{ | |
"best_metric": null, | |
"best_model_checkpoint": null, | |
"epoch": 0.2173263426693108, | |
"global_step": 8000, | |
"is_hyper_param_search": false, | |
"is_local_process_zero": true, | |
"is_world_process_zero": true, | |
"log_history": [ | |
{ | |
"epoch": 0.03, | |
"learning_rate": 1.269e-05, | |
"loss": 0.9046, | |
"step": 1000 | |
}, | |
{ | |
"epoch": 0.05, | |
"learning_rate": 1.128e-05, | |
"loss": 0.783, | |
"step": 2000 | |
}, | |
{ | |
"epoch": 0.08, | |
"learning_rate": 9.87e-06, | |
"loss": 0.7261, | |
"step": 3000 | |
}, | |
{ | |
"epoch": 0.11, | |
"learning_rate": 8.46e-06, | |
"loss": 0.7128, | |
"step": 4000 | |
}, | |
{ | |
"epoch": 0.14, | |
"learning_rate": 7.05e-06, | |
"loss": 0.7113, | |
"step": 5000 | |
}, | |
{ | |
"epoch": 0.16, | |
"learning_rate": 5.64e-06, | |
"loss": 0.7047, | |
"step": 6000 | |
}, | |
{ | |
"epoch": 0.19, | |
"learning_rate": 4.23e-06, | |
"loss": 0.7025, | |
"step": 7000 | |
}, | |
{ | |
"epoch": 0.22, | |
"learning_rate": 2.82e-06, | |
"loss": 0.7035, | |
"step": 8000 | |
} | |
], | |
"max_steps": 10000, | |
"num_train_epochs": 1, | |
"total_flos": 0.0, | |
"trial_name": null, | |
"trial_params": null | |
} | |