| INFO:__main__:Training/evaluation parameters FlaxSeq2SeqTrainingArguments( | |
| _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, | |
| debug=, | |
| deepspeed=None, | |
| disable_tqdm=None, | |
| do_eval=True, | |
| do_predict=True, | |
| do_train=True, | |
| eval_accumulation_steps=None, | |
| eval_delay=0, | |
| eval_steps=10000, | |
| evaluation_strategy=no, | |
| final_generation_max_length=200, | |
| final_generation_num_beams=5, | |
| fp16=False, | |
| 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_length_penalty=1.2, | |
| generation_max_length=200, | |
| generation_num_beams=5, | |
| gradient_accumulation_steps=1, | |
| gradient_checkpointing=True, | |
| greater_is_better=None, | |
| 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=0.0001, | |
| length_column_name=length, | |
| load_best_model_at_end=False, | |
| local_rank=-1, | |
| log_level=passive, | |
| log_level_replica=passive, | |
| log_on_each_node=True, | |
| logging_dir=None, | |
| logging_first_step=False, | |
| logging_nan_inf_filter=True, | |
| logging_steps=25, | |
| logging_strategy=steps, | |
| lr_scheduler_type=linear, | |
| matmul_precision=default, | |
| max_grad_norm=1.0, | |
| max_steps=50000, | |
| metric_for_best_model=None, | |
| mp_parameters=, | |
| no_cuda=False, | |
| num_train_epochs=3.0, | |
| optim=adamw_hf, | |
| output_dir=./, | |
| overwrite_output_dir=True, | |
| past_index=-1, | |
| per_device_eval_batch_size=4, | |
| per_device_train_batch_size=8, | |
| precision=full, | |
| 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=None, | |
| resume_from_checkpoint=None, | |
| run_name=None, | |
| save_on_each_node=False, | |
| save_steps=10000, | |
| 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, | |
| warmup_ratio=0.0, | |
| warmup_steps=500, | |
| weight_decay=0.0, | |
| xpu_backend=None, | |
| ) | |
| INFO:__main__:JAX devices: 8, matmul precision: default |