{ "epoch": 0.9999360981532366, "eval_logits/chosen": -1.3203125, "eval_logits/rejected": -0.9140625, "eval_logps/chosen": -376.0, "eval_logps/rejected": -418.0, "eval_loss": 0.23097696900367737, "eval_rewards/accuracies": 0.90625, "eval_rewards/chosen": -16.625, "eval_rewards/margins": 5.9375, "eval_rewards/rejected": -22.625, "eval_runtime": 1557.6405, "eval_samples": 55582, "eval_samples_per_second": 35.635, "eval_steps_per_second": 0.557, "total_flos": 0.0, "train_loss": 0.0, "train_runtime": 35.8808, "train_samples": 1001516, "train_samples_per_second": 27912.31, "train_steps_per_second": 218.055 }