{ "epoch": 0.9984431759211209, "eval_logits/chosen": -0.37566518783569336, "eval_logits/rejected": 2.1293272972106934, "eval_logps/chosen": -970.51123046875, "eval_logps/rejected": -1795.306396484375, "eval_loss": 0.1496390402317047, "eval_rewards/accuracies": 0.9313725233078003, "eval_rewards/chosen": -5.471029758453369, "eval_rewards/margins": 8.022629737854004, "eval_rewards/rejected": -13.493659973144531, "eval_runtime": 298.1728, "eval_samples": 6491, "eval_samples_per_second": 21.769, "eval_steps_per_second": 0.342, "total_flos": 0.0, "train_loss": 0.21509297628908297, "train_runtime": 13791.8998, "train_samples": 123309, "train_samples_per_second": 8.941, "train_steps_per_second": 0.035 }