| 12/13/2022 14:12:12 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True | |
| 12/13/2022 14:12:12 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( | |
| _n_gpu=1, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_pin_memory=True, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=1000, | |
| evaluation_strategy=steps, | |
| fp16=True, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| generation_max_length=225, | |
| generation_num_beams=None, | |
| gradient_accumulation_steps=8, | |
| gradient_checkpointing=True, | |
| greater_is_better=False, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=every_save, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=1e-05, | |
| length_column_name=input_length, | |
| load_best_model_at_end=True, | |
| local_rank=-1, | |
| log_level=passive, | |
| log_level_replica=passive, | |
| log_on_each_node=True, | |
| logging_dir=./runs/Dec13_14-12-12_4b942bf2873e, | |
| 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, | |
| metric_for_best_model=wer, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=3.0, | |
| optim=adamw_hf, | |
| optim_args=None, | |
| output_dir=./, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=True, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['tensorboard'], | |
| resume_from_checkpoint=None, | |
| run_name=./, | |
| save_on_each_node=False, | |
| save_steps=1000, | |
| save_strategy=steps, | |
| save_total_limit=None, | |
| seed=42, | |
| sharded_ddp=[], | |
| skip_memory_metrics=True, | |
| sortish_sampler=False, | |
| tf32=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=500, | |
| weight_decay=0.0, | |
| xpu_backend=None, | |
| ) | |
| 12/13/2022 14:12:12 - INFO - __main__ - Training/evaluation parameters Seq2SeqTrainingArguments( | |
| _n_gpu=1, | |
| adafactor=False, | |
| adam_beta1=0.9, | |
| adam_beta2=0.999, | |
| adam_epsilon=1e-08, | |
| auto_find_batch_size=False, | |
| bf16=False, | |
| bf16_full_eval=False, | |
| data_seed=None, | |
| dataloader_drop_last=False, | |
| dataloader_num_workers=0, | |
| dataloader_pin_memory=True, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=1000, | |
| evaluation_strategy=steps, | |
| fp16=True, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| generation_max_length=225, | |
| generation_num_beams=None, | |
| gradient_accumulation_steps=8, | |
| gradient_checkpointing=True, | |
| greater_is_better=False, | |
| group_by_length=False, | |
| half_precision_backend=auto, | |
| hub_model_id=None, | |
| hub_private_repo=False, | |
| hub_strategy=every_save, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=1e-05, | |
| length_column_name=input_length, | |
| load_best_model_at_end=True, | |
| local_rank=-1, | |
| log_level=passive, | |
| log_level_replica=passive, | |
| log_on_each_node=True, | |
| logging_dir=./runs/Dec13_14-12-12_4b942bf2873e, | |
| 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, | |
| metric_for_best_model=wer, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=3.0, | |
| optim=adamw_hf, | |
| optim_args=None, | |
| output_dir=./, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=8, | |
