{ "epoch": 0.99, "eval_logits/chosen": -1.1746665239334106, "eval_logits/rejected": -1.0633888244628906, "eval_logps/chosen": -394.94110107421875, "eval_logps/rejected": -613.10498046875, "eval_loss": 0.6342011094093323, "eval_rewards/accuracies": 0.78125, "eval_rewards/chosen": -0.07253288477659225, "eval_rewards/margins": 0.23117530345916748, "eval_rewards/rejected": -0.30370816588401794, "eval_runtime": 30.5473, "eval_samples": 240, "eval_samples_per_second": 7.857, "eval_steps_per_second": 0.262, "train_loss": 0.5082056158680027, "train_runtime": 904.9767, "train_samples": 3790, "train_samples_per_second": 4.188, "train_steps_per_second": 0.065 }