---
license: mit
tags:
- generated_from_trainer
datasets:
- quoref
model-index:
- name: roberta-base_mod_quoref
  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_mod_quoref

This model is a fine-tuned version of [damapika/roberta-base_mod_squad](https://huggingface.co/damapika/roberta-base_mod_squad) on the quoref dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5566

## 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: 3e-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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.1263        | 1.0   | 1213 | 1.2665          |
| 0.7404        | 2.0   | 2426 | 1.3567          |
| 0.5172        | 3.0   | 3639 | 1.5566          |


### Framework versions

- Transformers 4.28.1
- Pytorch 2.0.0+cu118
- Datasets 2.11.0
- Tokenizers 0.13.3