---
base_model: microsoft/mpnet-base
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: mpnet-base-airlines-news-multi-label
  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. -->

# mpnet-base-airlines-news-multi-label

This model is a fine-tuned version of [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2478
- F1: 0.8938
- Roc Auc: 0.6465

## 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: 7e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 40

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
| No log        | 1.0   | 57   | 0.3726          | 0.8319 | 0.5     |
| No log        | 2.0   | 114  | 0.3361          | 0.8319 | 0.5     |
| No log        | 3.0   | 171  | 0.3303          | 0.8319 | 0.5     |
| No log        | 4.0   | 228  | 0.3249          | 0.8319 | 0.5     |
| No log        | 5.0   | 285  | 0.3188          | 0.8319 | 0.5     |
| No log        | 6.0   | 342  | 0.3141          | 0.8319 | 0.5     |
| No log        | 7.0   | 399  | 0.3089          | 0.8319 | 0.5     |
| No log        | 8.0   | 456  | 0.3042          | 0.8319 | 0.5     |
| 0.3595        | 9.0   | 513  | 0.2997          | 0.8319 | 0.5     |
| 0.3595        | 10.0  | 570  | 0.2940          | 0.8319 | 0.5     |
| 0.3595        | 11.0  | 627  | 0.2898          | 0.8319 | 0.5     |
| 0.3595        | 12.0  | 684  | 0.2856          | 0.8463 | 0.5032  |
| 0.3595        | 13.0  | 741  | 0.2819          | 0.8593 | 0.5096  |
| 0.3595        | 14.0  | 798  | 0.2789          | 0.8600 | 0.5128  |
| 0.3595        | 15.0  | 855  | 0.2757          | 0.8701 | 0.5220  |
| 0.3595        | 16.0  | 912  | 0.2723          | 0.8733 | 0.5312  |
| 0.3595        | 17.0  | 969  | 0.2698          | 0.8733 | 0.5312  |
| 0.2983        | 18.0  | 1026 | 0.2670          | 0.8808 | 0.5629  |
| 0.2983        | 19.0  | 1083 | 0.2652          | 0.8814 | 0.5661  |
| 0.2983        | 20.0  | 1140 | 0.2630          | 0.8786 | 0.5744  |
| 0.2983        | 21.0  | 1197 | 0.2612          | 0.8807 | 0.5840  |
| 0.2983        | 22.0  | 1254 | 0.2596          | 0.8818 | 0.5900  |
| 0.2983        | 23.0  | 1311 | 0.2580          | 0.8841 | 0.6024  |
| 0.2983        | 24.0  | 1368 | 0.2562          | 0.8878 | 0.6153  |
| 0.2983        | 25.0  | 1425 | 0.2555          | 0.8851 | 0.6056  |
| 0.2983        | 26.0  | 1482 | 0.2544          | 0.8860 | 0.6088  |
| 0.2747        | 27.0  | 1539 | 0.2535          | 0.8868 | 0.6148  |
| 0.2747        | 28.0  | 1596 | 0.2527          | 0.8878 | 0.6153  |
| 0.2747        | 29.0  | 1653 | 0.2519          | 0.8869 | 0.6121  |
| 0.2747        | 30.0  | 1710 | 0.2512          | 0.8875 | 0.6180  |
| 0.2747        | 31.0  | 1767 | 0.2501          | 0.8900 | 0.6277  |
| 0.2747        | 32.0  | 1824 | 0.2495          | 0.8923 | 0.6401  |
| 0.2747        | 33.0  | 1881 | 0.2492          | 0.8907 | 0.6337  |
| 0.2747        | 34.0  | 1938 | 0.2488          | 0.8922 | 0.6401  |
| 0.2747        | 35.0  | 1995 | 0.2485          | 0.8915 | 0.6369  |
| 0.2633        | 36.0  | 2052 | 0.2480          | 0.8922 | 0.6401  |
| 0.2633        | 37.0  | 2109 | 0.2478          | 0.8938 | 0.6465  |
| 0.2633        | 38.0  | 2166 | 0.2477          | 0.8930 | 0.6433  |
| 0.2633        | 39.0  | 2223 | 0.2476          | 0.8938 | 0.6465  |
| 0.2633        | 40.0  | 2280 | 0.2476          | 0.8938 | 0.6465  |


### Framework versions

- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1