| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9981785063752276, |
| "eval_steps": 500, |
| "global_step": 274, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.18214936247723132, |
| "grad_norm": 2.3424386978149414, |
| "learning_rate": 4.5454545454545455e-06, |
| "logits/chosen": 0.3313373327255249, |
| "logits/rejected": 0.51214599609375, |
| "logps/chosen": -133.43138122558594, |
| "logps/rejected": -192.70355224609375, |
| "loss": 0.4056, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": 0.41640931367874146, |
| "rewards/margins": 0.7543150186538696, |
| "rewards/rejected": -0.33790573477745056, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.36429872495446264, |
| "grad_norm": 2.2886452674865723, |
| "learning_rate": 4.897914773180057e-06, |
| "logits/chosen": 0.03562241047620773, |
| "logits/rejected": 0.31711575388908386, |
| "logps/chosen": -147.89747619628906, |
| "logps/rejected": -268.35821533203125, |
| "loss": 0.2839, |
| "rewards/accuracies": 0.9950000047683716, |
| "rewards/chosen": 0.28251099586486816, |
| "rewards/margins": 1.3375725746154785, |
| "rewards/rejected": -1.0550616979599, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.546448087431694, |
| "grad_norm": 3.107114791870117, |
| "learning_rate": 4.5557177668257975e-06, |
| "logits/chosen": -0.2743435502052307, |
| "logits/rejected": -0.10878603160381317, |
| "logps/chosen": -208.27593994140625, |
| "logps/rejected": -473.1844787597656, |
| "loss": 0.157, |
| "rewards/accuracies": 1.0, |
| "rewards/chosen": -0.3748534321784973, |
| "rewards/margins": 2.790405511856079, |
| "rewards/rejected": -3.1652591228485107, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.7285974499089253, |
| "grad_norm": 6.934810638427734, |
| "learning_rate": 4.006586590948141e-06, |
| "logits/chosen": -0.08417636901140213, |
| "logits/rejected": -0.03048125095665455, |
| "logps/chosen": -362.09002685546875, |
| "logps/rejected": -824.4659423828125, |
| "loss": 0.0918, |
| "rewards/accuracies": 0.9850000143051147, |
| "rewards/chosen": -1.878377079963684, |
| "rewards/margins": 4.862216949462891, |
| "rewards/rejected": -6.740594387054443, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.9107468123861566, |
| "grad_norm": 7.77178430557251, |
| "learning_rate": 3.3057982907103e-06, |
| "logits/chosen": 0.220669686794281, |
| "logits/rejected": 0.25975489616394043, |
| "logps/chosen": -471.4226989746094, |
| "logps/rejected": -1041.406005859375, |
| "loss": 0.1067, |
| "rewards/accuracies": 0.9850000143051147, |
| "rewards/chosen": -2.964336633682251, |
| "rewards/margins": 5.914289474487305, |
| "rewards/rejected": -8.878626823425293, |
| "step": 250 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 548, |
| "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": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 0.0, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
