{ "epoch": 2.9667896678966788, "eval_logits/chosen": -2.0546815395355225, "eval_logits/rejected": -2.0197503566741943, "eval_logps/chosen": -301.71893310546875, "eval_logps/rejected": -247.9047393798828, "eval_loss": 0.4852559268474579, "eval_rewards/accuracies": 0.8548387289047241, "eval_rewards/chosen": 2.7506847381591797, "eval_rewards/margins": 3.2998063564300537, "eval_rewards/rejected": -0.5491215586662292, "eval_runtime": 128.5845, "eval_samples_per_second": 14.94, "eval_steps_per_second": 0.241, "total_flos": 2369906314051584.0, "train_loss": 0.26609369445202957, "train_runtime": 7643.0309, "train_samples_per_second": 6.784, "train_steps_per_second": 0.026 }