{ "epoch": 0.99, "eval_logits/chosen": 107.19742584228516, "eval_logits/rejected": 100.98101043701172, "eval_logps/chosen": -463.2886962890625, "eval_logps/rejected": -471.6917419433594, "eval_loss": 0.77150958776474, "eval_rewards/accuracies": 0.65625, "eval_rewards/chosen": -1.9768500328063965, "eval_rewards/margins": 2.051576852798462, "eval_rewards/rejected": -4.028427600860596, "eval_runtime": 51.2365, "eval_samples": 750, "eval_samples_per_second": 14.638, "eval_steps_per_second": 0.468, "train_loss": 0.8682076243253855, "train_runtime": 573.101, "train_samples": 6750, "train_samples_per_second": 11.778, "train_steps_per_second": 0.091 }