| predict_with_generate=True, | |
| prediction_loss_only=False, | |
| push_to_hub=True, | |
| push_to_hub_model_id=None, | |
| push_to_hub_organization=None, | |
| push_to_hub_token=<PUSH_TO_HUB_TOKEN>, | |
| ray_scope=last, | |
| remove_unused_columns=True, | |
| report_to=['tensorboard'], | |
| resume_from_checkpoint=None, | |
| run_name=./, | |
| save_on_each_node=False, | |
| save_steps=1000, | |
| save_strategy=steps, | |
| save_total_limit=None, | |
| seed=42, | |
| sharded_ddp=[], | |
| skip_memory_metrics=True, | |
| sortish_sampler=False, | |
| tf32=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=500, | |
| weight_decay=0.0, | |
| xpu_backend=None, | |
| ) | |
| 12/13/2022 14:12:15 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:15 - INFO - datasets.builder - Overwrite dataset info from restored data version. | |
| 12/13/2022 14:12:15 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:15 - WARNING - datasets.builder - Found cached dataset common_voice_11_0 (/root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f) | |
| 12/13/2022 14:12:15 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:19 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:19 - INFO - datasets.builder - Overwrite dataset info from restored data version. | |
| 12/13/2022 14:12:19 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:19 - WARNING - datasets.builder - Found cached dataset common_voice_11_0 (/root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f) | |
| 12/13/2022 14:12:19 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:22 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/mozilla-foundation--common_voice_11_0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:22 - INFO - datasets.builder - Overwrite dataset info from restored data version. | |
| 12/13/2022 14:12:22 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:12:22 - WARNING - datasets.builder - Found cached dataset common_voice_11_0 (/root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f) | |
| 12/13/2022 14:12:22 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f | |
| 12/13/2022 14:14:43 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-f4ebdf4955d452c1.arrow | |
| 12/13/2022 15:03:44 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-0bdc3bb096868b69.arrow | |
| 12/13/2022 15:31:19 - INFO - datasets.arrow_dataset - Caching processed dataset at /root/.cache/huggingface/datasets/mozilla-foundation___common_voice_11_0/cs/11.0.0/f8e47235d9b4e68fa24ed71d63266a02018ccf7194b2a8c9c598a5f3ab304d9f/cache-beeaca47803ef85b.arrow | |
| 12/13/2022 16:01:48 - WARNING - huggingface_hub.repository - /usr/src/app/models/whisper-large2-czech-cv11/./ is already a clone of https://huggingface.co/mikr/whisper-large2-czech-cv11. Make sure you pull the latest changes with `repo.git_pull()`. | |
| {'loss': 0.7151, 'learning_rate': 4.6000000000000004e-07, 'epoch': 0.11} | |
| {'loss': 0.4297, 'learning_rate': 9.400000000000001e-07, 'epoch': 0.21} | |
| {'loss': 0.2399, 'learning_rate': 1.42e-06, 'epoch': 0.32} | |
| {'loss': 0.1871, 'learning_rate': 1.9200000000000003e-06, 'epoch': 0.42} | |
