{ "epoch": 1.0, "eval_logits/chosen": 195.72586059570312, "eval_logits/rejected": 198.3043975830078, "eval_logps/chosen": -4.347492694854736, "eval_logps/rejected": -4.157506465911865, "eval_loss": 4.426907539367676, "eval_odds_ratio_loss": 0.79414963722229, "eval_rewards/accuracies": 0.0, "eval_rewards/chosen": -0.4347492754459381, "eval_rewards/margins": -0.01899862289428711, "eval_rewards/rejected": -0.415750652551651, "eval_runtime": 0.2975, "eval_samples_per_second": 3.361, "eval_sft_loss": 4.347492694854736, "eval_steps_per_second": 3.361, "total_flos": 748013124648960.0, "train_loss": 2.0597352981567383, "train_runtime": 12.1534, "train_samples_per_second": 0.741, "train_steps_per_second": 0.082 }