:51, 27.32s/it][INFO|trainer.py:3138] 2023-05-08 02:47:05,817 >> ***** Running Evaluation ***** -[INFO|trainer.py:3142] 2023-05-08 02:47:05,817 >> Num examples: Unknown -[INFO|trainer.py:3143] 2023-05-08 02:47:05,817 >> Batch size = 64 -{'loss': 0.005, 'learning_rate': 6.726666666666667e-06, 'epoch': 12.0} -{'loss': 0.0042, 'learning_rate': 6.671111111111112e-06, 'epoch': 12.01} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.63it/s] Reading metadata...: 10440it [00:00, 30685.17it/s] -[INFO|trainer_utils.py:693] 2023-05-08 02:47:16,424 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message. - 40%|████ | 2000/5000 [16:48:47<22:45:51, 27.32s/it][INFO|trainer.py:2877] 2023-05-08 03:22:58,551 >> Saving model checkpoint to ./checkpoint-2000 -[INFO|configuration_utils.py:458] 2023-05-08 03:22:58,556 >> Configuration saved in ./checkpoint-2000/config.json -[INFO|configuration_utils.py:364] 2023-05-08 03:22:58,560 >> Configuration saved in ./checkpoint-2000/generation_config.json -[INFO|modeling_utils.py:1855] 2023-05-08 03:23:01,997 >> Model weights saved in ./checkpoint-2000/pytorch_model.bin -[INFO|feature_extraction_utils.py:369] 2023-05-08 03:23:02,003 >> Feature extractor saved in ./checkpoint-2000/preprocessor_config.json -[INFO|feature_extraction_utils.py:369] 2023-05-08 03:23:12,574 >> Feature extractor saved in ./preprocessor_config.json -/home/local/QCRI/dizham/miniconda3/envs/whisper/lib/python3.9/site-packages/torch/nn/parallel/_functions.py:68: UserWarning: Was asked to gather along dimension 0, but all input tensors were scalars; will instead unsqueeze and return a vector. - warnings.warn('Was asked to gather along dimension 0, but all ' - 40%|████ | 2001/5000 [16:50:15<575:52:06, 691.27s/it] 40%|████ | 2002/5000 [16:50:44<410:07:12, 492.47s/it] 40%|████ | 2003/5000 [16:51:12<293:55:31, 353.06s/it] 40%|████ | 2004/5000 [16:51:40<212:47:31, 255.69s/it] 40%|████ | 2005/5000 [16:52:08<155:55:38, 187.43s/it] 40%|████ | 2006/5000 [16:52:36<115:59:50, 139.48s/it] 40%|████ | 2007/5000 [16:53:04<88:15:57, 106.17s/it] 40%|████ | 2008/5000 [16:53:32<68:35:54, 82.54s/it] 40%|████ | 2009/5000 [16:54:04<55:56:56, 67.34s/it] 40%|████ | 2010/5000 [16:54:32<46:18:30, 55.76s/it] 40%|████ | 2011/5000 [16:55:00<39:16:47, 47.31s/it] 40%|████ | 2012/5000 [16:55:28<34:31:10, 41.59s/it] 40%|████ | 2013/5000 [16:55:56<31:05:26, 37.47s/it] 40%|████ | 2014/5000 [16:56:23<28:28:12, 34.32s/it] 40%|████ | 2015/5000 [16:56:59<28:53:17, 34.84s/it] 40%|████ | 2016/5000 [16:57:26<27:00:51, 32.59s/it] 40%|████ | 2017/5000 [16:57:54<25:43:19, 31.04s/it] 40%|████ | 2018/5000 [16:58:23<25:22:10, 30.63s/it] 40%|████ | 2019/5000 [16:58:50<24:27:44, 29.54s/it] 40%|████ | 2020/5000 [16:59:18<23:55:39, 28.91s/it] 40%|████ | 2021/5000 [16:59:50<24:40:32, 29.82s/it] 40%|████ | 2022/5000 [17:00:17<24:03:44, 29.09s/it] 40%|████ | 2023/5000 [17:00:44<23:34:52, 28.52s/it] 40%|████ | 2024/5000 [17:01:13<23:31:21, 28.45s/it] 40%|████ | 2025/5000 [17:01:40<23:17:36, 28.19s/it] 40%|████ | 2025/5000 [17:01:40<23:17:36, 28.19s/it] 41%|████ | 2026/5000 [17:02:08<23:04:52, 27.94s/it] 41%|████ | 2027/5000 [17:02:41<24:23:49, 29.54s/it] 41%|████ | 2028/5000 [17:03:08<23:52:59, 28.93s/it] 41%|████ | 2029/5000 [17:03:37<23:46:55, 28.82s/it] 41%|████ | 2030/5000 [17:04:05<23:37:51, 28.64s/it] 41%|████ | 2031/5000 [17:04:32<23:16:57, 28.23s/it] 41%|████ | 2032/5000 [17:05:01<23:18:44, 28.28s/it] 41%|████ | 2033/5000 [17:05:28<22:55:21, 27.81s/it] 41%|████ | 2034/5000 [17:05:57<23:20:34, 28.33s/it] 41%|████ | 2035/5000 [17:06:25<23:20:06, 28.33s/it] 41%|████ | 2036/5000 [17:06:53<23:01:51, 27.97s/it] 41%|████ | 2037/5000 [17:07:20<22:56:05, 27.87s/it] 41%|████ | 2038/5000 [17:07:49<23:03:45, 28.03s/it] 41%|████ | 2039/5000 [17:08:16<22:53:08, 27.82s/it] 41%|████ | 2040/5000 [17:08:44<23:02:25, 28.02s/it] 41%|████ | 2041/5000 [17:09:13<23:06:53, 28.12s/it] 41%|████ | 2042/5000 [17:09:40<22:54:59, 27.89s/it] 41%|████ | 2043/5000 [17:10:08<22:55:59, 27.92s/it] 41%|████ | 2044/5000 [17:10:40<23:56:03, 29.15s/it] 41%|████ | 2045/5000 [17:11:07<23:21:57, 28.47s/it] 41%|████ | 2046/5000 [17:11:35<23:15:27, 28.34s/it] 41%|████ | 2047/5000 [17:12:06<23:59:12, 29.24s/it] 41%|████ | 2048/5000 [17:12:38<24:37:09, 30.02s/it] 41%|████ | 2049/5000 [17:13:06<23:57:15, 29.22s/it] 41%|████ | 2050/5000 [17:13:34<23:44:02, 28.96s/it] 41%|████ | 2050/5000 [17:13:34<23:44:02, 28.96s/it] 41%|████ | 2051/5000 [17:14:02<23:30:09, 28.69s/it] 41%|████ | 2052/5000 [17:14:29<23:08:17, 28.26s/it] 41%|████ | 2053/5000 [17:14:57<23:07:07, 28.24s/it] 41%|████ | 2054/5000 [17:15:25<22:54:13, 27.99s/it] 41%|████ | 2055/5000 [17:15:52<22:42:08, 27.75s/it] 41%|████ | 2056/5000 [17:16:20<22:49:50, 27.92s/it] 41%|████ | 2057/5000 [17:16:48<22:47:50, 27.89s/it] 41%|████ | 2058/5000 [17:17:15<22:35:43, 27.65s/it] 41%|████ | 2059/5000 [17:17:44<22:47:52, 27.91s/it] 41%|████ | 2060/5000 [17:18:12<22:51:21, 27.99s/it] 41%|████ | 2061/5000 [17:18:39<22:42:07, 27.81s/it] 41%|████ | 2062/5000 [17:19:12<23:52:27, 29.25s/it] 41%|████▏ | 2063/5000 [17:19:40<23:29:22, 28.79s/it] 41%|████▏ | 2064/5000 [17:20:07<23:07:05, 28.35s/it] 41%|████▏ | 2065/5000 [17:20:38<23:48:58, 29.21s/it] 41%|████▏ | 2066/5000 [17:21:06<23:23:37, 28.70s/it] 41%|████▏ | 2067/5000 [17:21:33<23:03:32, 28.30s/it] 41%|████▏ | 2068/5000 [17:22:03<23:22:05, 28.69s/it] 41%|████▏ | 2069/5000 [17:22:30<22:56:43, 28.18s/it] 41%|████▏ | 2070/5000 [17:22:57<22:38:14, 27.81s/it] 41%|████▏ | 2071/5000 [17:23:25<22:41:12, 27.88s/it] 41%|████▏ | 2072/5000 [17:23:57<23:39:09, 29.08s/it] 41%|████▏ | 2073/5000 [17:24:24<23:09:52, 28.49s/it] 41%|████▏ | 2074/5000 [17:24:50<22:41:09, 27.91s/it] 42%|████▏ | 2075/5000 [17:25:18<22:39:46, 27.89s/it] 42%|████▏ | 2075/5000 [17:25:18<22:39:46, 27.89s/it] 42%|████▏ | 2076/5000 [17:25:45<22:18:31, 27.47s/it] 42%|████▏ | 2077/5000 [17:26:12<22:13:41, 27.38s/it] 42%|████▏ | 2078/5000 [17:26:39<22:10:38, 27.32s/it] 42%|████▏ | 2079/5000 [17:27:07<22:19:16, 27.51s/it] 42%|████▏ | 2080/5000 [17:27:34<22:19:18, 27.52s/it] 42%|████▏ | 2081/5000 [17:28:08<23:45:12, 29.30s/it] 42%|████▏ | 2082/5000 [17:28:35<23:17:02, 28.73s/it] 42%|████▏ | 2083/5000 [17:29:03<22:56:21, 28.31s/it] 42%|████▏ | 2084/5000 [17:29:35<23:58:24, 29.60s/it] 42%|████▏ | 2085/5000 [17:30:02<23:19:06, 28.80s/it] 42%|████▏ | 2086/5000 [17:30:29<22:53:33, 28.28s/it] 42%|████▏ | 2087/5000 [17:31:03<24:20:01, 30.07s/it] 42%|████▏ | 2088/5000 [17:31:31<23:39:43, 29.25s/it] 42%|████▏ | 2089/5000 [17:31:58<23:10:48, 28.67s/it] 42%|████▏ | 2090/5000 [17:32:28<23:20:44, 28.88s/it] 42%|████▏ | 2091/5000 [17:32:54<22:38:12, 28.01s/it] 42%|████▏ | 2092/5000 [17:33:20<22:18:29, 27.62s/it] 42%|████▏ | 2093/5000 [17:33:48<22:13:59, 27.53s/it] 42%|████▏ | 2094/5000 [17:34:21<23:43:36, 29.39s/it] 42%|████▏ | 2095/5000 [17:34:49<23:12:33, 28.76s/it] 42%|████▏ | 2096/5000 [17:35:16<22:48:10, 28.27s/it] 42%|████▏ | 2097/5000 [17:35:44<22:51:37, 28.35s/it] 42%|████▏ | 2098/5000 [17:36:12<22:36:34, 28.05s/it] 42%|████▏ | 2099/5000 [17:36:39<22:30:05, 27.92s/it] 42%|████▏ | 2100/5000 [17:37:09<22:57:17, 28.50s/it] 42%|████▏ | 2100/5000 [17:37:09<22:57:17, 28.50s/it] 42%|████▏ | 2101/5000 [17:37:36<22:41:41, 28.18s/it] 42%|████▏ | 2102/5000 [17:38:04<22:26:09, 27.87s/it] 42%|████▏ | 2103/5000 [17:38:38<24:00:46, 29.84s/it] 42%|████▏ | 2104/5000 [17:39:05<23:23:18, 29.07s/it] 42%|████▏ | 2105/5000 [17:39:33<22:58:44, 28.57s/it] 42%|████▏ | 2106/5000 [17:40:03<23:17:05, 28.97s/it] 42%|████▏ | 2107/5000 [17:40:30<22:57:08, 28.56s/it] 42%|████▏ | 2108/5000 [17:40:58<22:41:59, 28.26s/it] 42%|████▏ | 2109/5000 [17:41:27<23:00:59, 28.66s/it] 42%|████▏ | 2110/5000 [17:41:54<22:37:18, 28.18s/it] 42%|████▏ | 2111/5000 [17:42:22<22:22:29, 27.88s/it] 42%|████▏ | 2112/5000 [17:42:55<23:39:12, 29.48s/it] 42%|████▏ | 2113/5000 [17:43:22<23:02:57, 28.74s/it] 42%|████▏ | 2114/5000 [17:43:50<22:47:42, 28.43s/it] 42%|████▏ | 2115/5000 [17:44:19<22:54:55, 28.59s/it] 42%|████▏ | 2116/5000 [17:44:46<22:37:04, 28.23s/it] 42%|████▏ | 2117/5000 [17:45:13<22:25:17, 28.00s/it] 42%|████▏ | 2118/5000 [17:45:43<22:48:33, 28.49s/it] 42%|████▏ | 2119/5000 [17:46:10<22:25:05, 28.01s/it] 42%|████▏ | 2120/5000 [17:46:37<22:08:51, 27.68s/it] 42%|████▏ | 2121/5000 [17:47:10<23:31:57, 29.43s/it] 42%|████▏ | 2122/5000 [17:47:24<19:48:48, 24.78s/it] 42%|████▏ | 2123/5000 [17:47:35<16:29:15, 20.63s/it] 42%|████▏ | 2124/5000 [17:47:46<14:08:07, 17.69s/it] 42%|████▎ | 2125/5000 [17:47:57<12:30:01, 15.65s/it] 42%|████▎ | 2125/5000 [17:47:57<12:30:01, 15.65s/it]{'eval_loss': 0.5698409676551819, 'eval_wer': 55.900000000000006, 'eval_runtime': 2152.7247, 'eval_samples_per_second': 4.85, 'eval_steps_per_second': 0.076, 'epoch': 12.01} -{'loss': 0.0045, 'learning_rate': 6.615555555555556e-06, 'epoch': 12.01} -{'loss': 0.0032, 'learning_rate': 6.560000000000001e-06, 'epoch': 12.02} -{'loss': 0.003, 'learning_rate': 6.504444444444446e-06, 'epoch': 12.02} -{'loss': 0.0036, 'learning_rate': 6.448888888888889e-06, 'epoch': 12.03} -{'loss': 0.0032, 'learning_rate': 6.393333333333334e-06, 'epoch': 12.