---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- sst2
metrics:
- accuracy
model-index:
- name: distilbert_base_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: 0.8967889908256881
---

<!-- 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. -->

# distilbert_base_SST2

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the sst2 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3718
- Accuracy: 0.8968

## 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: 1

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4401        | 0.06  | 500  | 0.3732          | 0.8417   |
| 0.3465        | 0.12  | 1000 | 0.3451          | 0.8761   |
| 0.3408        | 0.18  | 1500 | 0.3465          | 0.8612   |
| 0.3059        | 0.24  | 2000 | 0.4580          | 0.8589   |
| 0.2974        | 0.3   | 2500 | 0.3338          | 0.8830   |
| 0.3023        | 0.36  | 3000 | 0.4487          | 0.8475   |
| 0.2636        | 0.42  | 3500 | 0.4330          | 0.8888   |
| 0.2558        | 0.48  | 4000 | 0.4193          | 0.8876   |
| 0.2466        | 0.53  | 4500 | 0.4343          | 0.8945   |
| 0.2393        | 0.59  | 5000 | 0.4935          | 0.875    |
| 0.2279        | 0.65  | 5500 | 0.3818          | 0.8876   |
| 0.2181        | 0.71  | 6000 | 0.4003          | 0.8968   |
| 0.2245        | 0.77  | 6500 | 0.3496          | 0.9048   |
| 0.2279        | 0.83  | 7000 | 0.3759          | 0.9014   |
| 0.2152        | 0.89  | 7500 | 0.4037          | 0.8899   |
| 0.2174        | 0.95  | 8000 | 0.3718          | 0.8968   |


### Framework versions

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