{ "epoch": 2.997999555456768, "eval_logits/chosen": 254.46791076660156, "eval_logits/rejected": 254.66136169433594, "eval_logps/chosen": -1.2813518047332764, "eval_logps/rejected": -1.5003557205200195, "eval_loss": 1.347064733505249, "eval_odds_ratio_loss": 0.6571269631385803, "eval_rewards/accuracies": 0.5609999895095825, "eval_rewards/chosen": -0.12813518941402435, "eval_rewards/margins": 0.021900387480854988, "eval_rewards/rejected": -0.15003558993339539, "eval_runtime": 217.2016, "eval_samples_per_second": 4.604, "eval_sft_loss": 1.2813518047332764, "eval_steps_per_second": 2.302 }