|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 2118, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.71, |
|
"learning_rate": 3.819641170915959e-05, |
|
"loss": 2.6301, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 1.42, |
|
"learning_rate": 2.639282341831917e-05, |
|
"loss": 1.9457, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 2.12, |
|
"learning_rate": 1.4589235127478753e-05, |
|
"loss": 1.687, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 2.83, |
|
"learning_rate": 2.785646836638338e-06, |
|
"loss": 1.4368, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 2118, |
|
"total_flos": 604061361020928.0, |
|
"train_loss": 1.8985024759294404, |
|
"train_runtime": 372.3315, |
|
"train_samples_per_second": 22.73, |
|
"train_steps_per_second": 5.688 |
|
} |
|
], |
|
"max_steps": 2118, |
|
"num_train_epochs": 3, |
|
"total_flos": 604061361020928.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|