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.83it/s] - Reading metadata...: 14891it [00:00, 42873.14it/s] - Reading metadata...: 23650it [00:01, 18542.50it/s] Reading metadata...: 28043it [00:01, 22028.86it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.87it/s] Reading metadata...: 10438it [00:00, 24941.40it/s] - 43%|████▎ | 2126/5000 [17:49:36<32:26:44, 40.64s/it] 43%|████▎ | 2127/5000 [17:50:08<30:24:20, 38.10s/it] 43%|████▎ | 2128/5000 [17:50:47<30:41:33, 38.47s/it] 43%|████▎ | 2129/5000 [17:51:16<28:15:19, 35.43s/it] 43%|████▎ | 2130/5000 [17:51:43<26:19:49, 33.03s/it] 43%|████▎ | 2131/5000 [17:52:12<25:18:31, 31.76s/it] 43%|████▎ | 2132/5000 [17:52:44<25:22:16, 31.85s/it] 43%|████▎ | 2133/5000 [17:53:19<26:10:26, 32.87s/it] 43%|████▎ | 2134/5000 [17:53:48<25:16:20, 31.74s/it] 43%|████▎ | 2135/5000 [17:54:15<24:05:49, 30.28s/it] 43%|████▎ | 2136/5000 [17:54:43<23:32:58, 29.60s/it] 43%|████▎ | 2137/5000 [17:55:14<23:48:53, 29.95s/it] 43%|████▎ | 2138/5000 [17:55:41<23:10:27, 29.15s/it] 43%|████▎ | 2139/5000 [17:56:14<23:56:21, 30.12s/it] 43%|████▎ | 2140/5000 [17:56:44<23:53:26, 30.07s/it] 43%|████▎ | 2141/5000 [17:57:12<23:21:47, 29.42s/it] 43%|████▎ | 2142/5000 [17:57:40<23:06:21, 29.10s/it] 43%|████▎ | 2143/5000 [17:58:06<22:29:01, 28.33s/it] 43%|████▎ | 2144/5000 [17:58:34<22:23:25, 28.22s/it] 43%|████▎ | 2145/5000 [17:59:03<22:22:03, 28.20s/it] 43%|████▎ | 2146/5000 [17:59:30<22:07:21, 27.91s/it] 43%|████▎ | 2147/5000 [17:59:58<22:08:54, 27.95s/it] 43%|████▎ | 2148/5000 [18:00:26<22:14:28, 28.07s/it] 43%|████▎ | 2149/5000 [18:00:53<22:00:05, 27.78s/it] 43%|████▎ | 2150/5000 [18:01:21<22:05:14, 27.90s/it] 43%|████▎ | 2150/5000 [18:01:21<22:05:14, 27.90s/it] 43%|████▎ | 2151/5000 [18:01:49<22:03:19, 27.87s/it] 43%|████▎ | 2152/5000 [18:02:17<21:55:09, 27.71s/it] 43%|████▎ | 2153/5000 [18:02:45<22:04:49, 27.92s/it] 43%|████▎ | 2154/5000 [18:03:13<21:59:46, 27.82s/it] 43%|████▎ | 2155/5000 [18:03:39<21:43:07, 27.48s/it] 43%|████▎ | 2156/5000 [18:04:07<21:49:06, 27.62s/it] 43%|████▎ | 2157/5000 [18:04:35<21:47:00, 27.58s/it] 43%|████▎ | 2158/5000 [18:05:02<21:41:18, 27.47s/it] 43%|���███▎ | 2159/5000 [18:05:31<21:59:10, 27.86s/it] 43%|████▎ | 2160/5000 [18:05:58<21:51:53, 27.72s/it] 43%|████▎ | 2161/5000 [18:06:25<21:45:11, 27.58s/it] 43%|████▎ | 2162/5000 [18:06:54<21:58:45, 27.88s/it] 43%|████▎ | 2163/5000 [18:07:22<22:01:04, 27.94s/it] 43%|████▎ | 2164/5000 [18:07:49<21:47:30, 27.66s/it] 43%|████▎ | 2165/5000 [18:08:18<22:10:34, 28.16s/it] 43%|████▎ | 2166/5000 [18:08:47<22:10:04, 28.16s/it] 43%|████▎ | 2167/5000 [18:09:14<21:57:41, 27.91s/it] 43%|████▎ | 2168/5000 [18:09:43<22:20:03, 28.39s/it] 43%|████▎ | 2169/5000 [18:10:16<23:17:56, 29.63s/it] 43%|████▎ | 2170/5000 [18:10:43<22:44:11, 28.92s/it] 43%|████▎ | 2171/5000 [18:11:15<23:29:16, 29.89s/it] 43%|████▎ | 2172/5000 [18:11:44<23:05:07, 29.39s/it] 43%|████▎ | 2173/5000 [18:12:12<22:51:10, 29.10s/it] 43%|████▎ | 2174/5000 [18:12:39<22:18:15, 28.41s/it] 44%|████▎ | 2175/5000 [18:13:06<22:02:56, 28.10s/it] 44%|████▎ | 2175/5000 [18:13:06<22:02:56, 28.10s/it] 44%|████▎ | 2176/5000 [18:13:38<23:00:22, 29.33s/it] 44%|████▎ | 2177/5000 [18:14:06<22:34:23, 28.79s/it] 44%|████▎ | 2178/5000 [18:14:34<22:31:19, 28.73s/it] 44%|████▎ | 2179/5000 [18:15:04<22:40:00, 28.93s/it] 44%|████▎ | 2180/5000 [18:15:31<22:16:17, 28.43s/it] 44%|████▎ | 2181/5000 [18:15:59<22:09:26, 28.30s/it] 44%|████▎ | 2182/5000 [18:16:27<22:04:27, 28.20s/it] 44%|████▎ | 2183/5000 [18:16:54<21:52:10, 27.95s/it] 44%|████▎ | 2184/5000 [18:17:27<23:01:11, 29.43s/it] 44%|████▎ | 2185/5000 [18:17:55<22:35:52, 28.90s/it] 44%|████▎ | 2186/5000 [18:18:22<22:15:20, 28.47s/it] 44%|████▎ | 2187/5000 [18:18:52<22:23:49, 28.66s/it] 44%|████▍ | 2188/5000 [18:19:19<22:03:09, 28.23s/it] 44%|████▍ | 2189/5000 [18:19:46<21:46:31, 27.89s/it] 44%|████▍ | 2190/5000 [18:20:14<21:52:50, 28.03s/it] 44%|████▍ | 2191/5000 [18:20:42<21:51:54, 28.02s/it] 44%|████▍ | 2192/5000 [18:21:10<21:47:45, 27.94s/it] 44%|████▍ | 2193/5000 [18:21:38<21:52:51, 28.06s/it] 44%|████▍ | 2194/5000 [18:22:06<21:43:47, 27.88s/it] 44%|████▍ | 2195/5000 [18:22:33<21:35:11, 27.70s/it] 44%|████▍ | 2196/5000 [18:23:01<21:40:04, 27.82s/it] 44%|████▍ | 2197/5000 [18:23:33<22:29:39, 28.89s/it] 44%|████▍ | 2198/5000 [18:24:00<22:05:54, 28.39s/it] 44%|████▍ | 2199/5000 [18:24:28<22:05:44, 28.40s/it] 44%|████▍ | 2200/5000 [18:24:56<21:59:48, 28.28s/it] 44%|████▍ | 2200/5000 [18:24:56<21:59:48, 28.28s/it] 44%|████▍ | 2201/5000 [18:25:25<22:02:31, 28.35s/it] 44%|████▍ | 2202/5000 [18:25:52<21:48:13, 28.05s/it] 44%|████▍ | 2203/5000 [18:26:20<21:46:28, 28.03s/it] 44%|████▍ | 2204/5000 [18:26:48<21:47:56, 28.07s/it] 44%|████▍ | 2205/5000 [18:27:16<21:39:57, 27.91s/it] 44%|████▍ | 2206/5000 [18:27:44<21:47:59, 28.09s/it] 44%|████▍ | 2207/5000 [18:28:13<21:50:28, 28.15s/it] 44%|████▍ | 2208/5000 [18:28:39<21:23:54, 27.59s/it] 44%|████▍ | 2209/5000 [18:29:07<21:38:01, 27.90s/it] 44%|████▍ | 2210/5000 [18:29:36<21:47:06, 28.11s/it] 44%|████▍ | 2211/5000 [18:30:03<21:32:54, 27.81s/it] 44%|████▍ | 2212/5000 [18:30:31<21:34:12, 27.85s/it] 44%|████▍ | 2213/5000 [18:30:59<21:39:41, 27.98s/it] 44%|████▍ | 2214/5000 [18:31:26<21:25:29, 27.68s/it] 44%|████▍ | 2215/5000 [18:31:54<21:28:12, 27.75s/it] 44%|████▍ | 2216/5000 [18:32:26<22:15:56, 28.79s/it] 44%|████▍ | 2217/5000 [18:32:53<21:50:36, 28.26s/it] 44%|████▍ | 2218/5000 [18:33:21<21:50:56, 28.27s/it] 44%|████▍ | 2219/5000 [18:33:49<21:48:53, 28.24s/it] 44%|████▍ | 2220/5000 [18:34:16<21:36:00, 27.97s/it] 44%|████▍ | 2221/5000 [18:34:45<21:48:38, 28.25s/it] 44%|████▍ | 2222/5000 [18:35:14<21:49:49, 28.29s/it] 44%|████▍ | 2223/5000 [18:35:41<21:33:18, 27.94s/it] 44%|████▍ | 2224/5000 [18:36:09<21:36:49, 28.03s/it] 44%|████▍ | 2225/5000 [18:36:41<22:37:02, 29.34s/it] 44%|████▍ | 2225/5000 [18:36:41<22:37:02, 29.34s/it] 45%|████▍ | 2226/5000 [18:37:10<22:21:28, 29.02s/it] 45%|████▍ | 2227/5000 [18:37:36<21:47:48, 28.30s/it] 45%|████▍ | 2228/5000 [18:38:03<21:28:33, 27.89s/it] 45%|████▍ | 2229/5000 [18:38:31<21:25:48, 27.84s/it] 45%|████▍ | 2230/5000 [18:38:58<21:15:27, 27.63s/it] 45%|████▍ | 2231/5000 [18:39:25<21:07:28, 27.46s/it] 45%|████▍ | 2232/5000 [18:39:54<21:21:07, 27.77s/it] 45%|████▍ | 2233/5000 [18:40:21<21:10:34, 27.55s/it] 45%|████▍ | 2234/5000 [18:40:47<20:53:34, 27.19s/it] 45%|████▍ | 2235/5000 [18:41:16<21:18:57, 27.75s/it] 45%|████▍ | 2236/5000 [18:41:44<21:13:36, 27.65s/it] 45%|████▍ | 2237/5000 [18:42:11<21:07:32, 27.53s/it] 45%|████▍ | 2238/5000 [18:42:39<21:22:27, 27.86s/it] 45%|████▍ | 2239/5000 [18:43:07<21:14:19, 27.69s/it] 45%|████▍ | 2240/5000 [18:43:34<21:09:55, 27.61s/it] 45%|████▍ | 2241/5000 [18:44:02<21:13:58, 27.71s/it] 45%|████▍ | 2242/5000 [18:44:31<21:25:00, 27.96s/it] 45%|████▍ | 2243/5000 [18:44:58<21:12:43, 27.70s/it] 45%|████▍ | 2244/5000 [18:45:25<21:03:52, 