---
library_name: transformers
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: CS221-roberta-large-finetuned-semeval-aug
  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-large-finetuned-semeval-aug

This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2306
- F1: 0.8689
- Roc Auc: 0.8985
- Accuracy: 0.6856

## 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: 32
- eval_batch_size: 32
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
| 0.4139        | 1.0   | 139  | 0.3932          | 0.7018 | 0.7800  | 0.3902   |
| 0.3507        | 2.0   | 278  | 0.3303          | 0.7826 | 0.8432  | 0.5077   |
| 0.2475        | 3.0   | 417  | 0.2855          | 0.8098 | 0.8553  | 0.5727   |
| 0.164         | 4.0   | 556  | 0.2550          | 0.8416 | 0.8800  | 0.6350   |
| 0.0943        | 5.0   | 695  | 0.2306          | 0.8689 | 0.8985  | 0.6856   |
| 0.0774        | 6.0   | 834  | 0.2709          | 0.8624 | 0.8932  | 0.6829   |
| 0.0467        | 7.0   | 973  | 0.2766          | 0.8675 | 0.9049  | 0.6757   |
| 0.0274        | 8.0   | 1112 | 0.2610          | 0.8797 | 0.9089  | 0.7182   |


### Framework versions

- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0