{ "epoch": 0.9999635926748461, "eval_log_odds_chosen": 1.1701252460479736, "eval_log_odds_ratio": -0.47759079933166504, "eval_logits/chosen": -0.8645420074462891, "eval_logits/rejected": -0.7723644971847534, "eval_logps/chosen": -0.7588062882423401, "eval_logps/rejected": -1.6227697134017944, "eval_loss": 1.188714861869812, "eval_nll_loss": 1.136938452720642, "eval_rewards/accuracies": 0.7338129281997681, "eval_rewards/chosen": -0.07588158547878265, "eval_rewards/margins": 0.08640365302562714, "eval_rewards/rejected": -0.16227255761623383, "eval_runtime": 1369.8995, "eval_samples": 98376, "eval_samples_per_second": 71.429, "eval_steps_per_second": 1.116 }