{ "epoch": 1.9999360981532366, "eval_logits/chosen": -2.984375, "eval_logits/rejected": -2.765625, "eval_logps/chosen": -720.0, "eval_logps/rejected": -1080.0, "eval_loss": 0.23926551640033722, "eval_rewards/accuracies": 0.8974654674530029, "eval_rewards/chosen": -5.625, "eval_rewards/margins": 3.78125, "eval_rewards/rejected": -9.375, "eval_runtime": 1835.1519, "eval_samples": 55582, "eval_samples_per_second": 30.246, "eval_steps_per_second": 0.473, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 42.011, "train_samples": 1001516, "train_samples_per_second": 23839.372, "train_steps_per_second": 186.237 }