---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-large
tags:
- generated_from_trainer
model-index:
- name: deberta-large-semeval25_EN08_fold5
  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-large-semeval25_EN08_fold5

This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 7.7182
- Precision Samples: 0.1208
- Recall Samples: 0.8208
- F1 Samples: 0.2037
- Precision Macro: 0.3884
- Recall Macro: 0.6861
- F1 Macro: 0.2590
- Precision Micro: 0.1199
- Recall Micro: 0.7958
- F1 Micro: 0.2083
- Precision Weighted: 0.2373
- Recall Weighted: 0.7958
- F1 Weighted: 0.2493

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 8.4241        | 1.0   | 73   | 9.1963          | 0.1263            | 0.4598         | 0.1863     | 0.8558          | 0.3082       | 0.2345   | 0.1268          | 0.3514       | 0.1863   | 0.5821             | 0.3514          | 0.1117      |
| 9.9703        | 2.0   | 146  | 8.5160          | 0.1313            | 0.6118         | 0.1989     | 0.7084          | 0.4108       | 0.2495   | 0.1110          | 0.5495       | 0.1848   | 0.4273             | 0.5495          | 0.1497      |
| 8.6571        | 3.0   | 219  | 8.3760          | 0.1104            | 0.6956         | 0.1813     | 0.5869          | 0.4853       | 0.2363   | 0.1057          | 0.6366       | 0.1814   | 0.3062             | 0.6366          | 0.1831      |
| 9.387         | 4.0   | 292  | 8.1585          | 0.1134            | 0.7748         | 0.1885     | 0.5228          | 0.6063       | 0.2487   | 0.1050          | 0.7447       | 0.1840   | 0.2682             | 0.7447          | 0.2017      |
| 8.4583        | 5.0   | 365  | 8.1996          | 0.1173            | 0.7660         | 0.1960     | 0.4457          | 0.6482       | 0.2512   | 0.1156          | 0.7417       | 0.2001   | 0.2496             | 0.7417          | 0.2253      |
| 6.3786        | 6.0   | 438  | 7.6840          | 0.1057            | 0.8007         | 0.1802     | 0.4090          | 0.6701       | 0.2410   | 0.1031          | 0.7838       | 0.1822   | 0.2405             | 0.7838          | 0.2289      |
| 8.2131        | 7.0   | 511  | 7.8402          | 0.1154            | 0.8003         | 0.1953     | 0.3992          | 0.6695       | 0.2514   | 0.1125          | 0.7688       | 0.1963   | 0.2317             | 0.7688          | 0.2324      |
| 6.8285        | 8.0   | 584  | 7.7532          | 0.1177            | 0.8106         | 0.1991     | 0.3970          | 0.6775       | 0.2552   | 0.1173          | 0.7808       | 0.2040   | 0.2350             | 0.7808          | 0.2416      |
| 5.5413        | 9.0   | 657  | 7.7258          | 0.1201            | 0.8140         | 0.2027     | 0.3872          | 0.6811       | 0.2571   | 0.1187          | 0.7838       | 0.2062   | 0.2364             | 0.7838          | 0.2474      |
| 5.9931        | 10.0  | 730  | 7.7182          | 0.1208            | 0.8208         | 0.2037     | 0.3884          | 0.6861       | 0.2590   | 0.1199          | 0.7958       | 0.2083   | 0.2373             | 0.7958          | 0.2493      |


### Framework versions

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