---
base_model: cardiffnlp/twitter-roberta-base-irony
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: twitter-roberta-base_3epoch10.32
  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_3epoch10.32

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: 2.2125
- Accuracy: 0.7450
- F1: 0.4
- Precision: 0.6146
- Recall: 0.2965
- Precision Sarcastic: 0.6146
- Recall Sarcastic: 0.2965
- F1 Sarcastic: 0.4

## 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: 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------------------:|:----------------:|:------------:|
| No log        | 1.0   | 87   | 1.9011          | 0.7464   | 0.5138 | 0.5706    | 0.4673 | 0.5706              | 0.4673           | 0.5138       |
| No log        | 2.0   | 174  | 2.0529          | 0.7579   | 0.4510 | 0.6449    | 0.3467 | 0.6449              | 0.3467           | 0.4510       |
| No log        | 3.0   | 261  | 1.6275          | 0.7594   | 0.4862 | 0.6270    | 0.3970 | 0.6270              | 0.3970           | 0.4862       |
| No log        | 4.0   | 348  | 2.1947          | 0.7550   | 0.3796 | 0.6933    | 0.2613 | 0.6933              | 0.2613           | 0.3796       |
| No log        | 5.0   | 435  | 1.9559          | 0.7522   | 0.4971 | 0.5944    | 0.4271 | 0.5944              | 0.4271           | 0.4971       |
| 0.0241        | 6.0   | 522  | 2.1438          | 0.7478   | 0.3902 | 0.6364    | 0.2814 | 0.6364              | 0.2814           | 0.3902       |
| 0.0241        | 7.0   | 609  | 2.0612          | 0.7550   | 0.4817 | 0.6124    | 0.3970 | 0.6124              | 0.3970           | 0.4817       |
| 0.0241        | 8.0   | 696  | 2.1265          | 0.7565   | 0.4601 | 0.6316    | 0.3618 | 0.6316              | 0.3618           | 0.4601       |
| 0.0241        | 9.0   | 783  | 2.2016          | 0.7464   | 0.4054 | 0.6186    | 0.3015 | 0.6186              | 0.3015           | 0.4054       |
| 0.0241        | 10.0  | 870  | 2.2125          | 0.7450   | 0.4    | 0.6146    | 0.2965 | 0.6146              | 0.2965           | 0.4          |


### Framework versions

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