{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.9956331877729258, | |
"eval_steps": 500, | |
"global_step": 57, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.79, | |
"learning_rate": 4.705882352941177e-05, | |
"loss": 1.6474, | |
"step": 45 | |
} | |
], | |
"logging_steps": 45, | |
"max_steps": 57, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 1, | |
"save_steps": 500, | |
"total_flos": 1.998631107506995e+16, | |
"train_batch_size": 2, | |
"trial_name": null, | |
"trial_params": null | |
} | |