---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: deberta_rse
  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. -->

# deberta_rse

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0243
- Accuracy: 0.9961
- F1: 0.9961

## 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: 16
- eval_batch_size: 16
- seed: 42
- 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
- num_epochs: 15
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.8808        | 1.0   | 276  | 0.2620          | 0.9237   | 0.9242 |
| 0.3108        | 2.0   | 552  | 0.2273          | 0.9471   | 0.9470 |
| 0.2543        | 3.0   | 828  | 0.1193          | 0.9700   | 0.9700 |
| 0.1788        | 4.0   | 1104 | 0.1284          | 0.9702   | 0.9705 |
| 0.1296        | 5.0   | 1380 | 0.0549          | 0.9891   | 0.9891 |
| 0.0669        | 6.0   | 1656 | 0.0398          | 0.9927   | 0.9927 |
| 0.0658        | 7.0   | 1932 | 0.0299          | 0.9957   | 0.9957 |
| 0.0379        | 8.0   | 2208 | 0.0216          | 0.9964   | 0.9964 |
| 0.0312        | 9.0   | 2484 | 0.0243          | 0.9961   | 0.9961 |


### Framework versions

- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.1
- Tokenizers 0.21.0