---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_maxf1_fold3
  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. -->

# mdeberta-semeval25_maxf1_fold3

This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 9.3380
- Precision Samples: 0.1633
- Recall Samples: 0.5122
- F1 Samples: 0.2311
- Precision Macro: 0.8671
- Recall Macro: 0.2933
- F1 Macro: 0.2022
- Precision Micro: 0.1506
- Recall Micro: 0.3994
- F1 Micro: 0.2188
- Precision Weighted: 0.6317
- Recall Weighted: 0.3994
- F1 Weighted: 0.1249

## 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: 32
- eval_batch_size: 32
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 11.0696       | 1.0   | 19   | 10.6040         | 1.0               | 0.0            | 0.0        | 1.0             | 0.1556       | 0.1556   | 1.0             | 0.0          | 0.0      | 1.0                | 0.0             | 0.0         |
| 10.193        | 2.0   | 38   | 10.2581         | 0.1747            | 0.2540         | 0.1918     | 0.9816          | 0.1789       | 0.1641   | 0.1753          | 0.1445       | 0.1584   | 0.8838             | 0.1445          | 0.0480      |
| 9.6612        | 3.0   | 57   | 10.0671         | 0.1425            | 0.2939         | 0.1781     | 0.9714          | 0.1889       | 0.1637   | 0.1456          | 0.1700       | 0.1569   | 0.8577             | 0.1700          | 0.0472      |
| 9.0942        | 4.0   | 76   | 9.8758          | 0.1474            | 0.3411         | 0.1891     | 0.9189          | 0.2076       | 0.1690   | 0.1385          | 0.2181       | 0.1694   | 0.7494             | 0.2181          | 0.0607      |
| 9.3042        | 5.0   | 95   | 9.6689          | 0.1613            | 0.4720         | 0.2241     | 0.8971          | 0.2654       | 0.1874   | 0.1473          | 0.3598       | 0.2091   | 0.6810             | 0.3598          | 0.1058      |
| 9.0703        | 6.0   | 114  | 9.5397          | 0.1626            | 0.4743         | 0.2237     | 0.8953          | 0.2670       | 0.1855   | 0.1471          | 0.3626       | 0.2093   | 0.6781             | 0.3626          | 0.1029      |
| 9.5375        | 7.0   | 133  | 9.4382          | 0.1630            | 0.4948         | 0.2286     | 0.8764          | 0.2833       | 0.1983   | 0.1506          | 0.3853       | 0.2166   | 0.6480             | 0.3853          | 0.1220      |
| 8.4717        | 8.0   | 152  | 9.3612          | 0.1642            | 0.5086         | 0.2317     | 0.8738          | 0.2881       | 0.1987   | 0.1481          | 0.3966       | 0.2157   | 0.6417             | 0.3966          | 0.1207      |
| 9.1265        | 9.0   | 171  | 9.3158          | 0.1621            | 0.5051         | 0.2286     | 0.8604          | 0.2921       | 0.1978   | 0.1478          | 0.3994       | 0.2158   | 0.6221             | 0.3994          | 0.1195      |
| 9.0143        | 10.0  | 190  | 9.3380          | 0.1633            | 0.5122         | 0.2311     | 0.8671          | 0.2933       | 0.2022   | 0.1506          | 0.3994       | 0.2188   | 0.6317             | 0.3994          | 0.1249      |


### Framework versions

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