{ "epoch": 0.99, "eval_logits/chosen": 91.75543975830078, "eval_logits/rejected": 85.30099487304688, "eval_logps/chosen": -512.5901489257812, "eval_logps/rejected": -565.5089721679688, "eval_loss": 0.5580899119377136, "eval_rewards/accuracies": 0.6770833134651184, "eval_rewards/chosen": -0.5918566584587097, "eval_rewards/margins": 0.5477373003959656, "eval_rewards/rejected": -1.1395939588546753, "eval_runtime": 47.3786, "eval_samples": 750, "eval_samples_per_second": 15.83, "eval_steps_per_second": 0.507, "train_loss": 0.6015224342162793, "train_runtime": 574.0149, "train_samples": 6750, "train_samples_per_second": 11.759, "train_steps_per_second": 0.091 }