| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9872340425531915, |
| "eval_steps": 100, |
| "global_step": 29, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.3404255319148936, |
| "grad_norm": 147.85139886613985, |
| "learning_rate": 4.157806645601988e-07, |
| "logits/chosen": -0.6054112315177917, |
| "logits/rejected": -0.7670612335205078, |
| "logps/chosen": -22.662845611572266, |
| "logps/rejected": -23.650863647460938, |
| "loss": 0.6919, |
| "rewards/accuracies": 0.36250001192092896, |
| "rewards/chosen": -0.015123640187084675, |
| "rewards/margins": 0.030490612611174583, |
| "rewards/rejected": -0.045614250004291534, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.6808510638297872, |
| "grad_norm": 127.99255832153663, |
| "learning_rate": 1.3381920698905784e-07, |
| "logits/chosen": -0.6011680960655212, |
| "logits/rejected": -0.801101565361023, |
| "logps/chosen": -22.35640525817871, |
| "logps/rejected": -24.782512664794922, |
| "loss": 0.6685, |
| "rewards/accuracies": 0.5, |
| "rewards/chosen": -0.06451952457427979, |
| "rewards/margins": 0.014901568181812763, |
| "rewards/rejected": -0.07942108809947968, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.9872340425531915, |
| "step": 29, |
| "total_flos": 0.0, |
| "train_loss": 0.6756493963044266, |
| "train_runtime": 2698.1014, |
| "train_samples_per_second": 0.695, |
| "train_steps_per_second": 0.011 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 29, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 0.0, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
