{ "epoch": 3.0, "eval_logits/chosen": 0.53125, "eval_logits/rejected": 2.40625, "eval_logps/chosen": -1632.0, "eval_logps/rejected": -1728.0, "eval_loss": 1.5954219102859497, "eval_rewards/accuracies": 0.60546875, "eval_rewards/chosen": -13.125, "eval_rewards/margins": 1.3046875, "eval_rewards/rejected": -14.4375, "eval_runtime": 46.8279, "eval_samples": 2000, "eval_samples_per_second": 42.71, "eval_steps_per_second": 0.683, "total_flos": 0.0, "train_loss": 0.27230105622692674, "train_runtime": 12616.2292, "train_samples": 61119, "train_samples_per_second": 14.533, "train_steps_per_second": 0.227 }