|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.08, |
|
"eval_steps": 500, |
|
"global_step": 100, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"grad_norm": 0.0634765625, |
|
"learning_rate": 1e-05, |
|
"loss": 0.801, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 0.10302734375, |
|
"learning_rate": 2e-05, |
|
"loss": 0.8727, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"grad_norm": 0.1337890625, |
|
"learning_rate": 1.9238795325112867e-05, |
|
"loss": 0.9494, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"grad_norm": 0.353515625, |
|
"learning_rate": 1.7071067811865477e-05, |
|
"loss": 0.924, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"grad_norm": 0.2138671875, |
|
"learning_rate": 1.3826834323650899e-05, |
|
"loss": 0.8565, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"grad_norm": 0.1806640625, |
|
"learning_rate": 1e-05, |
|
"loss": 0.9148, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"grad_norm": 0.10205078125, |
|
"learning_rate": 6.173165676349103e-06, |
|
"loss": 0.9012, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"grad_norm": 0.10205078125, |
|
"learning_rate": 2.9289321881345257e-06, |
|
"loss": 0.8378, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"grad_norm": 0.0859375, |
|
"learning_rate": 7.612046748871327e-07, |
|
"loss": 0.8401, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"grad_norm": 1.5234375, |
|
"learning_rate": 0.0, |
|
"loss": 0.9031, |
|
"step": 100 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 50, |
|
"total_flos": 2.0519009896103936e+16, |
|
"train_batch_size": 1, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|