---
license: mit
tags:
- generated_from_trainer
metrics:
- f1
language:
- de
model-index:
- name: BACnet-Klassifizierung-Raumlufttechnik-bert-base-german-cased
  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. -->

# BACnet-Klassifizierung-Raumlufttechnik-bert-base-german-cased

This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the [gart-labor](https://huggingface.co/gart-labor) "klassifizierung_rlt_v2" dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0597
- F1: [0.98461538 0.66666667 1.         1.         1.         1.
 0.94736842 1.         1.         1.         1.         0.99115044
 0.85714286 1.         1.         1.         1.         0.  1.        ]

## Model description

This model makes it possible to classify the components of room ventilation technology described with the BACnet standard into different categories. 
The model is based on a German-language data set.

## Intended uses & limitations

The model divides descriptive texts into the following ventilation technology categories:
Exhaust air, Exhaust air filter, Exhaust air fan, Other, Outside air damper, Humidifier, Fire protection, Fire damper, Heater, Cooler, Reheater, AHU, Room, Fan, Preheater, Heat recovery, Supply air, Supply air filter and supply air fan.

## Training and evaluation data

The model is based on a German-language data set.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10.0

### Training results

| Training Loss | Epoch | Step | Validation Loss | F1                                                                                                                                                                                                            |
|:-------------:|:-----:|:----:|:---------------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
| 2.1097        | 0.99  | 18   | 1.1253          | [0.77966102 0.         0.7037037  0.         0.875      0.57142857
 0.         0.94736842 0.         0.92857143 0.         0.85496183
 0.         1.         0.69230769 0.         0.79569892 0.
 0.53333333] |
| 0.8677        | 1.99  | 36   | 0.4032          | [0.98461538 0.         0.91666667 0.90909091 1.         1.
- Transformers 4.21.1
- Pytorch 1.12.0+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1