{ "epoch": 3.0, "eval_dpo_losses": 0.6309279203414917, "eval_logits/chosen": -2.586883544921875, "eval_logits/rejected": -2.536296844482422, "eval_logps/chosen": -330.7057189941406, "eval_logps/rejected": -333.7965087890625, "eval_loss": 5.204337120056152, "eval_positive_losses": 49.692630767822266, "eval_rewards/accuracies": 0.670634925365448, "eval_rewards/chosen": -0.4548453986644745, "eval_rewards/margins": 0.2912927269935608, "eval_rewards/margins_max": 1.0734634399414062, "eval_rewards/margins_min": -0.5345237851142883, "eval_rewards/margins_std": 0.7254678010940552, "eval_rewards/rejected": -0.7461380958557129, "eval_runtime": 284.396, "eval_samples": 2000, "eval_samples_per_second": 7.032, "eval_steps_per_second": 0.222, "train_loss": 0.48024289137880566, "train_runtime": 8933.1726, "train_samples": 5678, "train_samples_per_second": 1.907, "train_steps_per_second": 0.119 }