---
license: mit
base_model: dathi103/bert-job-german
tags:
- generated_from_trainer
model-index:
- name: gerskill-bert-job
  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. -->

# gerskill-bert-job

This model is a fine-tuned version of [dathi103/bert-job-german](https://huggingface.co/dathi103/bert-job-german) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1565
- Hard: {'precision': 0.683698296836983, 'recall': 0.771978021978022, 'f1': 0.7251612903225807, 'number': 364}
- Soft: {'precision': 0.68, 'recall': 0.7727272727272727, 'f1': 0.7234042553191491, 'number': 66}
- Overall Precision: 0.6831
- Overall Recall: 0.7721
- Overall F1: 0.7249
- Overall Accuracy: 0.9584

## 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Hard                                                                                                     | Soft                                                                                                    | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
| No log        | 1.0   | 178  | 0.1225          | {'precision': 0.5902439024390244, 'recall': 0.6648351648351648, 'f1': 0.6253229974160206, 'number': 364} | {'precision': 0.625, 'recall': 0.6060606060606061, 'f1': 0.6153846153846154, 'number': 66}              | 0.5949            | 0.6558         | 0.6239     | 0.9537           |
| No log        | 2.0   | 356  | 0.1176          | {'precision': 0.6282973621103117, 'recall': 0.7197802197802198, 'f1': 0.6709346991037132, 'number': 364} | {'precision': 0.6351351351351351, 'recall': 0.7121212121212122, 'f1': 0.6714285714285715, 'number': 66} | 0.6293            | 0.7186         | 0.6710     | 0.9563           |
| 0.1349        | 3.0   | 534  | 0.1361          | {'precision': 0.6747572815533981, 'recall': 0.7637362637362637, 'f1': 0.7164948453608249, 'number': 364} | {'precision': 0.620253164556962, 'recall': 0.7424242424242424, 'f1': 0.6758620689655171, 'number': 66}  | 0.6660            | 0.7605         | 0.7101     | 0.9591           |
| 0.1349        | 4.0   | 712  | 0.1499          | {'precision': 0.672289156626506, 'recall': 0.7664835164835165, 'f1': 0.7163029525032093, 'number': 364}  | {'precision': 0.6944444444444444, 'recall': 0.7575757575757576, 'f1': 0.7246376811594203, 'number': 66} | 0.6756            | 0.7651         | 0.7176     | 0.9587           |
| 0.1349        | 5.0   | 890  | 0.1565          | {'precision': 0.683698296836983, 'recall': 0.771978021978022, 'f1': 0.7251612903225807, 'number': 364}   | {'precision': 0.68, 'recall': 0.7727272727272727, 'f1': 0.7234042553191491, 'number': 66}               | 0.6831            | 0.7721         | 0.7249     | 0.9584           |


### Framework versions

- Transformers 4.38.1
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2