Unverified50% confidenceBenchmarkExact time
In a sound classification experiment on the ESC-50 dataset, the top-1 hit rate was approximately 25% before training and rose to approximately 66% after about seven and a half minutes of training on an A100.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAfter 15 training epochs on the demonstration dataset, the text classification model achieves an accuracy of 99%, with a total of 110,000 model parameters (16,000 for Attention, 33,000 for FFN, and the remainder for Embedding)67% similarUnverifiedDuring training, the held-out FID dropped from 33.7 to 27.0, FD-DINOv2 dropped from 570 to 218, and detector-based object accuracy improved from 65% to 90%.66% similarUnverifiedAfter RL post-training, the small model's accuracy improves from 4% to 45% (pass@1).65% similarVerifiedIn a reproduction experiment training for 40 epochs on CIFAR-10, plain-56 achieved a training accuracy of 84.0% and plain-20 achieved a training accuracy of 95.1%, even though plain-56's parameter count (853,018) is approximately three times that of plain-20 (269,722).64% similarUnverifiedIn CLM training, pretraining alone scores 52% on the hard negative sample test; adding the hard negative sample stage jumps it to 69%; training with hard negative samples from day one peaks at only 62% and overfits quickly; omitting replay causes the hard negative sample score to drop from 69% back to 56%.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/989453API
curl https://kongchang.com/api/v1/knowledge/claims/989453MCP
get_claim(id=989453)