---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny-bert-sst2-mobilebert-distillation
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      config: sst2
      split: train
      args: sst2
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8394495412844036
---

<!-- 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. -->

# tiny-bert-sst2-mobilebert-distillation

This model is a fine-tuned version of [google/bert_uncased_L-2_H-128_A-2](https://huggingface.co/google/bert_uncased_L-2_H-128_A-2) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2829
- Accuracy: 0.8394

## 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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 33
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.3094        | 1.0   | 4210  | 1.3514          | 0.8165   |
| 0.7514        | 2.0   | 8420  | 1.2829          | 0.8394   |
| 0.5799        | 3.0   | 12630 | 1.4556          | 0.8349   |
| 0.4909        | 4.0   | 16840 | 1.7050          | 0.8268   |
| 0.4312        | 5.0   | 21050 | 1.6662          | 0.8245   |


### Framework versions

- Transformers 4.21.1
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1