---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_thresh07_fold4
  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_thresh07_fold4

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: 9.5003
- Precision Samples: 0.1588
- Recall Samples: 0.5436
- F1 Samples: 0.2269
- Precision Macro: 0.8128
- Recall Macro: 0.3798
- F1 Macro: 0.2888
- Precision Micro: 0.1456
- Recall Micro: 0.4556
- F1 Micro: 0.2207
- Precision Weighted: 0.5240
- Recall Weighted: 0.4556
- F1 Weighted: 0.1534

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 10.3744       | 1.0   | 19   | 10.7628         | 0.2690            | 0.1931         | 0.1931     | 0.9912          | 0.2441       | 0.2372   | 0.2090          | 0.0778       | 0.1134   | 0.9363             | 0.0778          | 0.0277      |
| 10.0961       | 2.0   | 38   | 10.4140         | 0.1563            | 0.2989         | 0.1865     | 0.9616          | 0.2687       | 0.2434   | 0.1537          | 0.1806       | 0.1660   | 0.8264             | 0.1806          | 0.0536      |
| 9.7494        | 3.0   | 57   | 10.2283         | 0.1244            | 0.3615         | 0.1701     | 0.9252          | 0.2917       | 0.2499   | 0.1213          | 0.2472       | 0.1627   | 0.7176             | 0.2472          | 0.0745      |
| 9.5342        | 4.0   | 76   | 10.0846         | 0.1375            | 0.4211         | 0.1914     | 0.9118          | 0.3172       | 0.2538   | 0.1304          | 0.3278       | 0.1866   | 0.6833             | 0.3278          | 0.0860      |
| 9.4527        | 5.0   | 95   | 9.8924          | 0.1393            | 0.4450         | 0.1954     | 0.8907          | 0.3274       | 0.2559   | 0.1305          | 0.3528       | 0.1905   | 0.6556             | 0.3528          | 0.0911      |
| 8.9545        | 6.0   | 114  | 9.7473          | 0.1500            | 0.4846         | 0.2113     | 0.8720          | 0.3485       | 0.2719   | 0.1398          | 0.3944       | 0.2064   | 0.6157             | 0.3944          | 0.1235      |
| 8.7472        | 7.0   | 133  | 9.6448          | 0.1705            | 0.5144         | 0.2317     | 0.8316          | 0.3604       | 0.2813   | 0.1522          | 0.4222       | 0.2237   | 0.5439             | 0.4222          | 0.1456      |
| 8.2567        | 8.0   | 152  | 9.5645          | 0.1648            | 0.5353         | 0.2314     | 0.8158          | 0.3752       | 0.2889   | 0.1497          | 0.4444       | 0.2239   | 0.5282             | 0.4444          | 0.1518      |
| 8.7461        | 9.0   | 171  | 9.5190          | 0.1593            | 0.5387         | 0.2270     | 0.8004          | 0.3789       | 0.2871   | 0.1467          | 0.45         | 0.2213   | 0.5041             | 0.45            | 0.1474      |
| 8.5203        | 10.0  | 190  | 9.5003          | 0.1588            | 0.5436         | 0.2269     | 0.8128          | 0.3798       | 0.2888   | 0.1456          | 0.4556       | 0.2207   | 0.5240             | 0.4556          | 0.1534      |


### Framework versions

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