{ "epoch": 3.0, "eval_logits/chosen": -2.359645366668701, "eval_logits/rejected": -2.326366901397705, "eval_logps/chosen": -246.08377075195312, "eval_logps/rejected": -224.16087341308594, "eval_loss": 0.564285397529602, "eval_rewards/accuracies": 0.800000011920929, "eval_rewards/chosen": 1.394153356552124, "eval_rewards/margins": 2.1888556480407715, "eval_rewards/rejected": -0.794702410697937, "eval_runtime": 125.4778, "eval_samples_per_second": 15.142, "eval_steps_per_second": 0.239, "total_flos": 2369906314051584.0, "train_loss": 0.34582118860524685, "train_runtime": 7382.5383, "train_samples_per_second": 6.946, "train_steps_per_second": 0.027 }