|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: bert-base-cased |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: qnli |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE QNLI |
|
type: glue |
|
args: qnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9077429983525536 |
|
--- |
|
|
|
# bert-base-cased-qnli |
|
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the GLUE QNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2835 |
|
- Accuracy: 0.9077 |
|
|
|
## Model description |
|
Please refer to [this repository](https://huggingface.co/google-bert/bert-base-cased). |
|
|
|
## Intended uses |
|
This model is for the artifact evaluation of the paper "SHAFT: Secure, Handy, Accurate, and Fast Transformer Inference." |
|
|
|
### Training hyperparameters |
|
The following hyperparameters were used during training: |
|
- learning_rate: 2e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Framework versions |
|
- Transformers 4.42.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
