---
base_model: SpanBERT/spanbert-base-cased
tags:
- generated_from_trainer
datasets:
- squad
metrics:
- f1
- exact_match

# Optional. Add this if you want to encode your eval results in a structured way.
model-index:
- name: spanbert-base-finetuned-squad
  results:
  - task:
      type: question-answering             # Required. Example: automatic-speech-recognition
      name: Closed-Domain Question Answering             # Optional. Example: Speech Recognition
    dataset:
      type: squad          # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
      name: SQuAD          # Required. A pretty name for the dataset. Example: Common Voice (French)
      config: squad      # Optional. The name of the dataset configuration used in `load_dataset()`. Example: fr in `load_dataset("common_voice", "fr")`. See the `datasets` docs for more info: https://huggingface.co/docs/datasets/package_reference/loading_methods#datasets.load_dataset.name
      split: validation        # Optional. Example: test
    metrics:
      - type: exact_match         # Required. Example: wer. Use metric id from https://hf.co/metrics
        value: 84.6168       # Required. Example: 20.90
        name: Exact Match         # Optional. Example: Test WER
      - type: f1         # Required. Example: wer. Use metric id from https://hf.co/metrics
        value: 91.6134       # Required. Example: 20.90
        name: F1         # Optional. Example: Test WER
---

<!-- 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. -->

# spanbert-base-finetuned-squad

This model is a fine-tuned version of [SpanBERT/spanbert-base-cased](https://huggingface.co/SpanBERT/spanbert-base-cased) on the squad dataset.

## 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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3

### Training results



### Framework versions

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