27.52s/it] 45%|████▍ | 2245/5000 [18:45:55<21:35:46, 28.22s/it] 45%|████▍ | 2246/5000 [18:46:20<21:00:52, 27.47s/it] 45%|████▍ | 2247/5000 [18:46:47<20:53:28, 27.32s/it] 45%|████▍ | 2248/5000 [18:47:15<20:55:42, 27.38s/it] 45%|████▍ | 2249/5000 [18:47:42<20:47:07, 27.20s/it] 45%|████▌ | 2250/5000 [18:48:12<21:33:57, 28.23s/it] 45%|████▌ | 2250/5000 [18:48:12<21:33:57, 28.23s/it] 45%|████▌ | 2251/5000 [18:48:40<21:28:25, 28.12s/it] 45%|████▌ | 2252/5000 [18:49:07<21:13:25, 27.80s/it] 45%|████▌ | 2253/5000 [18:49:34<21:04:44, 27.62s/it] 45%|████▌ | 2254/5000 [18:50:07<22:06:34, 28.99s/it] 45%|████▌ | 2255/5000 [18:50:34<21:41:50, 28.46s/it] 45%|████▌ | 2256/5000 [18:51:01<21:24:20, 28.08s/it] 45%|████▌ | 2257/5000 [18:51:30<21:35:26, 28.34s/it] 45%|████▌ | 2258/5000 [18:51:57<21:13:42, 27.87s/it] 45%|████▌ | 2259/5000 [18:52:24<21:05:39, 27.70s/it] 45%|████▌ | 2260/5000 [18:52:52<21:12:18, 27.86s/it] 45%|████▌ | 2261/5000 [18:53:18<20:42:14, 27.21s/it] 45%|████▌ | 2262/5000 [18:53:45<20:33:56, 27.04s/it] 45%|████▌ | 2263/5000 [18:54:14<21:05:09, 27.73s/it] 45%|████▌ | 2264/5000 [18:54:42<21:12:44, 27.91s/it] 45%|████▌ | 2265/5000 [18:55:09<21:01:56, 27.68s/it] 45%|████▌ | 2266/5000 [18:55:38<21:11:34, 27.91s/it] 45%|████▌ | 2267/5000 [18:56:06<21:09:04, 27.86s/it] 45%|████▌ | 2268/5000 [18:56:33<20:57:44, 27.62s/it] 45%|████▌ | 2269/5000 [18:57:01<21:03:36, 27.76s/it] 45%|████▌ | 2270/5000 [18:57:29<21:09:28, 27.90s/it] 45%|████▌ | 2271/5000 [18:57:56<20:58:55, 27.68s/it] 45%|████▌ | 2272/5000 [18:58:28<21:52:39, 28.87s/it] 45%|████▌ | 2273/5000 [18:58:56<21:46:27, 28.75s/it] 45%|████▌ | 2274/5000 [18:59:24<21:26:31, 28.32s/it] 46%|████▌ | 2275/5000 [18:59:53<21:41:32, 28.66s/it] 46%|████▌ | 2275/5000 [18:59:53<21:41:32, 28.66s/it] 46%|████▌ | 2276/5000 [19:00:20<21:20:33, 28.21s/it] 46%|████▌ | 2277/5000 [19:00:47<21:07:06, 27.92s/it] 46%|████▌ | 2278/5000 [19:01:16<21:19:39, 28.21s/it] 46%|████▌ | 2279/5000 [19:01:44<21:08:32, 27.97s/it] 46%|████▌ | 2280/5000 [19:02:10<20:49:57, 27.57s/it] 46%|████▌ | 2281/5000 [19:02:39<20:58:59, 27.78s/it] 46%|████▌ | 2282/5000 [19:03:07<21:01:20, 27.84s/it] 46%|████▌ | 2283/5000 [19:03:34<20:52:27, 27.66s/it] 46%|████▌ | 2284/5000 [19:04:03<21:11:37, 28.09s/it] 46%|████▌ | 2285/5000 [19:04:25<19:51:32, 26.33s/it] 46%|████▌ | 2286/5000 [19:04:36<16:23:03, 21.73s/it] 46%|████▌ | 2287/5000 [19:04:47<13:54:15, 18.45s/it] 46%|████▌ | 2288/5000 [19:04:58<12:11:22, 16.18s/it] 46%|████▌ | 2289/5000 [19:05:06<10:17:47, 13.67s/it]{'loss': 0.0036, 'learning_rate': 6.3377777777777786e-06, 'epoch': 13.0} -{'loss': 0.0038, 'learning_rate': 6.282222222222223e-06, 'epoch': 13.01} -{'loss': 0.0031, 'learning_rate': 6.2266666666666675e-06, 'epoch': 13.01} -{'loss': 0.0028, 'learning_rate': 6.171111111111112e-06, 'epoch': 13.02} -{'loss': 0.0028, 'learning_rate': 6.1155555555555555e-06, 'epoch': 13.02} -{'loss': 0.0029, 'learning_rate': 6.0600000000000004e-06, 'epoch': 13.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 1.27it/s] - Reading metadata...: 14501it [00:00, 22287.88it/s] - Reading metadata...: 23030it [00:01, 14373.66it/s] Reading metadata...: 28043it [00:01, 15886.58it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:02, 2.84s/it] Reading metadata...: 10438it [00:02, 3591.45it/s] - 46%|████▌ | 2290/5000 [19:06:52<31:19:22, 41.61s/it] 46%|████▌ | 2291/5000 [19:07:21<28:16:18, 37.57s/it] 46%|████▌ | 2292/5000 [19:07:48<26:00:56, 34.59s/it] 46%|████▌ | 2293/5000 [19:08:16<24:33:37, 32.66s/it] 46%|████▌ | 2294/5000 [19:08:44<23:27:26, 31.21s/it] 46%|████▌ | 2295/5000 [19:09:13<22:51:04, 30.41s/it] 46%|████▌ | 2296/5000 [19:09:40<22:08:27, 29.48s/it] 46%|████▌ | 2297/5000 [19:10:09<21:55:38, 29.20s/it] 46%|████▌ | 2298/5000 [19:10:36<21:26:57, 28.58s/it] 46%|████▌ | 2299/5000 [19:11:04<21:25:22, 28.55s/it] 46%|████▌ | 2300/5000 [19:11:32<21:11:12, 28.25s/it] 46%|████▌ | 2300/5000 [19:11:32<21:11:12, 28.25s/it] 46%|████▌ | 2301/5000 [19:12:00<21:14:04, 28.32s/it] 46%|████▌ | 2302/5000 [19:12:31<21:43:29, 28.99s/it] 46%|████▌ | 2303/5000 [19:13:03<22:21:19, 29.84s/it] 46%|████▌ | 2304/5000 [19:13:30<21:46:21, 29.07s/it] 46%|████▌ | 2305/5000 [19:13:57<21:22:12, 28.55s/it] 46%|████▌ | 2306/5000 [19:14:24<21:03:28, 28.14s/it] 46%|████▌ | 2307/5000 [19:14:52<20:52:19, 27.90s/it] 46%|████▌ | 2308/5000 [19:15:21<21:07:08, 28.24s/it] 46%|████▌ | 2309/5000 [19:15:48<20:57:15, 28.03s/it] 46%|████▌ | 2310/5000 [19:16:16<20:49:21, 27.87s/it] 46%|████▌ | 2311/5000 [19:16:49<21:59:29, 29.44s/it] 46%|████▌ | 2312/5000 [19:17:17<21:38:56, 28.99s/it] 46%|████▋ | 2313/5000 [19:17:43<21:03:29, 28.21s/it] 46%|████▋ | 2314/5000 [19:18:21<23:08:26, 31.01s/it] 46%|████▋ | 2315/5000 [19:18:48<22:15:25, 29.84s/it] 46%|████▋ | 2316/5000 [19:19:15<21:34:03, 28.93s/it] 46%|████▋ | 2317/5000 [19:19:46<22:04:23, 29.62s/it] 46%|████▋ | 2318/5000 [19:20:13<21:31:50, 28.90s/it] 46%|████▋ | 2319/5000 [19:20:40<21:02:59, 28.27s/it] 46%|████▋ | 2320/5000 [19:21:10<21:23:59, 28.75s/it] 46%|████▋ | 2321/5000 [19:21:37<20:57:47, 28.17s/it] 46%|████▋ | 2322/5000 [19:22:03<20:32:25, 27.61s/it] 46%|████▋ | 2323/5000 [19:22:31<20:31:36, 27.60s/it] 46%|████▋ | 2324/5000 [19:22:58<20:25:42, 27.48s/it] 46%|████▋ | 2325/5000 [19:23:25<20:23:05, 27.43s/it] 46%|████▋ | 2325/5000 [19:23:25<20:23:05, 27.43s/it] 47%|████▋ | 2326/5000 [19:23:54<20:42:06, 27.87s/it] 47%|████▋ | 2327/5000 [19:24:21<20:34:48, 27.72s/it] 47%|████▋ | 2328/5000 [19:24:49<20:31:22, 27.65s/it] 47%|████▋ | 2329/5000 [19:25:21<21:28:54, 28.95s/it] 47%|████▋ | 2330/5000 [19:25:48<21:05:39, 28.44s/it] 47%|████▋ | 2331/5000 [19:26:18<21:20:39, 28.79s/it] 47%|████▋ | 2332/5000 [19:26:44<20:51:56, 28.15s/it] 47%|████▋ | 2333/5000 [19:27:12<20:43:56, 27.99s/it] 47%|████▋ | 2334/5000 [19:27:45<21:44:26, 29.36s/it] 47%|████▋ | 2335/5000 [19:28:12<21:18:56, 28.79s/it] 47%|████▋ | 2336/5000 [19:28:40<21:10:42, 28.62s/it] 47%|████▋ | 2337/5000 [19:29:09<21:06:05, 28.53s/it] 47%|████▋ | 2338/5000 [19:29:36<20:48:45, 28.15s/it] 47%|████▋ | 2339/5000 [19:30:04<20:54:28, 28.29s/it] 47%|████▋ | 2340/5000 [19:30:32<20:48:11, 28.15s/it] 47%|████▋ | 2341/5000 [19:31:00<20:37:48, 27.93s/it] 47%|████▋ | 2342/5000 [19:31:28<20:46:28, 28.14s/it] 47%|████▋ | 2343/5000 [19:31:56<20:38:38, 27.97s/it] 47%|████▋ | 2344/5000 [19:32:23<20:31:45, 27.83s/it] 47%|████▋ | 2345/5000 [19:32:52<20:42:14, 28.07s/it] 47%|████▋ | 2346/5000 [19:33:19<20:30:33, 27.82s/it] 47%|████▋ | 2347/5000 [19:33:46<20:21:52, 27.63s/it] 47%|████▋ | 2348/5000 [19:34:16<20:45:23, 28.18s/it] 47%|████▋ | 2349/5000 [19:34:43<20:34:03, 27.93s/it] 47%|████▋ | 2350/5000 [19:35:11<20:27:14, 27.79s/it] 47%|████▋ | 2350/5000 [19:35:11<20:27:14, 27.79s/it] 47%|████▋ | 2351/5000 [19:35:43<21:23:18, 29.07s/it] 47%|████▋ | 2352/5000 [19:36:10<21:01:14, 28.58s/it] 47%|████▋ | 2353/5000 [19:36:37<20:42:42, 28.17s/it] 47%|████▋ | 2354/5000 [19:37:10<21:34:50, 29.36s/it] 47%|████▋ | 2355/5000 [19:37:37<21:09:37, 28.80s/it] 47%|████▋ | 2356/5000 [19:38:05<20:52:54, 28.43s/it] 47%|████▋ | 2357/5000 [19:38:33<20:52:08, 28.43s/it] 47%|████▋ | 2358/5000 [19:39:00<20:35:23, 28.06s/it] 47%|████▋ | 2359/5000 [19:39:28<20:31:38, 27.98s/it] 47%|████▋ | 2360/5000 [19:39:55<20:18:17, 27.69s/it] 47%|████▋ | 2361/5000 [19:40:27<21:14:06, 28.97s/it] 47%|████▋ | 2362/5000 [19:40:55<20:59:16, 28.64s/it] 47%|████▋ | 2363/5000 [19:41:22<20:42:02, 28.26s/it] 47%|████▋ | 2364/5000 [19:41:51<20:51:08, 28.48s/it] 47%|████▋ | 2365/5000 [19:42:20<20:48:55, 28.44s/it] 47%|████▋ | 2366/5000 [19:42:47<20:35:32, 28.14s/it] 47%|████▋ | 2367/5000 [19:43:15<20:38:38, 28.23s/it] 47%|████▋ | 2368/5000 [19:43:44<20:38:56, 28.24s/it] 47%|████▋ | 2369/5000 [19:44:11<20:30:50, 28.07s/it] 47%|████▋ | 2370/5000 [19:44:40<20:36:42, 28.21s/it] 47%|████▋ | 2371/5000 [19:45:08<20:39:23, 28.29s/it] 47%|████▋ | 2372/5000 [19:45:36<20:26:08, 27.99s/it] 47%|████▋ | 2373/5000 [19:46:04<20:26:30, 28.01s/it] 47%|████▋ | 2374/5000 [19:46:32<20:35:09, 28.22s/it] 48%|████▊ | 