| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.0, |
| "eval_steps": 200, |
| "global_step": 313, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.032, |
| "grad_norm": 0.43142589926719666, |
| "learning_rate": 5.6250000000000005e-05, |
| "loss": 1.9603242874145508, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.064, |
| "grad_norm": 0.7526686191558838, |
| "learning_rate": 9.997482711915927e-05, |
| "loss": 1.361489200592041, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.096, |
| "grad_norm": 0.2164563685655594, |
| "learning_rate": 9.952801401309503e-05, |
| "loss": 0.6197233200073242, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.128, |
| "grad_norm": 0.1643240749835968, |
| "learning_rate": 9.85275541204318e-05, |
| "loss": 0.4440761566162109, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.16, |
| "grad_norm": 0.15375693142414093, |
| "learning_rate": 9.698463103929542e-05, |
| "loss": 0.3721321105957031, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.192, |
| "grad_norm": 0.12146399170160294, |
| "learning_rate": 9.491649226936585e-05, |
| "loss": 0.3472585916519165, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.224, |
| "grad_norm": 0.1022258773446083, |
| "learning_rate": 9.23462564114396e-05, |
| "loss": 0.36702532768249513, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.256, |
| "grad_norm": 0.11705762147903442, |
| "learning_rate": 8.930265473713938e-05, |
| "loss": 0.3406258821487427, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.288, |
| "grad_norm": 0.11243300139904022, |
| "learning_rate": 8.581971001762286e-05, |
| "loss": 0.3221158504486084, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.32, |
| "grad_norm": 0.1187305673956871, |
| "learning_rate": 8.19363562014904e-05, |
| "loss": 0.3340264320373535, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.352, |
| "grad_norm": 0.11246190220117569, |
| "learning_rate": 7.769600319330552e-05, |
| "loss": 0.3267300844192505, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.384, |
| "grad_norm": 0.11410942673683167, |
| "learning_rate": 7.314605159783314e-05, |
| "loss": 0.32383055686950685, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.416, |
| "grad_norm": 0.1253771334886551, |
| "learning_rate": 6.833736285440632e-05, |
| "loss": 0.3223851680755615, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.448, |
| "grad_norm": 0.1398521512746811, |
| "learning_rate": 6.332369068450174e-05, |
| "loss": 0.3386288404464722, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.48, |
| "grad_norm": 0.133772611618042, |
| "learning_rate": 5.816108020806297e-05, |
| "loss": 0.3134670972824097, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.512, |
| "grad_norm": 0.14892226457595825, |
| "learning_rate": 5.290724144552379e-05, |
| "loss": 0.32947821617126466, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.544, |
| "grad_norm": 0.17407159507274628, |
| "learning_rate": 4.762090420881289e-05, |
| "loss": 0.33319165706634524, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.576, |
| "grad_norm": 0.18985338509082794, |
| "learning_rate": 4.236116159266265e-05, |
| "loss": 0.3404001951217651, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.608, |
| "grad_norm": 0.20351578295230865, |
| "learning_rate": 3.718680940497687e-05, |
| "loss": 0.31983892917633056, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.64, |
| "grad_norm": 0.2211553007364273, |
| "learning_rate": 3.215568892040641e-05, |
| "loss": 0.33751511573791504, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.64, |
| "eval_loss": 0.33180904388427734, |
| "eval_runtime": 26887.5706, |
| "eval_samples_per_second": 0.186, |
| "eval_steps_per_second": 0.186, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.672, |
| "grad_norm": 0.25888341665267944, |
| "learning_rate": 2.7324040304134123e-05, |
| "loss": 0.35176849365234375, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.704, |
| "grad_norm": 0.2853488326072693, |
| "learning_rate": 2.274587393359342e-05, |
| "loss": 0.3525731086730957, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.736, |
| "grad_norm": 0.3256794214248657, |
| "learning_rate": 1.847236664577389e-05, |
| "loss": 0.3709781408309937, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.768, |
| "grad_norm": 0.4498000741004944, |
| "learning_rate": 1.4551289659137496e-05, |
| "loss": 0.3664461851119995, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.8, |
| "grad_norm": 0.429522842168808, |
| "learning_rate": 1.1026474565096068e-05, |
| "loss": 0.3973574638366699, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.832, |
| "grad_norm": 0.4205247759819031, |
| "learning_rate": 7.937323358440935e-06, |
| "loss": 0.3905482292175293, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.864, |
| "grad_norm": 0.4229983389377594, |
| "learning_rate": 5.318367983829392e-06, |
| "loss": 0.40453038215637205, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.896, |
| "grad_norm": 0.419499933719635, |
| "learning_rate": 3.1988843219178777e-06, |
| "loss": 0.37432155609130857, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.928, |
| "grad_norm": 0.47077614068984985, |
| "learning_rate": 1.6025649301821876e-06, |
| "loss": 0.39239466190338135, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.96, |
| "grad_norm": 0.42529457807540894, |
| "learning_rate": 5.472541966768551e-07, |
| "loss": 0.3923347473144531, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.992, |
| "grad_norm": 0.47548553347587585, |
| "learning_rate": 4.474886730641004e-08, |
| "loss": 0.3882535696029663, |
| "step": 310 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 313, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.7890629030723994e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
