Improve README

README.md

@@ -7,28 +7,31 @@ thumbnail: https://huggingface.co/front/thumbnails/microsoft.png
 license: mit
 ---
 
-## DeBERTa: Decoding-enhanced BERT with Disentangled Attention
+## DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
 
 [DeBERTa](https://arxiv.org/abs/2006.03654) 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](https://github.com/microsoft/DeBERTa) for more details and updates.
+In [DeBERTa V3](https://arxiv.org/abs/2111.09543), we further improved the efficiency of DeBERTa using ELECTRA-Style pre-training with Gradient Disentangled Embedding Sharing. Compared to DeBERTa,  our V3 version significantly improves the model performance on downstream tasks.  You can find more technique details about the new model from our [paper](https://arxiv.org/abs/2111.09543).
 
-In [DeBERTa V3](https://arxiv.org/abs/2111.09543), we replaced the MLM objective with the RTD(Replaced Token Detection) objective introduced by ELECTRA for pre-training, as well as some innovations to be introduced in our upcoming paper. Compared to DeBERTa-V2,  our V3 version significantly improves the model performance in downstream tasks.  You can find a simple introduction about the model from the appendix A11 in our original [paper](https://arxiv.org/abs/2006.03654),  but we will provide more details in a separate write-up.
+Please check the [official repository](https://github.com/microsoft/DeBERTa) for more implementation details and updates.
 
-The DeBERTa V3 small model comes with 6 layers and a hidden size of 768. Its total parameter number is 143M since we use a vocabulary containing 128K tokens which introduce 98M parameters in the Embedding layer.  This model was trained using the 160GB data as DeBERTa V2.
+The DeBERTa V3 small model comes with 6 layers and a hidden size of 768. It has **44M** backbone parameters  with a vocabulary containing 128K tokens which introduces 98M parameters in the Embedding layer.  This model was trained using the 160GB data as DeBERTa V2.
 
 
 #### Fine-tuning on NLU tasks
 
-We present the dev results on SQuAD 1.1/2.0 and MNLI tasks.
+We present the dev results on SQuAD 2.0 and MNLI tasks.
 
-| Model             | SQuAD 1.1 | SQuAD 2.0 | MNLI-m |
-|-------------------|-----------|-----------|--------|
-| RoBERTa-base      | 91.5/84.6 | 83.7/80.5 | 87.6   |
-| XLNet-base        | -/-       | -/80.2    | 86.8   |
-|DeBERTa-base	|93.1/87.2|	86.2/83.1|	88.8|
-| **DeBERTa-v3-small**  | -/- | -/- | 88.2   |
-| DeBERTa-v3-small+SiFT  | -/- | -/- | 88.8   |
+| Model             |Vocabulary(K)|Backbone #Params(M)| SQuAD 2.0(F1/EM) | MNLI-m/mm(ACC)|
+|-------------------|----------|-------------------|-----------|----------|
+| RoBERTa-base      |50     |86                 | 83.7/80.5 | 87.6/-   |
+| XLNet-base        |32     |92                 | -/80.2    | 86.8/-   |
+| ELECTRA-base      |30    |86                  | -/80.5    | 88.8/    |
+| DeBERTa-base      |50     |100                |  86.2/83.1| 88.8/88.5|
+| DeBERTa-v3-large|128|304                      |           | -        |
+| DeBERTa-v3-base |128|86                       | 88.4/85.4 | 90.6/90.7|
+| **DeBERTa-v3-small**  |128|44                     | 82.8/80.4 | 88.3/87.7|
+| DeBERTa-v3-small+SiFT|128|22                 | -/-       | 88.8/88.5|
 
 
 #### Fine-tuning with HF transformers
@@ -55,9 +58,9 @@ python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
   --do_eval \
   --evaluation_strategy steps \
   --max_seq_length 256 \
-  --warmup_steps 1000 \
+  --warmup_steps 1500 \
   --per_device_train_batch_size ${batch_size} \
-  --learning_rate 3e-5 \
+  --learning_rate 4.5e-5 \
   --num_train_epochs 3 \
   --output_dir $output_dir \
   --overwrite_output_dir \
@@ -68,7 +71,7 @@ python -m torch.distributed.launch --nproc_per_node=${num_gpus} \
 
 ### Citation
 
-If you find DeBERTa useful for your work, please cite the following paper:
+If you find DeBERTa useful for your work, please cite the following papers:
 
 ``` latex
 @misc{he2021debertav3,
@@ -90,4 +93,4 @@ booktitle={International Conference on Learning Representations},
 year={2021},
 url={https://openreview.net/forum?id=XPZIaotutsD}
 }
-```
+```

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99cd3cbf49b4234e1e2210bf1a39565438f8957a3f6dfb43eab337c194b0ac41
+oid sha256:d4b0ebcc7799a2c2dde1a39199cb0ed709f2c6b63a48b8c05133b77955f271a9
 size 286059269