2375/5000 [19:47:01<20:35:00, 28.23s/it] 48%|████▊ | 2375/5000 [19:47:01<20:35:00, 28.23s/it] 48%|████▊ | 2376/5000 [19:47:27<20:15:55, 27.80s/it] 48%|████▊ | 2377/5000 [19:47:56<20:22:17, 27.96s/it] 48%|████▊ | 2378/5000 [19:48:27<21:02:34, 28.89s/it] 48%|████▊ | 2379/5000 [19:48:54<20:42:57, 28.45s/it] 48%|████▊ | 2380/5000 [19:49:22<20:34:55, 28.28s/it] 48%|████▊ | 2381/5000 [19:49:51<20:39:57, 28.41s/it] 48%|████▊ | 2382/5000 [19:50:18<20:28:21, 28.15s/it] 48%|████▊ | 2383/5000 [19:50:46<20:22:34, 28.03s/it] 48%|████▊ | 2384/5000 [19:51:15<20:29:11, 28.19s/it] 48%|████▊ | 2385/5000 [19:51:41<19:58:44, 27.50s/it] 48%|████▊ | 2386/5000 [19:52:09<20:03:30, 27.62s/it] 48%|████▊ | 2387/5000 [19:52:36<20:01:06, 27.58s/it] 48%|████▊ | 2388/5000 [19:53:03<19:56:36, 27.49s/it] 48%|████▊ | 2389/5000 [19:53:32<20:06:55, 27.73s/it] 48%|████▊ | 2390/5000 [19:54:00<20:14:06, 27.91s/it] 48%|████▊ | 2391/5000 [19:54:27<20:04:16, 27.70s/it] 48%|████▊ | 2392/5000 [19:54:55<20:04:05, 27.70s/it] 48%|████▊ | 2393/5000 [19:55:22<19:57:49, 27.57s/it] 48%|████▊ | 2394/5000 [19:55:49<19:50:05, 27.40s/it] 48%|████▊ | 2395/5000 [19:56:21<20:42:53, 28.63s/it] 48%|████▊ | 2396/5000 [19:56:48<20:25:50, 28.25s/it] 48%|████▊ | 2397/5000 [19:57:15<20:14:30, 27.99s/it] 48%|████▊ | 2398/5000 [19:57:43<20:15:46, 28.03s/it] 48%|████▊ | 2399/5000 [19:58:11<20:04:34, 27.79s/it] 48%|████▊ | 2400/5000 [19:58:38<19:53:53, 27.55s/it] 48%|████▊ | 2400/5000 [19:58:38<19:53:53, 27.55s/it] 48%|████▊ | 2401/5000 [19:59:06<20:05:32, 27.83s/it] 48%|████▊ | 2402/5000 [19:59:34<20:07:50, 27.89s/it] 48%|████▊ | 2403/5000 [20:00:02<19:59:22, 27.71s/it] 48%|████▊ | 2404/5000 [20:00:29<20:01:59, 27.78s/it] 48%|████▊ | 2405/5000 [20:00:56<19:48:46, 27.49s/it] 48%|████▊ | 2406/5000 [20:01:28<20:38:11, 28.64s/it] 48%|████▊ | 2407/5000 [20:01:54<20:10:17, 28.01s/it] 48%|████▊ | 2408/5000 [20:02:23<20:19:31, 28.23s/it] 48%|████▊ | 2409/5000 [20:02:49<19:56:53, 27.72s/it] 48%|████▊ | 2410/5000 [20:03:16<19:45:51, 27.47s/it] 48%|████▊ | 2411/5000 [20:03:45<19:59:36, 27.80s/it] 48%|████▊ | 2412/5000 [20:04:12<19:52:02, 27.64s/it] 48%|████▊ | 2413/5000 [20:04:40<19:48:48, 27.57s/it] 48%|████▊ | 2414/5000 [20:05:08<19:55:47, 27.74s/it] 48%|████▊ | 2415/5000 [20:05:35<19:46:15, 27.53s/it] 48%|████▊ | 2416/5000 [20:06:02<19:36:15, 27.31s/it] 48%|████▊ | 2417/5000 [20:06:32<20:20:40, 28.35s/it] 48%|████▊ | 2418/5000 [20:07:00<20:08:19, 28.08s/it] 48%|████▊ | 2419/5000 [20:07:27<19:55:48, 27.80s/it] 48%|████▊ | 2420/5000 [20:07:54<19:48:56, 27.65s/it] 48%|████▊ | 2421/5000 [20:08:23<20:00:37, 27.93s/it] 48%|████▊ | 2422/5000 [20:08:50<19:51:40, 27.73s/it] 48%|████▊ | 2423/5000 [20:09:17<19:45:02, 27.59s/it] 48%|████▊ | 2424/5000 [20:09:46<19:53:06, 27.79s/it] 48%|████▊ | 2425/5000 [20:10:13<19:49:52, 27.73s/it] 48%|████▊ | 2425/5000 [20:10:13<19:49:52, 27.73s/it] 49%|████▊ | 2426/5000 [20:10:40<19:37:49, 27.46s/it] 49%|██��█▊ | 2427/5000 [20:11:10<20:04:31, 28.09s/it] 49%|████▊ | 2428/5000 [20:11:37<19:51:06, 27.79s/it] 49%|████▊ | 2429/5000 [20:12:04<19:43:32, 27.62s/it] 49%|████▊ | 2430/5000 [20:12:32<19:50:39, 27.80s/it] 49%|████▊ | 2431/5000 [20:12:59<19:44:49, 27.67s/it] 49%|████▊ | 2432/5000 [20:13:27<19:38:50, 27.54s/it] 49%|████▊ | 2433/5000 [20:13:56<20:01:37, 28.09s/it] 49%|████▊ | 2434/5000 [20:14:23<19:51:06, 27.85s/it] 49%|████▊ | 2435/5000 [20:14:51<19:44:16, 27.70s/it] 49%|████▊ | 2436/5000 [20:15:19<19:56:15, 27.99s/it] 49%|████▊ | 2437/5000 [20:15:46<19:34:39, 27.50s/it] 49%|████▉ | 2438/5000 [20:16:12<19:23:03, 27.24s/it] 49%|████▉ | 2439/5000 [20:16:40<19:34:06, 27.51s/it] 49%|████▉ | 2440/5000 [20:17:08<19:31:14, 27.45s/it] 49%|████▉ | 2441/5000 [20:17:35<19:29:47, 27.43s/it] 49%|████▉ | 2442/5000 [20:18:04<19:42:37, 27.74s/it] 49%|████▉ | 2443/5000 [20:18:31<19:37:55, 27.64s/it] 49%|████▉ | 2444/5000 [20:18:58<19:33:46, 27.55s/it] 49%|████▉ | 2445/5000 [20:19:27<19:44:28, 27.82s/it] 49%|████▉ | 2446/5000 [20:19:54<19:38:18, 27.68s/it] 49%|████▉ | 2447/5000 [20:20:22<19:35:44, 27.63s/it] 49%|████▉ | 2448/5000 [20:20:51<19:56:19, 28.13s/it] 49%|████▉ | 2449/5000 [20:21:05<16:53:12, 23.83s/it] 49%|████▉ | 2450/5000 [20:21:16<14:09:22, 19.99s/it] 49%|████▉ | 2450/5000 [20:21:16<14:09:22, 19.99s/it] 49%|████▉ | 2451/5000 [20:21:27<12:12:47, 17.25s/it] 49%|████▉ | 2452/5000 [20:21:37<10:49:43, 15.30s/it]{'loss': 0.0025, 'learning_rate': 6.004444444444445e-06, 'epoch': 14.0} -{'loss': 0.0024, 'learning_rate': 5.948888888888889e-06, 'epoch': 14.01} -{'loss': 0.0022, 'learning_rate': 5.893333333333334e-06, 'epoch': 14.01} -{'loss': 0.0019, 'learning_rate': 5.837777777777777e-06, 'epoch': 14.02} -{'loss': 0.0018, 'learning_rate': 5.782222222222222e-06, 'epoch': 14.02} -{'loss': 0.0021, 'learning_rate': 5.726666666666667e-06, 'epoch': 14.03} -{'loss': 0.0016, 'learning_rate': 5.671111111111112e-06, 'epoch': 14.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:01, 1.09s/it] - Reading metadata...: 15097it [00:01, 17488.29it/s] - Reading metadata...: 23977it [00:01, 21556.38it/s] Reading metadata...: 28043it [00:01, 18517.58it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 2.34it/s] Reading metadata...: 10438it [00:00, 20922.81it/s] - 49%|████▉ | 2453/5000 [20:23:03<25:48:07, 36.47s/it] 49%|████▉ | 2454/5000 [20:23:31<23:58:31, 33.90s/it] 49%|████▉ | 2455/5000 [20:23:59<22:38:11, 32.02s/it] 49%|████▉ | 2456/5000 [20:24:27<21:47:23, 30.83s/it] 49%|████▉ | 2457/5000 [20:24:54<21:00:56, 29.75s/it] 49%|████▉ | 2458/5000 [20:25:22<20:34:42, 29.14s/it] 49%|████▉ | 2459/5000 [20:25:50<20:21:51, 28.85s/it] 49%|████▉ | 2460/5000 [20:26:18<20:13:51, 28.67s/it] 49%|████▉ | 2461/5000 [20:26:47<20:17:52, 28.78s/it] 49%|████▉ | 2462/5000 [20:27:15<20:02:28, 28.43s/it] 49%|████▉ | 2463/5000 [20:27:43<19:54:36, 28.25s/it] 49%|████▉ | 2464/5000 [20:28:11<19:57:13, 28.33s/it] 49%|████▉ | 2465/5000 [20:28:39<19:44:19, 28.03s/it] 49%|████▉ | 2466/5000 [20:29:06<19:42:23, 28.00s/it] 49%|████▉ | 2467/5000 [20:29:34<19:40:14, 27.96s/it] 49%|████▉ | 2468/5000 [20:30:03<19:52:35, 28.26s/it] 49%|████▉ | 2469/5000 [20:30:31<19:46:50, 28.14s/it] 49%|████▉ | 2470/5000 [20:30:58<19:31:33, 27.78s/it] 49%|████▉ | 2471/5000 [20:31:27<19:41:07, 28.02s/it] 49%|████▉ | 2472/5000 [20:31:55<19:44:35, 28.12s/it] 49%|████▉ | 2473/5000 [20:32:22<19:35:14, 27.90s/it] 49%|████▉ | 2474/5000 [20:32:51<19:38:28, 27.99s/it] 50%|████▉ | 2475/5000 [20:33:19<19:42:39, 28.10s/it] 50%|████▉ | 2475/5000 [20:33:19<19:42:39, 28.10s/it] 50%|████▉ | 2476/5000 [20:33:46<19:29:45, 27.81s/it] 50%|████▉ | 2477/5000 [20:34:14<19:35:50, 27.96s/it] 50%|████▉ | 2478/5000 [20:34:42<19:29:58, 27.83s/it] 50%|████▉ | 2479/5000 [20:35:09<19:22:56, 27.68s/it] 50%|████▉ | 2480/5000 [20:35:37<19:24:05, 27.72s/it] 50%|████▉ | 2481/5000 [20:36:05<19:29:59, 27.87s/it] 50%|████▉ | 2482/5000 [20:36:32<19:19:49, 27.64s/it] 50%|████▉ | 2483/5000 [20:37:00<19:24:27, 27.76s/it] 50%|████▉ | 2484/5000 [20:37:28<19:26:36, 27.82s/it] 50%|██���█▉ | 2485/5000 [20:37:56<19:22:27, 27.73s/it] 50%|████▉ | 2486/5000 [20:38:25<19:35:51, 28.06s/it] 50%|████▉ | 2487/5000 [20:38:52<19:25:35, 27.83s/it] 50%|████▉ | 2488/5000 [20:39:20<19:20:03, 27.71s/it] 50%|████▉ | 2489/5000 [20:39:47<19:21:41, 27.76s/it] 50%|████▉ | 2490/5000 [20:40:15<19:13:26, 27.57s/it] 50%|████▉ | 2491/5000 [20:40:42<19:08:29, 27.46s/it] 50%|████▉ | 2492/5000 [20:41:10<19:17:09, 27.68s/it] 50%|████▉ | 2493/5000 [20:41:38<19:26:46, 27.92s/it] 50%|████▉ | 2494/5000 [20:42:06<19:19:39, 27.76s/it] 50%|████▉ | 2495/5000 [20:42:34<19:24:25, 27.89s/it] 50%|████▉ | 2496/5000 [20:43:02<19:28:12, 27.99s/it] 50%|████▉ | 2497/5000 [20:43:30<19:20:00, 27.81s/it] 50%|████▉ | 2498/5000 [20:43:58<19:24:05, 27.92s/it] 50%|████▉ | 2499/5000 [20:44:26<19:28:55, 28.04s/it] 50%|█████ | 2500/5000 [20:44:54<19:26:57, 28.01s/it] 50%|█████ | 2500/5000 [20:44:54<19:26:57, 28.01s/it] 50%|█████ | 2501/5000 [20:45:21<19:18:54, 27.83s/it] 50%|█████ | 2502/5000 [20:45:49<19:12:51, 27.69s/it] 50%|█████ | 