Unverified50% confidenceFactExact time
Loss 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.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe pre-training validation loss across the three generations of models shows a steady downward trend: 2.87 → 2.78 → 2.59.77% similarUnverifiedUnder exactly the same initialization, data and learning rate schedule, the research team trained the same model from scratch on a 32-chip NPU and on a GPU respectively, and the Pearson correlation coefficient between the two loss curves reached 0.99.76% similarUnverifiedThe loss trajectory correlation coefficient usually refers to the Pearson correlation coefficient; 0.99 means the two curves move almost entirely in the same direction, but the correlation coefficient does not reflect absolute differences—even with a fixed offset it can still be close to 1.75% similarUnverifiedThroughout the entire training process, the flow-matching loss only slowly decreased from 0.805 to 0.754.72% 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 +0.079.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1044253API
curl https://kongchang.com/api/v1/knowledge/claims/1044253MCP
get_claim(id=1044253)