---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_narratives09_fold5
  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_fold5

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: 4.0227
- Precision Samples: 0.3630
- Recall Samples: 0.7663
- F1 Samples: 0.4583
- Precision Macro: 0.6929
- Recall Macro: 0.5586
- F1 Macro: 0.3787
- Precision Micro: 0.3170
- Recall Micro: 0.7293
- F1 Micro: 0.4419
- Precision Weighted: 0.4618
- Recall Weighted: 0.7293
- F1 Weighted: 0.4006

## 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 5.5606        | 1.0   | 19   | 5.1743          | 1.0               | 0.0            | 0.0        | 1.0             | 0.1429       | 0.1429   | 1.0             | 0.0          | 0.0      | 1.0                | 0.0             | 0.0         |
| 4.8513        | 2.0   | 38   | 4.9270          | 0.2759            | 0.2532         | 0.2276     | 0.9372          | 0.2238       | 0.1869   | 0.2865          | 0.2068       | 0.2402   | 0.8398             | 0.2068          | 0.1101      |
| 5.1086        | 3.0   | 57   | 4.6316          | 0.3810            | 0.4853         | 0.3601     | 0.8763          | 0.3242       | 0.2396   | 0.3420          | 0.4474       | 0.3876   | 0.6961             | 0.4474          | 0.2403      |
| 4.5134        | 4.0   | 76   | 4.4138          | 0.3413            | 0.6266         | 0.4146     | 0.7828          | 0.4166       | 0.2917   | 0.3196          | 0.5827       | 0.4128   | 0.5521             | 0.5827          | 0.3108      |
| 4.3876        | 5.0   | 95   | 4.2907          | 0.3599            | 0.6644         | 0.4357     | 0.7174          | 0.4444       | 0.3230   | 0.3259          | 0.6015       | 0.4227   | 0.4753             | 0.6015          | 0.3464      |
| 4.084         | 6.0   | 114  | 4.1465          | 0.3372            | 0.7364         | 0.4312     | 0.7116          | 0.5145       | 0.3409   | 0.2987          | 0.7030       | 0.4193   | 0.4704             | 0.7030          | 0.3684      |
| 3.9969        | 7.0   | 133  | 4.0975          | 0.3583            | 0.7479         | 0.4546     | 0.7007          | 0.5368       | 0.3753   | 0.3198          | 0.7105       | 0.4411   | 0.4677             | 0.7105          | 0.3978      |
| 3.9677        | 8.0   | 152  | 4.0623          | 0.3605            | 0.7543         | 0.4564     | 0.6912          | 0.5472       | 0.3758   | 0.3220          | 0.7105       | 0.4431   | 0.4631             | 0.7105          | 0.3995      |
| 4.0107        | 9.0   | 171  | 4.0401          | 0.3565            | 0.7571         | 0.4538     | 0.6965          | 0.5523       | 0.3805   | 0.3188          | 0.7143       | 0.4408   | 0.4649             | 0.7143          | 0.4006      |
| 3.9591        | 10.0  | 190  | 4.0227          | 0.3630            | 0.7663         | 0.4583     | 0.6929          | 0.5586       | 0.3787   | 0.3170          | 0.7293       | 0.4419   | 0.4618             | 0.7293          | 0.4006      |


### Framework versions

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