---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_10_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_km_10_v2_qqp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QQP
      type: glue
      args: qqp
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8163987138263665
    - name: F1
      type: f1
      value: 0.7454302273740526
---

<!-- 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. -->

# tiny_bert_km_10_v2_qqp

This model is a fine-tuned version of [Hartunka/tiny_bert_km_10_v2](https://huggingface.co/Hartunka/tiny_bert_km_10_v2) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4118
- Accuracy: 0.8164
- F1: 0.7454
- Combined Score: 0.7809

## 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: 5e-05
- train_batch_size: 256
- eval_batch_size: 256
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.49          | 1.0   | 1422  | 0.4449          | 0.7852   | 0.6797 | 0.7324         |
| 0.3992        | 2.0   | 2844  | 0.4204          | 0.8038   | 0.7170 | 0.7604         |
| 0.3367        | 3.0   | 4266  | 0.4118          | 0.8164   | 0.7454 | 0.7809         |
| 0.2845        | 4.0   | 5688  | 0.4297          | 0.8200   | 0.7449 | 0.7824         |
| 0.243         | 5.0   | 7110  | 0.4527          | 0.8228   | 0.7637 | 0.7932         |
| 0.2066        | 6.0   | 8532  | 0.4895          | 0.8199   | 0.7636 | 0.7918         |
| 0.1782        | 7.0   | 9954  | 0.5355          | 0.8205   | 0.7669 | 0.7937         |
| 0.1554        | 8.0   | 11376 | 0.5614          | 0.8253   | 0.7663 | 0.7958         |


### Framework versions

- Transformers 4.50.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.21.1