|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.6666666666666665, |
|
"eval_steps": 500, |
|
"global_step": 6, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.44, |
|
"grad_norm": 8.291832048121316, |
|
"learning_rate": 2e-05, |
|
"loss": 1.5309, |
|
"step": 1 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"eval_loss": 1.230512261390686, |
|
"eval_runtime": 20.4922, |
|
"eval_samples_per_second": 11.077, |
|
"eval_steps_per_second": 0.732, |
|
"step": 2 |
|
}, |
|
{ |
|
"epoch": 1.78, |
|
"eval_loss": 1.1438697576522827, |
|
"eval_runtime": 20.4412, |
|
"eval_samples_per_second": 11.105, |
|
"eval_steps_per_second": 0.734, |
|
"step": 4 |
|
}, |
|
{ |
|
"epoch": 2.22, |
|
"grad_norm": 2.897824695138987, |
|
"learning_rate": 1.9098300562505266e-06, |
|
"loss": 1.2386, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"eval_loss": 1.1274299621582031, |
|
"eval_runtime": 20.6039, |
|
"eval_samples_per_second": 11.017, |
|
"eval_steps_per_second": 0.728, |
|
"step": 6 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"step": 6, |
|
"total_flos": 1203933020160.0, |
|
"train_loss": 1.2448947429656982, |
|
"train_runtime": 161.7577, |
|
"train_samples_per_second": 2.43, |
|
"train_steps_per_second": 0.037 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 6, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"total_flos": 1203933020160.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|