{ "epoch": 4.0, "eval_logits/chosen": -2.2468910217285156, "eval_logits/rejected": -2.24200439453125, "eval_logps/chosen": -33.9367790222168, "eval_logps/rejected": -37.42759704589844, "eval_loss": 0.577243447303772, "eval_rewards/accuracies": 0.5307309031486511, "eval_rewards/chosen": 0.06843975186347961, "eval_rewards/margins": 0.0061217062175273895, "eval_rewards/rejected": 0.06231804937124252, "eval_runtime": 145.2917, "eval_samples": 343, "eval_samples_per_second": 2.361, "eval_steps_per_second": 0.296, "train_loss": 0.20226844080856868, "train_runtime": 10768.956, "train_samples": 3079, "train_samples_per_second": 1.144, "train_steps_per_second": 0.143 }