2503/5000 [20:46:18<19:27:44, 28.06s/it] 50%|█████ | 2504/5000 [20:46:45<19:20:52, 27.91s/it] 50%|█████ | 2505/5000 [20:47:14<19:27:27, 28.08s/it] 50%|█████ | 2506/5000 [20:47:42<19:33:14, 28.23s/it] 50%|█████ | 2507/5000 [20:48:10<19:22:44, 27.98s/it] 50%|█████ | 2508/5000 [20:48:43<20:26:12, 29.52s/it] 50%|█████ | 2509/5000 [20:49:10<20:01:37, 28.94s/it] 50%|█████ | 2510/5000 [20:49:38<19:45:00, 28.55s/it] 50%|█████ | 2511/5000 [20:50:12<20:46:43, 30.05s/it] 50%|█████ | 2512/5000 [20:50:39<20:11:18, 29.21s/it] 50%|█████ | 2513/5000 [20:51:06<19:48:25, 28.67s/it] 50%|█████ | 2514/5000 [20:51:34<19:36:37, 28.40s/it] 50%|█████ | 2515/5000 [20:52:01<19:23:28, 28.09s/it] 50%|█████ | 2516/5000 [20:52:29<19:15:24, 27.91s/it] 50%|█████ | 2517/5000 [20:52:57<19:16:38, 27.95s/it] 50%|█████ | 2518/5000 [20:53:25<19:13:39, 27.89s/it] 50%|█████ | 2519/5000 [20:53:52<19:06:33, 27.73s/it] 50%|█████ | 2520/5000 [20:54:20<19:08:34, 27.79s/it] 50%|█████ | 2521/5000 [20:54:48<19:14:00, 27.93s/it] 50%|█████ | 2522/5000 [20:55:16<19:05:29, 27.74s/it] 50%|█████ | 2523/5000 [20:55:44<19:08:49, 27.83s/it] 50%|█████ | 2524/5000 [20:56:12<19:11:49, 27.91s/it] 50%|█████ | 2525/5000 [20:56:39<19:02:25, 27.69s/it] 50%|█████ | 2525/5000 [20:56:39<19:02:25, 27.69s/it] 51%|█████ | 2526/5000 [20:57:08<19:15:07, 28.01s/it] 51%|█████ | 2527/5000 [20:57:35<19:03:57, 27.75s/it] 51%|█████ | 2528/5000 [20:58:03<19:04:42, 27.78s/it] 51%|█████ | 2529/5000 [20:58:30<18:59:48, 27.68s/it] 51%|█████ | 2530/5000 [20:58:57<18:54:29, 27.56s/it] 51%|█████ | 2531/5000 [20:59:26<19:05:29, 27.84s/it] 51%|█████ | 2532/5000 [20:59:53<19:02:33, 27.78s/it] 51%|█████ | 2533/5000 [21:00:26<19:54:56, 29.06s/it] 51%|█████ | 2534/5000 [21:00:54<19:40:59, 28.73s/it] 51%|█████ | 2535/5000 [21:01:21<19:23:51, 28.33s/it] 51%|█████ | 2536/5000 [21:01:49<19:22:17, 28.30s/it] 51%|█████ | 2537/5000 [21:02:17<19:14:32, 28.13s/it] 51%|█████ | 2538/5000 [21:02:43<18:50:31, 27.55s/it] 51%|█████ | 2539/5000 [21:03:10<18:44:55, 27.43s/it] 51%|█████ | 2540/5000 [21:03:38<18:52:46, 27.63s/it] 51%|█████ | 2541/5000 [21:04:05<18:39:33, 27.32s/it] 51%|█████ | 2542/5000 [21:04:32<18:40:42, 27.36s/it] 51%|█████ | 2543/5000 [21:05:00<18:45:18, 27.48s/it] 51%|█████ | 2544/5000 [21:05:27<18:41:19, 27.39s/it] 51%|█████ | 2545/5000 [21:05:57<19:15:20, 28.24s/it] 51%|█████ | 2546/5000 [21:06:26<19:14:31, 28.23s/it] 51%|█████ | 2547/5000 [21:06:52<18:52:26, 27.70s/it] 51%|█████ | 2548/5000 [21:07:20<18:51:45, 27.69s/it] 51%|█████ | 2549/5000 [21:07:48<18:50:45, 27.68s/it] 51%|█████ | 2550/5000 [21:08:15<18:45:33, 27.56s/it] 51%|█████ | 2550/5000 [21:08:15<18:45:33, 27.56s/it] 51%|█████ | 2551/5000 [21:08:45<19:19:18, 28.40s/it] 51%|█████ | 2552/5000 [21:09:14<19:18:52, 28.40s/it] 51%|█████ | 2553/5000 [21:09:42<19:16:42, 28.36s/it] 51%|█████ | 2554/5000 [21:10:10<19:08:51, 28.18s/it] 51%|█████ | 2555/5000 [21:10:38<19:11:14, 28.25s/it] 51%|█████ | 2556/5000 [21:11:06<19:03:22, 28.07s/it] 51%|█████ | 2557/5000 [21:11:33<18:55:46, 27.89s/it] 51%|█████ | 2558/5000 [21:12:00<18:47:57, 27.71s/it] 51%|█████ | 2559/5000 [21:12:29<18:55:23, 27.91s/it] 51%|█████ | 2560/5000 [21:12:56<18:44:59, 27.66s/it] 51%|█████ | 2561/5000 [21:13:23<18:42:06, 27.60s/it] 51%|█████ | 2562/5000 [21:13:52<18:53:46, 27.90s/it] 51%|█████▏ | 2563/5000 [21:14:19<18:45:16, 27.70s/it] 51%|█████▏ | 2564/5000 [21:14:46<18:38:46, 27.56s/it] 51%|█████▏ | 2565/5000 [21:15:15<18:56:55, 28.01s/it] 51%|█████▏ | 2566/5000 [21:15:43<18:49:50, 27.85s/it] 51%|█████▏ | 2567/5000 [21:16:11<18:53:56, 27.96s/it] 51%|█████▏ | 2568/5000 [21:16:40<18:59:02, 28.10s/it] 51%|█████▏ | 2569/5000 [21:17:07<18:53:18, 27.97s/it] 51%|█████▏ | 2570/5000 [21:17:35<18:45:31, 27.79s/it] 51%|█████▏ | 2571/5000 [21:18:02<18:41:33, 27.70s/it] 51%|█████▏ | 2572/5000 [21:18:30<18:40:45, 27.70s/it] 51%|█████▏ | 2573/5000 [21:18:57<18:37:15, 27.62s/it] 51%|█████▏ | 2574/5000 [21:19:27<19:00:41, 28.21s/it] 52%|█████▏ | 2575/5000 [21:19:53<18:40:44, 27.73s/it] 52%|█████▏ | 2575/5000 [21:19:53<18:40:44, 27.73s/it] 52%|█████▏ | 2576/5000 [21:20:20<18:23:25, 27.31s/it] 52%|█████▏ | 2577/5000 [21:20:47<18:23:25, 27.32s/it] 52%|█████▏ | 2578/5000 [21:21:15<18:27:12, 27.43s/it] 52%|█████▏ | 2579/5000 [21:21:42<18:27:53, 27.46s/it] 52%|█████▏ | 2580/5000 [21:22:10<18:24:39, 27.39s/it] 52%|█████▏ | 2581/5000 [21:22:38<18:36:51, 27.70s/it] 52%|█████▏ | 2582/5000 [21:23:05<18:31:11, 27.57s/it] 52%|█████▏ | 2583/5000 [21:23:32<18:22:59, 27.38s/it] 52%|█████▏ | 2584/5000 [21:24:01<18:36:49, 27.74s/it] 52%|█████▏ | 2585/5000 [21:24:28<18:30:07, 27.58s/it] 52%|█████▏ | 2586/5000 [21:24:55<18:27:47, 27.53s/it] 52%|█████▏ | 2587/5000 [21:25:25<18:46:04, 28.00s/it] 52%|█████▏ | 2588/5000 [21:25:52<18:40:46, 27.88s/it] 52%|█████▏ | 2589/5000 [21:26:19<18:29:06, 27.60s/it] 52%|█████▏ | 2590/5000 [21:26:47<18:36:05, 27.79s/it] 52%|█████▏ | 2591/5000 [21:27:15<18:39:51, 27.89s/it] 52%|█████▏ | 2592/5000 [21:27:43<18:30:39, 27.67s/it] 52%|█████▏ | 2593/5000 [21:28:11<18:34:07, 27.77s/it] 52%|█████▏ | 2594/5000 [21:28:39<18:36:46, 27.85s/it] 52%|█████▏ | 2595/5000 [21:29:06<18:31:16, 27.72s/it] 52%|█████▏ | 2596/5000 [21:29:34<18:38:15, 27.91s/it] 52%|█████▏ | 2597/5000 [21:30:03<18:45:47, 28.11s/it] 52%|█████▏ | 2598/5000 [21:30:30<18:38:27, 27.94s/it] 52%|█████▏ | 2599/5000 [21:30:59<18:50:17, 28.25s/it] 52%|█████▏ | 2600/5000 [21:31:27<18:47:00, 28.18s/it] 52%|█████▏ | 2600/5000 [21:31:27<18:47:00, 28.18s/it] 52%|█████▏ | 2601/5000 [21:31:55<18:38:47, 27.98s/it] 52%|█████▏ | 2602/5000 [21:32:24<18:51:26, 28.31s/it] 52%|█████▏ | 2603/5000 [21:32:52<18:40:26, 28.05s/it] 52%|█████▏ | 2604/5000 [21:33:19<18:29:38, 27.79s/it] 52%|█████▏ | 2605/5000 [21:33:48<18:42:02, 28.11s/it] 52%|█████▏ | 2606/5000 [21:34:15<18:33:04, 27.90s/it] 52%|█████▏ | 2607/5000 [21:34:42<18:27:30, 27.77s/it] 52%|█████▏ | 2608/5000 [21:35:10<18:29:49, 27.84s/it] 52%|█████▏ | 2609/5000 [21:35:38<18:22:58, 27.68s/it] 52%|█████▏ | 2610/5000 [21:36:05<18:16:19, 27.52s/it] 52%|█████▏ | 2611/5000 [21:36:33<18:24:03, 27.73s/it] 52%|█████▏ | 2612/5000 [21:36:55<17:17:28, 26.07s/it] 52%|█████▏ | 2613/5000 [21:37:06<14:15:29, 21.50s/it] 52%|█████▏ | 2614/5000 [21:37:17<12:09:15, 18.34s/it] 52%|█████▏ | 2615/5000 [21:37:28<10:38:42, 16.07s/it] 52%|█████▏ | 2616/5000 [21:37:36<8:59:53, 13.59s/it] {'loss': 0.0016, 'learning_rate': 5.615555555555556e-06, 'epoch': 15.0} -{'loss': 0.0018, 'learning_rate': 5.560000000000001e-06, 'epoch': 15.01} -{'loss': 0.0014, 'learning_rate': 5.504444444444444e-06, 'epoch': 15.01} -{'loss': 0.0013, 'learning_rate': 5.448888888888889e-06, 'epoch': 15.02} -{'loss': 0.0014, 'learning_rate': 5.393333333333334e-06, 'epoch': 15.02} -{'loss': 0.0015, 'learning_rate': 5.337777777777779e-06, 'epoch': 15.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.18it/s] - Reading metadata...: 14583it [00:00, 45554.73it/s] - Reading metadata...: 23161it [00:00, 35502.77it/s] Reading metadata...: 28043it [00:00, 37305.62it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.69it/s] Reading metadata...: 10438it [00:00, 30532.73it/s] - 52%|█████▏ | 2617/5000 [21:39:14<25:47:54, 38.97s/it] 52%|█████▏ | 2618/5000 [21:39:42<23:36:56, 35.69s/it] 52%|█████▏ | 2619/5000 [21:40:09<21:57:36, 33.20s/it] 52%|█████▏ | 2620/5000 [21:40:38<20:57:40, 31.71s/it] 52%|█████▏ | 2621/5000 [21:41:06<20:18:41, 30.74s/it] 52%|█████▏ | 2622/5000 [21:41:35<19:57:13, 30.21s/it] 52%|█████▏ | 2623/5000 [21:42:02<19:23:14, 29.36s/it] 52%|█████▏ | 2624/5000 [21:42:30<18:57:49, 28.73s/it] 52%|█████▎ | 2625/5000 [21:42:58<18:52:14, 28.60s/it] 52%|█████▎ | 2625/5000 [21:42:58<18:52:14, 28.60s/it] 53%|█████▎ | 2626/5000 [21:43:25<18:32:54, 28.13s/it] 53%|█████▎ | 2627/5000 [21:43:52<18:22:30, 27.88s/it] 53%|█████▎ | 2628/5000 [21:44:20<18:22:34, 27.89s/it] 53%|█████▎ | 2629/5000 [21:44:48<18:23:17, 27.92s/it] 53%|█████▎ | 2630/5000 [21:45:16<18:26:33, 28.01s/it] 53%|█████▎ | 2631/5000 [21:45:44<18:16:32, 27.77s/it] 53%|█████▎ | 2632/5000 [21:46:12<18:24:34, 27.99s/it] 53%|█████▎ | 2633/5000 [21:46:40<18:24:53, 28.01s/it] 53%|█████▎ | 2634/5000 [21:47:08<18:18:20, 27.85s/it] 53%|█████▎ | 2635/5000 [21:47:35<18:16:29, 27.82s/it] 53%|█████▎ | 2636/5000 [21:48:03<18:12:14, 27.72s/it] 53%|█████▎ | 2637/5000 [21:48:30<18:00:45, 27.44s/it] 53%|█████▎ | 2638/5000 [21:48:58<18:10:46, 27.71s/it] 53%|█████▎ | 2639/5000 [21:49:26<18:09:21, 27.68s/it] 53%|█████▎ | 2640/5000 [21:49:53<18:05:51, 27.61s/it] 53%|█████▎ | 2641/5000 [21:50:21<18:14:13, 27.83s/it] 53%|█████▎ | 2642/5000 [21:50:48<18:03:48, 27.58s/it] 53%|█████▎ | 2643/5000 [21:51:15<17:56:46, 27.41s/it] 53%|█████▎ | 2644/5000 [21:51:44<18:15:57, 27.91s/it] 53%|█████▎ | 2645/5000 [21:52:12<18:10:52, 27.79s/it] 53%|█████▎ | 2646/5000 [21:52:39<18:02:27, 27.59s/it] 53%|█████▎ | 2647/5000 [21:53:08<18:15:09, 27.93s/it] 53%|█████▎ | 2648/5000 [21:53:35<18:09:39, 27.80s/it] 53%|█████▎ | 2649/5000 [21:54:03<18:04:16, 27.67s/it] 53%|█████▎ | 2650/5000 [21:54:31<18:09:06, 27.81s/it] 53%|█████▎ | 2650/5000 [21:54:31<18:09:06, 27.81s/it] 53%|█████▎ | 2651/5000 [21:54:58<18:02:32, 27.65s/it] 53%|█████▎ | 2652/5000 [21:55:26<17:59:12, 27.58s/it] 53%|█████▎ | 2653/5000 [21:55:54<18:12:54, 27.94s/it] 53%|█████▎ | 2654/5000 [21:56:22<18:06:22, 27.78s/it] 53%|█████▎ | 2655/5000 [21:56:49<18:02:35, 27.70s/it] 53%|█████▎ | 2656/5000 [21:57:18<18:13:41, 28.00s/it] 53%|█████▎ | 2657/5000 [21:57:45<18:07:59, 27.86s/it] 53%|█████▎ | 2658/5000 [21:58:14<18:10:10, 27.93s/it] 53%|█████▎ | 2659/5000 [21:58:42<18:15:31, 28.08s/it] 53%|█████▎ | 2660/5000 [21:59:09<18:08:13, 27.90s/it] 53%|█████▎ | 2661/5000 [21:59:37<18:05:35, 27.85s/it] 53%|█████▎ | 2662/5000 [22:00:03<17:42:53, 27.28s/it] 53%|█████▎ | 2663/5000 [22:00:32<17:56:27, 27.64s/it] 53%|█████▎ | 2664/5000 [22:01:00<18:01:05, 27.77s/it] 53%|█████▎ | 2665/5000 [22:01:27<17:55:17, 27.63s/it] 53%|█████▎ | 2666/5000 [22:01:56<18:06:41, 27.94s/it] 53%|█████▎ | 2667/5000 [22:02:24<18:12:40, 28.10s/it] 53%|█████▎ | 2668/5000 [22:02:52<18:05:46, 27.94s/it] 53%|█████▎ | 2669/5000 [22:03:25<19:06:25, 29.51s/it] 53%|█████▎ | 2670/5000 [22:03:51<18:30:48, 28.60s/it] 53%|█████▎ | 2671/5000 [22:04:19<18:15:12, 28.22s/it] 53%|█████▎ | 2672/5000 [22:04:48<18:27:02, 28.53s/it] 53%|█████▎ | 2673/5000 [22:05:15<18:13:58, 28.21s/it] 53%|█████▎ | 2674/5000 [22:05:42<17:55:47, 27.75s/it] 54%|█████▎ | 2675/5000 [22:06:11<18:03:49, 27.97s/it] 54%|█████▎ | 2675/5000 [22:06:11<18:03:49, 27.97s/it] 54%|█████▎ | 2676/5000 [22:06:38<17:54:29, 27.74s/it] 54%|█████▎ | 2677/5000 [22:07:05<17:51:56, 27.69s/it] 54%|█████▎ | 2678/5000 [22:07:33<17:54:56, 27.78s/it] 54%|█████▎ | 2679/5000 [22:08:00<17:42:23, 27.46s/it] 54%|█████▎ | 2680/5000 [22:08:27<17:40:15, 27.42s/it] 54%|█████▎ | 2681/5000 [22:08:57<18:01:31, 27.98s/it] 54%|█████▎ | 2682/5000 [22:09:24<17:51:57, 27.75s/it] 54%|█████▎ | 2683/5000 [22:09:52<18:01:06, 28.00s/it] 54%|█████▎ | 2684/5000 [22:10:20<17:55:32, 27.86s/it] 54%|█████▎ | 2685/5000 [22:10:47<17:45:38, 27.62s/it] 54%|█████▎ | 2686/5000 [22:11:15<17:51:39, 27.79s/it] 54%|█████▎ | 2687/5000 [22:11:42<17:36:42, 27.41s/it] 54%|█████▍ | 2688/5000 [22:12:09<17:37:33, 27.45s/it] 54%|█████▍ | 2689/5000 [22:12:37<17:38:04, 27.47s/it] 54%|█████▍ | 2690/5000 [22:13:03<17:27:02, 27.20s/it] 54%|█████▍ | 2691/5000 [22:13:31<17:33:06, 27.37s/it] 54%|█████▍ | 2692/5000 [22:13:59<17:34:02, 27.40s/it] 54%|█████▍ | 2693/5000 [22:14:26<17:28:21, 27.27s/it] 54%|█████▍ | 2694/5000 [22:14:53<17:31:35, 27.36s/it] 54%|█████▍ | 2695/5000 [22:15:22<17:50:52, 27.88s/it] 54%|█████▍ | 2696/5000 [22:15:49<17:40:21, 27.61s/it] 54%|█████▍ | 2697/5000 [22:16:18<17:48:36, 27.84s/it] 54%|█████▍ | 2698/5000 [22:16:45<17:39:58, 27.63s/it] 54%|█████▍ | 2699/5000 [22:17:12<17:36:47, 27.56s/it] 54%|█████▍ | 2700/5000 [22:17:40<17:42:07, 27.71s/it] 54%|█████▍ | 2700/5000 [22:17:40<17:42:07, 27.71s/it] 54%|█████▍ | 2701/5000 [22:18:08<17:44:02, 27.77s/it] 54%|█████▍ | 2702/5000 [22:18:36<17:46:31, 27.85s/it] 54%|█████▍ | 2703/5000 [22:19:04<17:41:58, 27.74s/it] 54%|█████▍ | 2704/5000 [22:19:32<17:44:46, 27.83s/it] 54%|█████▍ | 2705/5000 [22:19:59<17:44:02, 27.82s/it] 54%|█████▍ | 2706/5000 [22:20:27<17:38:51, 27.69s/it] 54%|█████▍ | 2707/5000 [22:20:54<17:37:54, 27.68s/it] 54%|█████▍ | 2708/5000 [22:21:22<17:36:11, 27.65s/it] 54%|█████▍ | 2709/5000 [22:21:49<17:28:49, 27.47s/it] 54%|█████▍ | 2710/5000 [22:22:17<17:32:37, 27.58s/it] 54%|█████▍ | 2711/5000 [22:22:45<17:34:52, 27.65s/it] 54%|█████▍ | 2712/5000 [22:23:12<17:33:05, 27.62s/it] 54%|█████▍ | 2713/5000 [22:23:41<17:42:49, 27.88s/it] 54%|█████▍ | 2714/5000 [22:24:10<17:58:08, 28.30s/it] 54%|█████▍ | 2715/5000 [22:24:37<17:46:02, 27.99s/it] 54%|█████▍ | 2716/5000 [22:25:06<17:48:45, 28.08s/it] 54%|█████▍ | 2717/5000 [22:25:39<18:52:59, 29.78s/it] 54%|█████▍ | 2718/5000 [22:26:06<18:22:00, 28.97s/it] 54%|█████▍ | 2719/5000 [22:26:35<18:11:33, 28.71s/it] 54%|█████▍ | 2720/5000 [22:27:01<17:46:54, 28.08s/it] 54%|█████▍ | 2721/5000 [22:27:28<17:33:59, 27.75s/it] 54%|█████▍ | 2722/5000 [22:27:57<17:44:07, 28.03s/it] 54%|█████▍ | 2723/5000 [22:28:24<17:36:21, 27.84s/it] 54%|█████▍ | 2724/5000 [22:28:51<17:28:07, 27.63s/it] 55%|█████▍ | 2725/5000 [22:29:20<17:34:08, 27.80s/it] 55%|█████▍ | 2725/5000 [22:29:20<17:34:08, 27.80s/it] 55%|█████▍ | 2726/5000 [22:29:47<17:29:13, 27.68s/it] 55%|█████▍ | 2727/5000 [22:30:14<17:21:55, 27.50s/it] 55%|█████▍ | 2728/5000 [22:30:42<17:27:45, 27.67s/it] 55%|█████▍ | 2729/5000 [22:31:10<17:27:07, 27.67s/it] 55%|█████▍ | 2730/5000 [22:31:37<17:23:23, 27.58s/it] 55%|█████▍ | 2731/5000 [22:32:06<17:32:15, 27.83s/it] 55%|█████▍ | 2732/5000 [22:32:33<17:30:10, 27.78s/it] 55%|█████▍ | 2733/5000 [22:33:01<17:34:51, 27.92s/it] 55%|█████▍ | 2734/5000 [22:33:29<17:27:53, 27.75s/it] 55%|█████▍ | 2735/5000 [22:33:57<17:33:23, 27.90s/it] 55%|█████▍ | 2736/5000 [22:34:24<17:23:05, 27.64s/it] 55%|█████▍ | 2737/5000 [22:34:51<17:16:45, 27.49s/it] 55%|█████▍ | 2738/5000 [22:35:19<17:20:14, 27.59s/it] 55%|█████▍ | 2739/5000 [22:35:46<17:08:56, 27.30s/it] 55%|█████▍ | 2740/5000 [22:36:12<16:59:32, 27.07s/it] 55%|█████▍ | 2741/5000 [22:36:44<17:54:56, 28.55s/it] 55%|█████▍ | 2742/5000 [22:37:12<17:41:19, 28.20s/it] 55%|█████▍ | 2743/5000 [22:37:39<17:26:13, 27.81s/it] 55%|█████▍ | 2744/5000 [22:38:07<17:33:33, 28.02s/it] 55%|█████▍ | 2745/5000 [22:38:34<17:18:32, 27.63s/it] 55%|█████▍ | 2746/5000 [22:39:00<17:01:21, 27.19s/it] 55%|█████▍ | 2747/5000 [22:39:26<16:51:39, 26.94s/it] 55%|█████▍ | 2748/5000 [22:39:55<17:14:19, 27.56s/it] 55%|█████▍ | 2749/5000 [22:40:23<17:10:47, 27.48s/it] 55%|█████▌ | 2750/5000 [22:40:49<17:01:49, 27.25s/it] 55%|█████▌ | 2750/5000 [22:40:49<17:01:49, 27.25s/it] 55%|█████▌ | 2751/5000 [22:41:18<17:21:37, 27.79s/it] 55%|█████▌ | 2752/5000 [22:41:45<17:12:06, 27.55s/it] 55%|█████▌ | 2753/5000 [22:42:12<17:02:49, 27.31s/it] 55%|█████▌ | 2754/5000 [22:42:42<17:28:40, 28.01s/it] 55%|█████▌ | 2755/5000 [22:43:09<17:21:40, 27.84s/it] 55%|█████▌ | 2756/5000 [22:43:36<17:14:22, 27.66s/it] 55%|█████▌ | 2757/5000 [22:44:04<17:18:31, 27.78s/it] 55%|█████▌ | 2758/5000 [22:44:32<17:13:01, 27.65s/it] 55%|█████▌ | 2759/5000 [22:44:59<17:05:57, 27.47s/it] 55%|█████▌ | 2760/5000 [22:45:27<17:17:01, 27.78s/it] 55%|█████▌ | 2761/5000 [22:45:55<17:13:12, 27.69s/it] 55%|█████▌ | 2762/5000 [22:46:22<17:09:30, 27.60s/it] 55%|█████▌ | 2763/5000 [22:46:51<17:22:59, 27.97s/it] 55%|█████▌ | 2764/5000 [22:47:18<17:14:58, 27.77s/it] 55%|█████▌ | 2765/5000 [22:47:46<17:09:36, 27.64s/it] 55%|█████▌ | 2766/5000 [22:48:15<17:28:03, 28.15s/it] 55%|█████▌ | 2767/5000 [22:48:42<17:17:42, 27.88s/it] 55%|█████▌ | 2768/5000 [22:49:09<17:08:48, 27.66s/it] 55%|█████▌ | 2769/5000 [22:49:37<17:13:17, 27.79s/it] 55%|█████▌ | 2770/5000 [22:50:04<17:03:38, 27.54s/it] 55%|█████▌ | 2771/5000 [22:50:31<16:49:48, 27.18s/it] 55%|█████▌ | 2772/5000 [22:50:59<17:00:03, 27.47s/it] 55%|█████▌ | 2773/5000 [22:51:26<16:56:21, 27.38s/it] 55%|█████▌ | 2774/5000 [22:51:54<16:57:03, 27.41s/it] 56%|█████▌ | 2775/5000 [22:52:22<17:07:17, 27.70s/it] 56%|█████▌ | 2775/5000 [22:52:22<17:07:17, 27.70s/it] 56%|█████▌ | 2776/5000 [22:52:36<14:33:28, 23.57s/it] 56%|█████▌ | 2777/5000 [22:52:47<12:11:00, 19.73s/it] 56%|█████▌ | 2778/5000 [22:52:58<10:33:05, 17.09s/it] 56%|█████▌ | 2779/5000 [22:53:08<9:21:54, 15.18s/it] {'loss': 0.0013, 'learning_rate': 5.282222222222223e-06, 'epoch': 16.0} -{'loss': 0.0012, 'learning_rate': 5.226666666666667e-06, 'epoch': 16.01} -{'loss': 0.0013, 'learning_rate': 5.171111111111111e-06, 'epoch': 16.01} -{'loss': 0.001, 'learning_rate': 5.115555555555556e-06, 'epoch': 16.02} -{'loss': 0.0011, 'learning_rate': 5.060000000000001e-06, 'epoch': 16.02} -{'loss': 0.0011, 'learning_rate': 5.004444444444445e-06, 'epoch': 16.03} -{'loss': 0.0009, 'learning_rate': 4.94888888888889e-06, 'epoch': 16.