{ "epoch": 1.995276334435522, "eval_dpo_loss": 152.31141662597656, "eval_logits": -1.1890512704849243, "eval_logps": -79.32337188720703, "eval_loss": 153.9576873779297, "eval_objective": 152.31141662597656, "eval_ranking_idealized": 0.5092975497245789, "eval_ranking_idealized_expo": 0.5092975497245789, "eval_ranking_simple": 0.5227272510528564, "eval_regularize": 152.31141662597656, "eval_runtime": 259.7963, "eval_samples": 5790, "eval_samples_per_second": 22.287, "eval_steps_per_second": 0.931, "total_flos": 0.0, "train_loss": 58.09165079349821, "train_runtime": 14332.9867, "train_samples": 50802, "train_samples_per_second": 7.089, "train_steps_per_second": 0.025 }