| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9987560782539862, |
| "eval_steps": 500, |
| "global_step": 138, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.03618681442949225, |
| "grad_norm": 0.012892262078821659, |
| "learning_rate": 0.0002, |
| "loss": 0.2382, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.0723736288589845, |
| "grad_norm": 0.0053918142803013325, |
| "learning_rate": 0.00019930337092856243, |
| "loss": 0.0396, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.10856044328847676, |
| "grad_norm": 0.0037580234929919243, |
| "learning_rate": 0.00019722318955551306, |
| "loss": 0.0252, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.144747257717969, |
| "grad_norm": 0.0017777378670871258, |
| "learning_rate": 0.00019378843817721854, |
| "loss": 0.0158, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.18093407214746127, |
| "grad_norm": 0.0024384628050029278, |
| "learning_rate": 0.00018904697174694447, |
| "loss": 0.0151, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.21712088657695353, |
| "grad_norm": 0.0018282835371792316, |
| "learning_rate": 0.0001830648511318223, |
| "loss": 0.0112, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.2533077010064458, |
| "grad_norm": 0.002051867777481675, |
| "learning_rate": 0.00017592542271443887, |
| "loss": 0.0107, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.289494515435938, |
| "grad_norm": 0.0016758110141381621, |
| "learning_rate": 0.00016772815716257412, |
| "loss": 0.0106, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.3256813298654303, |
| "grad_norm": 0.002686451654881239, |
| "learning_rate": 0.00015858726354602248, |
| "loss": 0.0123, |
| "step": 45 |
| }, |
| { |
| "epoch": 0.36186814429492253, |
| "grad_norm": 0.0017138413386419415, |
| "learning_rate": 0.00014863009810942815, |
| "loss": 0.0115, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.39805495872441476, |
| "grad_norm": 0.003232393180951476, |
| "learning_rate": 0.000137995389871036, |
| "loss": 0.0096, |
| "step": 55 |
| }, |
| { |
| "epoch": 0.43424177315390705, |
| "grad_norm": 0.0028239295352250338, |
| "learning_rate": 0.0001268313077693485, |
| "loss": 0.014, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.4704285875833993, |
| "grad_norm": 0.0013771996600553393, |
| "learning_rate": 0.0001152933962873246, |
| "loss": 0.0113, |
| "step": 65 |
| }, |
| { |
| "epoch": 0.5066154020128916, |
| "grad_norm": 0.0019330934155732393, |
| "learning_rate": 0.00010354240831620541, |
| "loss": 0.0106, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.5428022164423838, |
| "grad_norm": 0.0029724629130214453, |
| "learning_rate": 9.174206545276677e-05, |
| "loss": 0.0094, |
| "step": 75 |
| }, |
| { |
| "epoch": 0.578989030871876, |
| "grad_norm": 0.0018539836164563894, |
| "learning_rate": 8.005677693484077e-05, |
| "loss": 0.0108, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.6151758453013683, |
| "grad_norm": 0.0012941986788064241, |
| "learning_rate": 6.864934899622191e-05, |
| "loss": 0.008, |
| "step": 85 |
| }, |
| { |
| "epoch": 0.6513626597308606, |
| "grad_norm": 0.0015225649112835526, |
| "learning_rate": 5.767871655555751e-05, |
| "loss": 0.009, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.6875494741603528, |
| "grad_norm": 0.0012339482782408595, |
| "learning_rate": 4.729772884265212e-05, |
| "loss": 0.0098, |
| "step": 95 |
| }, |
| { |
| "epoch": 0.7237362885898451, |
| "grad_norm": 0.0009091832325793803, |
| "learning_rate": 3.7651019814126654e-05, |
| "loss": 0.0071, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.7599231030193373, |
| "grad_norm": 0.0018332460895180702, |
| "learning_rate": 2.8872993029040508e-05, |
| "loss": 0.0085, |
| "step": 105 |
| }, |
| { |
| "epoch": 0.7961099174488295, |
| "grad_norm": 0.0009983633644878864, |
| "learning_rate": 2.1085949060360654e-05, |
| "loss": 0.0088, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.8322967318783219, |
| "grad_norm": 0.001077743829227984, |
| "learning_rate": 1.439838153227e-05, |
| "loss": 0.0074, |
| "step": 115 |
| }, |
| { |
| "epoch": 0.8684835463078141, |
| "grad_norm": 0.0009710977319628, |
| "learning_rate": 8.903465523913957e-06, |
| "loss": 0.0111, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.9046703607373063, |
| "grad_norm": 0.001384108909405768, |
| "learning_rate": 4.6777594000230855e-06, |
| "loss": 0.0104, |
| "step": 125 |
| }, |
| { |
| "epoch": 0.9408571751667986, |
| "grad_norm": 0.0009462545858696103, |
| "learning_rate": 1.7801381552624563e-06, |
| "loss": 0.0092, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.9770439895962908, |
| "grad_norm": 0.0013169609010219574, |
| "learning_rate": 2.509731335744281e-07, |
| "loss": 0.0088, |
| "step": 135 |
| }, |
| { |
| "epoch": 0.9987560782539862, |
| "step": 138, |
| "total_flos": 1.8184278196190236e+20, |
| "train_loss": 0.02029224556695292, |
| "train_runtime": 28844.8665, |
| "train_samples_per_second": 0.307, |
| "train_steps_per_second": 0.005 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 138, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.8184278196190236e+20, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
