|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"global_step": 3, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3e-05, |
|
"loss": 2.6917, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"eval_accuracy": 0.05304531642224865, |
|
"eval_loss": 2.66796875, |
|
"eval_runtime": 1.9177, |
|
"eval_samples_per_second": 15.122, |
|
"eval_steps_per_second": 0.521, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 3e-05, |
|
"loss": 2.8435, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_accuracy": 0.05304531642224865, |
|
"eval_loss": 2.66796875, |
|
"eval_runtime": 1.7979, |
|
"eval_samples_per_second": 16.13, |
|
"eval_steps_per_second": 0.556, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"learning_rate": 1.9999999999999998e-05, |
|
"loss": 2.7502, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_accuracy": 0.055489496630994846, |
|
"eval_loss": 2.6171875, |
|
"eval_runtime": 1.4088, |
|
"eval_samples_per_second": 20.586, |
|
"eval_steps_per_second": 0.71, |
|
"step": 3 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 3, |
|
"total_flos": 303365357568.0, |
|
"train_loss": 2.7618001302083335, |
|
"train_runtime": 2178.2199, |
|
"train_samples_per_second": 0.072, |
|
"train_steps_per_second": 0.001 |
|
} |
|
], |
|
"max_steps": 3, |
|
"num_train_epochs": 1, |
|
"total_flos": 303365357568.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|