---
tags:
- generated_from_trainer
datasets:
- sst2
metrics:
- accuracy
model-index:
- name: TinyBERT_SST2
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: sst2
      type: sst2
      config: default
      split: validation
      args: default
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8428899082568807
---

<!-- 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. -->

# TinyBERT_SST2

This model was trained from scratch on the sst2 dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1843
- Accuracy: 0.8429

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.012         | 0.06  | 500   | 1.4602          | 0.8475   |
| 0.0111        | 0.12  | 1000  | 1.4848          | 0.8475   |
| 0.0277        | 0.18  | 1500  | 1.5532          | 0.8452   |
| 0.0291        | 0.24  | 2000  | 1.4006          | 0.8440   |
| 0.0283        | 0.3   | 2500  | 1.4589          | 0.8406   |
| 0.0361        | 0.36  | 3000  | 1.2831          | 0.8429   |
| 0.0261        | 0.42  | 3500  | 1.3951          | 0.8417   |
| 0.04          | 0.48  | 4000  | 1.3990          | 0.8245   |
| 0.0333        | 0.53  | 4500  | 1.1859          | 0.8463   |
| 0.0475        | 0.59  | 5000  | 1.1699          | 0.8486   |
| 0.0304        | 0.65  | 5500  | 1.2672          | 0.8394   |
| 0.0323        | 0.71  | 6000  | 1.3541          | 0.8440   |
| 0.0482        | 0.77  | 6500  | 1.2858          | 0.8417   |
| 0.0393        | 0.83  | 7000  | 1.2595          | 0.8463   |
| 0.0371        | 0.89  | 7500  | 1.2028          | 0.8314   |
| 0.0444        | 0.95  | 8000  | 1.1606          | 0.8440   |
| 0.0407        | 1.01  | 8500  | 1.2363          | 0.8406   |
| 0.0238        | 1.07  | 9000  | 1.2556          | 0.8475   |
| 0.0253        | 1.13  | 9500  | 1.2557          | 0.8475   |
| 0.0234        | 1.19  | 10000 | 1.2927          | 0.8521   |
| 0.0293        | 1.25  | 10500 | 1.3345          | 0.8383   |
| 0.0235        | 1.31  | 11000 | 1.3742          | 0.8349   |
| 0.026         | 1.37  | 11500 | 1.3648          | 0.8337   |
| 0.0359        | 1.43  | 12000 | 1.3063          | 0.8337   |
| 0.0225        | 1.48  | 12500 | 1.3475          | 0.8360   |
| 0.0274        | 1.54  | 13000 | 1.3568          | 0.8337   |
| 0.0304        | 1.6   | 13500 | 1.3533          | 0.8372   |
| 0.0534        | 1.66  | 14000 | 1.2560          | 0.8417   |
| 0.0379        | 1.72  | 14500 | 1.2770          | 0.8417   |
| 0.0678        | 1.78  | 15000 | 1.1950          | 0.8429   |
| 0.0488        | 1.84  | 15500 | 1.1796          | 0.8440   |
| 0.0598        | 1.9   | 16000 | 1.1650          | 0.8452   |
| 0.0565        | 1.96  | 16500 | 1.1843          | 0.8429   |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0