{ "epoch": 2.9158878504672896, "eval_logits/chosen": -2.3212900161743164, "eval_logits/rejected": -2.2672712802886963, "eval_logps/chosen": -232.7576141357422, "eval_logps/rejected": -204.8365936279297, "eval_loss": 0.6312125325202942, "eval_rewards/accuracies": 0.75, "eval_rewards/chosen": 1.123730182647705, "eval_rewards/margins": 1.2085542678833008, "eval_rewards/rejected": -0.0848241075873375, "eval_runtime": 50.428, "eval_samples_per_second": 15.071, "eval_steps_per_second": 0.238, "total_flos": 919378820333568.0, "train_loss": 0.34083553231679475, "train_runtime": 2719.7499, "train_samples_per_second": 7.543, "train_steps_per_second": 0.029 }