|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 4.938271604938271, |
|
"eval_steps": 500, |
|
"global_step": 700, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.7054673721340388, |
|
"grad_norm": 0.16252084076404572, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6969, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 1.4109347442680775, |
|
"grad_norm": 0.16519103944301605, |
|
"learning_rate": 0.0002, |
|
"loss": 1.4729, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 2.1164021164021163, |
|
"grad_norm": 0.19196180999279022, |
|
"learning_rate": 0.0002, |
|
"loss": 1.4336, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 2.821869488536155, |
|
"grad_norm": 0.1939113885164261, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3806, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 3.527336860670194, |
|
"grad_norm": 0.2203884869813919, |
|
"learning_rate": 0.0002, |
|
"loss": 1.347, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 4.232804232804233, |
|
"grad_norm": 0.2938516139984131, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3009, |
|
"step": 600 |
|
}, |
|
{ |
|
"epoch": 4.938271604938271, |
|
"grad_norm": 0.2624386250972748, |
|
"learning_rate": 0.0002, |
|
"loss": 1.3224, |
|
"step": 700 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 705, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 5, |
|
"save_steps": 100, |
|
"total_flos": 8.028866127259238e+16, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|