finetuned-roberta-uncased-on-HOPE
This model is a fine-tuned version of FacebookAI/roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.3840
- Accuracy: 0.5350
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
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.3484 | 1.0 | 578 | 1.3959 | 0.5158 |
| 1.2817 | 2.0 | 1156 | 1.4068 | 0.5176 |
| 1.1726 | 3.0 | 1734 | 1.4124 | 0.5501 |
| 0.8788 | 4.0 | 2312 | 1.4765 | 0.5239 |
| 0.8274 | 5.0 | 2890 | 1.6174 | 0.5140 |
| 0.6239 | 6.0 | 3468 | 1.8005 | 0.5068 |
| 0.4586 | 7.0 | 4046 | 1.9531 | 0.4995 |
| 0.4038 | 8.0 | 4624 | 2.1295 | 0.4869 |
| 0.3829 | 9.0 | 5202 | 2.1942 | 0.4887 |
| 0.3445 | 10.0 | 5780 | 2.2519 | 0.4878 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1