|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 73632, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.3333333333333333e-05, |
|
"loss": 0.7143, |
|
"step": 24544 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.7503820682628629, |
|
"eval_loss": 0.6168540120124817, |
|
"eval_runtime": 71.4698, |
|
"eval_samples_per_second": 137.331, |
|
"eval_steps_per_second": 17.168, |
|
"step": 24544 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 6.666666666666667e-06, |
|
"loss": 0.5407, |
|
"step": 49088 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_accuracy": 0.7627101375445746, |
|
"eval_loss": 0.6218484044075012, |
|
"eval_runtime": 71.2675, |
|
"eval_samples_per_second": 137.72, |
|
"eval_steps_per_second": 17.217, |
|
"step": 49088 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"learning_rate": 0.0, |
|
"loss": 0.4178, |
|
"step": 73632 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_accuracy": 0.7657666836474784, |
|
"eval_loss": 0.6564478278160095, |
|
"eval_runtime": 71.6262, |
|
"eval_samples_per_second": 137.031, |
|
"eval_steps_per_second": 17.131, |
|
"step": 73632 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 73632, |
|
"total_flos": 2.095159996537344e+17, |
|
"train_loss": 0.5575872004317077, |
|
"train_runtime": 24054.786, |
|
"train_samples_per_second": 48.976, |
|
"train_steps_per_second": 3.061 |
|
} |
|
], |
|
"max_steps": 73632, |
|
"num_train_epochs": 3, |
|
"total_flos": 2.095159996537344e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|