{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0, | |
"eval_steps": 500, | |
"global_step": 1460, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.34, | |
"learning_rate": 3.287671232876712e-05, | |
"loss": 1.776, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.68, | |
"learning_rate": 1.5753424657534248e-05, | |
"loss": 1.6672, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 1.0, | |
"step": 1460, | |
"total_flos": 8.671679350623437e+16, | |
"train_loss": 1.700456760354238, | |
"train_runtime": 3303.7788, | |
"train_samples_per_second": 3.535, | |
"train_steps_per_second": 0.442 | |
} | |
], | |
"logging_steps": 500, | |
"max_steps": 1460, | |
"num_train_epochs": 1, | |
"save_steps": -1460, | |
"total_flos": 8.671679350623437e+16, | |
"trial_name": null, | |
"trial_params": null | |
} | |