<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Roberta-Sentiment-Classifier
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6645
- Accuracy: 0.7594
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: 1e-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 |
|---|---|---|---|---|
| 0.8429 | 0.5 | 500 | 0.7465 | 0.7193 |
| 0.7095 | 1.0 | 1000 | 0.6669 | 0.7559 |
| 0.5976 | 1.5 | 1500 | 0.6836 | 0.7634 |
| 0.6095 | 2.0 | 2000 | 0.6645 | 0.7594 |
| 0.4899 | 2.51 | 2500 | 0.7106 | 0.7649 |
| 0.493 | 3.01 | 3000 | 0.7011 | 0.7694 |
| 0.3982 | 3.51 | 3500 | 0.8443 | 0.7719 |
| 0.4098 | 4.01 | 4000 | 0.8376 | 0.7754 |
| 0.3435 | 4.51 | 4500 | 0.9237 | 0.7709 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1
