README.md

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

# content

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3534
- Accuracy: 0.9252
- F1: 0.9160
- Precision: 0.9677
- Recall: 0.8696

## 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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|
| 0.0926        | 0.97  | 9    | 0.2219          | 0.9320   | 0.9275 | 0.9275    | 0.9275 |
| 0.0674        | 1.95  | 18   | 0.4954          | 0.8639   | 0.8305 | 1.0       | 0.7101 |
| 0.0295        | 2.92  | 27   | 0.2664          | 0.9320   | 0.9275 | 0.9275    | 0.9275 |
| 0.0478        | 4.0   | 37   | 0.3316          | 0.9116   | 0.9078 | 0.8889    | 0.9275 |
| 0.0377        | 4.86  | 45   | 0.3534          | 0.9252   | 0.9160 | 0.9677    | 0.8696 |


### Framework versions

- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2