|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 10.0, |
|
"eval_steps": 500, |
|
"global_step": 1420, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 7.95774647887324e-05, |
|
"loss": 1.6627, |
|
"step": 113 |
|
}, |
|
{ |
|
"epoch": 1.59, |
|
"learning_rate": 9.342723004694837e-05, |
|
"loss": 0.9461, |
|
"step": 226 |
|
}, |
|
{ |
|
"epoch": 2.39, |
|
"learning_rate": 8.458528951486699e-05, |
|
"loss": 0.7273, |
|
"step": 339 |
|
}, |
|
{ |
|
"epoch": 3.18, |
|
"learning_rate": 7.57433489827856e-05, |
|
"loss": 0.661, |
|
"step": 452 |
|
}, |
|
{ |
|
"epoch": 3.98, |
|
"learning_rate": 6.690140845070422e-05, |
|
"loss": 0.6202, |
|
"step": 565 |
|
}, |
|
{ |
|
"epoch": 4.77, |
|
"learning_rate": 5.8059467918622856e-05, |
|
"loss": 0.5934, |
|
"step": 678 |
|
}, |
|
{ |
|
"epoch": 5.57, |
|
"learning_rate": 4.9217527386541474e-05, |
|
"loss": 0.5736, |
|
"step": 791 |
|
}, |
|
{ |
|
"epoch": 6.37, |
|
"learning_rate": 4.037558685446009e-05, |
|
"loss": 0.5608, |
|
"step": 904 |
|
}, |
|
{ |
|
"epoch": 7.16, |
|
"learning_rate": 3.153364632237872e-05, |
|
"loss": 0.5482, |
|
"step": 1017 |
|
}, |
|
{ |
|
"epoch": 7.96, |
|
"learning_rate": 2.269170579029734e-05, |
|
"loss": 0.5426, |
|
"step": 1130 |
|
}, |
|
{ |
|
"epoch": 8.75, |
|
"learning_rate": 1.3849765258215963e-05, |
|
"loss": 0.5362, |
|
"step": 1243 |
|
}, |
|
{ |
|
"epoch": 9.55, |
|
"learning_rate": 5.007824726134586e-06, |
|
"loss": 0.5328, |
|
"step": 1356 |
|
} |
|
], |
|
"logging_steps": 113, |
|
"max_steps": 1420, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 10, |
|
"save_steps": 500, |
|
"total_flos": 4.3668106018553856e+17, |
|
"train_batch_size": 12, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|