metadata
library_name: transformers
base_model: cardiffnlp/twitter-roberta-base-sentiment-latest
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: result5
results: []
result5
This model is a fine-tuned version of cardiffnlp/twitter-roberta-base-sentiment-latest on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.5748
- Accuracy: 0.6675
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.918 | 1.0 | 723 | 0.8138 | 0.5976 |
| 0.8076 | 2.0 | 1446 | 0.7441 | 0.6526 |
| 0.6241 | 3.0 | 2169 | 0.7686 | 0.6668 |
| 0.5388 | 4.0 | 2892 | 0.8273 | 0.6619 |
| 0.4128 | 5.0 | 3615 | 0.8671 | 0.6654 |
| 0.3533 | 6.0 | 4338 | 1.0156 | 0.6678 |
| 0.2767 | 7.0 | 5061 | 1.1771 | 0.6734 |
| 0.2269 | 8.0 | 5784 | 1.3952 | 0.6671 |
| 0.1886 | 9.0 | 6507 | 1.5021 | 0.6702 |
| 0.1501 | 10.0 | 7230 | 1.5748 | 0.6675 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.2.2+cu118
- Datasets 3.0.1
- Tokenizers 0.20.0