---
language:
- en
base_model: Hartunka/tiny_bert_km_50_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_km_50_v1_qnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE QNLI
      type: glue
      args: qnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6143144792238696
---

<!-- 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_qnli

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 QNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6450
- Accuracy: 0.6143

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.6696        | 1.0   | 410  | 0.6519          | 0.6119   |
| 0.6425        | 2.0   | 820  | 0.6450          | 0.6143   |
| 0.5989        | 3.0   | 1230 | 0.6501          | 0.6224   |
| 0.5322        | 4.0   | 1640 | 0.6924          | 0.6301   |
| 0.455         | 5.0   | 2050 | 0.7667          | 0.6233   |
| 0.3862        | 6.0   | 2460 | 0.8902          | 0.6130   |
| 0.3213        | 7.0   | 2870 | 1.0428          | 0.6085   |


### Framework versions

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