| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.0, |
| "eval_steps": 500, |
| "global_step": 48, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.425531914893617, |
| "grad_norm": 2.2258945245939725, |
| "learning_rate": 9.439426092011877e-06, |
| "loss": 0.772, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.851063829787234, |
| "grad_norm": 1.1866174973340418, |
| "learning_rate": 6.9920054492312086e-06, |
| "loss": 0.4783, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.2553191489361701, |
| "grad_norm": 1.2463263089760144, |
| "learning_rate": 3.6510161442148783e-06, |
| "loss": 0.4603, |
| "step": 30 |
| }, |
| { |
| "epoch": 1.6808510638297873, |
| "grad_norm": 1.1783626582936766, |
| "learning_rate": 9.151505349477901e-07, |
| "loss": 0.3974, |
| "step": 40 |
| }, |
| { |
| "epoch": 2.0, |
| "step": 48, |
| "total_flos": 1505780269056.0, |
| "train_loss": 0.5031078110138575, |
| "train_runtime": 93.2893, |
| "train_samples_per_second": 8.018, |
| "train_steps_per_second": 0.515 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 48, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1505780269056.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
