{ "epoch": 0.99, "eval_logits/chosen": 94.10542297363281, "eval_logits/rejected": 141.18112182617188, "eval_logps/chosen": -725.1587524414062, "eval_logps/rejected": -860.7156982421875, "eval_loss": 0.013092889450490475, "eval_rewards/accuracies": 0.9921875, "eval_rewards/chosen": 4.552516937255859, "eval_rewards/margins": 12.267425537109375, "eval_rewards/rejected": -7.714908599853516, "eval_runtime": 44.617, "eval_samples": 1000, "eval_samples_per_second": 22.413, "eval_steps_per_second": 0.717 }