|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 5.0, |
|
"eval_steps": 500, |
|
"global_step": 1060, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.00019900471698113207, |
|
"loss": 6.1329, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 5.14426851272583, |
|
"eval_runtime": 3.8194, |
|
"eval_samples_per_second": 176.991, |
|
"eval_steps_per_second": 22.255, |
|
"step": 212 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 0.00019800471698113207, |
|
"loss": 4.6548, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 3.559998035430908, |
|
"eval_runtime": 3.8713, |
|
"eval_samples_per_second": 174.616, |
|
"eval_steps_per_second": 21.956, |
|
"step": 424 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.00019700471698113207, |
|
"loss": 3.2979, |
|
"step": 636 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.3220388889312744, |
|
"eval_runtime": 3.7585, |
|
"eval_samples_per_second": 179.86, |
|
"eval_steps_per_second": 22.616, |
|
"step": 636 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"learning_rate": 0.00019600471698113207, |
|
"loss": 2.2394, |
|
"step": 848 |
|
}, |
|
{ |
|
"epoch": 4.0, |
|
"eval_loss": 1.5198729038238525, |
|
"eval_runtime": 3.8733, |
|
"eval_samples_per_second": 174.529, |
|
"eval_steps_per_second": 21.945, |
|
"step": 848 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"learning_rate": 0.00019500471698113208, |
|
"loss": 1.5436, |
|
"step": 1060 |
|
}, |
|
{ |
|
"epoch": 5.0, |
|
"eval_loss": 1.0844509601593018, |
|
"eval_runtime": 3.7882, |
|
"eval_samples_per_second": 178.45, |
|
"eval_steps_per_second": 22.438, |
|
"step": 1060 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 42400, |
|
"num_train_epochs": 200, |
|
"save_steps": 500, |
|
"total_flos": 1425048900923820.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|