---
library_name: transformers
license: mit
base_model: microsoft/deberta-v3-base
tags:
- generated_from_trainer
model-index:
- name: deberta-semeval25_EN08_CC_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. -->

# deberta-semeval25_EN08_CC_fold4

This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 9.2901
- Precision Samples: 0.2580
- Recall Samples: 0.6139
- F1 Samples: 0.3025
- Precision Macro: 0.8246
- Recall Macro: 0.3675
- F1 Macro: 0.2397
- Precision Micro: 0.2267
- Recall Micro: 0.4535
- F1 Micro: 0.3023
- Precision Weighted: 0.6457
- Recall Weighted: 0.4535
- F1 Weighted: 0.2035

## 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: 8
- eval_batch_size: 8
- 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 |
|:-------------:|:-----:|:----:|:---------------:|:-----------------:|:--------------:|:----------:|:---------------:|:------------:|:--------:|:---------------:|:------------:|:--------:|:------------------:|:---------------:|:-----------:|
| 8.5826        | 1.0   | 15   | 10.3420         | 1.0               | 0.0            | 0.0        | 1.0             | 0.1951       | 0.1951   | 1.0             | 0.0          | 0.0      | 1.0                | 0.0             | 0.0         |
| 8.6265        | 2.0   | 30   | 10.0401         | 0.2222            | 0.3833         | 0.2629     | 0.9437          | 0.2622       | 0.2216   | 0.2317          | 0.2209       | 0.2262   | 0.8171             | 0.2209          | 0.0948      |
| 7.4706        | 3.0   | 45   | 9.8509          | 0.2167            | 0.3278         | 0.1891     | 0.9180          | 0.2530       | 0.2189   | 0.1905          | 0.1860       | 0.1882   | 0.7653             | 0.1860          | 0.0844      |
| 7.3649        | 4.0   | 60   | 9.7126          | 0.3056            | 0.4333         | 0.2617     | 0.9250          | 0.2896       | 0.2308   | 0.2330          | 0.2791       | 0.2540   | 0.7841             | 0.2791          | 0.1163      |
| 6.8711        | 5.0   | 75   | 9.5275          | 0.4300            | 0.4222         | 0.2444     | 0.9056          | 0.2866       | 0.2368   | 0.25            | 0.2674       | 0.2584   | 0.6815             | 0.2674          | 0.1312      |
| 7.2056        | 6.0   | 90   | 9.4326          | 0.2260            | 0.4778         | 0.2542     | 0.8618          | 0.3154       | 0.2447   | 0.2090          | 0.3256       | 0.2545   | 0.6282             | 0.3256          | 0.1408      |
| 7.7788        | 7.0   | 105  | 9.6122          | 0.2333            | 0.5278         | 0.2710     | 0.8411          | 0.3407       | 0.2519   | 0.2162          | 0.3721       | 0.2735   | 0.6179             | 0.3721          | 0.1617      |
| 7.2763        | 8.0   | 120  | 9.3189          | 0.2293            | 0.5139         | 0.2608     | 0.8449          | 0.3382       | 0.2558   | 0.2138          | 0.3605       | 0.2684   | 0.6243             | 0.3605          | 0.1670      |
| 7.3285        | 9.0   | 135  | 9.2802          | 0.2552            | 0.6083         | 0.3031     | 0.8249          | 0.3650       | 0.2397   | 0.2331          | 0.4419       | 0.3052   | 0.6451             | 0.4419          | 0.2011      |
| 7.7699        | 10.0  | 150  | 9.2901          | 0.2580            | 0.6139         | 0.3025     | 0.8246          | 0.3675       | 0.2397   | 0.2267          | 0.4535       | 0.3023   | 0.6457             | 0.4535          | 0.2035      |


### Framework versions

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