{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.010029996250468692, | |
"eval_steps": 500, | |
"global_step": 321, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0, | |
"perplexity": 3.378679037094116, | |
"step": 0, | |
"step_loss": 1.2174848318099976 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 321, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 1, | |
"save_steps": 5000, | |
"stateful_callbacks": { | |
"TrainerControl": { | |
"args": { | |
"should_epoch_stop": false, | |
"should_evaluate": false, | |
"should_log": false, | |
"should_save": true, | |
"should_training_stop": true | |
}, | |
"attributes": {} | |
} | |
}, | |
"total_flos": 2.5345049235554304e+16, | |
"train_batch_size": 8, | |
"trial_name": null, | |
"trial_params": null | |
} | |