metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: stance_class_mod
results: []
stance_class_mod
This model is a fine-tuned version of vinai/bertweet-base on the dataset of 644 labeled tweets. It achieves the following results on the evaluation set:
- Loss: 0.5008
- Accuracy: 0.8605
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: 30
- eval_batch_size: 4
- 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 |
|---|---|---|---|---|
| 0.4898 | 1.0 | 13 | 0.4752 | 0.7752 |
| 0.4441 | 2.0 | 26 | 0.4355 | 0.7674 |
| 0.2363 | 3.0 | 39 | 0.5052 | 0.7984 |
| 0.2897 | 4.0 | 52 | 0.4911 | 0.7442 |
| 0.1451 | 5.0 | 65 | 0.3889 | 0.8295 |
| 0.0377 | 6.0 | 78 | 0.3988 | 0.8295 |
| 0.1236 | 7.0 | 91 | 0.4744 | 0.8605 |
| 0.1927 | 8.0 | 104 | 0.4761 | 0.8527 |
| 0.016 | 9.0 | 117 | 0.5158 | 0.8527 |
| 0.0145 | 10.0 | 130 | 0.5008 | 0.8605 |
Framework versions
- Transformers 4.24.0
- Pytorch 1.13.0+cu117
- Datasets 2.12.0
- Tokenizers 0.13.2