CS221-roberta-base-finetuned-semeval-new
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3023
- F1: 0.6800
- Roc Auc: 0.7986
- Accuracy: 0.5811
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 20
Training results
Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
---|---|---|---|---|---|---|
0.2592 | 1.0 | 1936 | 0.2815 | 0.6505 | 0.7740 | 0.5556 |
0.2839 | 2.0 | 3872 | 0.2787 | 0.6510 | 0.7688 | 0.5700 |
0.1879 | 3.0 | 5808 | 0.3023 | 0.6800 | 0.7986 | 0.5811 |
0.1552 | 4.0 | 7744 | 0.3485 | 0.6573 | 0.7867 | 0.5548 |
0.1182 | 5.0 | 9680 | 0.4063 | 0.6497 | 0.7833 | 0.5465 |
0.0822 | 6.0 | 11616 | 0.4614 | 0.6510 | 0.7747 | 0.5654 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 80
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.