{ "epoch": 0.9988571428571429, "eval_logits/chosen": -1.2403382062911987, "eval_logits/rejected": 0.062164660543203354, "eval_logps/chosen": -357.4463806152344, "eval_logps/rejected": -395.7604064941406, "eval_loss": 0.5215353965759277, "eval_rewards/accuracies": 0.7456896305084229, "eval_rewards/chosen": -0.8184244632720947, "eval_rewards/margins": 0.948418378829956, "eval_rewards/rejected": -1.7668428421020508, "eval_runtime": 92.4063, "eval_samples": 1831, "eval_samples_per_second": 19.815, "eval_steps_per_second": 0.314, "total_flos": 0.0, "train_loss": 0.5600041279258117, "train_runtime": 11271.3049, "train_samples": 55999, "train_samples_per_second": 4.968, "train_steps_per_second": 0.039 }