---
license: mit
tags:
- generated_from_trainer
datasets:
- swag
metrics:
- accuracy
model-index:
- name: roberta-base-finetuned-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. -->

# roberta-base-finetuned-swag

This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the swag dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4407
- Accuracy: 0.8367

## 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: 5e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: IPU
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- total_eval_batch_size: 40
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- training precision: Mixed Precision

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.5306        | 1.0   | 574  | 0.4961          | 0.8163   |
| 0.515         | 2.0   | 1148 | 0.4294          | 0.8328   |
| 0.3507        | 3.0   | 1722 | 0.4407          | 0.8367   |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.10.0+cpu
- Datasets 2.7.1
- Tokenizers 0.12.1