{ | |
"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_accuracy": 0.6054838709677419, | |
"eval_loss": 0.21967020630836487, | |
"eval_runtime": 1.4167, | |
"eval_samples_per_second": 2188.185, | |
"eval_steps_per_second": 45.881, | |
"step": 318 | |
}, | |
{ | |
"epoch": 1.57, | |
"learning_rate": 1.650593990216632e-05, | |
"loss": 0.3526, | |
"step": 500 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 2862, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 9, | |
"save_steps": 500, | |
"total_flos": 130072209152340.0, | |
"train_batch_size": 48, | |
"trial_name": null, | |
"trial_params": { | |
"alpha": 0.016710650067674027, | |
"num_train_epochs": 9, | |
"temperature": 6 | |
} | |
} | |