{ "epoch": 3.0, "eval_logits/chosen": -12.1875, "eval_logits/rejected": -11.75, "eval_logps/chosen": -660.0, "eval_logps/rejected": -652.0, "eval_loss": 1.0146249532699585, "eval_rewards/accuracies": 0.48828125, "eval_rewards/chosen": -3.4375, "eval_rewards/margins": 0.197265625, "eval_rewards/rejected": -3.625, "eval_runtime": 46.765, "eval_samples": 2000, "eval_samples_per_second": 42.767, "eval_steps_per_second": 0.684, "total_flos": 0.0, "train_loss": 0.06649821210216997, "train_runtime": 12540.8656, "train_samples": 61118, "train_samples_per_second": 14.621, "train_steps_per_second": 0.228 }