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

This model is a fine-tuned version of [dathi103/bert-job-german-extended](https://huggingface.co/dathi103/bert-job-german-extended) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1171
- Hard: {'precision': 0.7376681614349776, 'recall': 0.8225, 'f1': 0.7777777777777777, 'number': 800}
- Soft: {'precision': 0.7541899441340782, 'recall': 0.8709677419354839, 'f1': 0.8083832335329341, 'number': 155}
- Overall Precision: 0.7404
- Overall Recall: 0.8304
- Overall F1: 0.7828
- Overall Accuracy: 0.9675

## 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   | 158  | 0.1042          | {'precision': 0.6269592476489029, 'recall': 0.75, 'f1': 0.6829823562891292, 'number': 800}   | {'precision': 0.6632124352331606, 'recall': 0.8258064516129032, 'f1': 0.735632183908046, 'number': 155}  | 0.6330            | 0.7623         | 0.6917     | 0.9604           |
| No log        | 2.0   | 316  | 0.0984          | {'precision': 0.6931567328918322, 'recall': 0.785, 'f1': 0.7362250879249707, 'number': 800}  | {'precision': 0.6084905660377359, 'recall': 0.832258064516129, 'f1': 0.7029972752043598, 'number': 155}  | 0.6771            | 0.7927         | 0.7303     | 0.9635           |
| No log        | 3.0   | 474  | 0.1017          | {'precision': 0.7263513513513513, 'recall': 0.80625, 'f1': 0.764218009478673, 'number': 800} | {'precision': 0.696969696969697, 'recall': 0.8903225806451613, 'f1': 0.7818696883852692, 'number': 155}  | 0.7210            | 0.8199         | 0.7673     | 0.9674           |
| 0.1083        | 4.0   | 632  | 0.1105          | {'precision': 0.7414187643020596, 'recall': 0.81, 'f1': 0.7741935483870969, 'number': 800}   | {'precision': 0.7653631284916201, 'recall': 0.8838709677419355, 'f1': 0.8203592814371258, 'number': 155} | 0.7455            | 0.8220         | 0.7819     | 0.9685           |
| 0.1083        | 5.0   | 790  | 0.1171          | {'precision': 0.7376681614349776, 'recall': 0.8225, 'f1': 0.7777777777777777, 'number': 800} | {'precision': 0.7541899441340782, 'recall': 0.8709677419354839, 'f1': 0.8083832335329341, 'number': 155} | 0.7404            | 0.8304         | 0.7828     | 0.9675           |


### Framework versions

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