---
license: apache-2.0
base_model: distilbert/distilbert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: my_awesome_qa_model
  results: []
---
This is real link of this model:
https://huggingface.co/docs/transformers/tasks/question_answering

I wrote it to understand the basic logic.

# my_awesome_qa_model
This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an squad dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6236

## Model description

This model was written using the Hugging Face question_answering site. 


## 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: 3

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| No log        | 1.0   | 250  | 2.1966          |
| 2.6617        | 2.0   | 500  | 1.6980          |
| 2.6617        | 3.0   | 750  | 1.6236          |


### Framework versions

- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1