---
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
datasets:
- cosmos_qa
metrics:
- accuracy
model-index:
- name: roberta-large-finetuned-cosmos
  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-large-finetuned-cosmos

This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on the cosmos_qa dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3863
- Accuracy: 0.2533

## 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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.39          | 1.0   | 12631 | 1.3863          | 0.2586   |
| 1.3956        | 2.0   | 25262 | 1.3863          | 0.2563   |
| 1.3902        | 3.0   | 37893 | 1.3863          | 0.2533   |


### Framework versions

- Transformers 4.32.1
- Pytorch 2.1.1+cu121
- Datasets 2.12.0
- Tokenizers 0.13.2