|
{ |
|
"best_metric": 2.4982783794403076, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 0.36429872495446264, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 0.0002, |
|
"loss": 2.7392, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"eval_loss": 2.641645669937134, |
|
"eval_runtime": 216.5632, |
|
"eval_samples_per_second": 28.971, |
|
"eval_steps_per_second": 3.625, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 0.0002, |
|
"loss": 2.6048, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"eval_loss": 2.5937132835388184, |
|
"eval_runtime": 206.5927, |
|
"eval_samples_per_second": 30.369, |
|
"eval_steps_per_second": 3.8, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 0.0002, |
|
"loss": 2.5626, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"eval_loss": 2.556633949279785, |
|
"eval_runtime": 206.6295, |
|
"eval_samples_per_second": 30.364, |
|
"eval_steps_per_second": 3.799, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"learning_rate": 0.0002, |
|
"loss": 2.5359, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.29, |
|
"eval_loss": 2.52408504486084, |
|
"eval_runtime": 206.6465, |
|
"eval_samples_per_second": 30.361, |
|
"eval_steps_per_second": 3.799, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 0.0002, |
|
"loss": 2.4941, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"eval_loss": 2.4982783794403076, |
|
"eval_runtime": 206.6237, |
|
"eval_samples_per_second": 30.364, |
|
"eval_steps_per_second": 3.799, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 4116, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 1.459702746464256e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|