---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_5_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: tiny_bert_km_5_v2_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.2086240433941912
---

<!-- 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_5_v2_stsb

This model is a fine-tuned version of [Hartunka/tiny_bert_km_5_v2](https://huggingface.co/Hartunka/tiny_bert_km_5_v2) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3479
- Pearson: 0.2208
- Spearmanr: 0.2086
- Combined Score: 0.2147

## 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 | Pearson | Spearmanr | Combined Score |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.7925        | 1.0   | 23   | 2.3610          | 0.1193  | 0.1045    | 0.1119         |
| 2.0233        | 2.0   | 46   | 2.7265          | 0.1054  | 0.1047    | 0.1050         |
| 1.9375        | 3.0   | 69   | 2.3724          | 0.1641  | 0.1518    | 0.1580         |
| 1.8081        | 4.0   | 92   | 2.3479          | 0.2208  | 0.2086    | 0.2147         |
| 1.593         | 5.0   | 115  | 2.5032          | 0.2346  | 0.2337    | 0.2342         |
| 1.4271        | 6.0   | 138  | 2.3830          | 0.2663  | 0.2675    | 0.2669         |
| 1.2196        | 7.0   | 161  | 2.3673          | 0.3016  | 0.3058    | 0.3037         |
| 1.0511        | 8.0   | 184  | 2.5029          | 0.2915  | 0.2969    | 0.2942         |
| 0.9721        | 9.0   | 207  | 2.5246          | 0.2912  | 0.2977    | 0.2944         |


### Framework versions

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