Verified65% confidenceBenchmarkExact time
The pre-training validation loss across the three generations of models shows a steady downward trend: 2.87 → 2.78 → 2.59.
3
Sources
65%
Confidence
Long-term
Relevance
8/29/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLoss correlation refers to the Pearson correlation coefficient between the two loss curves during training; 0.99 means that at each training step the NPU-side loss value rises and falls almost in sync with the GPU side.77% similarUnverifiedAt a training scale approaching 100 billion tokens, the difference in final smoothed training loss between the polynomial version and the native implementation falls between -0.107 and +0.079.77% similarUnverifiedThroughout the entire training process, the flow-matching loss only slowly decreased from 0.805 to 0.754.75% similarUnverifiedUnder the multi-pass training mode, overall submission calibration error decreases by 63%–68%.75% similarUnverifiedDuring the course's training process, the loss value decreases from approximately 3.36 to around 0.3274% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/819747API
curl https://kongchang.com/api/v1/knowledge/claims/819747MCP
get_claim(id=819747)