| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 132, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.22857142857142856, |
| "grad_norm": 0.6778433322906494, |
| "learning_rate": 3.2142857142857144e-05, |
| "loss": 4.6452, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.45714285714285713, |
| "grad_norm": 0.6552432775497437, |
| "learning_rate": 4.9778820775100185e-05, |
| "loss": 4.7314, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.6857142857142857, |
| "grad_norm": 1.0648839473724365, |
| "learning_rate": 4.803279944676032e-05, |
| "loss": 4.4278, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.9142857142857143, |
| "grad_norm": 0.7492648959159851, |
| "learning_rate": 4.466378889506607e-05, |
| "loss": 4.2958, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.1371428571428572, |
| "grad_norm": 1.1295640468597412, |
| "learning_rate": 3.990918396346254e-05, |
| "loss": 4.5745, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.3657142857142857, |
| "grad_norm": 1.1639342308044434, |
| "learning_rate": 3.410401438132056e-05, |
| "loss": 4.2608, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.5942857142857143, |
| "grad_norm": 1.0422941446304321, |
| "learning_rate": 2.7657337141184138e-05, |
| "loss": 4.1288, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.822857142857143, |
| "grad_norm": 0.8440783023834229, |
| "learning_rate": 2.1023412599523204e-05, |
| "loss": 4.0658, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.045714285714286, |
| "grad_norm": 0.7604417204856873, |
| "learning_rate": 1.4669695355790552e-05, |
| "loss": 4.2423, |
| "step": 90 |
| }, |
| { |
| "epoch": 2.2742857142857145, |
| "grad_norm": 3.8797717094421387, |
| "learning_rate": 9.043895408879505e-06, |
| "loss": 3.9711, |
| "step": 100 |
| }, |
| { |
| "epoch": 2.5028571428571427, |
| "grad_norm": 0.7863895893096924, |
| "learning_rate": 4.542430602295774e-06, |
| "loss": 4.1899, |
| "step": 110 |
| }, |
| { |
| "epoch": 2.7314285714285713, |
| "grad_norm": 1.85634446144104, |
| "learning_rate": 1.4824933332241692e-06, |
| "loss": 4.1274, |
| "step": 120 |
| }, |
| { |
| "epoch": 2.96, |
| "grad_norm": 0.6992499232292175, |
| "learning_rate": 7.969982423124689e-08, |
| "loss": 4.4828, |
| "step": 130 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 132, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 46939787919360.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
