{ "epoch": 0.9999354130336499, "eval_log_odds_chosen": 1.242581844329834, "eval_log_odds_ratio": -0.47447991371154785, "eval_logits/chosen": -1.2279024124145508, "eval_logits/rejected": -1.0133243799209595, "eval_logps/chosen": -0.8291401863098145, "eval_logps/rejected": -1.7743595838546753, "eval_loss": 1.2853127717971802, "eval_nll_loss": 1.246997594833374, "eval_rewards/accuracies": 0.7431685924530029, "eval_rewards/chosen": -0.0829220786690712, "eval_rewards/margins": 0.09452750533819199, "eval_rewards/rejected": -0.1774357259273529, "eval_runtime": 905.5189, "eval_samples": 54974, "eval_samples_per_second": 60.743, "eval_steps_per_second": 0.95, "total_flos": 0.0, "train_loss": 0.9929802710657941, "train_runtime": 57443.5833, "train_samples": 990885, "train_samples_per_second": 17.25, "train_steps_per_second": 0.135 }