---
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-01
  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-01

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: 0.0401
- Accuracy: 0.9877
- F1: 0.6362
- Precision: 0.7046
- Recall: 0.5799

## 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 |
|:-------------:|:-------:|:-----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.0941        | 0.4931  | 1000  | 0.0904          | 0.9814   | 0.0    | 0.0       | 0.0    |
| 0.0787        | 0.9862  | 2000  | 0.0705          | 0.9814   | 0.0    | 0.0       | 0.0    |
| 0.0628        | 1.4793  | 3000  | 0.0571          | 0.9822   | 0.1170 | 0.7402    | 0.0635 |
| 0.0537        | 1.9724  | 4000  | 0.0501          | 0.9842   | 0.3163 | 0.7991    | 0.1972 |
| 0.0478        | 2.4655  | 5000  | 0.0469          | 0.9851   | 0.4211 | 0.7561    | 0.2918 |
| 0.0453        | 2.9586  | 6000  | 0.0443          | 0.9857   | 0.4941 | 0.7238    | 0.3751 |
| 0.0389        | 3.4517  | 7000  | 0.0417          | 0.9863   | 0.5359 | 0.7234    | 0.4255 |
| 0.0393        | 3.9448  | 8000  | 0.0410          | 0.9862   | 0.5412 | 0.7034    | 0.4398 |
| 0.0349        | 4.4379  | 9000  | 0.0397          | 0.9868   | 0.5693 | 0.7206    | 0.4704 |
| 0.0344        | 4.9310  | 10000 | 0.0389          | 0.9870   | 0.5744 | 0.7307    | 0.4731 |
| 0.0302        | 5.4241  | 11000 | 0.0384          | 0.9872   | 0.5891 | 0.7262    | 0.4955 |
| 0.0305        | 5.9172  | 12000 | 0.0386          | 0.9870   | 0.5894 | 0.7087    | 0.5045 |
| 0.027         | 6.4103  | 13000 | 0.0384          | 0.9873   | 0.5966 | 0.7229    | 0.5079 |
| 0.0282        | 6.9034  | 14000 | 0.0380          | 0.9874   | 0.6018 | 0.7255    | 0.5141 |
| 0.0235        | 7.3964  | 15000 | 0.0382          | 0.9874   | 0.6185 | 0.7089    | 0.5485 |
| 0.0255        | 7.8895  | 16000 | 0.0380          | 0.9874   | 0.6198 | 0.7077    | 0.5512 |
| 0.0214        | 8.3826  | 17000 | 0.0382          | 0.9876   | 0.6292 | 0.7049    | 0.5681 |
| 0.0222        | 8.8757  | 18000 | 0.0386          | 0.9876   | 0.6271 | 0.7083    | 0.5626 |
| 0.0192        | 9.3688  | 19000 | 0.0397          | 0.9874   | 0.6294 | 0.6936    | 0.5761 |
| 0.0189        | 9.8619  | 20000 | 0.0396          | 0.9875   | 0.6300 | 0.6993    | 0.5732 |
| 0.0159        | 10.3550 | 21000 | 0.0401          | 0.9877   | 0.6362 | 0.7046    | 0.5799 |


### Framework versions

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