---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_narratives_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_narratives_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: 3.7738
- Precision Samples: 0.3380
- Recall Samples: 0.8009
- F1 Samples: 0.4403
- Precision Macro: 0.6671
- Recall Macro: 0.5160
- F1 Macro: 0.2621
- Precision Micro: 0.2894
- Recall Micro: 0.7843
- F1 Micro: 0.4228
- Precision Weighted: 0.4553
- Recall Weighted: 0.7843
- F1 Weighted: 0.3823

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 5.7927        | 1.0   | 19   | 4.9876          | 0.2483            | 0.1091         | 0.1382     | 0.9632          | 0.0952       | 0.0652   | 0.2270          | 0.1255       | 0.1616   | 0.9030             | 0.1255          | 0.0464      |
| 5.0898        | 2.0   | 38   | 4.7749          | 0.2379            | 0.5017         | 0.3043     | 0.8531          | 0.2349       | 0.1180   | 0.2254          | 0.4588       | 0.3023   | 0.6408             | 0.4588          | 0.1736      |
| 5.1841        | 3.0   | 57   | 4.4511          | 0.3230            | 0.6657         | 0.4132     | 0.7709          | 0.3350       | 0.1954   | 0.3002          | 0.6039       | 0.4010   | 0.5402             | 0.6039          | 0.3045      |
| 4.8203        | 4.0   | 76   | 4.2527          | 0.3084            | 0.7145         | 0.4023     | 0.7292          | 0.4023       | 0.2114   | 0.2723          | 0.6824       | 0.3893   | 0.4982             | 0.6824          | 0.3252      |
| 4.6179        | 5.0   | 95   | 4.0366          | 0.3637            | 0.7630         | 0.4515     | 0.7081          | 0.4523       | 0.2479   | 0.3008          | 0.7373       | 0.4273   | 0.4834             | 0.7373          | 0.3739      |
| 4.4285        | 6.0   | 114  | 3.9329          | 0.3333            | 0.7917         | 0.4395     | 0.6691          | 0.5050       | 0.2637   | 0.2901          | 0.7725       | 0.4218   | 0.4555             | 0.7725          | 0.3812      |
| 4.094         | 7.0   | 133  | 3.8543          | 0.3329            | 0.8044         | 0.4390     | 0.6657          | 0.5146       | 0.2607   | 0.2899          | 0.7843       | 0.4233   | 0.4555             | 0.7843          | 0.3826      |
| 4.1865        | 8.0   | 152  | 3.8027          | 0.3463            | 0.8113         | 0.4497     | 0.6703          | 0.5162       | 0.2663   | 0.2987          | 0.7882       | 0.4332   | 0.4619             | 0.7882          | 0.3909      |
| 4.3648        | 9.0   | 171  | 3.7872          | 0.3388            | 0.8078         | 0.4420     | 0.6670          | 0.5176       | 0.2625   | 0.2896          | 0.7882       | 0.4236   | 0.4545             | 0.7882          | 0.3824      |
| 3.9481        | 10.0  | 190  | 3.7738          | 0.3380            | 0.8009         | 0.4403     | 0.6671          | 0.5160       | 0.2621   | 0.2894          | 0.7843       | 0.4228   | 0.4553             | 0.7843          | 0.3823      |


### Framework versions

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