|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: FacebookAI/roberta-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: CS221-roberta-base-finetuned-semeval-new |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# CS221-roberta-base-finetuned-semeval-new |
|
|
|
This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/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 |
|
|
