---
library_name: transformers
base_model: cardiffnlp/twitter-roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
- precision
- recall
model-index:
- name: sarcasm-detector-roberta
  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. -->

# sarcasm-detector-roberta

This model is a fine-tuned version of [cardiffnlp/twitter-roberta-base](https://huggingface.co/cardiffnlp/twitter-roberta-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6026
- F1: 0.7528
- Accuracy: 0.7538
- Precision: 0.7633
- Recall: 0.7734

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 32
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:---------:|:------:|
| 0.5678        | 1.0   | 179  | 0.6256          | 0.6490 | 0.6555   | 0.6808    | 0.6630 |
| 0.5366        | 2.0   | 358  | 0.5578          | 0.7204 | 0.7204   | 0.7211    | 0.7214 |
| 0.4206        | 3.0   | 537  | 0.6071          | 0.7214 | 0.7215   | 0.7221    | 0.7224 |
| 0.3041        | 4.0   | 716  | 0.6764          | 0.7338 | 0.7340   | 0.7391    | 0.7369 |
| 0.3386        | 5.0   | 895  | 0.6968          | 0.7298 | 0.7298   | 0.7316    | 0.7315 |


### Framework versions

- Transformers 5.6.2
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.22.2