| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 128, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.15625, |
| "grad_norm": 4.292955157495703, |
| "learning_rate": 9.959935885253715e-06, |
| "loss": 0.9569953918457031, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3125, |
| "grad_norm": 3.060322232904907, |
| "learning_rate": 9.643264997861312e-06, |
| "loss": 0.5637986660003662, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.46875, |
| "grad_norm": 2.7839506167035184, |
| "learning_rate": 9.030141317270026e-06, |
| "loss": 0.4681210517883301, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.625, |
| "grad_norm": 2.510337644579003, |
| "learning_rate": 8.15971019223152e-06, |
| "loss": 0.47556314468383787, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.78125, |
| "grad_norm": 2.1045031515130557, |
| "learning_rate": 7.087544961425317e-06, |
| "loss": 0.401263952255249, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.9375, |
| "grad_norm": 2.503694960262919, |
| "learning_rate": 5.882098831289044e-06, |
| "loss": 0.4282387256622314, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.09375, |
| "grad_norm": 1.7913716046435064, |
| "learning_rate": 4.62033442887377e-06, |
| "loss": 0.33012914657592773, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.25, |
| "grad_norm": 1.8343822008931805, |
| "learning_rate": 3.3828100642538097e-06, |
| "loss": 0.2982927322387695, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.40625, |
| "grad_norm": 2.0663716099928258, |
| "learning_rate": 2.2485364238130435e-06, |
| "loss": 0.28581976890563965, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.5625, |
| "grad_norm": 1.89019347548271, |
| "learning_rate": 1.2899320727454472e-06, |
| "loss": 0.2792069435119629, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.71875, |
| "grad_norm": 2.0554575491119187, |
| "learning_rate": 5.681998365579594e-07, |
| "loss": 0.2790872097015381, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.875, |
| "grad_norm": 1.8691547477870472, |
| "learning_rate": 1.2941926002306536e-07, |
| "loss": 0.27373080253601073, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 128, |
| "total_flos": 17462995582976.0, |
| "train_loss": 0.4119406156241894, |
| "train_runtime": 337.9669, |
| "train_samples_per_second": 6.06, |
| "train_steps_per_second": 0.379 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 128, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 170, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 17462995582976.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
