{ "epoch": 0.9963369963369964, "eval_logits/chosen": -2.5392236709594727, "eval_logits/rejected": -2.520923614501953, "eval_logps/chosen": -538.8605346679688, "eval_logps/rejected": -740.7106323242188, "eval_loss": 0.39680731296539307, "eval_rewards/accuracies": 0.78125, "eval_rewards/chosen": -1.508690357208252, "eval_rewards/margins": 2.2141778469085693, "eval_rewards/rejected": -3.7228684425354004, "eval_runtime": 2.9476, "eval_samples": 200, "eval_samples_per_second": 67.851, "eval_steps_per_second": 0.679, "total_flos": 0.0, "train_loss": 0.4527332771058176, "train_runtime": 5381.1516, "train_samples": 209650, "train_samples_per_second": 38.96, "train_steps_per_second": 0.038 }