---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: tiny_bert_rand_100_v2_qqp
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QQP
      type: glue
      args: qqp
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.800123670541677
    - name: F1
      type: f1
      value: 0.7117942865294768
---

<!-- 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_100_v2_qqp

This model is a fine-tuned version of [Hartunka/tiny_bert_rand_100_v2](https://huggingface.co/Hartunka/tiny_bert_rand_100_v2) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4254
- Accuracy: 0.8001
- F1: 0.7118
- Combined Score: 0.7560

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4966        | 1.0   | 1422 | 0.4605          | 0.7802   | 0.6672 | 0.7237         |
| 0.4107        | 2.0   | 2844 | 0.4254          | 0.8001   | 0.7118 | 0.7560         |
| 0.3516        | 3.0   | 4266 | 0.4326          | 0.8092   | 0.7235 | 0.7664         |
| 0.3052        | 4.0   | 5688 | 0.4260          | 0.8184   | 0.7399 | 0.7791         |
| 0.2689        | 5.0   | 7110 | 0.4374          | 0.8202   | 0.7592 | 0.7897         |
| 0.2372        | 6.0   | 8532 | 0.4387          | 0.8209   | 0.7595 | 0.7902         |
| 0.2121        | 7.0   | 9954 | 0.4771          | 0.8233   | 0.7579 | 0.7906         |


### Framework versions

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