|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
model-index: |
|
- name: bert-base-uncased-sst2-unstructured80-PTQ |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# bert-base-uncased-sst2-unstructured80-PTQ |
|
|
|
This model conducts simple post training quantization of [yujiepan/bert-base-uncased-sst2-unstructured-sparsity-80](https://huggingface.co/yujiepan/bert-base-uncased-sst2-unstructured-sparsity-80) on the GLUE SST2 dataset. |
|
It achieves the following results on the evaluation set: |
|
- torch loss: 0.4029 |
|
- torch accuracy: 0.9128 |
|
- OpenVINO IR accuracy: 0.9117 |
|
- Sparsity in transformer block linear layers: 0.80 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 3e-05 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 8 |
|
- seed: 1 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine_with_restarts |
|
- num_epochs: 12.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.8.0 |
|
- Tokenizers 0.13.2 |
|
|
