---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_20_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_rand_20_v1_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.13154162033718833
---

<!-- 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_rand_20_v1_stsb

This model is a fine-tuned version of [Hartunka/bert_base_rand_20_v1](https://huggingface.co/Hartunka/bert_base_rand_20_v1) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3186
- Pearson: 0.1505
- Spearmanr: 0.1315
- Combined Score: 0.1410

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.5033        | 1.0   | 23   | 2.3186          | 0.1505  | 0.1315    | 0.1410         |
| 1.8985        | 2.0   | 46   | 2.5296          | 0.1855  | 0.1748    | 0.1802         |
| 1.6671        | 3.0   | 69   | 2.5970          | 0.2019  | 0.2018    | 0.2018         |
| 1.3208        | 4.0   | 92   | 2.3513          | 0.2943  | 0.2964    | 0.2954         |
| 0.982         | 5.0   | 115  | 2.5607          | 0.2799  | 0.2755    | 0.2777         |
| 0.7114        | 6.0   | 138  | 2.4146          | 0.3261  | 0.3240    | 0.3250         |


### Framework versions

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