| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 111, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2702702702702703, |
| "grad_norm": 75424.7421875, |
| "learning_rate": 2.976784795504466e-05, |
| "loss": 0.3673, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 71373.71875, |
| "learning_rate": 2.8375080559518636e-05, |
| "loss": 0.3382, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.8108108108108109, |
| "grad_norm": 68977.6640625, |
| "learning_rate": 2.5837574131992033e-05, |
| "loss": 0.349, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 59054.2890625, |
| "learning_rate": 2.2372507375697017e-05, |
| "loss": 0.2637, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.3513513513513513, |
| "grad_norm": 70157.2578125, |
| "learning_rate": 1.8276446516666194e-05, |
| "loss": 0.1804, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.6216216216216215, |
| "grad_norm": 68264.1171875, |
| "learning_rate": 1.3899962956837443e-05, |
| "loss": 0.1706, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.8918918918918919, |
| "grad_norm": 59071.28125, |
| "learning_rate": 9.617628761892964e-06, |
| "loss": 0.1793, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 40122.65625, |
| "learning_rate": 5.795957993502093e-06, |
| "loss": 0.1201, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.4324324324324325, |
| "grad_norm": 56133.69140625, |
| "learning_rate": 2.7620377055756426e-06, |
| "loss": 0.0901, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.7027027027027026, |
| "grad_norm": 56840.14453125, |
| "learning_rate": 7.755333975558704e-07, |
| "loss": 0.0825, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.972972972972973, |
| "grad_norm": 45475.2421875, |
| "learning_rate": 6.464906595023967e-09, |
| "loss": 0.084, |
| "step": 110 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 111, |
| "total_flos": 1.969709143346381e+16, |
| "train_loss": 0.20128302772839865, |
| "train_runtime": 84.2176, |
| "train_samples_per_second": 41.891, |
| "train_steps_per_second": 1.318 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 111, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "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": 1.969709143346381e+16, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
