metadata
base_model: cardiffnlp/twitter-roberta-base-irony
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: twitter-roberta-base_3epoch
results: []
twitter-roberta-base_3epoch
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-irony on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9201
- Accuracy: 0.7723
- F1: 0.5183
- Precision: 0.6589
- Recall: 0.4271
- Precision Sarcastic: 0.6589
- Recall Sarcastic: 0.4271
- F1 Sarcastic: 0.5183
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 174 | 0.6210 | 0.7248 | 0.1116 | 0.75 | 0.0603 | 0.75 | 0.0603 | 0.1116 |
| No log | 2.0 | 348 | 0.5732 | 0.7767 | 0.5016 | 0.6964 | 0.3920 | 0.6964 | 0.3920 | 0.5016 |
| 0.3415 | 3.0 | 522 | 0.9201 | 0.7723 | 0.5183 | 0.6589 | 0.4271 | 0.6589 | 0.4271 | 0.5183 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1