---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_km_100_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: tiny_bert_km_100_v2_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.29279076301228635
---

<!-- 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_v2_stsb

This model is a fine-tuned version of [Hartunka/tiny_bert_km_100_v2](https://huggingface.co/Hartunka/tiny_bert_km_100_v2) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2118
- Pearson: 0.3037
- Spearmanr: 0.2928
- Combined Score: 0.2983

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 3.6374        | 1.0   | 23   | 2.2224          | 0.1110  | 0.1009    | 0.1060         |
| 2.0858        | 2.0   | 46   | 2.5104          | 0.1490  | 0.1353    | 0.1422         |
| 1.9616        | 3.0   | 69   | 2.2581          | 0.1995  | 0.1781    | 0.1888         |
| 1.8487        | 4.0   | 92   | 2.3268          | 0.2449  | 0.2255    | 0.2352         |
| 1.6866        | 5.0   | 115  | 2.4420          | 0.2440  | 0.2279    | 0.2359         |
| 1.5138        | 6.0   | 138  | 2.2118          | 0.3037  | 0.2928    | 0.2983         |
| 1.2926        | 7.0   | 161  | 2.4205          | 0.3232  | 0.3177    | 0.3204         |
| 1.0946        | 8.0   | 184  | 2.5488          | 0.3149  | 0.3092    | 0.3121         |
| 0.9053        | 9.0   | 207  | 2.5821          | 0.3028  | 0.2994    | 0.3011         |
| 0.7569        | 10.0  | 230  | 2.5048          | 0.3204  | 0.3157    | 0.3180         |
| 0.6373        | 11.0  | 253  | 2.5968          | 0.3135  | 0.3117    | 0.3126         |


### Framework versions

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