{ "epoch": 0.9999635741084762, "eval_log_odds_chosen": 0.9230248332023621, "eval_log_odds_ratio": -0.5139190554618835, "eval_logits/chosen": -0.882161021232605, "eval_logits/rejected": -0.7823830246925354, "eval_logps/chosen": -0.6252197027206421, "eval_logps/rejected": -1.228542447090149, "eval_loss": 1.046362042427063, "eval_nll_loss": 1.0217794179916382, "eval_rewards/accuracies": 0.7051994800567627, "eval_rewards/chosen": -0.031262174248695374, "eval_rewards/margins": 0.03016679547727108, "eval_rewards/rejected": -0.06142931059002876, "eval_runtime": 1393.0666, "eval_samples": 98364, "eval_samples_per_second": 70.219, "eval_steps_per_second": 1.098 }