{ "epoch": 0.9989528795811519, "eval_logits/chosen": -0.7394673824310303, "eval_logits/rejected": -0.7407819628715515, "eval_logps/chosen": -288.1478271484375, "eval_logps/ref_chosen": -289.1346435546875, "eval_logps/ref_rejected": -264.7782287597656, "eval_logps/rejected": -273.09014892578125, "eval_loss": 0.5070626139640808, "eval_r_dpo/chosen_len": 291.2619934082031, "eval_r_dpo/length_delta": 42.86600112915039, "eval_r_dpo/regularization_term": 0.0, "eval_r_dpo/rejected_len": 248.39599609375, "eval_runtime": 81.9848, "eval_samples": 2000, "eval_samples_per_second": 24.395, "eval_steps_per_second": 1.525 }