---
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: best_model_bert_uncasedbert-base-uncased-finetuned-sst2
  results: []
---

<!-- 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. -->

# best_model_bert_uncasedbert-base-uncased-finetuned-sst2

This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4410
- Accuracy: 0.9071

## 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: 1.4078269054384274e-05
- train_batch_size: 4
- eval_batch_size: 16
- seed: 34
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 1684 | 0.3870          | 0.9025   |
| No log        | 2.0   | 3368 | 0.4139          | 0.9060   |
| 0.4762        | 3.0   | 5052 | 0.4410          | 0.9071   |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2