---
language:
- en
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
widget:
- text: Forest fire near La Ronge Sask. Canada
  example_title: 有灾情
- text: Summer is lovely
  example_title: 无灾情
base_model: roberta-large
model-index:
- name: roberta-large-finetuned-disaster
  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. -->

# roberta-large-finetuned-disaster

This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the [Disaster Tweets](https://www.kaggle.com/competitions/nlp-getting-started/data).
It achieves the following results on the evaluation set:
- Loss: 0.3668
- Accuracy: 0.8399
- F1: 0.8396

## Model description
The model is a fine-tuned version on the disaster dataset on Kaggle. You can enter the following statement to see if the label changes:
```txt
Forest fire near La Ronge Sask. Canada

Just happened a terrible car crash

What's up man?

Summer is lovely
```


## 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: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- 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 | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.446         | 1.0   | 226  | 0.3657          | 0.8583   | 0.8580 |
| 0.3295        | 2.0   | 452  | 0.3668          | 0.8399   | 0.8396 |


### Framework versions

- Transformers 4.26.1
- Pytorch 1.13.0
- Datasets 2.1.0
- Tokenizers 0.13.2