---
base_model: huawei-noah/TinyBERT_General_4L_312D
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: 0.8795871559633027
---

<!-- 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 is a fine-tuned version of [huawei-noah/TinyBERT_General_4L_312D](https://huggingface.co/huawei-noah/TinyBERT_General_4L_312D) on the sst2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5289
- Accuracy: 0.8796

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.4655        | 0.06  | 500   | 0.4229          | 0.8234   |
| 0.3869        | 0.12  | 1000  | 0.3870          | 0.8383   |
| 0.3786        | 0.18  | 1500  | 0.4844          | 0.8234   |
| 0.3573        | 0.24  | 2000  | 0.4276          | 0.8532   |
| 0.3502        | 0.3   | 2500  | 0.4048          | 0.8372   |
| 0.3473        | 0.36  | 3000  | 0.3623          | 0.8658   |
| 0.3283        | 0.42  | 3500  | 0.4937          | 0.8681   |
| 0.3198        | 0.48  | 4000  | 0.4020          | 0.8532   |
| 0.3006        | 0.53  | 4500  | 0.4514          | 0.8612   |
| 0.3254        | 0.59  | 5000  | 0.4370          | 0.8624   |
| 0.2923        | 0.65  | 5500  | 0.5068          | 0.8544   |
| 0.2959        | 0.71  | 6000  | 0.4557          | 0.8704   |
| 0.3003        | 0.77  | 6500  | 0.4536          | 0.8647   |
| 0.3049        | 0.83  | 7000  | 0.4810          | 0.8704   |
| 0.3008        | 0.89  | 7500  | 0.4431          | 0.8681   |
| 0.2937        | 0.95  | 8000  | 0.5207          | 0.8693   |
| 0.2805        | 1.01  | 8500  | 0.4972          | 0.8784   |
| 0.2176        | 1.07  | 9000  | 0.5370          | 0.8773   |
| 0.2379        | 1.13  | 9500  | 0.5453          | 0.8807   |
| 0.2639        | 1.19  | 10000 | 0.5117          | 0.8693   |
| 0.2555        | 1.25  | 10500 | 0.6062          | 0.8670   |
| 0.2324        | 1.31  | 11000 | 0.5623          | 0.8704   |
| 0.2225        | 1.37  | 11500 | 0.5804          | 0.8773   |
| 0.2332        | 1.43  | 12000 | 0.5089          | 0.8807   |
| 0.2214        | 1.48  | 12500 | 0.5565          | 0.8796   |
| 0.2105        | 1.54  | 13000 | 0.5614          | 0.8739   |
| 0.2174        | 1.6   | 13500 | 0.5561          | 0.875    |
| 0.2196        | 1.66  | 14000 | 0.5165          | 0.8819   |
| 0.2067        | 1.72  | 14500 | 0.5249          | 0.8796   |
| 0.1986        | 1.78  | 15000 | 0.5121          | 0.875    |
| 0.2103        | 1.84  | 15500 | 0.5044          | 0.875    |
| 0.2115        | 1.9   | 16000 | 0.5241          | 0.8784   |
| 0.2011        | 1.96  | 16500 | 0.5289          | 0.8796   |


### Framework versions

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