{ "epoch": 2.997999555456768, "eval_logits/chosen": -3.1171207427978516, "eval_logits/rejected": -3.145516872406006, "eval_logps/chosen": -0.8098240494728088, "eval_logps/rejected": -1.0174543857574463, "eval_loss": 0.8734214901924133, "eval_odds_ratio_loss": 0.6359757781028748, "eval_rewards/accuracies": 0.5720000267028809, "eval_rewards/chosen": -0.08098240196704865, "eval_rewards/margins": 0.02076304331421852, "eval_rewards/rejected": -0.10174543410539627, "eval_runtime": 189.0411, "eval_samples_per_second": 5.29, "eval_sft_loss": 0.8098240494728088, "eval_steps_per_second": 2.645, "total_flos": 1.9814178520144282e+18, "train_loss": 0.8985705958283811, "train_runtime": 25618.6466, "train_samples_per_second": 1.054, "train_steps_per_second": 0.066 }