{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 218225, | |
"global_step": 8729, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"grad_norm": 1.6379305124282837, | |
"learning_rate": 0.0002, | |
"loss": 0.5327, | |
"step": 8729 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 0.4650146961212158, | |
"eval_runtime": 118.5706, | |
"eval_samples_per_second": 1.51, | |
"eval_steps_per_second": 1.51, | |
"step": 8729 | |
} | |
], | |
"logging_steps": 218225, | |
"max_steps": 436450, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 50, | |
"save_steps": 218225, | |
"total_flos": 5.016997246887936e+16, | |
"train_batch_size": 1, | |
"trial_name": null, | |
"trial_params": null | |
} | |