{ "epoch": 1.0, "eval_logits/chosen": -2.1435508728027344, "eval_logits/rejected": -2.114776372909546, "eval_logps/chosen": -71.79116821289062, "eval_logps/rejected": -85.50504302978516, "eval_loss": 0.6928141117095947, "eval_pred_label": 5654.5712890625, "eval_rewards/accuracies": 0.3531745970249176, "eval_rewards/chosen": -0.02890622988343239, "eval_rewards/margins": 0.07216347008943558, "eval_rewards/rejected": -0.10106971114873886, "eval_runtime": 245.7902, "eval_samples": 2000, "eval_samples_per_second": 8.137, "eval_steps_per_second": 0.256, "eval_use_label": 14417.4287109375, "train_loss": 0.692275420283772, "train_runtime": 20019.5915, "train_samples": 61135, "train_samples_per_second": 3.054, "train_steps_per_second": 0.048 }