---
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
datasets:
- swag
metrics:
- accuracy
model-index:
- name: fine-tuned-roberta-large-swag
  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. -->

# fine-tuned-roberta-large-swag

This model is a fine-tuned version of [FacebookAI/roberta-large](https://huggingface.co/FacebookAI/roberta-large) on the swag dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5723
- Accuracy: 0.8876

## 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: 1.5e-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: 4

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.6007        | 1.0   | 4597  | 0.3438          | 0.8695   |
| 0.3897        | 2.0   | 9194  | 0.3190          | 0.8824   |
| 0.2257        | 3.0   | 13791 | 0.3866          | 0.8862   |
| 0.1238        | 4.0   | 18388 | 0.5723          | 0.8876   |


### Framework versions

- Transformers 4.41.2
- Pytorch 1.11.0
- Datasets 2.19.1
- Tokenizers 0.19.1