TweetRoberta_5epochs
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3387
- Accuracy: 0.9452
- F1: 0.9454
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
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| 0.2755 | 1.0 | 2500 | 0.4153 | 0.9176 | 0.9129 |
| 0.2107 | 2.0 | 5000 | 0.3076 | 0.9312 | 0.9341 |
| 0.1421 | 3.0 | 7500 | 0.2812 | 0.9428 | 0.9424 |
| 0.081 | 4.0 | 10000 | 0.3304 | 0.9464 | 0.9466 |
| 0.0601 | 5.0 | 12500 | 0.3387 | 0.9452 | 0.9454 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 17
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.