{ "epoch": 1.0, "eval_logits/chosen": 0.5316108465194702, "eval_logits/rejected": 0.9396071434020996, "eval_logps/chosen": -447.05303955078125, "eval_logps/rejected": -536.2667236328125, "eval_loss": 0.49303239583969116, "eval_rewards/accuracies": 0.7242063283920288, "eval_rewards/chosen": -1.7955820560455322, "eval_rewards/margins": 0.9434418678283691, "eval_rewards/rejected": -2.7390236854553223, "eval_runtime": 363.1163, "eval_samples": 2000, "eval_samples_per_second": 5.508, "eval_steps_per_second": 0.173, "train_loss": 0.5264237219126436, "train_runtime": 29801.8239, "train_samples": 61135, "train_samples_per_second": 2.051, "train_steps_per_second": 0.032 }