{ "epoch": 2.997999555456768, "eval_logits/chosen": -14.466456413269043, "eval_logits/rejected": -14.543242454528809, "eval_logps/chosen": -1.44402277469635, "eval_logps/rejected": -1.5389362573623657, "eval_loss": 1.5154520273208618, "eval_odds_ratio_loss": 0.7142924666404724, "eval_rewards/accuracies": 0.5090000033378601, "eval_rewards/chosen": -0.14440228044986725, "eval_rewards/margins": 0.00949135422706604, "eval_rewards/rejected": -0.15389364957809448, "eval_runtime": 412.9523, "eval_samples_per_second": 2.422, "eval_sft_loss": 1.44402277469635, "eval_steps_per_second": 1.211 }