{ "epoch": 2.9974597798475866, "eval_logits/chosen": -3.130527973175049, "eval_logits/rejected": -3.1507296562194824, "eval_logps/chosen": -0.7867480516433716, "eval_logps/rejected": -0.9955620169639587, "eval_loss": 0.8505691885948181, "eval_odds_ratio_loss": 0.638211727142334, "eval_rewards/accuracies": 0.5723809599876404, "eval_rewards/chosen": -0.0786748081445694, "eval_rewards/margins": 0.020881392061710358, "eval_rewards/rejected": -0.09955620020627975, "eval_runtime": 194.0793, "eval_samples_per_second": 5.41, "eval_sft_loss": 0.7867480516433716, "eval_steps_per_second": 2.705 }