---
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
datasets:
- sberquad
model-index:
- name: qa_model_study_1
  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. -->

# qa_model_study_1

This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the sberquad dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4337

## 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: 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 3.1351        | 1.0   | 750  | 2.6338          |
| 2.5385        | 2.0   | 1500 | 2.4813          |
| 2.3433        | 3.0   | 2250 | 2.4337          |


### Framework versions

- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1