---
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-03_train-00
  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-03_train-00

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: 0.0386
- Accuracy: 0.9878
- F1: 0.6345
- Precision: 0.7182
- Recall: 0.5683

## 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 |
|:-------------:|:------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.0929        | 0.4931 | 1000  | 0.0910          | 0.9814   | 0.0    | 0.0       | 0.0    |
| 0.0785        | 0.9862 | 2000  | 0.0705          | 0.9814   | 0.0    | 0.0       | 0.0    |
| 0.0622        | 1.4793 | 3000  | 0.0574          | 0.9823   | 0.1041 | 0.8481    | 0.0554 |
| 0.0542        | 1.9724 | 4000  | 0.0501          | 0.9841   | 0.3259 | 0.7604    | 0.2074 |
| 0.048         | 2.4655 | 5000  | 0.0462          | 0.9851   | 0.4206 | 0.7612    | 0.2906 |
| 0.0436        | 2.9586 | 6000  | 0.0435          | 0.9860   | 0.5018 | 0.7354    | 0.3808 |
| 0.0384        | 3.4517 | 7000  | 0.0416          | 0.9863   | 0.5336 | 0.7234    | 0.4226 |
| 0.0385        | 3.9448 | 8000  | 0.0401          | 0.9865   | 0.5279 | 0.7530    | 0.4064 |
| 0.0343        | 4.4379 | 9000  | 0.0399          | 0.9867   | 0.5560 | 0.7353    | 0.4470 |
| 0.0343        | 4.9310 | 10000 | 0.0387          | 0.9872   | 0.5752 | 0.7457    | 0.4681 |
| 0.0304        | 5.4241 | 11000 | 0.0388          | 0.9870   | 0.5786 | 0.7267    | 0.4807 |
| 0.0299        | 5.9172 | 12000 | 0.0374          | 0.9874   | 0.6033 | 0.7259    | 0.5162 |
| 0.0265        | 6.4103 | 13000 | 0.0379          | 0.9874   | 0.6096 | 0.7145    | 0.5315 |
| 0.0261        | 6.9034 | 14000 | 0.0373          | 0.9875   | 0.6072 | 0.7321    | 0.5187 |
| 0.0236        | 7.3964 | 15000 | 0.0379          | 0.9876   | 0.6190 | 0.7221    | 0.5416 |
| 0.0236        | 7.8895 | 16000 | 0.0379          | 0.9878   | 0.6202 | 0.7324    | 0.5379 |
| 0.0215        | 8.3826 | 17000 | 0.0382          | 0.9877   | 0.6290 | 0.7156    | 0.5611 |
| 0.0216        | 8.8757 | 18000 | 0.0383          | 0.9877   | 0.6305 | 0.7156    | 0.5635 |
| 0.0177        | 9.3688 | 19000 | 0.0386          | 0.9878   | 0.6345 | 0.7182    | 0.5683 |


### Framework versions

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