metadata
thumbnail: https://huggingface.co/front/thumbnails/microsoft.png
license: mit
DeBERTa: Decoding-enhanced BERT with Disentangled Attention
DeBERTa improves the BERT and RoBERTa models using disentangled attention and enhanced mask decoder. With those two improvements, DeBERTa out perform RoBERTa on a majority of NLU tasks with 80GB training data.
Please check the official repository for more details and updates.
This the DeBERTa V2 xxlarge model(60%) with 48 layers, 1536 hidden size. Total parameters 1.5B.
Fine-tuning on NLU tasks
We present the dev results on SQuAD 1.1/2.0 and several GLUE benchmark tasks.
| Model | SQuAD 1.1 | SQuAD 2.0 | MNLI-m/mm | SST-2 | QNLI | CoLA | RTE | MRPC(acc/f1) | QQP | STS-B |
|---|---|---|---|---|---|---|---|---|---|---|
| BERT-Large | 90.9/84.1 | 81.8/79.0 | 86.6/- | 93.2 | 92.3 | 60.6 | 70.4 | 88.0/- | 91.3 | 90.0 |
| RoBERTa-Large | 94.6/88.9 | 89.4/86.5 | 90.2/- | 96.4 | 93.9 | 68.0 | 86.6 | 90.9/- | 92.2 | 92.4 |
| XLNet-Large | 95.1/89.7 | 90.6/87.9 | 90.8/- | 97.0 | 94.9 | 69.0 | 85.9 | 90.8/- | 92.3 | 92.5 |
| DeBERTa-Large | 95.5/90.1 | 90.7/88.0 | 91.3/91.1 | 96.5 | 95.3 | 69.5 | 86.6 | 92.6/94.6 | 92.3 | 92.5 |
| DeBERTa-XLarge | -/- | -/- | 91.5/91.0 | - | - | - | 89.5 | 92.1/94.3 | - | - |
| DeBERTa-XLarge-V2 | - | - | 91.7/91.6 | - | - | - | - | - | - | - |
| DeBERTa-XXLarge-V2(60%) | 96.1/91.4 | 92.2/89.7 | 91.7/91.8 | - | - | - | - | - | - | - |
| DeBERTa-XLarge-V2-mnli | - | - | 91.7/91.6 | - | - | - | 93.9 | - | - | - |
| DeBERTa-XXLarge-V2-mnli | - | - | 91.7/91.8 | - | - | - | 93.5 | - | - | - |
Note
To try the XXLarge model with HF transformers, you need to specify --sharded_ddp
cd transformers/examples/text-classification/
python -m torch.distributed.launch --nproc_per_node=8 run_glue.py --model_name_or_path microsoft/deberta-xxlarge-v2 \
--task_name $TASK_NAME --do_train --do_eval --max_seq_length 128 --per_device_train_batch_size 4 \
--learning_rate 3e-6 --num_train_epochs 3 --output_dir /tmp/$TASK_NAME/ --overwrite_output_dir --sharded_ddp
Citation
If you find DeBERTa useful for your work, please cite the following paper:
@misc{he2020deberta,
title={DeBERTa: Decoding-enhanced BERT with Disentangled Attention},
author={Pengcheng He and Xiaodong Liu and Jianfeng Gao and Weizhu Chen},
year={2020},
eprint={2006.03654},
archivePrefix={arXiv},
primaryClass={cs.CL}
}