{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.9912023460410557, | |
"eval_steps": 500, | |
"global_step": 510, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.8, | |
"learning_rate": 8.169934640522877e-05, | |
"loss": 1.1531, | |
"step": 136 | |
}, | |
{ | |
"epoch": 1.6, | |
"learning_rate": 5.206971677559913e-05, | |
"loss": 0.4309, | |
"step": 272 | |
}, | |
{ | |
"epoch": 2.39, | |
"learning_rate": 2.24400871459695e-05, | |
"loss": 0.3755, | |
"step": 408 | |
} | |
], | |
"logging_steps": 136, | |
"max_steps": 510, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 3, | |
"save_steps": 500, | |
"total_flos": 1.6159879775807078e+18, | |
"train_batch_size": 10, | |
"trial_name": null, | |
"trial_params": null | |
} | |