{ "epoch": 0.9999812632328418, "eval_log_odds_chosen": 0.4230777621269226, "eval_log_odds_ratio": -0.6252666711807251, "eval_logits/chosen": -0.735567569732666, "eval_logits/rejected": -0.6452904939651489, "eval_logps/chosen": -0.7526504993438721, "eval_logps/rejected": -1.0431419610977173, "eval_loss": 1.0906352996826172, "eval_nll_loss": 1.0300488471984863, "eval_rewards/accuracies": 0.5944454073905945, "eval_rewards/chosen": -0.07526461780071259, "eval_rewards/margins": 0.02905045822262764, "eval_rewards/rejected": -0.10431348532438278, "eval_runtime": 2395.4247, "eval_samples": 189840, "eval_samples_per_second": 79.242, "eval_steps_per_second": 1.238 }