---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_10_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_km_10_v1_qqp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QQP
      type: glue
      args: qqp
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8211723967350977
    - name: F1
      type: f1
      value: 0.7434714731762703
---

<!-- 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_v1_qqp

This model is a fine-tuned version of [Hartunka/tiny_bert_km_10_v1](https://huggingface.co/Hartunka/tiny_bert_km_10_v1) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4171
- Accuracy: 0.8212
- F1: 0.7435
- Combined Score: 0.7823

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.494         | 1.0   | 1422  | 0.4530          | 0.7837   | 0.6826 | 0.7331         |
| 0.4064        | 2.0   | 2844  | 0.4255          | 0.8001   | 0.7039 | 0.7520         |
| 0.3487        | 3.0   | 4266  | 0.4186          | 0.8138   | 0.7303 | 0.7721         |
| 0.3007        | 4.0   | 5688  | 0.4171          | 0.8212   | 0.7435 | 0.7823         |
| 0.261         | 5.0   | 7110  | 0.4421          | 0.8216   | 0.7587 | 0.7902         |
| 0.2272        | 6.0   | 8532  | 0.4579          | 0.8228   | 0.7617 | 0.7922         |
| 0.2           | 7.0   | 9954  | 0.4847          | 0.8272   | 0.7666 | 0.7969         |
| 0.176         | 8.0   | 11376 | 0.5298          | 0.8280   | 0.7642 | 0.7961         |
| 0.1561        | 9.0   | 12798 | 0.5477          | 0.8293   | 0.7700 | 0.7997         |


### Framework versions

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