{ "epoch": 3.0, "eval_logits/chosen": -2.1217968463897705, "eval_logits/rejected": -2.000995397567749, "eval_logps/chosen": -265.43603515625, "eval_logps/rejected": -224.63743591308594, "eval_loss": 0.5667475461959839, "eval_rewards/accuracies": 0.7059999704360962, "eval_rewards/chosen": -0.07752041518688202, "eval_rewards/margins": 0.4577913284301758, "eval_rewards/rejected": -0.5353116989135742, "eval_runtime": 441.295, "eval_samples": 2000, "eval_samples_per_second": 4.532, "eval_steps_per_second": 0.283, "train_loss": 0.6037136622532668, "train_runtime": 61083.6691, "train_samples": 61966, "train_samples_per_second": 3.043, "train_steps_per_second": 0.012 }