{ "epoch": 0.998660594695955, "eta/annotator_0": 0.9730426073074341, "eval_agreement_weights/mean": 0.9695923328399658, "eval_agreement_weights/std": 0.018151868134737015, "eval_loss": 0.7976000905036926, "eval_rewards/accuracies": 0.5507165789604187, "eval_rewards/chosen": -1.2290558815002441, "eval_rewards/margins": 0.09547457098960876, "eval_rewards/rejected": -1.3243849277496338, "eval_runtime": 101.569, "eval_samples": 2994, "eval_samples_per_second": 29.478, "eval_steps_per_second": 0.925 }