Verified75% confidenceTradeoffExact time
During cross-domain fine-tuning, an excessively large learning rate will destroy pre-trained weights, while an excessively small one will result in almost no learning, requiring a careful trade-off.
3
Sources
75%
Confidence
Long-term
Relevance
7/16/2026
First Seen
Sources
Related Claims
VerifiedThe learning rate determines how large each step is: too large causes overshooting the valley bottom and divergence, while too small makes training extremely time-consuming.83% similarVerifiedBehavioral cloning simplifies the problem to supervised learning, but suffers from distribution shift, where differences between the state distributions at training time and execution time lead to error accumulation.78% similarUnverified在稠密检索中，批内负样本训练要求批次包含有信息量的负样本，随机采样会导致训练损失快速收敛但泛化性能差78% similarUnverifiedExperiments show that after only a few generations of self-training, the variance of model outputs drops sharply and the text tends toward homogeneity77% similarUnverifiedNaïve post-training quantization causes individual weight errors to accumulate and amplify across multiple layers—a phenomenon known as compounding error—and at 2-bit or 1-bit precision the model structure collapses77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/527174API
curl https://kongchang.com/api/v1/knowledge/claims/527174MCP
get_claim(id=527174)