Views
No views yet
Table 2 - oBERT - SQuADv1 97% (in the upcoming updated version of the paper).Pruning method: oBERT upstream unstructured + sparse-transfer to downstream
Paper: https://arxiv.org/abs/2203.07259
Dataset: SQuADv1
Sparsity: 97%
Number of layers: 12(*)):| oBERT 97% | F1 | EM |
| ------------- | ----- | ----- |
| seed=42 | 84.92 | 76.94 |
| seed=3407 | 84.87 | 76.71 |
| seed=123 | 84.95 | 77.06 |
| seed=12345 (*)| 84.95 | 76.90 |
| ------------- | ----- | ----- |
| mean | 84.92 | 76.90 |
| stdev | 0.037 | 0.145 |1@article{kurtic2022optimal,
2 title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models},
3 author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan},
4 journal={arXiv preprint arXiv:2203.07259},
5 year={2022}
6}