---
language:
- en
base_model: Hartunka/tiny_bert_km_100_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: tiny_bert_km_100_v1_mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MNLI
      type: glue
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6392392188771359
---

<!-- 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_100_v1_mnli

This model is a fine-tuned version of [Hartunka/tiny_bert_km_100_v1](https://huggingface.co/Hartunka/tiny_bert_km_100_v1) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8203
- Accuracy: 0.6392

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 1.0013        | 1.0   | 1534  | 0.9411          | 0.5438   |
| 0.9118        | 2.0   | 3068  | 0.8921          | 0.5829   |
| 0.8579        | 3.0   | 4602  | 0.8575          | 0.6049   |
| 0.811         | 4.0   | 6136  | 0.8428          | 0.6192   |
| 0.7625        | 5.0   | 7670  | 0.8314          | 0.6324   |
| 0.7165        | 6.0   | 9204  | 0.8438          | 0.6409   |
| 0.6721        | 7.0   | 10738 | 0.8498          | 0.6440   |
| 0.6294        | 8.0   | 12272 | 0.8689          | 0.6462   |
| 0.5874        | 9.0   | 13806 | 0.9020          | 0.6466   |
| 0.5462        | 10.0  | 15340 | 0.9526          | 0.6473   |


### Framework versions

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