|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 0.00013384247701784754, |
|
"loss": 3.4817, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 0.0001240985658141214, |
|
"loss": 3.1272, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 0.00010892206830726365, |
|
"loss": 3.0271, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 8.97985658141214e-05, |
|
"loss": 2.9857, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 6.86e-05, |
|
"loss": 2.9297, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 4.740143418587861e-05, |
|
"loss": 2.9014, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 2.8277931692736352e-05, |
|
"loss": 2.905, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 1.3101434185878613e-05, |
|
"loss": 2.996, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.9, |
|
"learning_rate": 3.357522982152468e-06, |
|
"loss": 2.9399, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 0.0, |
|
"loss": 2.9631, |
|
"step": 50 |
|
} |
|
], |
|
"max_steps": 50, |
|
"num_train_epochs": 1, |
|
"total_flos": 51474530304000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|