---
license: mit
base_model: microsoft/deberta-v3-small
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: DeBERTaV3_model_V5
  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. -->

# DeBERTaV3_model_V5

This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1164
- Accuracy: 0.9652
- F1: 0.8192
- Precision: 0.8524
- Recall: 0.7885

## 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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 12

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| No log        | 1.0   | 182  | 0.2809          | 0.9      | 0.0    | 0.0       | 0.0    |
| No log        | 2.0   | 364  | 0.2176          | 0.9216   | 0.4027 | 0.8451    | 0.2643 |
| 0.2842        | 3.0   | 546  | 0.1558          | 0.9493   | 0.7074 | 0.8373    | 0.6123 |
| 0.2842        | 4.0   | 728  | 0.1302          | 0.9568   | 0.7742 | 0.8116    | 0.7401 |
| 0.2842        | 5.0   | 910  | 0.1164          | 0.9652   | 0.8192 | 0.8524    | 0.7885 |
| 0.1025        | 6.0   | 1092 | 0.1193          | 0.9634   | 0.8135 | 0.8303    | 0.7974 |
| 0.1025        | 7.0   | 1274 | 0.1242          | 0.9648   | 0.8214 | 0.8326    | 0.8106 |
| 0.1025        | 8.0   | 1456 | 0.1266          | 0.9626   | 0.8098 | 0.8227    | 0.7974 |
| 0.0376        | 9.0   | 1638 | 0.1259          | 0.9648   | 0.8206 | 0.8356    | 0.8062 |
| 0.0376        | 10.0  | 1820 | 0.1269          | 0.9661   | 0.8285 | 0.8378    | 0.8194 |
| 0.023         | 11.0  | 2002 | 0.1290          | 0.9661   | 0.8293 | 0.8348    | 0.8238 |
| 0.023         | 12.0  | 2184 | 0.1312          | 0.9630   | 0.8150 | 0.8150    | 0.8150 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1