{ "epoch": 1.0, "eval_logits/chosen": -2.3070545196533203, "eval_logits/rejected": -2.138820171356201, "eval_logps/chosen": -151.25401306152344, "eval_logps/rejected": -157.17115783691406, "eval_loss": 0.12742868065834045, "eval_rewards/accuracies": 0.9765625, "eval_rewards/chosen": -1.1806919574737549, "eval_rewards/margins": 6.254101276397705, "eval_rewards/rejected": -7.434792995452881, "eval_runtime": 160.2204, "eval_samples": 512, "eval_samples_per_second": 3.196, "eval_steps_per_second": 0.1, "train_loss": 0.20032393871645335, "train_runtime": 8133.5998, "train_samples": 15685, "train_samples_per_second": 1.928, "train_steps_per_second": 0.06 }