{ "epoch": 2.986666666666667, "eval_logits/chosen": -2.286210060119629, "eval_logits/rejected": -2.3124423027038574, "eval_logps/chosen": -0.5537902116775513, "eval_logps/rejected": -0.900057315826416, "eval_loss": 0.5931902527809143, "eval_odds_ratio_loss": 5.369002819061279, "eval_rewards/accuracies": 0.7799999713897705, "eval_rewards/chosen": -0.055379029363393784, "eval_rewards/margins": 0.034626711159944534, "eval_rewards/rejected": -0.09000573307275772, "eval_runtime": 2.8075, "eval_samples_per_second": 17.809, "eval_sft_loss": 0.056289929896593094, "eval_steps_per_second": 8.905, "total_flos": 2.2783332409344e+16, "train_loss": 0.8738818849836077, "train_runtime": 261.5721, "train_samples_per_second": 5.161, "train_steps_per_second": 0.321 }