---
library_name: transformers
language:
- en
base_model: Hartunka/tiny_bert_rand_5_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: tiny_bert_rand_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: 0.2033573197630174
---

<!-- 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_rand_5_v2_stsb

This model is a fine-tuned version of [Hartunka/tiny_bert_rand_5_v2](https://huggingface.co/Hartunka/tiny_bert_rand_5_v2) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.2907
- Pearson: 0.2162
- Spearmanr: 0.2034
- Combined Score: 0.2098

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 3.1743        | 1.0   | 23   | 2.2973          | 0.1229  | 0.1070    | 0.1149         |
| 2.0355        | 2.0   | 46   | 2.5679          | 0.1150  | 0.1022    | 0.1086         |
| 1.8438        | 3.0   | 69   | 2.2907          | 0.2162  | 0.2034    | 0.2098         |
| 1.6639        | 4.0   | 92   | 2.3388          | 0.2725  | 0.2702    | 0.2714         |
| 1.3815        | 5.0   | 115  | 2.3873          | 0.2710  | 0.2714    | 0.2712         |
| 1.1561        | 6.0   | 138  | 2.3997          | 0.2922  | 0.2918    | 0.2920         |
| 0.9378        | 7.0   | 161  | 2.4841          | 0.3049  | 0.3078    | 0.3064         |
| 0.7814        | 8.0   | 184  | 2.5902          | 0.2925  | 0.2950    | 0.2938         |


### Framework versions

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