|
{ |
|
"best_metric": 0.721502423286438, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 2.6666666666666665, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 1.0771, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 0.8566448092460632, |
|
"eval_runtime": 229.494, |
|
"eval_samples_per_second": 8.41, |
|
"eval_steps_per_second": 1.054, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8856, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"eval_loss": 0.8006419539451599, |
|
"eval_runtime": 229.5751, |
|
"eval_samples_per_second": 8.407, |
|
"eval_steps_per_second": 1.054, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8356, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"eval_loss": 0.7660272717475891, |
|
"eval_runtime": 229.5539, |
|
"eval_samples_per_second": 8.408, |
|
"eval_steps_per_second": 1.054, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 0.0002, |
|
"loss": 0.8076, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"eval_loss": 0.7408167123794556, |
|
"eval_runtime": 229.5926, |
|
"eval_samples_per_second": 8.406, |
|
"eval_steps_per_second": 1.054, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 0.0002, |
|
"loss": 0.7819, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"eval_loss": 0.721502423286438, |
|
"eval_runtime": 229.6082, |
|
"eval_samples_per_second": 8.406, |
|
"eval_steps_per_second": 1.054, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 561, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 3.51635490349056e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|