| {'loss': 0.161, 'learning_rate': 2.42e-06, 'epoch': 0.53} | |
| {'loss': 0.1511, 'learning_rate': 2.92e-06, 'epoch': 0.64} | |
| {'loss': 0.1481, 'learning_rate': 3.4200000000000007e-06, 'epoch': 0.74} | |
| {'loss': 0.1392, 'learning_rate': 3.920000000000001e-06, 'epoch': 0.85} | |
| {'loss': 0.1328, 'learning_rate': 4.42e-06, 'epoch': 0.95} | |
| {'loss': 0.1152, 'learning_rate': 4.92e-06, 'epoch': 1.06} | |
| {'loss': 0.0998, 'learning_rate': 5.420000000000001e-06, 'epoch': 1.17} | |
| {'loss': 0.0936, 'learning_rate': 5.92e-06, 'epoch': 1.28} | |
| {'loss': 0.0953, 'learning_rate': 6.4000000000000006e-06, 'epoch': 1.38} | |
| {'loss': 0.0962, 'learning_rate': 6.9e-06, 'epoch': 1.49} | |
| {'loss': 0.0971, 'learning_rate': 7.4e-06, 'epoch': 1.59} | |
| {'loss': 0.1003, 'learning_rate': 7.9e-06, 'epoch': 1.7} | |
| {'loss': 0.0931, 'learning_rate': 8.400000000000001e-06, 'epoch': 1.81} | |
| {'loss': 0.0925, 'learning_rate': 8.900000000000001e-06, 'epoch': 1.91} | |
| {'loss': 0.092, 'learning_rate': 9.4e-06, 'epoch': 2.02} | |
| {'loss': 0.0509, 'learning_rate': 9.9e-06, 'epoch': 2.13} | |
| {'loss': 0.0563, 'learning_rate': 9.955555555555556e-06, 'epoch': 2.23} | |
| {'loss': 0.0563, 'learning_rate': 9.9e-06, 'epoch': 2.34} | |
| {'loss': 0.0581, 'learning_rate': 9.844444444444446e-06, 'epoch': 2.45} | |
| {'loss': 0.0557, 'learning_rate': 9.78888888888889e-06, 'epoch': 2.55} | |
| {'loss': 0.0561, 'learning_rate': 9.733333333333334e-06, 'epoch': 2.66} | |
| {'loss': 0.0548, 'learning_rate': 9.677777777777778e-06, 'epoch': 2.76} | |
| {'loss': 0.056, 'learning_rate': 9.622222222222222e-06, 'epoch': 2.87} | |
| {'loss': 0.0582, 'learning_rate': 9.566666666666668e-06, 'epoch': 2.98} | |
| {'loss': 0.0341, 'learning_rate': 9.511111111111112e-06, 'epoch': 3.08} | |
| {'loss': 0.0256, 'learning_rate': 9.455555555555557e-06, 'epoch': 3.19} | |
| {'loss': 0.0263, 'learning_rate': 9.4e-06, 'epoch': 3.3} | |
| {'loss': 0.0275, 'learning_rate': 9.344444444444446e-06, 'epoch': 3.4} | |
| {'loss': 0.0289, 'learning_rate': 9.28888888888889e-06, 'epoch': 3.51} | |
| {'loss': 0.0274, 'learning_rate': 9.233333333333334e-06, 'epoch': 3.62} | |
| {'loss': 0.0309, 'learning_rate': 9.17777777777778e-06, 'epoch': 3.72} | |
| {'loss': 0.0307, 'learning_rate': 9.122222222222223e-06, 'epoch': 3.83} | |
| {'loss': 0.0304, 'learning_rate': 9.066666666666667e-06, 'epoch': 3.93} | |
| {'loss': 0.026, 'learning_rate': 9.011111111111111e-06, 'epoch': 4.04} | |
| {'loss': 0.0139, 'learning_rate': 8.955555555555555e-06, 'epoch': 4.15} | |
| {'loss': 0.0149, 'learning_rate': 8.900000000000001e-06, 'epoch': 4.25} | |
| {'eval_loss': 0.16215506196022034, 'eval_wer': 10.040330748973316, 'eval_runtime': 17422.9164, 'eval_samples_per_second': 0.443, 'eval_steps_per_second': 0.055, 'epoch': 4.25} | |
| {'loss': 0.0141, 'learning_rate': 8.844444444444445e-06, 'epoch': 4.36} | |
| {'loss': 0.0159, 'learning_rate': 8.788888888888891e-06, 'epoch': 4.47} | |
| {'loss': 0.0165, 'learning_rate': 8.733333333333333e-06, 'epoch': 4.57} | |
| {'loss': 0.0134, 'learning_rate': 8.677777777777779e-06, 'epoch': 4.68} | |
