---
license: apache-2.0
base_model: albert-large-v2
tags:
- generated_from_trainer
datasets:
- squad
model-index:
- name: albert-large-v2-finetuned-squad
  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. -->

# albert-large-v2-finetuned-squad

This model is a fine-tuned version of [albert-large-v2](https://huggingface.co/albert-large-v2) on the squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2470
- Exact Match: 83.30179
- F1 score: 90.98849

## 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: 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: 5

### Training results

| Training Loss | Epoch | Step  | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 0.8306        | 1.0   | 5540  | 0.8740          |
| 0.6869        | 2.0   | 11080 | 0.8217          |
| 0.5048        | 3.0   | 16620 | 0.9404          |
| 0.3837        | 4.0   | 22160 | 1.0320          |
| 0.2634        | 5.0   | 27700 | 1.2470          |


### Framework versions

- Transformers 4.34.0
- Pytorch 1.12.1
- Datasets 2.14.5
- Tokenizers 0.14.1