| 12/10/2022 23:08:05 - WARNING - __main__ - Process rank: -1, device: cuda:0, n_gpu: 1distributed training: False, 16-bits training: True | |
| 12/10/2022 23:08:05 - 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=1, | |
| 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/Dec10_23-08-05_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=32, | |
| per_device_train_batch_size=64, | |
| 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, | |
| ) | |
| 12/10/2022 23:08:05 - 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=1, | |
| 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/Dec10_23-08-05_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=32, | |
| per_device_train_batch_size=64, | |
| 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, | |
| ) | |
| 12/10/2022 23:08:07 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604 | |
| 12/10/2022 23:08:10 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604 | |
| 12/10/2022 23:08:13 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/facebook--voxpopuli/b5ff837284f0778eefe0f642734e142d8c3f574eba8c9c8a4b13602297f73604 | |
| 12/10/2022 23:08:23 - WARNING - huggingface_hub.repository - /usr/src/app/models/whisper-small-hr-vox/./ is already a clone of https://huggingface.co/mikr/whisper-small-hr-vox. Make sure you pull the latest changes with `repo.git_pull()`. | |
| {'loss': 1.4901, 'learning_rate': 4.800000000000001e-07, 'epoch': 0.01} | |
| {'loss': 1.2499, 'learning_rate': 9.800000000000001e-07, 'epoch': 1.0} | |
| {'loss': 1.0153, 'learning_rate': 1.48e-06, 'epoch': 1.01} | |
| {'loss': 0.8027, 'learning_rate': 1.98e-06, 'epoch': 2.0} | |
| {'loss': 0.6815, 'learning_rate': 2.4800000000000004e-06, 'epoch': 3.0} | |
| {'loss': 0.5597, 'learning_rate': 2.9800000000000003e-06, 'epoch': 3.01} | |
| {'loss': 0.4858, 'learning_rate': 3.48e-06, 'epoch': 4.0} | |
| {'loss': 0.4394, 'learning_rate': 3.980000000000001e-06, 'epoch': 4.01} | |
| {'loss': 0.37, 'learning_rate': 4.48e-06, 'epoch': 5.0} | |
| {'loss': 0.3308, 'learning_rate': 4.980000000000001e-06, 'epoch': 6.0} | |
| {'loss': 0.2815, 'learning_rate': 5.480000000000001e-06, 'epoch': 6.01} | |
| {'loss': 0.2378, 'learning_rate': 5.98e-06, 'epoch': 7.0} | |
| {'loss': 0.2064, 'learning_rate': 6.480000000000001e-06, 'epoch': 8.0} | |
| {'loss': 0.1689, 'learning_rate': 6.98e-06, 'epoch': 8.01} | |
| {'loss': 0.1392, 'learning_rate': 7.48e-06, 'epoch': 9.0} | |
| {'loss': 0.1138, 'learning_rate': 7.980000000000002e-06, 'epoch': 9.01} | |
| {'loss': 0.088, 'learning_rate': 8.48e-06, 'epoch': 10.01} | |
| {'loss': 0.0765, 'learning_rate': 8.98e-06, 'epoch': 11.0} | |
| {'loss': 0.0608, 'learning_rate': 9.48e-06, 'epoch': 11.01} | |
| {'loss': 0.0437, 'learning_rate': 9.980000000000001e-06, 'epoch': 12.0} | |
| {'loss': 0.043, 'learning_rate': 9.946666666666667e-06, 'epoch': 13.0} | |
| {'loss': 0.0325, 'learning_rate': 9.891111111111113e-06, 'epoch': 13.01} | |
| {'loss': 0.0241, 'learning_rate': 9.835555555555556e-06, 'epoch': 14.0} | |
| {'loss': 0.0225, 'learning_rate': 9.780000000000001e-06, 'epoch': 14.01} | |
| {'loss': 0.0149, 'learning_rate': 9.724444444444445e-06, 'epoch': 15.01} | |
| {'loss': 0.0148, 'learning_rate': 9.66888888888889e-06, 'epoch': 16.0} | |
| {'loss': 0.0127, 'learning_rate': 9.613333333333335e-06, 'epoch': 16.01} | |
| {'loss': 0.0089, 'learning_rate': 9.557777777777777e-06, 'epoch': 17.0} | |
| {'loss': 0.0071, 'learning_rate': 9.502222222222223e-06, 'epoch': 18.0} | |
| {'loss': 0.0066, 'learning_rate': 9.446666666666667e-06, 'epoch': 18.01} | |
| {'loss': 0.005, 'learning_rate': 9.391111111111111e-06, 'epoch': 19.0} | |
| {'loss': 0.0047, 'learning_rate': 9.335555555555557e-06, 'epoch': 19.01} | |
| {'loss': 0.0036, 'learning_rate': 9.280000000000001e-06, 'epoch': 20.0} | |
| {'loss': 0.0032, 'learning_rate': 9.224444444444445e-06, 'epoch': 21.0} | |
| {'loss': 0.0033, 'learning_rate': 9.168888888888889e-06, 'epoch': 21.01} | |
| {'loss': 0.003, 'learning_rate': 9.113333333333335e-06, 'epoch': 22.0} | |
| {'loss': 0.0029, 'learning_rate': 9.057777777777779e-06, 'epoch': 23.0} | |
| {'loss': 0.0026, 'learning_rate': 9.002222222222223e-06, 'epoch': 23.01} | |
| {'loss': 0.0026, 'learning_rate': 8.946666666666669e-06, 'epoch': 24.0} | |
| {'loss': 0.0027, 'learning_rate': 8.891111111111111e-06, 'epoch': 24.01} | |
| 12/11/2022 03:20:30 - WARNING - datasets.download.streaming_download_manager - Got disconnected from remote data host. Retrying in 5sec [1/20] | |