| # oBERT-12-downstream-pruned-unstructured-80-mnli |
|
|
| This model is obtained with [The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models](https://arxiv.org/abs/2203.07259). |
|
|
|
|
| It corresponds to the model presented in the `Table 1 - 30 Epochs - oBERT - MNLI 80%`. |
|
|
| ``` |
| Pruning method: oBERT downstream unstructured |
| Paper: https://arxiv.org/abs/2203.07259 |
| Dataset: MNLI |
| Sparsity: 80% |
| Number of layers: 12 |
| ``` |
|
|
| The dev-set performance reported in the paper is averaged over three seeds, and we release the best model (marked with `(*)`): |
|
|
| ``` |
| | oBERT 80% | m-acc | mm-acc| |
| | ------------ | ----- | ----- | |
| | seed=42 | 84.30 | 84.98 | |
| | seed=3407 (*)| 84.46 | 84.99 | |
| | seed=54321 | 84.18 | 84.76 | |
| | ------------ | ----- | ----- | |
| | mean | 84.32 | 84.91 | |
| | stdev | 0.140 | 0.133 | |
| ``` |
|
|
| Code: _coming soon_ |
|
|
| ## BibTeX entry and citation info |
| ```bibtex |
| @article{kurtic2022optimal, |
| title={The Optimal BERT Surgeon: Scalable and Accurate Second-Order Pruning for Large Language Models}, |
| author={Kurtic, Eldar and Campos, Daniel and Nguyen, Tuan and Frantar, Elias and Kurtz, Mark and Fineran, Benjamin and Goin, Michael and Alistarh, Dan}, |
| journal={arXiv preprint arXiv:2203.07259}, |
| year={2022} |
| } |
| ``` |
