---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_km_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: 0.8197378184516448
    - name: F1
      type: f1
      value: 0.7687523797436223
---

<!-- 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. -->

# bert_base_km_100_v2_qqp

This model is a fine-tuned version of [Hartunka/bert_base_km_100_v2](https://huggingface.co/Hartunka/bert_base_km_100_v2) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4003
- Accuracy: 0.8197
- F1: 0.7688
- Combined Score: 0.7942

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4851        | 1.0   | 1422  | 0.4543          | 0.7842   | 0.6573 | 0.7207         |
| 0.3784        | 2.0   | 2844  | 0.4032          | 0.8116   | 0.7570 | 0.7843         |
| 0.2978        | 3.0   | 4266  | 0.4003          | 0.8197   | 0.7688 | 0.7942         |
| 0.2292        | 4.0   | 5688  | 0.4379          | 0.8305   | 0.7631 | 0.7968         |
| 0.1741        | 5.0   | 7110  | 0.4736          | 0.8309   | 0.7750 | 0.8030         |
| 0.1338        | 6.0   | 8532  | 0.5308          | 0.8355   | 0.7702 | 0.8029         |
| 0.1055        | 7.0   | 9954  | 0.5860          | 0.8292   | 0.7774 | 0.8033         |
| 0.0843        | 8.0   | 11376 | 0.6412          | 0.8315   | 0.7762 | 0.8038         |


### Framework versions

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