摸索和延迟泛化测验

当您参加测验时，就会出现答案和解释。

1. 哪种性能模式是所研究的 Grokking 现象的特征？
   • Held-out accuracy must improve before any training example is learned
   • Training accuracy can never become high
   • Every model loses all training information at once
   • Held-out generalization improves substantially after the training examples have already been fit
2. 原始 Grokking 论文使用了哪些任务作为受控设置？
   • Only large-scale photorealistic image generation
   • Small algorithmically generated tasks such as modular arithmetic
   • Only real-time online advertising auctions
   • Only unlabelled random filenames
3. 原始 Grokking 实验中检查了哪些正则化干预措施？
   • Weight decay
   • Mandatory deletion of every activation function
   • A proof that all test labels must be randomized
   • Automatic enlargement of the vocabulary on every step
4. 所引用的模加法机制研究在训练好的小型 Transformer 中识别出了什么计算？
   • A universal rule for every large deployed model
   • Only a table containing every held-out answer
   • A Fourier-based algorithm using trigonometric relationships
   • No identifiable structured computation
5. 《Grokking 的进度度量》描述了所研究训练动力学中的哪种阶段排序？
   • Cleanup, deletion of all data, then no computation
   • Memorization, circuit formation, then cleanup
   • Perfect held-out performance before any circuit formation
   • A mandatory switch to image-only inputs
6. 格罗克法对练习者提出了哪些实际注意事项？
   • 训练准确率达到 100% 时始终停止训练
   • 验证准确性无关紧要
   • 早期验证停滞并不总是意味着模型无法学习
   • 永远不应该使用正则化
7. For the modular-addition task, what is (6+5) modulo 7?
   • 11
   • 7
   • 1
   • 4
8. What dataset-size trend did the original grokking paper report in its studied setups?
   • Smaller training datasets required more optimization to reach generalization
   • Smaller datasets always generalized immediately with no optimization
   • Dataset size was never varied
   • Every larger dataset prevented all training accuracy