Chaos and Order https://www.youngju.dev/blog 천천히 올바르게. AI Researcher & DevOps Engineer Youngju's blog. GPU/CUDA, LLM, MLOps, Kubernetes AI workloads, and data engineering — plus mindset essays on confidence, routines, health, and sport psychology. ko fjvbn2003@gmail.com (Youngju Kim) fjvbn2003@gmail.com (Youngju Kim) Fri, 21 Aug 2026 00:00:00 GMT https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text.en AI for Everyone, Part 3 — Loss of 0.0017, Accuracy of 7.5%: The Culprit Was One Padding Slot https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text.en We built a VQA model — one that answers questions about an image — with 1.48 million parameters. Training loss fell to 0.0017 while accuracy sat at 7.5%, worse than guessing. The cause was not the model but a single line in the code that builds the targets, and fixing it produced 99.5%. This is a look at why low loss does not guarantee a good model, and how to spot the trap, using the real outputs. Fri, 21 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aivqamultimodaldebuggingpytorchtiny-models https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text.ja みんなのためのAI 第3回 — 損失0.0017なのに正解率7.5%、犯人はパディング1マスだった https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text.ja 画像と質問を一緒に受け取って答える VQA モデルを148万パラメータで作りました。学習損失は0.0017まで落ちたのに正解率は7.5%。ランダムより悪い数値です。原因はモデルではなく正解を作るコード1行で、直したら99.5%になりました。なぜ低い損失が良いモデルを保証しないのか、その罠をどう見抜くのかを実際の出力で確認します。 Fri, 21 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aivqamultimodaldebuggingpytorchtiny-models https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text 모두를 위한 AI 3편 — 손실 0.0017인데 정확도 7.5%, 범인은 패딩 한 칸이었다 https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text 이미지와 질문을 함께 받아 답하는 VQA 모델을 148만 파라미터로 만들었습니다. 학습 손실은 0.0017까지 떨어졌는데 정확도는 7.5%였습니다. 무작위보다 나쁜 수치였죠. 원인은 모델이 아니라 정답을 만드는 코드 한 줄이었고, 고치자 99.5%가 됐습니다. 왜 낮은 손실이 좋은 모델을 보장하지 않는지, 그리고 그 함정을 어떻게 알아채는지를 실제 출력으로 확인합니다. Fri, 21 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aivqamultimodaldebuggingpytorchtiny-models https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text.zh 人人可懂的 AI 第3篇 — 损失0.0017却只有7.5%正确率，元凶是一格填充 https://www.youngju.dev/blog/ai/tiny-models-03-image-text-to-text.zh 我们用148万参数做了一个 VQA 模型：同时接收图像和问题并给出答案。训练损失降到 0.0017，正确率却只有 7.5%，比随机猜还差。原因不在模型，而在生成标签的一行代码；改掉之后变成 99.5%。本文用真实输出说明：为什么低损失并不保证好模型，以及如何识破这个陷阱。 Fri, 21 Aug 2026 00:00:00 GMT fjvbn2003@gmail.com (Youngju Kim) aivqamultimodaldebuggingpytorchtiny-models