{ "epoch": 0.99, "eval_logits/chosen": -1.1745316982269287, "eval_logits/rejected": -1.0640313625335693, "eval_logps/chosen": -395.233642578125, "eval_logps/rejected": -613.1549072265625, "eval_loss": 0.6347063779830933, "eval_rewards/accuracies": 0.78125, "eval_rewards/chosen": -0.0754583477973938, "eval_rewards/margins": 0.22874917089939117, "eval_rewards/rejected": -0.3042075037956238, "eval_runtime": 30.2202, "eval_samples": 240, "eval_samples_per_second": 7.942, "eval_steps_per_second": 0.265, "train_loss": 0.5081947011462713, "train_runtime": 896.7003, "train_samples": 3790, "train_samples_per_second": 4.227, "train_steps_per_second": 0.066 }