{ "epoch": 1.0, "eval_logits/chosen": -0.4858700931072235, "eval_logits/rejected": 0.4996632933616638, "eval_logps/chosen": -365.4620361328125, "eval_logps/rejected": -464.2830505371094, "eval_loss": 0.5057845711708069, "eval_rewards/accuracies": 0.77734375, "eval_rewards/chosen": -1.0286751985549927, "eval_rewards/margins": 0.9872558116912842, "eval_rewards/rejected": -2.0159308910369873, "eval_runtime": 92.7118, "eval_samples": 2000, "eval_samples_per_second": 21.572, "eval_steps_per_second": 0.345, "total_flos": 0.0, "train_loss": 0.5389037092360492, "train_runtime": 7287.4677, "train_samples": 61134, "train_samples_per_second": 8.389, "train_steps_per_second": 0.066 }