|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 0.2680515999329871, |
|
"eval_steps": 500, |
|
"global_step": 400, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.99993842168232e-05, |
|
"loss": 1.2211, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.01, |
|
"learning_rate": 4.9997536897627915e-05, |
|
"loss": 1.0276, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.02, |
|
"learning_rate": 4.9994458133418e-05, |
|
"loss": 0.8587, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.999014807586154e-05, |
|
"loss": 0.7431, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.03, |
|
"learning_rate": 4.9984606937283405e-05, |
|
"loss": 0.6841, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.04, |
|
"learning_rate": 4.9977834990654804e-05, |
|
"loss": 0.6452, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.99698325695798e-05, |
|
"loss": 0.6347, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.05, |
|
"learning_rate": 4.9960600068278876e-05, |
|
"loss": 0.6109, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.06, |
|
"learning_rate": 4.995013794156957e-05, |
|
"loss": 0.5911, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.993844670484401e-05, |
|
"loss": 0.5803, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.07, |
|
"learning_rate": 4.992552693404354e-05, |
|
"loss": 0.5902, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.08, |
|
"learning_rate": 4.991137926563036e-05, |
|
"loss": 0.5745, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.9896004396556176e-05, |
|
"loss": 0.5538, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 0.09, |
|
"learning_rate": 4.987940308422783e-05, |
|
"loss": 0.5495, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 0.1, |
|
"learning_rate": 4.986157614647005e-05, |
|
"loss": 0.5433, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.984252446148508e-05, |
|
"loss": 0.548, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 0.11, |
|
"learning_rate": 4.98222489678095e-05, |
|
"loss": 0.5361, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 0.12, |
|
"learning_rate": 4.980075066426796e-05, |
|
"loss": 0.5331, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.977803060992393e-05, |
|
"loss": 0.53, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 0.13, |
|
"learning_rate": 4.97540899240276e-05, |
|
"loss": 0.5135, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 0.14, |
|
"learning_rate": 4.972892978596069e-05, |
|
"loss": 0.5101, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.970255143517838e-05, |
|
"loss": 0.5125, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 0.15, |
|
"learning_rate": 4.967495617114826e-05, |
|
"loss": 0.4928, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 0.16, |
|
"learning_rate": 4.964614535328626e-05, |
|
"loss": 0.4878, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.961612040088973e-05, |
|
"loss": 0.5017, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 0.17, |
|
"learning_rate": 4.9584882793067534e-05, |
|
"loss": 0.4863, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 0.18, |
|
"learning_rate": 4.955243406866713e-05, |
|
"loss": 0.4847, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.951877582619881e-05, |
|
"loss": 0.4868, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 0.19, |
|
"learning_rate": 4.948390972375694e-05, |
|
"loss": 0.4748, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 0.2, |
|
"learning_rate": 4.944783747893825e-05, |
|
"loss": 0.4764, |
|
"step": 300 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.941056086875727e-05, |
|
"loss": 0.4712, |
|
"step": 310 |
|
}, |
|
{ |
|
"epoch": 0.21, |
|
"learning_rate": 4.937208172955876e-05, |
|
"loss": 0.4642, |
|
"step": 320 |
|
}, |
|
{ |
|
"epoch": 0.22, |
|
"learning_rate": 4.9332401956927224e-05, |
|
"loss": 0.4642, |
|
"step": 330 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.9291523505593604e-05, |
|
"loss": 0.4709, |
|
"step": 340 |
|
}, |
|
{ |
|
"epoch": 0.23, |
|
"learning_rate": 4.9249448389338905e-05, |
|
"loss": 0.461, |
|
"step": 350 |
|
}, |
|
{ |
|
"epoch": 0.24, |
|
"learning_rate": 4.920617868089501e-05, |
|
"loss": 0.4677, |
|
"step": 360 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.9161716511842614e-05, |
|
"loss": 0.4564, |
|
"step": 370 |
|
}, |
|
{ |
|
"epoch": 0.25, |
|
"learning_rate": 4.911606407250617e-05, |
|
"loss": 0.4663, |
|
"step": 380 |
|
}, |
|
{ |
|
"epoch": 0.26, |
|
"learning_rate": 4.9069223611846014e-05, |
|
"loss": 0.4682, |
|
"step": 390 |
|
}, |
|
{ |
|
"epoch": 0.27, |
|
"learning_rate": 4.9021197437347555e-05, |
|
"loss": 0.4636, |
|
"step": 400 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 4476, |
|
"num_train_epochs": 3, |
|
"save_steps": 200, |
|
"total_flos": 3.6377843599451095e+18, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|