|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.0006218905472636816, |
|
"eval_steps": 1000, |
|
"global_step": 25, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0, |
|
"loss": 1.9492, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0, |
|
"loss": 1.9778, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4e-05, |
|
"loss": 2.0908, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 4e-05, |
|
"loss": 2.0456, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 8e-05, |
|
"loss": 2.2288, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00012, |
|
"loss": 1.7521, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00016, |
|
"loss": 1.746, |
|
"step": 7 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0002, |
|
"loss": 1.6457, |
|
"step": 8 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00019789473684210526, |
|
"loss": 1.6226, |
|
"step": 9 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00019578947368421054, |
|
"loss": 1.643, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0001936842105263158, |
|
"loss": 1.7807, |
|
"step": 11 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00019157894736842104, |
|
"loss": 1.7257, |
|
"step": 12 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00018947368421052632, |
|
"loss": 1.6412, |
|
"step": 13 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0001873684210526316, |
|
"loss": 1.6792, |
|
"step": 14 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00018526315789473685, |
|
"loss": 1.4892, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0001831578947368421, |
|
"loss": 1.4418, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00018105263157894739, |
|
"loss": 1.5064, |
|
"step": 17 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00017894736842105264, |
|
"loss": 1.5943, |
|
"step": 18 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0001768421052631579, |
|
"loss": 1.419, |
|
"step": 19 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00017473684210526317, |
|
"loss": 1.5235, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00017263157894736842, |
|
"loss": 1.6562, |
|
"step": 21 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.0001705263157894737, |
|
"loss": 1.4182, |
|
"step": 22 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00016842105263157895, |
|
"loss": 1.7132, |
|
"step": 23 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00016631578947368423, |
|
"loss": 1.7307, |
|
"step": 24 |
|
}, |
|
{ |
|
"epoch": 0.0, |
|
"learning_rate": 0.00016421052631578948, |
|
"loss": 1.7079, |
|
"step": 25 |
|
} |
|
], |
|
"logging_steps": 1, |
|
"max_steps": 100, |
|
"num_train_epochs": 1, |
|
"save_steps": 25, |
|
"total_flos": 1319123636748288.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|