|
{ |
|
"best_metric": 1.3869292736053467, |
|
"best_model_checkpoint": "./outputs/checkpoint-500", |
|
"epoch": 0.6666666666666666, |
|
"eval_steps": 100, |
|
"global_step": 500, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 0.0002, |
|
"loss": 1.357, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"eval_loss": 1.4659545421600342, |
|
"eval_runtime": 114.978, |
|
"eval_samples_per_second": 12.62, |
|
"eval_steps_per_second": 1.583, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1954, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"eval_loss": 1.4343539476394653, |
|
"eval_runtime": 112.6008, |
|
"eval_samples_per_second": 12.886, |
|
"eval_steps_per_second": 1.616, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1774, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"eval_loss": 1.4164679050445557, |
|
"eval_runtime": 112.4536, |
|
"eval_samples_per_second": 12.903, |
|
"eval_steps_per_second": 1.618, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1691, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"eval_loss": 1.4017506837844849, |
|
"eval_runtime": 112.3429, |
|
"eval_samples_per_second": 12.916, |
|
"eval_steps_per_second": 1.62, |
|
"step": 400 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"learning_rate": 0.0002, |
|
"loss": 1.1554, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.67, |
|
"eval_loss": 1.3869292736053467, |
|
"eval_runtime": 112.4263, |
|
"eval_samples_per_second": 12.906, |
|
"eval_steps_per_second": 1.619, |
|
"step": 500 |
|
} |
|
], |
|
"logging_steps": 100, |
|
"max_steps": 2250, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"total_flos": 3.186244674256896e+16, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|