---
license: apache-2.0
base_model: Yama/bert-base-uncased-finetuned-swag
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: bert-base-uncased-finetuned-swag
  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. -->

# bert-base-uncased-finetuned-swag

This model is a fine-tuned version of [Yama/bert-base-uncased-finetuned-swag](https://huggingface.co/Yama/bert-base-uncased-finetuned-swag) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0061
- Accuracy: 0.9958

## 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: 40

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| No log        | 1.0   | 150  | 1.3780          | 0.3592   |
| No log        | 2.0   | 300  | 1.3234          | 0.4383   |
| No log        | 3.0   | 450  | 1.3158          | 0.4992   |
| 1.3577        | 4.0   | 600  | 1.1356          | 0.5792   |
| 1.3577        | 5.0   | 750  | 0.7939          | 0.7217   |
| 1.3577        | 6.0   | 900  | 0.6167          | 0.7958   |
| 1.0479        | 7.0   | 1050 | 0.4737          | 0.8467   |
| 1.0479        | 8.0   | 1200 | 0.3424          | 0.8867   |
| 1.0479        | 9.0   | 1350 | 0.2448          | 0.9142   |
| 0.5968        | 10.0  | 1500 | 0.2117          | 0.9158   |
| 0.5968        | 11.0  | 1650 | 0.1589          | 0.9467   |
| 0.5968        | 12.0  | 1800 | 0.1420          | 0.9492   |
| 0.5968        | 13.0  | 1950 | 0.0970          | 0.9675   |
| 0.3341        | 14.0  | 2100 | 0.1014          | 0.9725   |
| 0.3341        | 15.0  | 2250 | 0.0678          | 0.9742   |
| 0.3341        | 16.0  | 2400 | 0.0624          | 0.9825   |
| 0.1802        | 17.0  | 2550 | 0.0407          | 0.9783   |
| 0.1802        | 18.0  | 2700 | 0.0501          | 0.9858   |
| 0.1802        | 19.0  | 2850 | 0.0341          | 0.9867   |
| 0.1213        | 20.0  | 3000 | 0.0284          | 0.9883   |
| 0.1213        | 21.0  | 3150 | 0.0398          | 0.9883   |
| 0.1213        | 22.0  | 3300 | 0.0290          | 0.9908   |
| 0.1213        | 23.0  | 3450 | 0.0211          | 0.9908   |
| 0.0758        | 24.0  | 3600 | 0.0179          | 0.9908   |
| 0.0758        | 25.0  | 3750 | 0.0151          | 0.9917   |
| 0.0758        | 26.0  | 3900 | 0.0154          | 0.9933   |
| 0.0464        | 27.0  | 4050 | 0.0216          | 0.9942   |
| 0.0464        | 28.0  | 4200 | 0.0124          | 0.9942   |
| 0.0464        | 29.0  | 4350 | 0.0122          | 0.9942   |
| 0.0306        | 30.0  | 4500 | 0.0103          | 0.9942   |
| 0.0306        | 31.0  | 4650 | 0.0094          | 0.9942   |
| 0.0306        | 32.0  | 4800 | 0.0083          | 0.9942   |
| 0.0306        | 33.0  | 4950 | 0.0079          | 0.9958   |
| 0.0201        | 34.0  | 5100 | 0.0079          | 0.9950   |
| 0.0201        | 35.0  | 5250 | 0.0069          | 0.9958   |
| 0.0201        | 36.0  | 5400 | 0.0069          | 0.9950   |
| 0.0205        | 37.0  | 5550 | 0.0060          | 0.9967   |
| 0.0205        | 38.0  | 5700 | 0.0060          | 0.9958   |
| 0.0205        | 39.0  | 5850 | 0.0061          | 0.9958   |
| 0.0102        | 40.0  | 6000 | 0.0061          | 0.9958   |


### Framework versions

- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1