metadata
base_model: cardiffnlp/twitter-roberta-base-irony
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: twitter-roberta-base_3epoch3
results: []
twitter-roberta-base_3epoch3
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: 1.6791
- Accuracy: 0.7565
- F1: 0.4955
- Precision: 0.6103
- Recall: 0.4171
- Precision Sarcastic: 0.6103
- Recall Sarcastic: 0.4171
- F1 Sarcastic: 0.4955
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: 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 | 1.4006 | 0.7450 | 0.5042 | 0.5696 | 0.4523 | 0.5696 | 0.4523 | 0.5042 |
| No log | 2.0 | 348 | 1.5769 | 0.7608 | 0.5311 | 0.6065 | 0.4724 | 0.6065 | 0.4724 | 0.5311 |
| 0.0602 | 3.0 | 522 | 1.6791 | 0.7565 | 0.4955 | 0.6103 | 0.4171 | 0.6103 | 0.4171 | 0.4955 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1