{ "epoch": 3.0, "eval_logits/chosen": -1.9734503030776978, "eval_logits/rejected": -1.9131892919540405, "eval_logps/chosen": -207.2900390625, "eval_logps/rejected": -242.21389770507812, "eval_loss": 0.4500236213207245, "eval_rewards/accuracies": 0.8205645084381104, "eval_rewards/chosen": -0.6970584392547607, "eval_rewards/margins": 3.703523635864258, "eval_rewards/rejected": -4.400582313537598, "eval_runtime": 246.9541, "eval_samples_per_second": 15.881, "eval_steps_per_second": 0.251, "total_flos": 4881795388538880.0, "train_loss": 0.21825214281030322, "train_runtime": 15718.3029, "train_samples_per_second": 6.736, "train_steps_per_second": 0.026 }