---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: deberta-semeval25_EN08_CC_fold2
  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-semeval25_EN08_CC_fold2

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: 6.8873
- Precision Samples: 0.1892
- Recall Samples: 0.5700
- F1 Samples: 0.2529
- Precision Macro: 0.8502
- Recall Macro: 0.5481
- F1 Macro: 0.4558
- Precision Micro: 0.2086
- Recall Micro: 0.4203
- F1 Micro: 0.2788
- Precision Weighted: 0.6329
- Recall Weighted: 0.4203
- F1 Weighted: 0.2177

## 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: 8
- eval_batch_size: 8
- 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: 10

### Training results

| Training Loss | Epoch | Step | Validation Loss | Precision Samples | Recall Samples | F1 Samples | Precision Macro | Recall Macro | F1 Macro | Precision Micro | Recall Micro | F1 Micro | Precision Weighted | Recall Weighted | F1 Weighted |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 9.3158        | 1.0   | 15   | 8.1700          | 0.8333            | 0.1278         | 0.1389     | 0.9878          | 0.4024       | 0.4024   | 0.5             | 0.0725       | 0.1266   | 0.9275             | 0.0725          | 0.0725      |
| 9.1274        | 2.0   | 30   | 7.7022          | 0.2500            | 0.4444         | 0.3033     | 0.9462          | 0.4530       | 0.4198   | 0.2727          | 0.3043       | 0.2877   | 0.7473             | 0.3043          | 0.1448      |
| 8.3785        | 3.0   | 45   | 7.4694          | 0.2078            | 0.4772         | 0.2741     | 0.9072          | 0.4890       | 0.4315   | 0.2232          | 0.3623       | 0.2762   | 0.6906             | 0.3623          | 0.1636      |
| 8.317         | 4.0   | 60   | 7.2468          | 0.4567            | 0.4444         | 0.2226     | 0.9037          | 0.4617       | 0.4269   | 0.2333          | 0.3043       | 0.2642   | 0.7035             | 0.3043          | 0.1741      |
| 6.5284        | 5.0   | 75   | 7.2364          | 0.4400            | 0.4333         | 0.2026     | 0.9047          | 0.4592       | 0.4274   | 0.2105          | 0.2899       | 0.2439   | 0.7075             | 0.2899          | 0.1751      |
| 7.3718        | 6.0   | 90   | 7.0546          | 0.2717            | 0.4756         | 0.2479     | 0.8863          | 0.5156       | 0.4387   | 0.2252          | 0.3623       | 0.2778   | 0.6995             | 0.3623          | 0.1893      |
| 7.9602        | 7.0   | 105  | 6.9761          | 0.2278            | 0.5172         | 0.2535     | 0.8724          | 0.5272       | 0.4464   | 0.2109          | 0.3913       | 0.2741   | 0.6745             | 0.3913          | 0.2039      |
| 7.905         | 8.0   | 120  | 6.9036          | 0.1914            | 0.5700         | 0.2561     | 0.8506          | 0.5481       | 0.4564   | 0.2117          | 0.4203       | 0.2816   | 0.6331             | 0.4203          | 0.2181      |
| 7.4649        | 9.0   | 135  | 6.8797          | 0.1892            | 0.5811         | 0.2598     | 0.8503          | 0.5505       | 0.4564   | 0.2128          | 0.4348       | 0.2857   | 0.6328             | 0.4348          | 0.2208      |
| 7.3108        | 10.0  | 150  | 6.8873          | 0.1892            | 0.5700         | 0.2529     | 0.8502          | 0.5481       | 0.4558   | 0.2086          | 0.4203       | 0.2788   | 0.6329             | 0.4203          | 0.2177      |


### Framework versions

- Transformers 4.46.0
- Pytorch 2.3.1
- Datasets 2.21.0
- Tokenizers 0.20.1