---
library_name: transformers
language:
- en
base_model: Hartunka/bert_base_rand_10_v1
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: bert_base_rand_10_v1_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.2237898877305157
---

<!-- 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_10_v1_stsb

This model is a fine-tuned version of [Hartunka/bert_base_rand_10_v1](https://huggingface.co/Hartunka/bert_base_rand_10_v1) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.3422
- Pearson: 0.2300
- Spearmanr: 0.2238
- Combined Score: 0.2269

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.5501        | 1.0   | 23   | 2.5206          | 0.1247  | 0.1086    | 0.1166         |
| 1.9123        | 2.0   | 46   | 2.3921          | 0.1624  | 0.1434    | 0.1529         |
| 1.6606        | 3.0   | 69   | 2.3422          | 0.2300  | 0.2238    | 0.2269         |
| 1.2907        | 4.0   | 92   | 2.5930          | 0.2617  | 0.2667    | 0.2642         |
| 0.9783        | 5.0   | 115  | 2.4709          | 0.2854  | 0.2803    | 0.2828         |
| 0.7673        | 6.0   | 138  | 2.4687          | 0.3073  | 0.3021    | 0.3047         |
| 0.5922        | 7.0   | 161  | 2.4917          | 0.3069  | 0.3033    | 0.3051         |
| 0.4832        | 8.0   | 184  | 2.7527          | 0.2931  | 0.2892    | 0.2911         |


### Framework versions

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