{ "epoch": 1.9977349943374858, "eval_logits/chosen": -0.8419910669326782, "eval_logits/rejected": -0.7616477012634277, "eval_logps/chosen": -610.5119018554688, "eval_logps/rejected": -721.5773315429688, "eval_loss": 0.6218873858451843, "eval_rewards/accuracies": 0.6875, "eval_rewards/chosen": -3.3169686794281006, "eval_rewards/margins": 1.3756744861602783, "eval_rewards/rejected": -4.692643165588379, "eval_runtime": 1.4063, "eval_samples": 100, "eval_samples_per_second": 71.106, "eval_steps_per_second": 1.422, "total_flos": 0.0, "train_loss": 0.32467431276022984, "train_runtime": 5857.252, "train_samples": 112998, "train_samples_per_second": 38.584, "train_steps_per_second": 0.151 }