---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_maxf1_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. -->

# mdeberta-semeval25_maxf1_fold2

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: 8.8694
- Precision Samples: 0.1448
- Recall Samples: 0.4710
- F1 Samples: 0.2054
- Precision Macro: 0.8790
- Recall Macro: 0.3070
- F1 Macro: 0.2198
- Precision Micro: 0.1280
- Recall Micro: 0.3545
- F1 Micro: 0.1881
- Precision Weighted: 0.6566
- Recall Weighted: 0.3545
- F1 Weighted: 0.1024

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 10.355        | 1.0   | 19   | 9.8646          | 0.4690            | 0.1586         | 0.1586     | 0.9914          | 0.1974       | 0.1928   | 0.23            | 0.0697       | 0.1070   | 0.9300             | 0.0697          | 0.0322      |
| 10.0042       | 2.0   | 38   | 9.5711          | 0.1517            | 0.2663         | 0.1814     | 0.9710          | 0.2144       | 0.1962   | 0.1493          | 0.1515       | 0.1504   | 0.8541             | 0.1515          | 0.0453      |
| 9.8111        | 3.0   | 57   | 9.4447          | 0.1190            | 0.31           | 0.1625     | 0.9497          | 0.2248       | 0.1978   | 0.1202          | 0.1818       | 0.1448   | 0.7968             | 0.1818          | 0.0506      |
| 9.5882        | 4.0   | 76   | 9.3361          | 0.1149            | 0.3593         | 0.1645     | 0.9292          | 0.2427       | 0.2010   | 0.1124          | 0.2333       | 0.1517   | 0.7463             | 0.2333          | 0.0586      |
| 9.2717        | 5.0   | 95   | 9.2287          | 0.1179            | 0.3825         | 0.1684     | 0.8992          | 0.2584       | 0.2061   | 0.1135          | 0.2667       | 0.1593   | 0.6898             | 0.2667          | 0.0697      |
| 9.4865        | 6.0   | 114  | 9.1175          | 0.1358            | 0.4366         | 0.1948     | 0.9025          | 0.2876       | 0.2179   | 0.1253          | 0.3182       | 0.1798   | 0.6965             | 0.3182          | 0.0869      |
| 9.2006        | 7.0   | 133  | 8.9906          | 0.1428            | 0.4627         | 0.2029     | 0.8891          | 0.3008       | 0.2184   | 0.1275          | 0.3455       | 0.1863   | 0.6810             | 0.3455          | 0.0981      |
| 9.0527        | 8.0   | 152  | 8.9299          | 0.1434            | 0.4696         | 0.2040     | 0.8874          | 0.3057       | 0.2181   | 0.1271          | 0.3515       | 0.1866   | 0.6767             | 0.3515          | 0.0977      |
| 9.3313        | 9.0   | 171  | 8.8794          | 0.1450            | 0.4727         | 0.2053     | 0.8803          | 0.3092       | 0.2203   | 0.1280          | 0.3576       | 0.1885   | 0.6602             | 0.3576          | 0.1037      |
| 8.4989        | 10.0  | 190  | 8.8694          | 0.1448            | 0.4710         | 0.2054     | 0.8790          | 0.3070       | 0.2198   | 0.1280          | 0.3545       | 0.1881   | 0.6566             | 0.3545          | 0.1024      |


### Framework versions

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