---
library_name: transformers
license: mit
base_model: microsoft/mdeberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: mdeberta-semeval25_narratives09_maxf1_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_maxf1_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: 4.0204
- Precision Samples: 0.3603
- Recall Samples: 0.7663
- F1 Samples: 0.4556
- Precision Macro: 0.6906
- Recall Macro: 0.5586
- F1 Macro: 0.3769
- Precision Micro: 0.3165
- Recall Micro: 0.7293
- F1 Micro: 0.4414
- Precision Weighted: 0.4601
- Recall Weighted: 0.7293
- F1 Weighted: 0.3993

## 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   | 5.1744          | 1.0               | 0.0            | 0.0        | 1.0             | 0.1429       | 0.1429   | 1.0             | 0.0          | 0.0      | 1.0                | 0.0             | 0.0         |
| 4.8514        | 2.0   | 38   | 4.9269          | 0.2759            | 0.2532         | 0.2276     | 0.9377          | 0.2238       | 0.1873   | 0.2880          | 0.2068       | 0.2407   | 0.8409             | 0.2068          | 0.1109      |
| 5.1079        | 3.0   | 57   | 4.6308          | 0.3793            | 0.4853         | 0.3604     | 0.8762          | 0.3242       | 0.2396   | 0.3420          | 0.4474       | 0.3876   | 0.6961             | 0.4474          | 0.2402      |
| 4.5129        | 4.0   | 76   | 4.4135          | 0.3422            | 0.6197         | 0.4125     | 0.7822          | 0.4150       | 0.2908   | 0.3175          | 0.5789       | 0.4101   | 0.5507             | 0.5789          | 0.3086      |
| 4.3874        | 5.0   | 95   | 4.2916          | 0.3576            | 0.6623         | 0.4341     | 0.7168          | 0.4431       | 0.3203   | 0.3265          | 0.6015       | 0.4233   | 0.4756             | 0.6015          | 0.3449      |
| 4.0833        | 6.0   | 114  | 4.1434          | 0.3378            | 0.7416         | 0.4323     | 0.7113          | 0.5131       | 0.3405   | 0.2992          | 0.7030       | 0.4198   | 0.4708             | 0.7030          | 0.3689      |
| 3.9936        | 7.0   | 133  | 4.0974          | 0.3532            | 0.7462         | 0.4496     | 0.6927          | 0.5341       | 0.3701   | 0.3160          | 0.7068       | 0.4367   | 0.4609             | 0.7068          | 0.3929      |
| 3.9677        | 8.0   | 152  | 4.0596          | 0.3606            | 0.7537         | 0.4543     | 0.6921          | 0.5484       | 0.3768   | 0.3193          | 0.7105       | 0.4406   | 0.4618             | 0.7105          | 0.3981      |
| 4.0104        | 9.0   | 171  | 4.0379          | 0.3547            | 0.7571         | 0.4524     | 0.6964          | 0.5523       | 0.3803   | 0.3177          | 0.7143       | 0.4398   | 0.4641             | 0.7143          | 0.3998      |
| 3.9613        | 10.0  | 190  | 4.0204          | 0.3603            | 0.7663         | 0.4556     | 0.6906          | 0.5586       | 0.3769   | 0.3165          | 0.7293       | 0.4414   | 0.4601             | 0.7293          | 0.3993      |


### Framework versions

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