---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-xsmall
tags:
- generated_from_trainer
model-index:
- name: capricious-gnu-139
  results: []
---

<!-- 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. -->

# capricious-gnu-139

This model is a fine-tuned version of [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1831
- Hamming Loss: 0.0661
- Zero One Loss: 0.4537
- Jaccard Score: 0.4105
- Hamming Loss Optimised: 0.0659
- Hamming Loss Threshold: 0.6135
- Zero One Loss Optimised: 0.4087
- Zero One Loss Threshold: 0.4316
- Jaccard Score Optimised: 0.3479
- Jaccard Score Threshold: 0.3462

## 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: 5.0943791435964314e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 2024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9

### Training results

| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
|:-------------:|:-----:|:----:|:---------------:|:------------:|:-------------:|:-------------:|:----------------------:|:----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|
| 0.4159        | 1.0   | 100  | 0.3376          | 0.1123       | 1.0           | 1.0           | 0.1123                 | 0.9000                 | 1.0                     | 0.9000                  | 1.0                     | 0.9000                  |
| 0.3121        | 2.0   | 200  | 0.2841          | 0.0932       | 0.8113        | 0.8087        | 0.0931                 | 0.4416                 | 0.6963                  | 0.1641                  | 0.6101                  | 0.1642                  |
| 0.2602        | 3.0   | 300  | 0.2338          | 0.092        | 0.785         | 0.7819        | 0.0765                 | 0.3980                 | 0.6113                  | 0.3139                  | 0.5072                  | 0.2086                  |
| 0.2174        | 4.0   | 400  | 0.2063          | 0.0712       | 0.5975        | 0.5703        | 0.0698                 | 0.4494                 | 0.5363                  | 0.3378                  | 0.4363                  | 0.2553                  |
| 0.1896        | 5.0   | 500  | 0.1967          | 0.0694       | 0.5813        | 0.5551        | 0.0661                 | 0.4552                 | 0.4513                  | 0.3622                  | 0.3900                  | 0.2346                  |
| 0.1726        | 6.0   | 600  | 0.1910          | 0.07         | 0.4988        | 0.4614        | 0.0695                 | 0.5944                 | 0.4400                  | 0.4036                  | 0.3569                  | 0.3149                  |
| 0.1618        | 7.0   | 700  | 0.1861          | 0.0679       | 0.475         | 0.4339        | 0.0651                 | 0.5430                 | 0.4237                  | 0.4130                  | 0.3652                  | 0.3483                  |
| 0.1522        | 8.0   | 800  | 0.1845          | 0.0683       | 0.4712        | 0.4328        | 0.0663                 | 0.5807                 | 0.4337                  | 0.4266                  | 0.3585                  | 0.3310                  |
| 0.1484        | 9.0   | 900  | 0.1831          | 0.0661       | 0.4537        | 0.4105        | 0.0659                 | 0.6135                 | 0.4087                  | 0.4316                  | 0.3479                  | 0.3462                  |


### Framework versions

- Transformers 4.45.1
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3