---
library_name: transformers
language:
- en
base_model: Hartunka/distilbert_km_50_v2
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- spearmanr
model-index:
- name: distilbert_km_50_v2_stsb
  results:
  - task:
      name: Text Classification
      type: text-classification
    dataset:
      name: GLUE STSB
      type: glue
      args: stsb
    metrics:
    - name: Spearmanr
      type: spearmanr
      value: 0.1491903358366117
---

<!-- 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. -->

# distilbert_km_50_v2_stsb

This model is a fine-tuned version of [Hartunka/distilbert_km_50_v2](https://huggingface.co/Hartunka/distilbert_km_50_v2) on the GLUE STSB dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4866
- Pearson: 0.1696
- Spearmanr: 0.1492
- Combined Score: 0.1594

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:---------:|:--------------:|
| 2.9949        | 1.0   | 23   | 2.4938          | 0.0914  | 0.0800    | 0.0857         |
| 1.9579        | 2.0   | 46   | 2.4972          | 0.1782  | 0.1647    | 0.1715         |
| 1.7843        | 3.0   | 69   | 2.4866          | 0.1696  | 0.1492    | 0.1594         |
| 1.5797        | 4.0   | 92   | 2.5044          | 0.2261  | 0.2100    | 0.2180         |
| 1.3075        | 5.0   | 115  | 2.5789          | 0.2531  | 0.2445    | 0.2488         |
| 1.0461        | 6.0   | 138  | 2.7867          | 0.2381  | 0.2219    | 0.2300         |
| 0.8285        | 7.0   | 161  | 2.6396          | 0.2729  | 0.2742    | 0.2735         |
| 0.6271        | 8.0   | 184  | 2.8820          | 0.2805  | 0.2815    | 0.2810         |


### Framework versions

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