{ "epoch": 4.988190836088805, "eval_dpo_loss": 0.6834712028503418, "eval_logits": -1.542122483253479, "eval_logps": -93.61229705810547, "eval_loss": 0.40609216690063477, "eval_objective": 0.40819352865219116, "eval_ranking_idealized": 0.5888429880142212, "eval_ranking_idealized_expo": 0.5103305578231812, "eval_ranking_simple": 0.5216942429542542, "eval_regularize": 0.40819352865219116, "eval_runtime": 260.0694, "eval_samples": 5790, "eval_samples_per_second": 22.263, "eval_steps_per_second": 0.931 }