{ "epoch": 0.999244142101285, "eval_fcm_dpo/beta": 0.22239074110984802, "eval_fcm_dpo/delta": 0.017137322574853897, "eval_fcm_dpo/margin": 4.419626235961914, "eval_fcm_dpo/q_t": 0.3427804410457611, "eval_logits/chosen": 0.3007291853427887, "eval_logits/rejected": 0.25601860880851746, "eval_logps/chosen": -82.5825424194336, "eval_logps/ref_chosen": -74.85946655273438, "eval_logps/ref_rejected": -79.54898834228516, "eval_logps/rejected": -91.69168853759766, "eval_loss": 0.5452697277069092, "eval_margin_dpo/margin_mean": 4.419626235961914, "eval_margin_dpo/margin_std": 7.256680488586426, "eval_runtime": 38.1623, "eval_samples": 2303, "eval_samples_per_second": 60.347, "eval_steps_per_second": 1.887 }