{ "epoch": 3.0, "eval_logits/chosen": -2.3145642280578613, "eval_logits/rejected": -2.2872278690338135, "eval_logps/chosen": -253.4990997314453, "eval_logps/rejected": -229.3269500732422, "eval_loss": 0.5580384731292725, "eval_rewards/accuracies": 0.8125, "eval_rewards/chosen": 1.1190966367721558, "eval_rewards/margins": 2.8352162837982178, "eval_rewards/rejected": -1.716119647026062, "eval_runtime": 124.3079, "eval_samples_per_second": 15.285, "eval_steps_per_second": 0.241, "total_flos": 2369906314051584.0, "train_loss": 0.3258563337560317, "train_runtime": 7340.6492, "train_samples_per_second": 6.986, "train_steps_per_second": 0.027 }