| {'loss': 0.0174, 'learning_rate': 8.622222222222223e-06, 'epoch': 4.78} | |
| {'loss': 0.0147, 'learning_rate': 8.566666666666667e-06, 'epoch': 4.89} | |
| {'loss': 0.0179, 'learning_rate': 8.511111111111113e-06, 'epoch': 5.0} | |
| {'loss': 0.01, 'learning_rate': 8.455555555555555e-06, 'epoch': 5.11} | |
| {'loss': 0.0094, 'learning_rate': 8.400000000000001e-06, 'epoch': 5.21} | |
| {'loss': 0.0087, 'learning_rate': 8.344444444444445e-06, 'epoch': 5.32} | |
| {'loss': 0.0087, 'learning_rate': 8.288888888888889e-06, 'epoch': 5.42} | |
| {'loss': 0.0113, 'learning_rate': 8.233333333333335e-06, 'epoch': 5.53} | |
| {'loss': 0.0126, 'learning_rate': 8.177777777777779e-06, 'epoch': 5.64} | |
| {'loss': 0.0107, 'learning_rate': 8.122222222222223e-06, 'epoch': 5.74} | |
| {'loss': 0.0105, 'learning_rate': 8.066666666666667e-06, 'epoch': 5.85} | |
| {'loss': 0.0104, 'learning_rate': 8.011111111111113e-06, 'epoch': 5.95} | |
| {'loss': 0.0082, 'learning_rate': 7.955555555555557e-06, 'epoch': 6.06} | |
| {'loss': 0.0056, 'learning_rate': 7.9e-06, 'epoch': 6.17} | |
| {'loss': 0.0056, 'learning_rate': 7.844444444444446e-06, 'epoch': 6.28} | |
| {'loss': 0.007, 'learning_rate': 7.788888888888889e-06, 'epoch': 6.38} | |
| {'loss': 0.0062, 'learning_rate': 7.733333333333334e-06, 'epoch': 6.49} | |
| {'loss': 0.0058, 'learning_rate': 7.677777777777778e-06, 'epoch': 6.59} | |
| {'loss': 0.0061, 'learning_rate': 7.622222222222223e-06, 'epoch': 6.7} | |
| {'loss': 0.0055, 'learning_rate': 7.566666666666667e-06, 'epoch': 6.81} | |
| {'loss': 0.006, 'learning_rate': 7.511111111111111e-06, 'epoch': 6.91} | |
| {'loss': 0.0063, 'learning_rate': 7.455555555555556e-06, 'epoch': 7.02} | |
| {'loss': 0.0043, 'learning_rate': 7.4e-06, 'epoch': 7.13} | |
| {'loss': 0.0035, 'learning_rate': 7.344444444444445e-06, 'epoch': 7.23} | |
| {'loss': 0.0035, 'learning_rate': 7.28888888888889e-06, 'epoch': 7.34} | |
| {'loss': 0.004, 'learning_rate': 7.233333333333334e-06, 'epoch': 7.45} | |
| {'loss': 0.0034, 'learning_rate': 7.177777777777778e-06, 'epoch': 7.55} | |
| {'loss': 0.0042, 'learning_rate': 7.122222222222222e-06, 'epoch': 7.66} | |
| {'loss': 0.0042, 'learning_rate': 7.066666666666667e-06, 'epoch': 7.76} | |
| {'loss': 0.0042, 'learning_rate': 7.011111111111112e-06, 'epoch': 7.87} | |
| {'loss': 0.0043, 'learning_rate': 6.955555555555557e-06, 'epoch': 7.98} | |
| {'loss': 0.0034, 'learning_rate': 6.9e-06, 'epoch': 8.08} | |
| {'loss': 0.0029, 'learning_rate': 6.844444444444445e-06, 'epoch': 8.19} | |
| {'loss': 0.0034, 'learning_rate': 6.788888888888889e-06, 'epoch': 8.3} | |
| {'loss': 0.0033, 'learning_rate': 6.733333333333334e-06, 'epoch': 8.4} | |
| {'loss': 0.0027, 'learning_rate': 6.677777777777779e-06, 'epoch': 8.51} | |
| {'eval_loss': 0.18483087420463562, 'eval_wer': 9.51363694959577, 'eval_runtime': 21193.0144, 'eval_samples_per_second': 0.364, 'eval_steps_per_second': 0.046, 'epoch': 8.51} | |
| {'loss': 0.0042, 'learning_rate': 6.6222222222222236e-06, 'epoch': 8.62} | |
| {'loss': 0.0042, 'learning_rate': 6.566666666666667e-06, 'epoch': 8.72} | |
