| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.282051282051282, |
| "eval_steps": 50.0, |
| "global_step": 150, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.008547008547008548, |
| "grad_norm": 13.935976028442383, |
| "learning_rate": 1.25e-06, |
| "loss": 1.2302496433258057, |
| "step": 1, |
| "token_acc": 0.7555120910384068 |
| }, |
| { |
| "epoch": 0.042735042735042736, |
| "grad_norm": 12.733538627624512, |
| "learning_rate": 6.25e-06, |
| "loss": 1.1761837005615234, |
| "step": 5, |
| "token_acc": 0.7647914645974782 |
| }, |
| { |
| "epoch": 0.08547008547008547, |
| "grad_norm": 3.3333914279937744, |
| "learning_rate": 9.998067787472772e-06, |
| "loss": 0.896819019317627, |
| "step": 10, |
| "token_acc": 0.7896966517032977 |
| }, |
| { |
| "epoch": 0.1282051282051282, |
| "grad_norm": 3.5416104793548584, |
| "learning_rate": 9.976347543410487e-06, |
| "loss": 0.7495913505554199, |
| "step": 15, |
| "token_acc": 0.8130858441520439 |
| }, |
| { |
| "epoch": 0.17094017094017094, |
| "grad_norm": 3.1907875537872314, |
| "learning_rate": 9.930597024496933e-06, |
| "loss": 0.6861935615539551, |
| "step": 20, |
| "token_acc": 0.8265455118441095 |
| }, |
| { |
| "epoch": 0.21367521367521367, |
| "grad_norm": 3.0737252235412598, |
| "learning_rate": 9.861037155322777e-06, |
| "loss": 0.6162723064422607, |
| "step": 25, |
| "token_acc": 0.8381843560978132 |
| }, |
| { |
| "epoch": 0.2564102564102564, |
| "grad_norm": 3.321166753768921, |
| "learning_rate": 9.768003833403278e-06, |
| "loss": 0.5933701515197753, |
| "step": 30, |
| "token_acc": 0.8392482419056003 |
| }, |
| { |
| "epoch": 0.29914529914529914, |
| "grad_norm": 2.5869693756103516, |
| "learning_rate": 9.651946307163417e-06, |
| "loss": 0.6245723724365234, |
| "step": 35, |
| "token_acc": 0.8400627408615442 |
| }, |
| { |
| "epoch": 0.3418803418803419, |
| "grad_norm": 3.3702032566070557, |
| "learning_rate": 9.51342500656308e-06, |
| "loss": 0.5320750713348389, |
| "step": 40, |
| "token_acc": 0.8597009626829829 |
| }, |
| { |
| "epoch": 0.38461538461538464, |
| "grad_norm": 2.5714972019195557, |
| "learning_rate": 9.353108836837907e-06, |
| "loss": 0.6000706672668457, |
| "step": 45, |
| "token_acc": 0.8455385915790586 |
| }, |
| { |
| "epoch": 0.42735042735042733, |
| "grad_norm": 2.7259583473205566, |
| "learning_rate": 9.171771948424138e-06, |
| "loss": 0.4976496696472168, |
| "step": 50, |
| "token_acc": 0.8652953087066456 |
| }, |
| { |
| "epoch": 0.4700854700854701, |
| "grad_norm": 1.6538729667663574, |
| "learning_rate": 8.970289998665083e-06, |
| "loss": 0.5108413696289062, |
| "step": 55, |
| "token_acc": 0.8643437786086937 |
| }, |
| { |
| "epoch": 0.5128205128205128, |
| "grad_norm": 1.9930307865142822, |
| "learning_rate": 8.749635923351108e-06, |
| "loss": 0.5116062164306641, |
| "step": 60, |
| "token_acc": 0.8584137276609205 |
| }, |
| { |
| "epoch": 0.5555555555555556, |
| "grad_norm": 1.778527021408081, |
| "learning_rate": 8.510875238511911e-06, |
| "loss": 0.4901996612548828, |
| "step": 65, |
| "token_acc": 0.8642093487261697 |
| }, |
| { |
| "epoch": 0.5982905982905983, |
| "grad_norm": 2.789698362350464, |
| "learning_rate": 8.255160895148263e-06, |
| "loss": 0.49276137351989746, |
| "step": 70, |
| "token_acc": 0.8632728710522414 |
| }, |
| { |
| "epoch": 0.6410256410256411, |
| "grad_norm": 2.4906489849090576, |
| "learning_rate": 7.983727711749194e-06, |
| "loss": 0.46578373908996584, |
| "step": 75, |
