---
language:
- en
base_model: Hartunka/tiny_bert_km_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_km_50_v1_qqp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QQP
      type: glue
      args: qqp
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8108582735592382
    - name: F1
      type: f1
      value: 0.7288970822845393
---

<!-- 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_50_v1_qqp

This model is a fine-tuned version of [Hartunka/tiny_bert_km_50_v1](https://huggingface.co/Hartunka/tiny_bert_km_50_v1) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4193
- Accuracy: 0.8109
- F1: 0.7289
- Combined Score: 0.7699

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 50

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Accuracy | F1     | Combined Score |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.5011        | 1.0   | 1422  | 0.4514          | 0.7840   | 0.6809 | 0.7325         |
| 0.4146        | 2.0   | 2844  | 0.4233          | 0.7997   | 0.7107 | 0.7552         |
| 0.3605        | 3.0   | 4266  | 0.4193          | 0.8109   | 0.7289 | 0.7699         |
| 0.3153        | 4.0   | 5688  | 0.4298          | 0.8143   | 0.7395 | 0.7769         |
| 0.2768        | 5.0   | 7110  | 0.4367          | 0.8161   | 0.7463 | 0.7812         |
| 0.245         | 6.0   | 8532  | 0.4542          | 0.8137   | 0.7588 | 0.7862         |
| 0.2174        | 7.0   | 9954  | 0.4738          | 0.8195   | 0.7598 | 0.7896         |
| 0.1927        | 8.0   | 11376 | 0.5163          | 0.8237   | 0.7575 | 0.7906         |


### Framework versions

- Transformers 4.40.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.19.1