metadata
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: twitter-roberta-base-stance-abortionV3
results: []
twitter-roberta-base-stance-abortionV3
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-stance-abortion on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5095
- F1: 0.7917
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 |
|---|---|---|---|---|
| 0.8492 | 1.0 | 12 | 0.4862 | 0.7917 |
| 0.7291 | 2.0 | 24 | 0.4264 | 0.7917 |
| 0.5465 | 3.0 | 36 | 0.6450 | 0.7917 |
| 0.5905 | 4.0 | 48 | 0.5857 | 0.7917 |
| 0.4556 | 5.0 | 60 | 0.5095 | 0.7917 |
Framework versions
- Transformers 4.21.2
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1