---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_5_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_rand_5_v1_qqp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QQP
      type: glue
      args: qqp
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.8182785060598565
    - name: F1
      type: f1
      value: 0.7529506708362756
---

<!-- 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_rand_5_v1_qqp

This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v1](https://huggingface.co/Hartunka/tiny_bert_rand_5_v1) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4080
- Accuracy: 0.8183
- F1: 0.7530
- Combined Score: 0.7856

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4808        | 1.0   | 1422  | 0.4440          | 0.7895   | 0.6843 | 0.7369         |
| 0.3876        | 2.0   | 2844  | 0.4098          | 0.8119   | 0.7334 | 0.7727         |
| 0.328         | 3.0   | 4266  | 0.4080          | 0.8183   | 0.7530 | 0.7856         |
| 0.28          | 4.0   | 5688  | 0.4340          | 0.8232   | 0.7445 | 0.7838         |
| 0.2399        | 5.0   | 7110  | 0.4673          | 0.8303   | 0.7601 | 0.7952         |
| 0.2063        | 6.0   | 8532  | 0.4612          | 0.8258   | 0.7651 | 0.7955         |
| 0.1799        | 7.0   | 9954  | 0.5017          | 0.8303   | 0.7709 | 0.8006         |
| 0.1581        | 8.0   | 11376 | 0.5429          | 0.8344   | 0.7715 | 0.8030         |


### Framework versions

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