| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.46222735808175647, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "entropy": 0.11948550771921873, |
| "epoch": 0.023111367904087823, |
| "grad_norm": 0.26614415645599365, |
| "learning_rate": 6.923076923076924e-05, |
| "loss": 0.27834961414337156, |
| "mean_token_accuracy": 0.9158459510654211, |
| "num_tokens": 91409.0, |
| "step": 10 |
| }, |
| { |
| "entropy": 0.14536615274846554, |
| "epoch": 0.046222735808175645, |
| "grad_norm": 0.28414708375930786, |
| "learning_rate": 9.994965332706573e-05, |
| "loss": 0.13056882619857788, |
| "mean_token_accuracy": 0.9612345997244119, |
| "num_tokens": 186627.0, |
| "step": 20 |
| }, |
| { |
| "entropy": 0.11003581081749872, |
| "epoch": 0.06933410371226346, |
| "grad_norm": 0.2106354683637619, |
| "learning_rate": 9.964234631709187e-05, |
| "loss": 0.09309924244880677, |
| "mean_token_accuracy": 0.9709797658026218, |
| "num_tokens": 276604.0, |
| "step": 30 |
| }, |
| { |
| "entropy": 0.0915378995705396, |
| "epoch": 0.09244547161635129, |
| "grad_norm": 0.2663438022136688, |
| "learning_rate": 9.905741916970864e-05, |
| "loss": 0.10451314449310303, |
| "mean_token_accuracy": 0.9715173915028572, |
| "num_tokens": 368108.0, |
| "step": 40 |
| }, |
| { |
| "entropy": 0.10749789654510096, |
| "epoch": 0.11555683952043912, |
| "grad_norm": 0.17998279631137848, |
| "learning_rate": 9.819814303479267e-05, |
| "loss": 0.10180811882019043, |
| "mean_token_accuracy": 0.9665989849716425, |
| "num_tokens": 457334.0, |
| "step": 50 |
| }, |
| { |
| "entropy": 0.08793499013991095, |
| "epoch": 0.13866820742452693, |
| "grad_norm": 0.18421846628189087, |
| "learning_rate": 9.706932333304517e-05, |
| "loss": 0.10302398204803467, |
| "mean_token_accuracy": 0.9739916753023863, |
| "num_tokens": 547458.0, |
| "step": 60 |
| }, |
| { |
| "entropy": 0.10031854717526585, |
| "epoch": 0.16177957532861476, |
| "grad_norm": 0.1583297848701477, |
| "learning_rate": 9.567727288213005e-05, |
| "loss": 0.09594225287437438, |
| "mean_token_accuracy": 0.9684251010417938, |
| "num_tokens": 633576.0, |
| "step": 70 |
| }, |
| { |
| "entropy": 0.10018112544203177, |
| "epoch": 0.18489094323270258, |
| "grad_norm": 0.17029769718647003, |
| "learning_rate": 9.40297765928369e-05, |
| "loss": 0.08666939735412597, |
| "mean_token_accuracy": 0.9722081393003463, |
| "num_tokens": 725021.0, |
| "step": 80 |
| }, |
| { |
| "entropy": 0.08978840237832628, |
| "epoch": 0.2080023111367904, |
| "grad_norm": 0.21113114058971405, |
| "learning_rate": 9.213604793270196e-05, |
| "loss": 0.10337703227996826, |
| "mean_token_accuracy": 0.9718282397836446, |
| "num_tokens": 809468.0, |
| "step": 90 |
| }, |
| { |
| "entropy": 0.08143368383025518, |
| "epoch": 0.23111367904087823, |
| "grad_norm": 0.2660817801952362, |
| "learning_rate": 9.000667740056032e-05, |
| "loss": 0.07579125165939331, |
| "mean_token_accuracy": 0.9780994143337012, |
| "num_tokens": 898185.0, |
| "step": 100 |
| }, |
| { |
