---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: bert_base_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: 0.8152114766262676
    - name: F1
      type: f1
      value: 0.7580086159427332
---

<!-- 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_50_v1_qqp

This model is a fine-tuned version of [Hartunka/bert_base_km_50_v1](https://huggingface.co/Hartunka/bert_base_km_50_v1) on the GLUE QQP dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3936
- Accuracy: 0.8152
- F1: 0.7580
- Combined Score: 0.7866

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.4867        | 1.0   | 1422 | 0.4667          | 0.7797   | 0.6393 | 0.7095         |
| 0.3802        | 2.0   | 2844 | 0.3936          | 0.8152   | 0.7580 | 0.7866         |
| 0.3026        | 3.0   | 4266 | 0.3944          | 0.8212   | 0.7720 | 0.7966         |
| 0.2343        | 4.0   | 5688 | 0.4298          | 0.8319   | 0.7715 | 0.8017         |
| 0.181         | 5.0   | 7110 | 0.4610          | 0.8310   | 0.7775 | 0.8042         |
| 0.1403        | 6.0   | 8532 | 0.5262          | 0.8368   | 0.7770 | 0.8069         |
| 0.1126        | 7.0   | 9954 | 0.5778          | 0.8349   | 0.7810 | 0.8079         |


### Framework versions

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