metadata
base_model: cardiffnlp/twitter-roberta-base-irony
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: twitter-roberta-base_3epoch5.16
results: []
twitter-roberta-base_3epoch5.16
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: 2.2787
- Accuracy: 0.7579
- F1: 0.4510
- Precision: 0.6449
- Recall: 0.3467
- Precision Sarcastic: 0.6449
- Recall Sarcastic: 0.3467
- F1 Sarcastic: 0.4510
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | Precision Sarcastic | Recall Sarcastic | F1 Sarcastic |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 174 | 2.3653 | 0.7421 | 0.3584 | 0.625 | 0.2513 | 0.625 | 0.2513 | 0.3584 |
| No log | 2.0 | 348 | 2.4304 | 0.7032 | 0.5209 | 0.4848 | 0.5628 | 0.4848 | 0.5628 | 0.5209 |
| 0.0162 | 3.0 | 522 | 2.1549 | 0.7622 | 0.4695 | 0.6518 | 0.3668 | 0.6518 | 0.3668 | 0.4695 |
| 0.0162 | 4.0 | 696 | 2.3336 | 0.7392 | 0.4901 | 0.5577 | 0.4372 | 0.5577 | 0.4372 | 0.4901 |
| 0.0162 | 5.0 | 870 | 2.2787 | 0.7579 | 0.4510 | 0.6449 | 0.3467 | 0.6449 | 0.3467 | 0.4510 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1