Unverified50% confidenceFactExact time
根据Chinchilla定律及其后续研究，模型性能与训练计算量之间存在幂律关系
1
Sources
50%
Confidence
Long-term
Relevance
8/14/2026
First Seen
Sources
Related Claims
UnverifiedThe paper found that for a fixed compute budget, training a smaller model for longer tends to yield better results than training a larger model, which contradicts the Chinchilla law.75% similarUnverifiedKaplan等人2020年的研究表明模型参数量、训练数据量、训练计算量三者与性能之间存在可预测的幂律关系73% similarUnverified缩放定律表明模型在特定任务上的表现与训练数据量、模型参数量和计算量之间存在幂律关系，OpenAI、DeepMind等机构的研究支持这一发现73% similarUnverifiedThe Chinchilla law states that under a fixed compute budget, appropriately reducing model size and increasing training data volume often yields better performance.72% similarUnverifiedThe Chinchilla scaling law states that the optimal number of training tokens should be proportional to the number of model parameters, meaning that when parameters are doubled, training data and computational cost should at least double as well.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/746816API
curl https://kongchang.com/api/v1/knowledge/claims/746816MCP
get_claim(id=746816)