| {'loss': 0.0046, 'learning_rate': 6.511111111111112e-06, 'epoch': 8.83} | |
| {'loss': 0.004, 'learning_rate': 6.455555555555556e-06, 'epoch': 8.93} | |
| {'loss': 0.004, 'learning_rate': 6.4000000000000006e-06, 'epoch': 9.04} | |
| {'loss': 0.0029, 'learning_rate': 6.3444444444444454e-06, 'epoch': 9.15} | |
| {'loss': 0.0027, 'learning_rate': 6.28888888888889e-06, 'epoch': 9.25} | |
| {'loss': 0.003, 'learning_rate': 6.2333333333333335e-06, 'epoch': 9.36} | |
| {'loss': 0.003, 'learning_rate': 6.177777777777778e-06, 'epoch': 9.47} | |
| {'loss': 0.0031, 'learning_rate': 6.1222222222222224e-06, 'epoch': 9.57} | |
| {'loss': 0.0028, 'learning_rate': 6.066666666666667e-06, 'epoch': 9.68} | |
| {'loss': 0.0029, 'learning_rate': 6.011111111111112e-06, 'epoch': 9.78} | |
| {'loss': 0.003, 'learning_rate': 5.955555555555555e-06, 'epoch': 9.89} | |
| {'loss': 0.0035, 'learning_rate': 5.9e-06, 'epoch': 10.0} | |
| {'loss': 0.0023, 'learning_rate': 5.844444444444445e-06, 'epoch': 10.11} | |
| {'loss': 0.0019, 'learning_rate': 5.788888888888889e-06, 'epoch': 10.21} | |
| {'loss': 0.002, 'learning_rate': 5.733333333333334e-06, 'epoch': 10.32} | |
| {'loss': 0.0024, 'learning_rate': 5.677777777777779e-06, 'epoch': 10.42} | |
| {'loss': 0.0021, 'learning_rate': 5.622222222222222e-06, 'epoch': 10.53} | |
| {'loss': 0.0021, 'learning_rate': 5.566666666666667e-06, 'epoch': 10.64} | |
| {'loss': 0.0019, 'learning_rate': 5.511111111111112e-06, 'epoch': 10.74} | |
| {'loss': 0.002, 'learning_rate': 5.455555555555556e-06, 'epoch': 10.85} | |
| {'loss': 0.0018, 'learning_rate': 5.400000000000001e-06, 'epoch': 10.95} | |
| {'loss': 0.0017, 'learning_rate': 5.344444444444446e-06, 'epoch': 11.06} | |
| {'loss': 0.0024, 'learning_rate': 5.288888888888889e-06, 'epoch': 11.17} | |
| {'loss': 0.0019, 'learning_rate': 5.233333333333334e-06, 'epoch': 11.28} | |
| {'loss': 0.0018, 'learning_rate': 5.177777777777779e-06, 'epoch': 11.38} | |
| {'loss': 0.0017, 'learning_rate': 5.122222222222223e-06, 'epoch': 11.49} | |
| {'loss': 0.0014, 'learning_rate': 5.0666666666666676e-06, 'epoch': 11.59} | |
| {'loss': 0.0014, 'learning_rate': 5.011111111111111e-06, 'epoch': 11.7} | |
| {'loss': 0.0015, 'learning_rate': 4.9555555555555565e-06, 'epoch': 11.81} | |
| {'loss': 0.0017, 'learning_rate': 4.9000000000000005e-06, 'epoch': 11.91} | |
| {'loss': 0.0016, 'learning_rate': 4.8444444444444446e-06, 'epoch': 12.02} | |
| {'loss': 0.001, 'learning_rate': 4.7888888888888894e-06, 'epoch': 12.13} | |
| {'loss': 0.001, 'learning_rate': 4.7333333333333335e-06, 'epoch': 12.23} | |
| {'loss': 0.0018, 'learning_rate': 4.677777777777778e-06, 'epoch': 12.34} | |
| {'loss': 0.0014, 'learning_rate': 4.622222222222222e-06, 'epoch': 12.45} | |
| {'loss': 0.0012, 'learning_rate': 4.566666666666667e-06, 'epoch': 12.55} | |
| {'loss': 0.0012, 'learning_rate': 4.511111111111111e-06, 'epoch': 12.66} | |
| {'loss': 0.0008, 'learning_rate': 4.455555555555555e-06, 'epoch': 12.76} | |
| {'eval_loss': 0.19296467304229736, 'eval_wer': 9.31658717150697, 'eval_runtime': 16619.4936, 'eval_samples_per_second': 0.464, 'eval_steps_per_second': 0.058, 'epoch': 12.76} | |
