{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 41509, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 1.0, | |
"grad_norm": 1.6171875, | |
"learning_rate": 0.00016, | |
"loss": 0.8639, | |
"step": 41509 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 1.0884636640548706, | |
"eval_runtime": 1478.2279, | |
"eval_samples_per_second": 7.556, | |
"eval_steps_per_second": 3.778, | |
"step": 41509 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 207545, | |
"num_input_tokens_seen": 0, | |
"num_train_epochs": 5, | |
"save_steps": 500, | |
"stateful_callbacks": { | |
"TrainerControl": { | |
"args": { | |
"should_epoch_stop": false, | |
"should_evaluate": false, | |
"should_log": false, | |
"should_save": true, | |
"should_training_stop": false | |
}, | |
"attributes": {} | |
} | |
}, | |
"total_flos": 2.359924612023976e+18, | |
"train_batch_size": 2, | |
"trial_name": null, | |
"trial_params": null | |
} | |