---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: deberta-v3-large-csb
  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-v3-large-csb

This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2608
- Accuracy: 0.8813
- F1: 0.8805

## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.4418        | 1.0   | 228  | 0.3463          | 0.8396   | 0.8397 |
| 0.3375        | 2.0   | 456  | 0.2615          | 0.8703   | 0.8705 |
| 0.2706        | 3.0   | 684  | 0.2608          | 0.8813   | 0.8805 |
| 0.2298        | 4.0   | 912  | 0.3437          | 0.8791   | 0.8780 |
| 0.1609        | 5.0   | 1140 | 0.6636          | 0.8132   | 0.8050 |
| 0.1665        | 6.0   | 1368 | 0.5089          | 0.8791   | 0.8791 |
| 0.099         | 7.0   | 1596 | 0.6432          | 0.8813   | 0.8804 |
| 0.075         | 8.0   | 1824 | 0.7101          | 0.8747   | 0.8741 |
| 0.044         | 9.0   | 2052 | 0.7694          | 0.8681   | 0.8673 |
| 0.0478        | 10.0  | 2280 | 0.8504          | 0.8593   | 0.8573 |


### Framework versions

- Transformers 4.57.3
- Pytorch 2.2.1
- Datasets 4.4.1
- Tokenizers 0.22.1