|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 14052, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.8220893822943356e-05, |
|
"loss": 2.2627, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.644178764588671e-05, |
|
"loss": 1.8478, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.466268146883006e-05, |
|
"loss": 1.6547, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.43, |
|
"learning_rate": 4.2883575291773416e-05, |
|
"loss": 1.5303, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.53, |
|
"learning_rate": 4.110446911471677e-05, |
|
"loss": 1.4348, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 3.9325362937660123e-05, |
|
"loss": 1.36, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.75, |
|
"learning_rate": 3.754625676060348e-05, |
|
"loss": 1.3118, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.85, |
|
"learning_rate": 3.5767150583546824e-05, |
|
"loss": 1.2551, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 3.3988044406490184e-05, |
|
"loss": 1.2125, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 1.07, |
|
"learning_rate": 3.220893822943353e-05, |
|
"loss": 1.174, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 1.17, |
|
"learning_rate": 3.0429832052376888e-05, |
|
"loss": 1.1241, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 2.8650725875320238e-05, |
|
"loss": 1.0909, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.39, |
|
"learning_rate": 2.6871619698263595e-05, |
|
"loss": 1.061, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.49, |
|
"learning_rate": 2.5092513521206945e-05, |
|
"loss": 1.0389, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 2.33134073441503e-05, |
|
"loss": 1.0249, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.71, |
|
"learning_rate": 2.1534301167093655e-05, |
|
"loss": 0.9963, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.81, |
|
"learning_rate": 1.975519499003701e-05, |
|
"loss": 0.9854, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 1.797608881298036e-05, |
|
"loss": 0.9605, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 2.03, |
|
"learning_rate": 1.6196982635923712e-05, |
|
"loss": 0.9448, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 2.13, |
|
"learning_rate": 1.4417876458867066e-05, |
|
"loss": 0.9212, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 1.263877028181042e-05, |
|
"loss": 0.9118, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 2.35, |
|
"learning_rate": 1.0859664104753773e-05, |
|
"loss": 0.9049, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 2.46, |
|
"learning_rate": 9.080557927697125e-06, |
|
"loss": 0.8889, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 7.301451750640478e-06, |
|
"loss": 0.8752, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.67, |
|
"learning_rate": 5.5223455735838315e-06, |
|
"loss": 0.8754, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.78, |
|
"learning_rate": 3.743239396527185e-06, |
|
"loss": 0.8668, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 1.964133219470538e-06, |
|
"loss": 0.854, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.99, |
|
"learning_rate": 1.8502704241389127e-07, |
|
"loss": 0.8554, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 14052, |
|
"total_flos": 1.3105172644574003e+17, |
|
"train_loss": 1.1496979724027274, |
|
"train_runtime": 14912.9972, |
|
"train_samples_per_second": 9.422, |
|
"train_steps_per_second": 0.942 |
|
} |
|
], |
|
"max_steps": 14052, |
|
"num_train_epochs": 3, |
|
"total_flos": 1.3105172644574003e+17, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|