|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 3.0, |
|
"global_step": 18750, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 2.2222222222222223e-05, |
|
"loss": 0.0109, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.4444444444444447e-05, |
|
"loss": 0.0035, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.893617021276596e-05, |
|
"loss": 0.0034, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.32, |
|
"learning_rate": 4.751773049645391e-05, |
|
"loss": 0.0032, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.4, |
|
"learning_rate": 4.609929078014185e-05, |
|
"loss": 0.0033, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.48, |
|
"learning_rate": 4.468085106382979e-05, |
|
"loss": 0.0032, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.56, |
|
"learning_rate": 4.3262411347517734e-05, |
|
"loss": 0.0032, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.64, |
|
"learning_rate": 4.1843971631205674e-05, |
|
"loss": 0.0031, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.72, |
|
"learning_rate": 4.0425531914893614e-05, |
|
"loss": 0.0031, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"learning_rate": 3.900709219858156e-05, |
|
"loss": 0.003, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.88, |
|
"learning_rate": 3.75886524822695e-05, |
|
"loss": 0.0031, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.96, |
|
"learning_rate": 3.617021276595745e-05, |
|
"loss": 0.0029, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 1.04, |
|
"learning_rate": 3.4751773049645395e-05, |
|
"loss": 0.0026, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 1.12, |
|
"learning_rate": 3.3333333333333335e-05, |
|
"loss": 0.0022, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 1.2, |
|
"learning_rate": 3.191489361702128e-05, |
|
"loss": 0.0022, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.28, |
|
"learning_rate": 3.0496453900709222e-05, |
|
"loss": 0.0022, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.36, |
|
"learning_rate": 2.9080851063829788e-05, |
|
"loss": 0.0022, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.44, |
|
"learning_rate": 2.766241134751773e-05, |
|
"loss": 0.0021, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.52, |
|
"learning_rate": 2.6243971631205678e-05, |
|
"loss": 0.0022, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"learning_rate": 2.4825531914893618e-05, |
|
"loss": 0.0022, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.68, |
|
"learning_rate": 2.3409929078014188e-05, |
|
"loss": 0.0021, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.76, |
|
"learning_rate": 2.1991489361702128e-05, |
|
"loss": 0.0022, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.84, |
|
"learning_rate": 2.057304964539007e-05, |
|
"loss": 0.0022, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.92, |
|
"learning_rate": 1.9154609929078015e-05, |
|
"loss": 0.0021, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"learning_rate": 1.7736170212765958e-05, |
|
"loss": 0.0021, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 2.08, |
|
"learning_rate": 1.63177304964539e-05, |
|
"loss": 0.0016, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 2.16, |
|
"learning_rate": 1.4899290780141845e-05, |
|
"loss": 0.0016, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 2.24, |
|
"learning_rate": 1.3480851063829788e-05, |
|
"loss": 0.0016, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 2.32, |
|
"learning_rate": 1.2065248226950356e-05, |
|
"loss": 0.0016, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 2.4, |
|
"learning_rate": 1.0646808510638298e-05, |
|
"loss": 0.0015, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 2.48, |
|
"learning_rate": 9.228368794326241e-06, |
|
"loss": 0.0016, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.56, |
|
"learning_rate": 7.809929078014185e-06, |
|
"loss": 0.0016, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.64, |
|
"learning_rate": 6.394326241134752e-06, |
|
"loss": 0.0015, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.72, |
|
"learning_rate": 4.975886524822695e-06, |
|
"loss": 0.0015, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 2.8, |
|
"learning_rate": 3.557446808510639e-06, |
|
"loss": 0.0016, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.88, |
|
"learning_rate": 2.1390070921985814e-06, |
|
"loss": 0.0015, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.96, |
|
"learning_rate": 7.23404255319149e-07, |
|
"loss": 0.0015, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 18750, |
|
"total_flos": 0, |
|
"train_runtime": 2733.1751, |
|
"train_samples_per_second": 6.86 |
|
} |
|
], |
|
"max_steps": 18750, |
|
"num_train_epochs": 3, |
|
"total_flos": 0, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|