| 01/29/2024 19:52:08 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: True, 16-bits training: True | |
| 01/29/2024 19:52:08 - INFO - __main__ - Training/evaluation parameters TrainingArguments( | |
| _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_persistent_workers=False, | |
| dataloader_pin_memory=True, | |
| dataloader_prefetch_factor=None, | |
| ddp_backend=None, | |
| ddp_broadcast_buffers=None, | |
| ddp_bucket_cap_mb=None, | |
| ddp_find_unused_parameters=None, | |
| ddp_timeout=1800, | |
| debug=[], | |
| deepspeed=None, | |
| disable_tqdm=False, | |
| dispatch_batches=None, | |
| do_eval=True, | |
| do_predict=False, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=200, | |
| evaluation_strategy=IntervalStrategy.STEPS, | |
| fp16=True, | |
| fp16_backend=auto, | |
| fp16_full_eval=False, | |
| fp16_opt_level=O1, | |
| fsdp=[], | |
| fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False}, | |
| fsdp_min_num_params=0, | |
| fsdp_transformer_layer_cls_to_wrap=None, | |
| full_determinism=False, | |
| gradient_accumulation_steps=1, | |
| gradient_checkpointing=True, | |
| gradient_checkpointing_kwargs=None, | |
| greater_is_better=None, | |
| group_by_length=True, | |
| half_precision_backend=auto, | |
| hub_always_push=False, | |
| hub_model_id=simpragma/breeze-listen-w2v2-ml, | |
| hub_private_repo=False, | |
| hub_strategy=HubStrategy.EVERY_SAVE, | |
| hub_token=<HUB_TOKEN>, | |
| ignore_data_skip=False, | |
| include_inputs_for_metrics=False, | |
| include_num_input_tokens_seen=False, | |
| include_tokens_per_second=False, | |
| jit_mode_eval=False, | |
| label_names=None, | |
| label_smoothing_factor=0.0, | |
| learning_rate=0.001, | |
| length_column_name=input_length, | |
| load_best_model_at_end=False, | |
| local_rank=0, | |
| log_level=passive, | |
| log_level_replica=warning, | |
| log_on_each_node=True, | |
| logging_dir=/cosmos/home/sp-operator/ai/training/models/simpragma/breeze-listen-w2v2-ml/runs/Jan29_19-52-08_knight, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=500, | |
| logging_strategy=IntervalStrategy.STEPS, | |
| lr_scheduler_kwargs={}, | |
| lr_scheduler_type=SchedulerType.LINEAR, | |
| max_grad_norm=1.0, | |
| max_steps=-1, | |
| metric_for_best_model=None, | |
| mp_parameters=, | |
| neftune_noise_alpha=None, | |
| no_cuda=False, | |
| num_train_epochs=4.0, | |
| optim=OptimizerNames.ADAMW_BNB, | |
| optim_args=None, | |
| output_dir=/cosmos/home/sp-operator/ai/training/models/simpragma/breeze-listen-w2v2-ml, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=8, | |
| per_device_train_batch_size=4, | |
| 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=[], | |
| resume_from_checkpoint=None, | |
| run_name=/cosmos/home/sp-operator/ai/training/models/simpragma/breeze-listen-w2v2-ml, | |
| save_on_each_node=False, | |
| save_only_model=False, | |
| save_safetensors=True, | |
| save_steps=200, | |
| save_strategy=IntervalStrategy.STEPS, | |
| save_total_limit=3, | |
| seed=42, | |
| skip_memory_metrics=True, | |
| split_batches=False, | |
| tf32=None, | |
| torch_compile=False, | |
| torch_compile_backend=None, | |
| torch_compile_mode=None, | |
| torchdynamo=None, | |
| tpu_metrics_debug=False, | |
| tpu_num_cores=None, | |
| use_cpu=False, | |
| use_ipex=False, | |
| use_legacy_prediction_loop=False, | |
| use_mps_device=False, | |
| warmup_ratio=0.0, | |
| warmup_steps=100, | |
| weight_decay=0.0, | |
| ) | |
| {'eval_loss': 5.472805500030518, 'eval_wer': 1.075673807878369, 'eval_runtime': 162.595, 'eval_samples_per_second': 4.078, 'eval_steps_per_second': 0.51, 'epoch': 0.41} | |
| {'eval_loss': 5.127437114715576, 'eval_wer': 1.003800967519005, 'eval_runtime': 163.1607, 'eval_samples_per_second': 4.063, 'eval_steps_per_second': 0.509, 'epoch': 0.81} | |
| {'loss': 6.5037, 'learning_rate': 0.0007890792291220557, 'epoch': 1.02} | |
| {'eval_loss': 0.6166694760322571, 'eval_wer': 0.8130615065653075, 'eval_runtime': 161.3235, 'eval_samples_per_second': 4.11, 'eval_steps_per_second': 0.514, 'epoch': 1.22} | |
| {'eval_loss': 0.328411728143692, 'eval_wer': 0.582930200414651, 'eval_runtime': 162.053, 'eval_samples_per_second': 4.091, 'eval_steps_per_second': 0.512, 'epoch': 1.63} | |
| {'loss': 1.0482, 'learning_rate': 0.0005214132762312634, 'epoch': 2.03} | |
| {'eval_loss': 0.3169207274913788, 'eval_wer': 0.5666897028334485, 'eval_runtime': 165.1028, 'eval_samples_per_second': 4.016, 'eval_steps_per_second': 0.503, 'epoch': 2.03} | |
| {'eval_loss': 0.28758111596107483, 'eval_wer': 0.5425017277125086, 'eval_runtime': 160.9496, 'eval_samples_per_second': 4.119, 'eval_steps_per_second': 0.516, 'epoch': 2.44} | |
| {'eval_loss': 0.2846720516681671, 'eval_wer': 0.5521769177608846, 'eval_runtime': 161.8788, 'eval_samples_per_second': 4.096, 'eval_steps_per_second': 0.513, 'epoch': 2.85} | |
| {'loss': 0.4314, 'learning_rate': 0.00025374732334047106, 'epoch': 3.05} | |
| {'eval_loss': 0.27460750937461853, 'eval_wer': 0.5393918451969593, 'eval_runtime': 160.7333, 'eval_samples_per_second': 4.125, 'eval_steps_per_second': 0.516, 'epoch': 3.25} | |
| {'eval_loss': 0.26981213688850403, 'eval_wer': 0.5345542501727713, 'eval_runtime': 160.1257, 'eval_samples_per_second': 4.14, 'eval_steps_per_second': 0.518, 'epoch': 3.66} | |
| {'train_runtime': 5112.0325, 'train_samples_per_second': 1.54, 'train_steps_per_second': 0.385, 'train_loss': 2.1205503649827913, 'epoch': 4.0} | |