---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: RawAndNoisy-deberta-v3-small-Label_B-768-epochs-3
  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. -->

# RawAndNoisy-deberta-v3-small-Label_B-768-epochs-3

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: 0.6315
- Accuracy: 0.9046
- F1: 0.9054
- Precision: 0.9261
- Recall: 0.9046

## 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: 12
- eval_batch_size: 12
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 48
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:------:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.0444        | 0.9996 | 2132 | 0.8599          | 0.8423   | 0.8461 | 0.9025    | 0.8423 |
| 0.0227        | 1.9996 | 4264 | 0.6255          | 0.8906   | 0.8902 | 0.9197    | 0.8906 |
| 0.0           | 2.9996 | 6396 | 0.6315          | 0.9046   | 0.9054 | 0.9261    | 0.9046 |


### Framework versions

- Transformers 4.47.0
- Pytorch 2.5.1+cu118
- Tokenizers 0.21.0