{ "epoch": 0.9989528795811519, "eval_KL/chosen_KL_mean": -48.39694595336914, "eval_KL/mean": -76.14442443847656, "eval_KL/rejected_KL_mean": -103.89189147949219, "eval_KL/std": 75.29983520507812, "eval_fcm_dpo/beta": 0.003546761581674218, "eval_logits/chosen": 1.4365565776824951, "eval_logits/rejected": 1.5009914636611938, "eval_logps/chosen": -328.81365966796875, "eval_logps/ref_chosen": -280.41668701171875, "eval_logps/ref_rejected": -264.6455383300781, "eval_logps/rejected": -368.53741455078125, "eval_loss": 0.6136210560798645, "eval_margin_dpo/margin_mean": 55.49495315551758, "eval_margin_dpo/margin_std": 87.28593444824219, "eval_runtime": 88.1538, "eval_samples": 2000, "eval_samples_per_second": 22.688, "eval_steps_per_second": 2.836 }