---
base_model: cardiffnlp/twitter-roberta-base-irony
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: twitter-roberta-base_3epoch10.8
  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. -->

# twitter-roberta-base_3epoch10.8

This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base-irony](https://huggingface.co/cardiffnlp/twitter-roberta-base-irony) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3313
- Accuracy: 0.7579
- F1: 0.4324
- Precision: 0.6598
- Recall: 0.3216
- Precision Sarcastic: 0.6598
- Recall Sarcastic: 0.3216
- F1 Sarcastic: 0.4324

## 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:|
| No log        | 1.0   | 347  | 2.2730          | 0.7464   | 0.4568 | 0.592     | 0.3719 | 0.592               | 0.3719           | 0.4568       |
| 0.0571        | 2.0   | 694  | 1.9955          | 0.7594   | 0.3971 | 0.7051    | 0.2764 | 0.7051              | 0.2764           | 0.3971       |
| 0.0756        | 3.0   | 1041 | 1.9672          | 0.7421   | 0.4526 | 0.5781    | 0.3719 | 0.5781              | 0.3719           | 0.4526       |
| 0.0756        | 4.0   | 1388 | 2.0562          | 0.7493   | 0.4695 | 0.5969    | 0.3869 | 0.5969              | 0.3869           | 0.4695       |
| 0.0421        | 5.0   | 1735 | 2.2045          | 0.7522   | 0.4416 | 0.6239    | 0.3417 | 0.6239              | 0.3417           | 0.4416       |
| 0.0268        | 6.0   | 2082 | 2.2693          | 0.7594   | 0.4099 | 0.6905    | 0.2915 | 0.6905              | 0.2915           | 0.4099       |
| 0.0268        | 7.0   | 2429 | 2.1746          | 0.7536   | 0.4466 | 0.6273    | 0.3467 | 0.6273              | 0.3467           | 0.4466       |
| 0.0145        | 8.0   | 2776 | 2.3412          | 0.7550   | 0.4178 | 0.6559    | 0.3065 | 0.6559              | 0.3065           | 0.4178       |
| 0.0051        | 9.0   | 3123 | 2.3512          | 0.7565   | 0.4232 | 0.6596    | 0.3116 | 0.6596              | 0.3116           | 0.4232       |
| 0.0051        | 10.0  | 3470 | 2.3313          | 0.7579   | 0.4324 | 0.6598    | 0.3216 | 0.6598              | 0.3216           | 0.4324       |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1