|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.9615384615384616, |
|
"eval_steps": 10, |
|
"global_step": 50, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 2.272727272727273e-05, |
|
"loss": 1.7377, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"eval_loss": 1.3826087713241577, |
|
"eval_runtime": 164.229, |
|
"eval_samples_per_second": 0.304, |
|
"eval_steps_per_second": 0.043, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"learning_rate": 2.0202020202020203e-05, |
|
"loss": 1.0247, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.38, |
|
"eval_loss": 0.6683715581893921, |
|
"eval_runtime": 163.0119, |
|
"eval_samples_per_second": 0.307, |
|
"eval_steps_per_second": 0.043, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"learning_rate": 1.7676767676767676e-05, |
|
"loss": 0.4914, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.58, |
|
"eval_loss": 0.34242257475852966, |
|
"eval_runtime": 164.0724, |
|
"eval_samples_per_second": 0.305, |
|
"eval_steps_per_second": 0.043, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"learning_rate": 1.5151515151515153e-05, |
|
"loss": 0.3506, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.77, |
|
"eval_loss": 0.3160565197467804, |
|
"eval_runtime": 163.8993, |
|
"eval_samples_per_second": 0.305, |
|
"eval_steps_per_second": 0.043, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.2626262626262628e-05, |
|
"loss": 0.3133, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"eval_loss": 0.3000437915325165, |
|
"eval_runtime": 163.2552, |
|
"eval_samples_per_second": 0.306, |
|
"eval_steps_per_second": 0.043, |
|
"step": 50 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 100, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 2, |
|
"save_steps": 10, |
|
"total_flos": 2190925941964800.0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|