---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_20_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: bert_base_km_20_v2_mnli
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MNLI
      type: glue
      args: mnli
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6644629780309195
---

<!-- 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_20_v2_mnli

This model is a fine-tuned version of [Hartunka/bert_base_km_20_v2](https://huggingface.co/Hartunka/bert_base_km_20_v2) on the GLUE MNLI dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7873
- Accuracy: 0.6645

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
| 0.9876        | 1.0   | 1534  | 0.9146          | 0.5727   |
| 0.8776        | 2.0   | 3068  | 0.8655          | 0.6046   |
| 0.7975        | 3.0   | 4602  | 0.8097          | 0.6418   |
| 0.7185        | 4.0   | 6136  | 0.8000          | 0.6566   |
| 0.6415        | 5.0   | 7670  | 0.7951          | 0.6616   |
| 0.5611        | 6.0   | 9204  | 0.8547          | 0.6600   |
| 0.4782        | 7.0   | 10738 | 0.9200          | 0.6601   |
| 0.3996        | 8.0   | 12272 | 1.0102          | 0.6587   |
| 0.3293        | 9.0   | 13806 | 1.1861          | 0.6507   |
| 0.2684        | 10.0  | 15340 | 1.2364          | 0.6570   |


### Framework versions

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