{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 11.67728237791932, | |
"eval_steps": 500, | |
"global_step": 220000, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"avg_loss": 0.29662682761985026, | |
"grad_norm": 32.271949768066406, | |
"learning_rate": 6.674212038333604e-05, | |
"loss": 0.06960329413414001, | |
"lr": 6.668070762644054e-05, | |
"step": 219999 | |
} | |
], | |
"logging_steps": 1500, | |
"max_steps": 37680000, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 2000, | |
"save_steps": 110000, | |
"stateful_callbacks": { | |
"TrainerControl": { | |
"args": { | |
"should_epoch_stop": false, | |
"should_evaluate": false, | |
"should_log": false, | |
"should_save": true, | |
"should_training_stop": false | |
}, | |
"attributes": {} | |
} | |
}, | |
"total_flos": 0.0, | |
"train_batch_size": 2, | |
"trial_name": null, | |
"trial_params": null | |
} | |