|
{ |
|
"best_metric": 2.2774927616119385, |
|
"best_model_checkpoint": "output/upsahl/checkpoint-48", |
|
"epoch": 3.0, |
|
"global_step": 48, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.31, |
|
"learning_rate": 0.00010671211798514472, |
|
"loss": 3.2946, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.62, |
|
"learning_rate": 4.2347916539754844e-05, |
|
"loss": 2.928, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.94, |
|
"learning_rate": 1.3181297643383925e-06, |
|
"loss": 3.0697, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 2.612957000732422, |
|
"eval_runtime": 0.9789, |
|
"eval_samples_per_second": 22.474, |
|
"eval_steps_per_second": 3.065, |
|
"step": 16 |
|
}, |
|
{ |
|
"epoch": 1.25, |
|
"learning_rate": 2.009247481060283e-05, |
|
"loss": 2.7458, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 1.56, |
|
"learning_rate": 8.19831960903064e-05, |
|
"loss": 2.9099, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 1.88, |
|
"learning_rate": 0.00013197813593027427, |
|
"loss": 2.7352, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 2.414498805999756, |
|
"eval_runtime": 0.9833, |
|
"eval_samples_per_second": 22.373, |
|
"eval_steps_per_second": 3.051, |
|
"step": 32 |
|
}, |
|
{ |
|
"epoch": 2.19, |
|
"learning_rate": 0.0001256388154039546, |
|
"loss": 2.4889, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 2.5, |
|
"learning_rate": 6.860000000000001e-05, |
|
"loss": 2.2818, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 2.81, |
|
"learning_rate": 1.1561184596045404e-05, |
|
"loss": 2.4598, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 2.2774927616119385, |
|
"eval_runtime": 0.9931, |
|
"eval_samples_per_second": 22.154, |
|
"eval_steps_per_second": 3.021, |
|
"step": 48 |
|
} |
|
], |
|
"max_steps": 48, |
|
"num_train_epochs": 3, |
|
"total_flos": 48600317952000.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|