---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_narratives09_fold1
  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_narratives09_fold1

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: 4.1440
- Precision Samples: 0.3489
- Recall Samples: 0.7666
- F1 Samples: 0.4484
- Precision Macro: 0.6713
- Recall Macro: 0.4701
- F1 Macro: 0.2642
- Precision Micro: 0.3133
- Recall Micro: 0.7518
- F1 Micro: 0.4423
- Precision Weighted: 0.4454
- Recall Weighted: 0.7518
- F1 Weighted: 0.3929

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 5.3976        | 1.0   | 19   | 5.3094          | 1.0               | 0.0            | 0.0        | 1.0             | 0.0476       | 0.0476   | 1.0             | 0.0          | 0.0      | 1.0                | 0.0             | 0.0         |
| 5.0729        | 2.0   | 38   | 5.0051          | 0.2991            | 0.4812         | 0.3465     | 0.8683          | 0.2245       | 0.1355   | 0.3056          | 0.4496       | 0.3639   | 0.6682             | 0.4496          | 0.2244      |
| 4.799         | 3.0   | 57   | 4.7268          | 0.3634            | 0.5035         | 0.3759     | 0.8348          | 0.2364       | 0.1574   | 0.3291          | 0.4640       | 0.3851   | 0.6206             | 0.4640          | 0.2617      |
| 4.4077        | 4.0   | 76   | 4.5072          | 0.3846            | 0.6225         | 0.4435     | 0.7933          | 0.3190       | 0.2043   | 0.3383          | 0.5755       | 0.4261   | 0.5591             | 0.5755          | 0.3232      |
| 4.1905        | 5.0   | 95   | 4.3919          | 0.4006            | 0.6444         | 0.4575     | 0.7484          | 0.3320       | 0.2140   | 0.3395          | 0.5935       | 0.4319   | 0.5242             | 0.5935          | 0.3411      |
| 4.1939        | 6.0   | 114  | 4.2724          | 0.3817            | 0.7296         | 0.4634     | 0.7094          | 0.4205       | 0.2478   | 0.3229          | 0.7050       | 0.4429   | 0.4663             | 0.7050          | 0.3791      |
| 3.9286        | 7.0   | 133  | 4.2600          | 0.3753            | 0.7336         | 0.4620     | 0.6853          | 0.4257       | 0.2568   | 0.3311          | 0.7050       | 0.4506   | 0.4556             | 0.7050          | 0.3882      |
| 3.8896        | 8.0   | 152  | 4.1871          | 0.3528            | 0.7581         | 0.4505     | 0.6713          | 0.4559       | 0.2625   | 0.3188          | 0.7374       | 0.4452   | 0.4462             | 0.7374          | 0.3929      |
| 3.993         | 9.0   | 171  | 4.1598          | 0.3525            | 0.7629         | 0.4503     | 0.6712          | 0.4645       | 0.2639   | 0.3170          | 0.7446       | 0.4447   | 0.4443             | 0.7446          | 0.3920      |
| 4.1424        | 10.0  | 190  | 4.1440          | 0.3489            | 0.7666         | 0.4484     | 0.6713          | 0.4701       | 0.2642   | 0.3133          | 0.7518       | 0.4423   | 0.4454             | 0.7518          | 0.3929      |


### Framework versions

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