---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: doc-topic-model_eval-04_train-02
  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. -->

# doc-topic-model_eval-04_train-02

This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0374
- Accuracy: 0.9879
- F1: 0.6272
- Precision: 0.7299
- Recall: 0.5498

## 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: 2e-05
- train_batch_size: 4
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step  | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.0944        | 0.4931 | 1000  | 0.0895          | 0.9815   | 0.0    | 0.0       | 0.0    |
| 0.0769        | 0.9862 | 2000  | 0.0685          | 0.9815   | 0.0014 | 1.0       | 0.0007 |
| 0.0607        | 1.4793 | 3000  | 0.0560          | 0.9823   | 0.1066 | 0.8022    | 0.0571 |
| 0.0535        | 1.9724 | 4000  | 0.0501          | 0.9846   | 0.3748 | 0.7494    | 0.2498 |
| 0.0466        | 2.4655 | 5000  | 0.0450          | 0.9858   | 0.4899 | 0.7338    | 0.3677 |
| 0.0441        | 2.9586 | 6000  | 0.0421          | 0.9863   | 0.5084 | 0.7553    | 0.3832 |
| 0.0391        | 3.4517 | 7000  | 0.0404          | 0.9868   | 0.5581 | 0.7311    | 0.4513 |
| 0.0372        | 3.9448 | 8000  | 0.0393          | 0.9870   | 0.5568 | 0.7564    | 0.4405 |
| 0.0336        | 4.4379 | 9000  | 0.0382          | 0.9872   | 0.5749 | 0.7485    | 0.4666 |
| 0.0337        | 4.9310 | 10000 | 0.0375          | 0.9874   | 0.5938 | 0.7375    | 0.4970 |
| 0.0297        | 5.4241 | 11000 | 0.0368          | 0.9875   | 0.6079 | 0.7260    | 0.5228 |
| 0.0296        | 5.9172 | 12000 | 0.0376          | 0.9875   | 0.5899 | 0.7526    | 0.4850 |
| 0.0263        | 6.4103 | 13000 | 0.0372          | 0.9877   | 0.6211 | 0.7210    | 0.5455 |
| 0.0272        | 6.9034 | 14000 | 0.0376          | 0.9875   | 0.6194 | 0.7061    | 0.5516 |
| 0.0234        | 7.3964 | 15000 | 0.0373          | 0.9878   | 0.6222 | 0.7304    | 0.5420 |
| 0.0243        | 7.8895 | 16000 | 0.0374          | 0.9879   | 0.6272 | 0.7299    | 0.5498 |


### Framework versions

- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1