bertweet-olid
This model is a fine-tuned version of finiteautomata/bertweet-base-sentiment-analysis on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.0303
- Accuracy: 0.8104
- F1: 0.8082
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|---|
| 0.3675 | 1.0 | 774 | 0.4257 | 0.8233 | 0.8217 |
| 0.3006 | 2.0 | 1548 | 0.3651 | 0.8385 | 0.8383 |
| 0.2461 | 3.0 | 2322 | 0.4812 | 0.8301 | 0.8298 |
| 0.202 | 4.0 | 3096 | 0.6835 | 0.8324 | 0.8324 |
| 0.1533 | 5.0 | 3870 | 1.0303 | 0.8104 | 0.8082 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 2
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.