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.30it/s] - Reading metadata...: 14288it [00:00, 45788.86it/s] - Reading metadata...: 22692it [00:00, 34929.73it/s] Reading metadata...: 28043it [00:00, 37576.14it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.17it/s] Reading metadata...: 10438it [00:00, 27193.36it/s] - 56%|█████▌ | 2780/5000 [22:54:36<22:44:03, 36.87s/it] 56%|█████▌ | 2781/5000 [22:55:04<21:02:19, 34.13s/it] 56%|█████▌ | 2782/5000 [22:55:31<19:47:19, 32.12s/it] 56%|█████▌ | 2783/5000 [22:55:59<19:06:51, 31.04s/it] 56%|█████▌ | 2784/5000 [22:56:27<18:23:20, 29.87s/it] 56%|█████▌ | 2785/5000 [22:56:54<17:56:35, 29.16s/it] 56%|█████▌ | 2786/5000 [22:57:22<17:36:24, 28.63s/it] 56%|█████▌ | 2787/5000 [22:57:50<17:32:53, 28.55s/it] 56%|█████▌ | 2788/5000 [22:58:18<17:22:06, 28.27s/it] 56%|█████▌ | 2789/5000 [22:58:44<16:59:44, 27.67s/it] 56%|█████▌ | 2790/5000 [22:59:12<17:05:03, 27.83s/it] 56%|█████▌ | 2791/5000 [22:59:40<17:08:10, 27.93s/it] 56%|█████▌ | 2792/5000 [23:00:08<17:02:12, 27.78s/it] 56%|█████▌ | 2793/5000 [23:00:35<17:02:59, 27.81s/it] 56%|█████▌ | 2794/5000 [23:01:10<18:16:18, 29.82s/it] 56%|█████▌ | 2795/5000 [23:01:38<17:51:19, 29.15s/it] 56%|█████▌ | 2796/5000 [23:02:05<17:28:57, 28.56s/it] 56%|█████▌ | 2797/5000 [23:02:32<17:12:50, 28.13s/it] 56%|█████▌ | 2798/5000 [23:03:00<17:16:18, 28.24s/it] 56%|█████▌ | 2799/5000 [23:03:28<17:07:04, 28.00s/it] 56%|█████▌ | 2800/5000 [23:03:55<17:01:12, 27.85s/it] 56%|█████▌ | 2800/5000 [23:03:55<17:01:12, 27.85s/it] 56%|█████▌ | 2801/5000 [23:04:24<17:05:13, 27.97s/it] 56%|█████▌ | 2802/5000 [23:04:51<16:59:14, 27.82s/it] 56%|█████▌ | 2803/5000 [23:05:18<16:53:06, 27.67s/it] 56%|█████▌ | 2804/5000 [23:05:47<16:59:15, 27.85s/it] 56%|█████▌ | 2805/5000 [23:06:14<16:57:04, 27.80s/it] 56%|█████▌ | 2806/5000 [23:06:41<16:49:54, 27.62s/it] 56%|█████▌ | 2807/5000 [23:07:09<16:51:46, 27.68s/it] 56%|█████▌ | 2808/5000 [23:07:37<16:52:54, 27.73s/it] 56%|█████▌ | 2809/5000 [23:08:04<16:47:12, 27.58s/it] 56%|█████▌ | 2810/5000 [23:08:33<16:55:41, 27.83s/it] 56%|█████▌ | 2811/5000 [23:09:01<16:57:45, 27.90s/it] 56%|█████▌ | 2812/5000 [23:09:28<16:52:27, 27.76s/it] 56%|█████▋ | 2813/5000 [23:09:56<16:53:44, 27.81s/it] 56%|█████▋ | 2814/5000 [23:10:23<16:42:35, 27.52s/it] 56%|█████▋ | 2815/5000 [23:10:51<16:41:52, 27.51s/it] 56%|█████▋ | 2816/5000 [23:11:18<16:45:57, 27.64s/it] 56%|█████▋ | 2817/5000 [23:11:46<16:48:25, 27.72s/it] 56%|█████▋ | 2818/5000 [23:12:14<16:47:14, 27.70s/it] 56%|█████▋ | 2819/5000 [23:12:42<16:54:54, 27.92s/it] 56%|█████▋ | 2820/5000 [23:13:10<16:52:25, 27.86s/it] 56%|█████▋ | 2821/5000 [23:13:37<16:37:44, 27.47s/it] 56%|█████▋ | 2822/5000 [23:14:05<16:48:12, 27.77s/it] 56%|█████▋ | 2823/5000 [23:14:33<16:46:23, 27.74s/it] 56%|█████▋ | 2824/5000 [23:15:00<16:41:20, 27.61s/it] 56%|█████▋ | 2825/5000 [23:15:28<16:46:36, 27.77s/it] 56%|█████▋ | 2825/5000 [23:15:28<16:46:36, 27.77s/it] 57%|█████▋ | 2826/5000 [23:15:57<16:50:55, 27.90s/it] 57%|█████▋ | 2827/5000 [23:16:25<16:53:54, 28.00s/it] 57%|█████▋ | 2828/5000 [23:16:52<16:46:06, 27.79s/it] 57%|█████▋ | 2829/5000 [23:17:20<16:42:23, 27.70s/it] 57%|█████▋ | 2830/5000 [23:17:48<16:53:11, 28.01s/it] 57%|█████▋ | 2831/5000 [23:18:16<16:47:03, 27.86s/it] 57%|█████▋ | 2832/5000 [23:18:44<16:47:58, 27.90s/it] 57%|█████▋ | 2833/5000 [23:19:12<16:52:58, 28.05s/it] 57%|█████▋ | 2834/5000 [23:19:39<16:41:15, 27.74s/it] 57%|█████▋ | 2835/5000 [23:20:07<16:43:16, 27.80s/it] 57%|█████▋ | 2836/5000 [23:20:35<16:43:57, 27.84s/it] 57%|█████▋ | 2837/5000 [23:21:03<16:39:17, 27.72s/it] 57%|█████▋ | 2838/5000 [23:21:30<16:39:05, 27.73s/it] 57%|█████▋ | 2839/5000 [23:21:57<16:24:10, 27.33s/it] 57%|█████▋ | 2840/5000 [23:22:24<16:23:26, 27.32s/it] 57%|█████▋ | 2841/5000 [23:22:52<16:29:12, 27.49s/it] 57%|█████▋ | 2842/5000 [23:23:19<16:25:41, 27.41s/it] 57%|█████▋ | 2843/5000 [23:23:46<16:24:17, 27.38s/it] 57%|█████▋ | 2844/5000 [23:24:16<16:46:29, 28.01s/it] 57%|█████▋ | 2845/5000 [23:24:44<16:50:06, 28.12s/it] 57%|█████▋ | 2846/5000 [23:25:12<16:43:36, 27.96s/it] 57%|█████▋ | 2847/5000 [23:25:40<16:41:43, 27.92s/it] 57%|█████▋ | 2848/5000 [23:26:07<16:38:25, 27.84s/it] 57%|█████▋ | 2849/5000 [23:26:34<16:24:17, 27.46s/it] 57%|█████▋ | 2850/5000 [23:27:02<16:33:55, 27.74s/it] 57%|█████▋ | 2850/5000 [23:27:02<16:33:55, 27.74s/it] 57%|█████▋ | 2851/5000 [23:27:31<16:41:09, 27.95s/it] 57%|█████▋ | 2852/5000 [23:27:58<16:34:40, 27.78s/it] 57%|█████▋ | 2853/5000 [23:28:26<16:30:38, 27.68s/it] 57%|█████▋ | 2854/5000 [23:28:54<16:33:21, 27.77s/it] 57%|█████▋ | 2855/5000 [23:29:21<16:34:44, 27.82s/it] 57%|█████▋ | 2856/5000 [23:29:49<16:31:38, 27.75s/it] 57%|█████▋ | 2857/5000 [23:30:17<16:32:53, 27.80s/it] 57%|█████▋ | 2858/5000 [23:30:45<16:32:09, 27.79s/it] 57%|█████▋ | 2859/5000 [23:31:12<16:25:49, 27.63s/it] 57%|█████▋ | 2860/5000 [23:31:43<17:02:27, 28.67s/it] 57%|█████▋ | 2861/5000 [23:32:11<16:56:58, 28.53s/it] 57%|█████▋ | 2862/5000 [23:32:39<16:46:50, 28.26s/it] 57%|█████▋ | 2863/5000 [23:33:07<16:43:52, 28.19s/it] 57%|█████▋ | 2864/5000 [23:33:35<16:43:56, 28.20s/it] 57%|█████▋ | 2865/5000 [23:34:03<16:35:22, 27.97s/it] 57%|█████▋ | 2866/5000 [23:34:31<16:36:19, 28.01s/it] 57%|█████▋ | 2867/5000 [23:34:58<16:31:58, 27.90s/it] 57%|█████▋ | 2868/5000 [23:35:26<16:26:57, 27.78s/it] 57%|█████▋ | 2869/5000 [23:35:54<16:34:45, 28.01s/it] 57%|█████▋ | 2870/5000 [23:36:23<16:36:57, 28.08s/it] 57%|█████▋ | 2871/5000 [23:36:50<16:31:34, 27.94s/it] 57%|█████▋ | 2872/5000 [23:37:18<16:32:29, 27.98s/it] 57%|█████▋ | 2873/5000 [23:37:47<16:36:56, 28.12s/it] 57%|█████▋ | 2874/5000 [23:38:14<16:29:40, 27.93s/it] 57%|█████▊ | 2875/5000 [23:38:42<16:22:42, 27.75s/it] 57%|█████▊ | 2875/5000 [23:38:42<16:22:42, 27.75s/it] 58%|█████▊ | 2876/5000 [23:39:13<16:55:59, 28.70s/it] 58%|█████▊ | 2877/5000 [23:39:40<16:37:28, 28.19s/it] 58%|█████▊ | 2878/5000 [23:40:07<16:29:12, 27.97s/it] 58%|█████▊ | 2879/5000 [23:40:35<16:32:48, 28.09s/it] 58%|█████▊ | 2880/5000 [23:41:03<16:31:54, 28.07s/it] 58%|█████▊ | 2881/5000 [23:41:30<16:20:19, 27.76s/it] 58%|█████▊ | 2882/5000 [23:41:59<16:25:02, 27.90s/it] 58%|█████▊ | 2883/5000 [23:42:27<16:25:38, 27.94s/it] 58%|█████▊ | 2884/5000 [23:42:53<16:11:31, 27.55s/it] 58%|█████▊ | 2885/5000 [23:43:20<15:57:00, 27.15s/it] 58%|█████▊ | 2886/5000 [23:43:47<15:54:48, 27.10s/it] 58%|█████▊ | 2887/5000 [23:44:14<15:56:46, 27.17s/it] 58%|█████▊ | 2888/5000 [23:44:41<15:55:00, 27.13s/it] 58%|█████▊ | 2889/5000 [23:45:10<16:11:35, 27.62s/it] 58%|█████▊ | 2890/5000 [23:45:37<16:07:21, 27.51s/it] 58%|█████▊ | 2891/5000 [23:46:04<16:03:26, 27.41s/it] 58%|█████▊ | 2892/5000 [23:46:32<16:11:04, 27.64s/it] 58%|█████▊ | 2893/5000 [23:47:00<16:07:11, 27.54s/it] 58%|█████▊ | 2894/5000 [23:47:27<16:07:07, 27.55s/it] 58%|█████▊ | 2895/5000 [23:47:55<16:13:39, 27.75s/it] 58%|█████▊ | 2896/5000 [23:48:23<16:13:17, 27.76s/it] 58%|█████▊ | 2897/5000 [23:48:51<16:11:19, 27.71s/it] 58%|█████▊ | 2898/5000 [23:49:19<16:13:03, 27.78s/it] 58%|█████▊ | 2899/5000 [23:49:46<16:09:24, 27.68s/it] 58%|█████▊ | 2900/5000 [23:50:14<16:06:03, 27.60s/it] 58%|█████▊ | 2900/5000 [23:50:14<16:06:03, 27.60s/it] 58%|█████▊ | 2901/5000 [23:50:41<16:06:17, 27.62s/it] 58%|█████▊ | 2902/5000 [23:51:09<16:03:01, 27.54s/it] 58%|█████▊ | 2903/5000 [23:51:36<16:00:53, 27.49s/it] 58%|█████▊ | 2904/5000 [23:52:04<16:04:36, 27.61s/it] 58%|█████▊ | 2905/5000 [23:52:32<16:06:50, 27.69s/it] 58%|█████▊ | 2906/5000 [23:52:59<16:02:53, 27.59s/it] 58%|█████▊ | 2907/5000 [23:53:25<15:40:11, 26.95s/it] 58%|█████▊ | 2908/5000 [23:53:53<15:59:35, 27.52s/it] 58%|█████▊ | 2909/5000 [23:54:21<15:58:44, 27.51s/it] 58%|█████▊ | 2910/5000 [23:54:48<15:54:50, 27.41s/it] 58%|█████▊ | 2911/5000 [23:55:18<16:22:29, 28.22s/it] 58%|█████▊ | 2912/5000 [23:55:46<16:13:18, 27.97s/it] 58%|█████▊ | 2913/5000 [23:56:13<16:06:19, 27.78s/it] 58%|█████▊ | 2914/5000 [23:56:41<16:08:47, 27.87s/it] 58%|█████▊ | 2915/5000 [23:57:08<16:03:34, 27.73s/it] 58%|█████▊ | 2916/5000 [23:57:36<16:00:12, 27.65s/it] 58%|█████▊ | 2917/5000 [23:58:04<16:06:29, 27.84s/it] 58%|█████▊ | 2918/5000 [23:58:33<16:13:11, 28.05s/it] 58%|█████▊ | 2919/5000 [23:59:00<16:01:22, 27.72s/it] 58%|█████▊ | 2920/5000 [23:59:28<16:08:58, 27.95s/it] 58%|█████▊ | 2921/5000 [23:59:55<15:53:29, 27.52s/it] 58%|█████▊ | 2922/5000 [24:00:22<15:50:26, 27.44s/it] 58%|█████▊ | 2923/5000 [24:00:50<15:55:02, 27.59s/it] 58%|█████▊ | 2924/5000 [24:01:17<15:52:41, 27.53s/it] 58%|█████▊ | 2925/5000 [24:01:44<15:49:02, 27.44s/it] 58%|█████▊ | 2925/5000 [24:01:44<15:49:02, 27.44s/it] 59%|█████▊ | 2926/5000 [24:02:13<16:02:45, 27.85s/it] 59%|█████▊ | 2927/5000 [24:02:41<15:59:22, 27.77s/it] 59%|█████▊ | 2928/5000 [24:03:08<15:55:21, 27.66s/it] 59%|█████▊ | 2929/5000 [24:03:36<15:55:53, 27.69s/it] 59%|█████▊ | 2930/5000 [24:04:03<15:50:33, 27.55s/it] 59%|█████▊ | 2931/5000 [24:04:31<15:48:03, 27.49s/it] 59%|█████▊ | 2932/5000 [24:04:59<15:55:23, 27.72s/it] 59%|█████▊ | 2933/5000 [24:05:26<15:51:21, 27.62s/it] 59%|█████▊ | 2934/5000 [24:05:53<15:46:11, 27.48s/it] 59%|█████▊ | 2935/5000 [24:06:21<15:51:34, 27.65s/it] 59%|█████▊ | 2936/5000 [24:06:49<15:52:51, 27.70s/it] 59%|█████▊ | 2937/5000 [24:07:16<15:47:59, 27.57s/it] 59%|█████▉ | 2938/5000 [24:07:45<15:52:57, 27.73s/it] 59%|█████▉ | 2939/5000 [24:08:07<14:53:51, 26.02s/it] 59%|█████▉ | 2940/5000 [24:08:17<12:16:55, 21.46s/it] 59%|█████▉ | 2941/5000 [24:08:28<10:29:07, 18.33s/it] 59%|█████▉ | 2942/5000 [24:08:39<9:11:35, 16.08s/it] 59%|█████▉ | 2943/5000 [24:08:47<7:45:50, 13.59s/it]{'loss': 0.0011, 'learning_rate': 4.893333333333334e-06, 'epoch': 17.0} -{'loss': 0.0011, 'learning_rate': 4.837777777777778e-06, 'epoch': 17.01} -{'loss': 0.0009, 'learning_rate': 4.7822222222222226e-06, 'epoch': 17.01} -{'loss': 0.0009, 'learning_rate': 4.7266666666666674e-06, 'epoch': 17.02} -{'loss': 0.0009, 'learning_rate': 4.6711111111111115e-06, 'epoch': 17.02} -{'loss': 0.0009, 'learning_rate': 4.6155555555555555e-06, 'epoch': 17.03} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.18it/s] - Reading metadata...: 15142it [00:00, 47342.33it/s] - Reading metadata...: 24049it [00:00, 36474.26it/s] Reading metadata...: 28043it [00:00, 37345.01it/s] - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.59it/s] - Reading metadata...: 7929it [00:00, 20560.13it/s] Reading metadata...: 10438it [00:00, 21471.13it/s] - 59%|█████▉ | 2944/5000 [24:10:26<22:24:19, 39.23s/it] 59%|█████▉ | 2945/5000 [24:10:53<20:20:21, 35.63s/it] 59%|█████▉ | 2946/5000 [24:11:21<18:55:07, 33.16s/it] 59%|█████▉ | 2947/5000 [24:11:49<18:05:56, 31.74s/it] 59%|█████▉ | 2948/5000 [24:12:17<17:25:15, 30.56s/it] 59%|█████▉ | 2949/5000 [24:12:45<17:03:19, 29.94s/it] 59%|█████▉ | 2950/5000 [24:13:13<16:37:08, 29.18s/it] 59%|█████▉ | 2950/5000 [24:13:13<16:37:08, 29.18s/it] 59%|█████▉ | 2951/5000 [24:13:41<16:22:52, 28.78s/it] 59%|█████▉ | 2952/5000 [24:14:09<16:14:10, 28.54s/it] 59%|█████▉ | 2953/5000 [24:14:36<16:01:31, 28.18s/it] 59%|█████▉ | 2954/5000 [24:15:03<15:50:42, 27.88s/it] 59%|█████▉ | 2955/5000 [24:15:30<15:40:25, 27.59s/it] 59%|█████▉ | 2956/5000 [24:15:58<15:40:50, 27.62s/it] 59%|█████▉ | 2957/5000 [24:16:26<15:46:11, 27.79s/it] 59%|█████▉ | 2958/5000 [24:16:54<15:44:29, 27.75s/it] 59%|█████▉ | 2959/5000 [24:17:21<15:44:37, 27.77s/it] 59%|█████▉ | 2960/5000 [24:17:50<15:50:25, 27.95s/it] 59%|█████▉ | 2961/5000 [24:18:17<15:42:40, 27.74s/it] 59%|█████▉ | 2962/5000 [24:18:45<15:47:59, 27.91s/it] 59%|█████▉ | 2963/5000 [24:19:13<15:39:17, 27.67s/it] 59%|█████▉ | 2964/5000 [24:19:40<15:37:02, 27.61s/it] 59%|█████▉ | 2965/5000 [24:20:09<15:47:26, 27.93s/it] 59%|█████▉ | 2966/5000 [24:20:36<15:44:20, 27.86s/it] 59%|█████▉ | 2967/5000 [24:21:04<15:39:09, 27.72s/it] 59%|█████▉ | 2968/5000 [24:21:32<15:40:53, 27.78s/it] 59%|█████▉ | 2969/5000 [24:21:59<15:33:36, 27.58s/it] 59%|█████▉ | 2970/5000 [24:22:26<15:32:07, 27.55s/it] 59%|█████▉ | 2971/5000 [24:22:54<15:30:41, 27.52s/it] 59%|█████▉ | 2972/5000 [24:23:21<15:29:53, 27.51s/it] 59%|█████▉ | 2973/5000 [24:23:49<15:29:53, 27.53s/it] 59%|█████▉ | 2974/5000 [24:24:18<15:46:57, 28.04s/it] 60%|█████▉ | 2975/5000 [24:24:45<15:39:20, 27.83s/it] 60%|█████▉ | 2975/5000 [24:24:45<15:39:20, 27.83s/it] 60%|█████▉ | 2976/5000 [24:25:13<15:37:13, 27.78s/it] 60%|█████▉ | 2977/5000 [24:25:43<16:00:17, 28.48s/it] 60%|█████▉ | 2978/5000 [24:26:10<15:47:31, 28.12s/it] 60%|█████▉ | 2979/5000 [24:26:37<15:33:50, 27.72s/it] 60%|█████▉ | 2980/5000 [24:27:04<15:25:22, 27.49s/it] 60%|█████▉ | 2981/5000 [24:27:31<15:16:13, 27.23s/it] 60%|█████▉ | 2982/5000 [24:27:58<15:16:24, 27.25s/it] 60%|█████▉ | 2983/5000 [24:28:27<15:33:26, 27.77s/it] 60%|█████▉ | 2984/5000 [24:28:54<15:29:30, 27.66s/it] 60%|█████▉ | 2985/5000 [24:29:23<15:34:14, 27.82s/it] 60%|█████▉ | 2986/5000 [24:29:52<15:45:11, 28.16s/it] 60%|█████▉ | 2987/5000 [24:30:19<15:38:44, 27.98s/it] 60%|█████▉ | 2988/5000 [24:30:47<15:37:10, 27.95s/it] 60%|█████▉ | 2989/5000 [24:31:14<15:24:20, 27.58s/it] 60%|█████▉ | 2990/5000 [24:31:43<15:36:29, 27.96s/it] 60%|█████▉ | 2991/5000 [24:32:11<15:40:06, 28.08s/it] 60%|█████▉ | 2992/5000 [24:32:38<15:32:54, 27.88s/it] 60%|█████▉ | 2993/5000 [24:33:07<15:37:14, 28.02s/it] 60%|█████▉ | 2994/5000 [24:33:35<15:40:28, 28.13s/it] 60%|█████▉ | 2995/5000 [24:34:03<15:33:19, 27.93s/it] 60%|█████▉ | 2996/5000 [24:34:31<15:36:31, 28.04s/it] 60%|█████▉ | 2997/5000 [24:34:58<15:29:03, 27.83s/it] 60%|█████▉ | 2998/5000 [24:35:26<15:24:05, 27.69s/it] 60%|█████▉ | 2999/5000 [24:35:54<15:31:47, 27.94s/it] 60%|██████ | 3000/5000 [24:36:21<15:21:38, 27.65s/it] 60%|██████ | 3000/5000 [24:36:21<15:21:38, 27.65s/it][INFO|trainer.py:3138] 2023-05-08 11:10:32,150 >> ***** Running Evaluation ***** -[INFO|trainer.py:3142] 2023-05-08 11:10:32,150 >> Num examples: Unknown -[INFO|trainer.py:3143] 2023-05-08 11:10:32,150 >> Batch size = 64 -{'loss': 0.0009, 'learning_rate': 4.56e-06, 'epoch': 18.0} -{'loss': 0.0009, 'learning_rate': 4.504444444444444e-06, 'epoch': 18.01} -{'loss': 0.0012, 'learning_rate': 4.448888888888889e-06, 'epoch': 18.01} - - Reading metadata...: 0it [00:00, ?it/s] - Reading metadata...: 1it [00:00, 3.82it/s] Reading metadata...: 10440it [00:00, 31946.72it/s] -[INFO|trainer_utils.py:693] 2023-05-08 11:10:42,418 >> The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`, you can safely ignore this message. - 60%|██████ | 3000/5000 [25:12:09<15:21:38, 27.65s/it][INFO|trainer.py:2877] 2023-05-08 11:46:20,051 >> Saving model checkpoint to ./checkpoint-3000 -[INFO|configuration_utils.py:458] 2023-05-08 11:46:20,057 >> Configuration saved in ./checkpoint-3000/config.json -[INFO|configuration_utils.py:364] 2023-05-08 11:46:20,060 >> Configuration saved in ./checkpoint-3000/generation_config.json -[INFO|modeling_utils.py:1855] 2023-05-08 11:46:22,975 >> Model weights saved in ./checkpoint-3000/pytorch_model.bin -[INFO|feature_extraction_utils.py:369] 2023-05-08 11:46:22,981 >> Feature extractor saved in ./checkpoint-3000/preprocessor_config.json -[INFO|feature_extraction_utils.py:369] 2023-05-08 11:46:33,415 >> Feature extractor saved in ./preprocessor_config.json