| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.986666666666667, |
| "eval_steps": 500, |
| "global_step": 84, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.35555555555555557, |
| "grad_norm": 7.250613212585449, |
| "learning_rate": 4.997807075247147e-06, |
| "loss": 1.6943, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.7111111111111111, |
| "grad_norm": 4.487943172454834, |
| "learning_rate": 4.7392794005985324e-06, |
| "loss": 1.3902, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.0666666666666667, |
| "grad_norm": 3.5589382648468018, |
| "learning_rate": 4.172826515897146e-06, |
| "loss": 1.1637, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.4222222222222223, |
| "grad_norm": 3.4332292079925537, |
| "learning_rate": 3.272542485937369e-06, |
| "loss": 0.9457, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.7777777777777777, |
| "grad_norm": 3.133143663406372, |
| "learning_rate": 2.238678841830867e-06, |
| "loss": 0.7794, |
| "step": 50 |
| }, |
| { |
| "epoch": 2.1333333333333333, |
| "grad_norm": 3.03181791305542, |
| "learning_rate": 1.2500000000000007e-06, |
| "loss": 0.6799, |
| "step": 60 |
| }, |
| { |
| "epoch": 2.488888888888889, |
| "grad_norm": 2.9826202392578125, |
| "learning_rate": 4.774575140626317e-07, |
| "loss": 0.6377, |
| "step": 70 |
| }, |
| { |
| "epoch": 2.8444444444444446, |
| "grad_norm": 3.1845717430114746, |
| "learning_rate": 5.463099816548578e-08, |
| "loss": 0.625, |
| "step": 80 |
| }, |
| { |
| "epoch": 2.986666666666667, |
| "step": 84, |
| "total_flos": 7565873752571904.0, |
| "train_loss": 0.9732896827516102, |
| "train_runtime": 178.1411, |
| "train_samples_per_second": 7.578, |
| "train_steps_per_second": 0.472 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 84, |
| "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": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7565873752571904.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