| "entropy": 0.07822052207193338, |
| "epoch": 0.25422504694496606, |
| "grad_norm": 0.25105559825897217, |
| "learning_rate": 8.765357330018056e-05, |
| "loss": 0.0827728271484375, |
| "mean_token_accuracy": 0.9731388352811337, |
| "num_tokens": 988490.0, |
| "step": 110 |
| }, |
| { |
| "entropy": 0.0850134992855601, |
| "epoch": 0.27733641484905386, |
| "grad_norm": 0.15802568197250366, |
| "learning_rate": 8.508989514419958e-05, |
| "loss": 0.07012671828269959, |
| "mean_token_accuracy": 0.9775275759398937, |
| "num_tokens": 1078890.0, |
| "step": 120 |
| }, |
| { |
| "entropy": 0.07775390069000424, |
| "epoch": 0.3004477827531417, |
| "grad_norm": 0.3077862858772278, |
| "learning_rate": 8.232998006078997e-05, |
| "loss": 0.07896218299865723, |
| "mean_token_accuracy": 0.9768860664218664, |
| "num_tokens": 1171456.0, |
| "step": 130 |
| }, |
| { |
| "entropy": 0.06990418929490261, |
| "epoch": 0.3235591506572295, |
| "grad_norm": 0.20379361510276794, |
| "learning_rate": 7.938926261462366e-05, |
| "loss": 0.0791102945804596, |
| "mean_token_accuracy": 0.9748555511236191, |
| "num_tokens": 1267191.0, |
| "step": 140 |
| }, |
| { |
| "entropy": 0.07729233189020306, |
| "epoch": 0.34667051856131736, |
| "grad_norm": 0.2790727913379669, |
| "learning_rate": 7.628418849052523e-05, |
| "loss": 0.07758013606071472, |
| "mean_token_accuracy": 0.9756737377494573, |
| "num_tokens": 1354080.0, |
| "step": 150 |
| }, |
| { |
| "entropy": 0.08708043664228171, |
| "epoch": 0.36978188646540516, |
| "grad_norm": 0.269930899143219, |
| "learning_rate": 7.303212252253162e-05, |
| "loss": 0.08181141018867492, |
| "mean_token_accuracy": 0.9762891136109829, |
| "num_tokens": 1442199.0, |
| "step": 160 |
| }, |
| { |
| "entropy": 0.081081559494487, |
| "epoch": 0.392893254369493, |
| "grad_norm": 0.1513710916042328, |
| "learning_rate": 6.965125158269619e-05, |
| "loss": 0.0810213029384613, |
| "mean_token_accuracy": 0.9729760400950909, |
| "num_tokens": 1537565.0, |
| "step": 170 |
| }, |
| { |
| "entropy": 0.07967969757737592, |
| "epoch": 0.4160046222735808, |
| "grad_norm": 0.26842933893203735, |
| "learning_rate": 6.616048287272301e-05, |
| "loss": 0.0828117549419403, |
| "mean_token_accuracy": 0.9750622134655714, |
| "num_tokens": 1631534.0, |
| "step": 180 |
| }, |
| { |
| "entropy": 0.08117348714149557, |
| "epoch": 0.4391159901776686, |
| "grad_norm": 1.2517547607421875, |
| "learning_rate": 6.257933818722543e-05, |
| "loss": 0.07101889252662659, |
| "mean_token_accuracy": 0.9764051765203476, |
| "num_tokens": 1718429.0, |
| "step": 190 |
| }, |
| { |
| "entropy": 0.0724065299378708, |
| "epoch": 0.46222735808175647, |
| "grad_norm": 0.3557807505130768, |
| "learning_rate": 5.8927844739931834e-05, |
| "loss": 0.07825151681900025, |
| "mean_token_accuracy": 0.9812528945505619, |
| "num_tokens": 1804347.0, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 433, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.742120422856602e+16, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
