Unverified50% confidenceFactExact time
Mainstream CUA training is divided into three stages: pre-training, supervised fine-tuning (SFT), and reinforcement learning (RL); data shows that the success rate is approximately 0.5 after SFT and can climb above 0.6 after RL.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/26/2026
First Seen
Valid until: 12/25/2026
Sources
Related Entities
Related Claims
UnverifiedThe learning rate during the SFT stage is typically 1–2 orders of magnitude lower than during pre-training, to avoid disrupting the general knowledge learned during the pre-training stage.71% similarUnverified预训练阶段在海量无标注语料上通过自监督学习完成，计算成本极高、周期通常以月计，而指令微调、RLHF对齐等工程阶段可在数周甚至数天内完成65% similarVerifiedTraining speed is increased 2-5x when using Unsloth.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/951428API
curl https://kongchang.com/api/v1/knowledge/claims/951428MCP
get_claim(id=951428)