---
license: mit
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: data2vec-text-base-finetuned-sst2
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: glue
      type: glue
      args: sst2
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.9231651376146789
---

<!-- 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. -->

# data2vec-text-base-finetuned-sst2

This model is a fine-tuned version of [facebook/data2vec-text-base](https://huggingface.co/facebook/data2vec-text-base) on the glue dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3600
- Accuracy: 0.9232

## 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: 1.1519343408010398e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.2865        | 1.0   | 4210  | 0.2662          | 0.9128   |
| 0.2256        | 2.0   | 8420  | 0.3698          | 0.9002   |
| 0.1676        | 3.0   | 12630 | 0.3107          | 0.9186   |
| 0.1481        | 4.0   | 16840 | 0.3425          | 0.9186   |
| 0.1429        | 5.0   | 21050 | 0.3600          | 0.9232   |


### Framework versions

- Transformers 4.18.0
- Pytorch 1.11.0+cu113
- Datasets 2.1.0
- Tokenizers 0.12.1