{ "epoch": 1.0, "eval_logits/chosen": -2.6530776023864746, "eval_logits/rejected": -2.627399444580078, "eval_logps/chosen": -1348.6318359375, "eval_logps/rejected": -1865.716796875, "eval_loss": 0.041974812746047974, "eval_rewards/accuracies": 0.9949495196342468, "eval_rewards/chosen": -5.514344692230225, "eval_rewards/margins": 7.546464920043945, "eval_rewards/rejected": -13.060811042785645, "eval_runtime": 138.5776, "eval_samples": 198, "eval_samples_per_second": 1.429, "eval_steps_per_second": 1.429, "train_loss": 0.24469107510474733, "train_runtime": 1322.9236, "train_samples": 791, "train_samples_per_second": 0.598, "train_steps_per_second": 0.149 }