---
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_km_20_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
- f1
model-index:
- name: distilbert_km_20_v2_mrpc
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE MRPC
      type: glue
      args: mrpc
    metrics:
    - name: Accuracy
      type: accuracy
      value: 0.6813725490196079
    - name: F1
      type: f1
      value: 0.8
---

<!-- 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. -->

# distilbert_km_20_v2_mrpc

This model is a fine-tuned version of [Hartunka/distilbert_km_20_v2](https://huggingface.co/Hartunka/distilbert_km_20_v2) on the GLUE MRPC dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6079
- Accuracy: 0.6814
- F1: 0.8
- Combined Score: 0.7407

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:--------------:|
| 0.6244        | 1.0   | 15   | 0.6130          | 0.7034   | 0.8136 | 0.7585         |
| 0.5689        | 2.0   | 30   | 0.6079          | 0.6814   | 0.8    | 0.7407         |
| 0.5055        | 3.0   | 45   | 0.6477          | 0.7108   | 0.8168 | 0.7638         |
| 0.4324        | 4.0   | 60   | 0.6750          | 0.6691   | 0.7660 | 0.7176         |
| 0.3194        | 5.0   | 75   | 0.7787          | 0.6667   | 0.7631 | 0.7149         |
| 0.1929        | 6.0   | 90   | 1.0004          | 0.6691   | 0.7576 | 0.7134         |
| 0.1087        | 7.0   | 105  | 1.2846          | 0.6275   | 0.7206 | 0.6740         |


### Framework versions

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