---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_km_20_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_km_20_v2_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.22422958358388922
---

<!-- 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_stsb

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 STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2841
- Pearson: 0.2453
- Spearmanr: 0.2242
- Combined Score: 0.2348

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.8315        | 1.0   | 23   | 2.3673          | 0.1768  | 0.1697    | 0.1733         |
| 1.9303        | 2.0   | 46   | 2.2888          | 0.2170  | 0.2008    | 0.2089         |
| 1.709         | 3.0   | 69   | 2.2841          | 0.2453  | 0.2242    | 0.2348         |
| 1.4178        | 4.0   | 92   | 2.4758          | 0.2475  | 0.2303    | 0.2389         |
| 1.0869        | 5.0   | 115  | 2.6407          | 0.2646  | 0.2468    | 0.2557         |
| 0.8003        | 6.0   | 138  | 2.4700          | 0.3042  | 0.2980    | 0.3011         |
| 0.6337        | 7.0   | 161  | 2.4532          | 0.3205  | 0.3252    | 0.3228         |
| 0.4849        | 8.0   | 184  | 2.6830          | 0.2970  | 0.2900    | 0.2935         |


### Framework versions

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