{ "epoch": 0.99, "eval_logits/chosen": -3.203406810760498, "eval_logits/rejected": -3.3099639415740967, "eval_logps/chosen": -651.1673583984375, "eval_logps/rejected": -1410.1324462890625, "eval_loss": 0.26801708340644836, "eval_rewards/accuracies": 0.8909090757369995, "eval_rewards/chosen": -0.5188338756561279, "eval_rewards/margins": 2.65336275100708, "eval_rewards/rejected": -3.172196626663208, "eval_runtime": 727.4355, "eval_samples": 7040, "eval_samples_per_second": 9.678, "eval_steps_per_second": 0.302, "train_loss": 0.44661769921752226, "train_runtime": 1188.3148, "train_samples": 5572, "train_samples_per_second": 4.689, "train_steps_per_second": 0.073 }