{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 1.0587612493382743, | |
"global_step": 2000, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.26, | |
"learning_rate": 1.8235397917769543e-05, | |
"loss": 21.3637, | |
"step": 500 | |
}, | |
{ | |
"epoch": 0.53, | |
"learning_rate": 1.6470795835539088e-05, | |
"loss": 10.4706, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 0.79, | |
"learning_rate": 1.470619375330863e-05, | |
"loss": 5.7273, | |
"step": 1500 | |
}, | |
{ | |
"epoch": 1.0, | |
"eval_loss": 1.1415340900421143, | |
"eval_runtime": 9.212, | |
"eval_samples_per_second": 182.262, | |
"eval_steps_per_second": 11.398, | |
"step": 1889 | |
}, | |
{ | |
"epoch": 1.06, | |
"learning_rate": 1.2941591671078173e-05, | |
"loss": 3.094, | |
"step": 2000 | |
} | |
], | |
"max_steps": 5667, | |
"num_train_epochs": 3, | |
"total_flos": 2114205638983680.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |