{ "epoch": 1.0, "eval_log_odds_chosen": 1.0485382080078125, "eval_log_odds_ratio": -0.5006263852119446, "eval_logits/chosen": -0.8404242396354675, "eval_logits/rejected": -0.757588803768158, "eval_logps/chosen": -0.7668778300285339, "eval_logps/rejected": -1.5307999849319458, "eval_loss": 1.1802747249603271, "eval_nll_loss": 1.1388089656829834, "eval_rewards/accuracies": 0.7127641439437866, "eval_rewards/chosen": -0.07668878138065338, "eval_rewards/margins": 0.07640629261732101, "eval_rewards/rejected": -0.15308316051959991, "eval_runtime": 1297.6344, "eval_samples": 94220, "eval_samples_per_second": 72.349, "eval_steps_per_second": 1.131, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 21.0695, "train_samples": 1686735, "train_samples_per_second": 80055.918, "train_steps_per_second": 625.455 }