| "token_acc": 0.8713921087941244 |
| }, |
| { |
| "epoch": 0.6837606837606838, |
| "grad_norm": 2.1418581008911133, |
| "learning_rate": 7.697886411479422e-06, |
| "loss": 0.46045923233032227, |
| "step": 80, |
| "token_acc": 0.8719648648325216 |
| }, |
| { |
| "epoch": 0.7264957264957265, |
| "grad_norm": 1.8900772333145142, |
| "learning_rate": 7.399017292830848e-06, |
| "loss": 0.49722442626953123, |
| "step": 85, |
| "token_acc": 0.861450770602471 |
| }, |
| { |
| "epoch": 0.7692307692307693, |
| "grad_norm": 9.884895324707031, |
| "learning_rate": 7.088563564301874e-06, |
| "loss": 0.4920672416687012, |
| "step": 90, |
| "token_acc": 0.8587491425333293 |
| }, |
| { |
| "epoch": 0.811965811965812, |
| "grad_norm": 2.0830328464508057, |
| "learning_rate": 6.768024375290747e-06, |
| "loss": 0.5075239181518555, |
| "step": 95, |
| "token_acc": 0.8566905419232774 |
| }, |
| { |
| "epoch": 0.8547008547008547, |
| "grad_norm": 2.6918821334838867, |
| "learning_rate": 6.4389475768559675e-06, |
| "loss": 0.4198714256286621, |
| "step": 100, |
| "token_acc": 0.8777022792164509 |
| }, |
| { |
| "epoch": 0.8974358974358975, |
| "grad_norm": 2.4037363529205322, |
| "learning_rate": 6.1029222473013705e-06, |
| "loss": 0.44579553604125977, |
| "step": 105, |
| "token_acc": 0.8723411714183048 |
| }, |
| { |
| "epoch": 0.9401709401709402, |
| "grad_norm": 2.708740234375, |
| "learning_rate": 5.761571018679025e-06, |
| "loss": 0.46126999855041506, |
| "step": 110, |
| "token_acc": 0.8693372368665406 |
| }, |
| { |
| "epoch": 0.9829059829059829, |
| "grad_norm": 1.4541316032409668, |
| "learning_rate": 5.416542241264524e-06, |
| "loss": 0.41992721557617185, |
| "step": 115, |
| "token_acc": 0.8794615180232043 |
| }, |
| { |
| "epoch": 1.0256410256410255, |
| "grad_norm": 1.3620638847351074, |
| "learning_rate": 5.069502023841576e-06, |
| "loss": 0.37786569595336916, |
| "step": 120, |
| "token_acc": 0.890482741876745 |
| }, |
| { |
| "epoch": 1.0683760683760684, |
| "grad_norm": 1.4797122478485107, |
| "learning_rate": 4.722126188232586e-06, |
| "loss": 0.2962369441986084, |
| "step": 125, |
| "token_acc": 0.911854977939766 |
| }, |
| { |
| "epoch": 1.1111111111111112, |
| "grad_norm": 1.6938647031784058, |
| "learning_rate": 4.3760921769259585e-06, |
| "loss": 0.26640729904174804, |
| "step": 130, |
| "token_acc": 0.9200576903265685 |
| }, |
| { |
| "epoch": 1.1538461538461537, |
| "grad_norm": 1.6591416597366333, |
| "learning_rate": 4.033070952877362e-06, |
| "loss": 0.32262775897979734, |
| "step": 135, |
| "token_acc": 0.9023160952065692 |
| }, |
| { |
| "epoch": 1.1965811965811965, |
| "grad_norm": 1.874250054359436, |
| "learning_rate": 3.694718930600012e-06, |
| "loss": 0.2847463607788086, |
| "step": 140, |
| "token_acc": 0.913816095518685 |
| }, |
| { |
| "epoch": 1.2393162393162394, |
| "grad_norm": 3.5652880668640137, |
| "learning_rate": 3.3626699775078884e-06, |
| "loss": 0.3009438753128052, |
| "step": 145, |
| "token_acc": 0.9092695643455156 |
| }, |
| { |
| "epoch": 1.282051282051282, |
| "grad_norm": 2.1268937587738037, |
| "learning_rate": 3.0385275241365965e-06, |
| "loss": 0.27616229057312014, |
| "step": 150, |
| "token_acc": 0.9170621396948753 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 234, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 50, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8955203096294195e+18, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
