|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 1.0, |
|
"eval_steps": 500, |
|
"global_step": 151, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.9864853689026556e-05, |
|
"loss": 0.7986, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.9460875918135804e-05, |
|
"loss": 0.6672, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.879243437576383e-05, |
|
"loss": 0.5207, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.786675605459487e-05, |
|
"loss": 0.4819, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.669384911544927e-05, |
|
"loss": 0.3268, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.528639468200226e-05, |
|
"loss": 0.2877, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.3659609736217344e-05, |
|
"loss": 0.2931, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.1831082596828106e-05, |
|
"loss": 0.2654, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.3, |
|
"learning_rate": 3.9820582759626825e-05, |
|
"loss": 0.2728, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.33, |
|
"learning_rate": 3.764984715551032e-05, |
|
"loss": 0.2057, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.36, |
|
"learning_rate": 3.534234513719821e-05, |
|
"loss": 0.2175, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 3.292302473551757e-05, |
|
"loss": 0.1262, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 3.0418042928656414e-05, |
|
"loss": 0.2185, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.46, |
|
"learning_rate": 2.7854482840634965e-05, |
|
"loss": 0.1775, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.5, |
|
"learning_rate": 2.526006092656161e-05, |
|
"loss": 0.1499, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 2.2662827310499995e-05, |
|
"loss": 0.1326, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 2.0090862515805898e-05, |
|
"loss": 0.1409, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.6, |
|
"learning_rate": 1.7571973866795815e-05, |
|
"loss": 0.1064, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.63, |
|
"learning_rate": 1.5133394844163093e-05, |
|
"loss": 0.1177, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.66, |
|
"learning_rate": 1.2801490644621789e-05, |
|
"loss": 0.0922, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.7, |
|
"learning_rate": 1.0601473128180855e-05, |
|
"loss": 0.1759, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 0.73, |
|
"learning_rate": 8.55712823495419e-06, |
|
"loss": 0.1185, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.76, |
|
"learning_rate": 6.690558818595943e-06, |
|
"loss": 0.091, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 0.79, |
|
"learning_rate": 5.02194567676986e-06, |
|
"loss": 0.1172, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.83, |
|
"learning_rate": 3.5693293623207086e-06, |
|
"loss": 0.089, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 0.86, |
|
"learning_rate": 2.348415134141102e-06, |
|
"loss": 0.1183, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.89, |
|
"learning_rate": 1.3724031565473112e-06, |
|
"loss": 0.0716, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 0.93, |
|
"learning_rate": 6.51845782998356e-07, |
|
"loss": 0.1496, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 1.9453346716462317e-07, |
|
"loss": 0.1009, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 0.99, |
|
"learning_rate": 5.41053484192644e-09, |
|
"loss": 0.1001, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"step": 151, |
|
"total_flos": 6843505735041024.0, |
|
"train_loss": 0.22363514384094452, |
|
"train_runtime": 698.3029, |
|
"train_samples_per_second": 3.458, |
|
"train_steps_per_second": 0.216 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 151, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 1, |
|
"save_steps": 100, |
|
"total_flos": 6843505735041024.0, |
|
"train_batch_size": 4, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|