ft-bert-base-uncased-for-sentiment-classification
This model is a fine-tuned version of bert-base-uncased on the https://huggingface.co/datasets/takala/financial_phrasebank dataset. It achieves the following results on the evaluation set:
- Loss: 0.1120
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 |
|---|---|---|---|
| 0.1649 | 1.0 | 128 | 0.1319 |
| 0.1322 | 2.0 | 256 | 0.1232 |
| 0.0092 | 3.0 | 384 | 0.1120 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1