| {'loss': 0.0009, 'learning_rate': 4.4e-06, 'epoch': 12.87} | |
| {'loss': 0.001, 'learning_rate': 4.344444444444445e-06, 'epoch': 12.98} | |
| {'loss': 0.0007, 'learning_rate': 4.288888888888889e-06, 'epoch': 13.08} | |
| {'loss': 0.0007, 'learning_rate': 4.233333333333334e-06, 'epoch': 13.19} | |
| {'loss': 0.0009, 'learning_rate': 4.177777777777778e-06, 'epoch': 13.3} | |
| {'loss': 0.0006, 'learning_rate': 4.122222222222222e-06, 'epoch': 13.4} | |
| {'loss': 0.0007, 'learning_rate': 4.066666666666667e-06, 'epoch': 13.51} | |
| {'loss': 0.0006, 'learning_rate': 4.011111111111111e-06, 'epoch': 13.62} | |
| {'loss': 0.0008, 'learning_rate': 3.955555555555556e-06, 'epoch': 13.72} | |
| {'loss': 0.0007, 'learning_rate': 3.900000000000001e-06, 'epoch': 13.83} | |
| {'loss': 0.0007, 'learning_rate': 3.844444444444445e-06, 'epoch': 13.93} | |
| {'loss': 0.0006, 'learning_rate': 3.7888888888888893e-06, 'epoch': 14.04} | |
| {'loss': 0.0005, 'learning_rate': 3.7333333333333337e-06, 'epoch': 14.15} | |
| {'loss': 0.0005, 'learning_rate': 3.6777777777777778e-06, 'epoch': 14.25} | |
| {'loss': 0.0005, 'learning_rate': 3.6222222222222226e-06, 'epoch': 14.36} | |
| {'loss': 0.0005, 'learning_rate': 3.566666666666667e-06, 'epoch': 14.47} | |
| {'loss': 0.0005, 'learning_rate': 3.511111111111111e-06, 'epoch': 14.57} | |
| {'loss': 0.0005, 'learning_rate': 3.455555555555556e-06, 'epoch': 14.68} | |
| {'loss': 0.0011, 'learning_rate': 3.4000000000000005e-06, 'epoch': 14.78} | |
| {'loss': 0.0005, 'learning_rate': 3.3444444444444445e-06, 'epoch': 14.89} | |
| {'loss': 0.0008, 'learning_rate': 3.2888888888888894e-06, 'epoch': 15.0} | |
| {'loss': 0.0008, 'learning_rate': 3.2333333333333334e-06, 'epoch': 15.11} | |
| {'loss': 0.0005, 'learning_rate': 3.177777777777778e-06, 'epoch': 15.21} | |
| {'loss': 0.0007, 'learning_rate': 3.1222222222222228e-06, 'epoch': 15.32} | |
| {'loss': 0.0005, 'learning_rate': 3.066666666666667e-06, 'epoch': 15.42} | |
| {'loss': 0.0005, 'learning_rate': 3.0111111111111113e-06, 'epoch': 15.53} | |
| {'loss': 0.0009, 'learning_rate': 2.955555555555556e-06, 'epoch': 15.64} | |
| {'loss': 0.0005, 'learning_rate': 2.9e-06, 'epoch': 15.74} | |
| {'loss': 0.0005, 'learning_rate': 2.8444444444444446e-06, 'epoch': 15.85} | |
| {'loss': 0.0006, 'learning_rate': 2.788888888888889e-06, 'epoch': 15.95} | |
| {'loss': 0.0005, 'learning_rate': 2.7333333333333336e-06, 'epoch': 16.06} | |
| {'loss': 0.0004, 'learning_rate': 2.677777777777778e-06, 'epoch': 16.17} | |
| {'loss': 0.0007, 'learning_rate': 2.6222222222222225e-06, 'epoch': 16.28} | |
| {'loss': 0.0005, 'learning_rate': 2.566666666666667e-06, 'epoch': 16.38} | |
| {'loss': 0.0005, 'learning_rate': 2.5111111111111114e-06, 'epoch': 16.49} | |
| {'loss': 0.0004, 'learning_rate': 2.455555555555556e-06, 'epoch': 16.59} | |
| {'loss': 0.0005, 'learning_rate': 2.4000000000000003e-06, 'epoch': 16.7} | |
| {'loss': 0.0004, 'learning_rate': 2.3444444444444448e-06, 'epoch': 16.81} | |
| {'loss': 0.0004, 'learning_rate': 2.2888888888888892e-06, 'epoch': 16.91} | |
| {'loss': 0.0004, 'learning_rate': 2.2333333333333333e-06, 'epoch': 17.02} | |