{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 2.88, | |
"eval_steps": 500, | |
"global_step": 18, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.8, | |
"grad_norm": 15.661816596984863, | |
"learning_rate": 4.1069690242163484e-05, | |
"loss": 3.5217, | |
"step": 5 | |
}, | |
{ | |
"epoch": 1.6, | |
"grad_norm": 10.799736022949219, | |
"learning_rate": 2.0658795558326743e-05, | |
"loss": 2.4036, | |
"step": 10 | |
}, | |
{ | |
"epoch": 2.4, | |
"grad_norm": 13.889681816101074, | |
"learning_rate": 3.3493649053890326e-06, | |
"loss": 1.7286, | |
"step": 15 | |
} | |
], | |
"logging_steps": 5, | |
"max_steps": 18, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 3, | |
"save_steps": 100, | |
"stateful_callbacks": { | |
"TrainerControl": { | |
"args": { | |
"should_epoch_stop": false, | |
"should_evaluate": false, | |
"should_log": false, | |
"should_save": true, | |
"should_training_stop": true | |
}, | |
"attributes": {} | |
} | |
}, | |
"total_flos": 1391853169803264.0, | |
"train_batch_size": 2, | |
"trial_name": null, | |
"trial_params": null | |
} | |