{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.5723270440251573, | |
"eval_steps": 500, | |
"global_step": 500, | |
"is_hyper_param_search": true, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"eval_loss": 0.4282287061214447, | |
"eval_runtime": 3.2319, | |
"eval_samples_per_second": 959.178, | |
"eval_steps_per_second": 20.112, | |
"step": 318 | |
}, | |
{ | |
"epoch": 1.57, | |
"grad_norm": 0.861090898513794, | |
"learning_rate": 1.371069182389937e-05, | |
"loss": 0.6575, | |
"step": 500 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 1590, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 5, | |
"save_steps": 500, | |
"total_flos": 130072209152340.0, | |
"train_batch_size": 48, | |
"trial_name": null, | |
"trial_params": { | |
"alpha": 0.31661862639116345, | |
"num_train_epochs": 9, | |
"temperature": 2 | |
} | |
} | |