|
--- |
|
license: mit |
|
base_model: bert-base-german-cased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: Germeval24StageTask2 |
|
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. --> |
|
|
|
# Germeval24StageTask2 |
|
|
|
This model is a fine-tuned version of [bert-base-german-cased](https://huggingface.co/bert-base-german-cased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4272 |
|
- Precision: 1.0 |
|
- Recall: 1.0 |
|
- F1: 1.0 |
|
- Accuracy: 0.8575 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|:--------:| |
|
| No log | 1.0 | 150 | 0.4852 | 1.0 | 1.0 | 1.0 | 0.8099 | |
|
| No log | 2.0 | 300 | 0.4305 | 1.0 | 1.0 | 1.0 | 0.8499 | |
|
| No log | 3.0 | 450 | 0.4272 | 1.0 | 1.0 | 1.0 | 0.8575 | |
|
| 0.4985 | 4.0 | 600 | 0.4776 | 1.0 | 1.0 | 1.0 | 0.8510 | |
|
| 0.4985 | 5.0 | 750 | 0.5090 | 1.0 | 1.0 | 1.0 | 0.8629 | |
|
| 0.4985 | 6.0 | 900 | 0.5940 | 1.0 | 1.0 | 1.0 | 0.8521 | |
|
| 0.1257 | 7.0 | 1050 | 0.5592 | 1.0 | 1.0 | 1.0 | 0.8618 | |
|
| 0.1257 | 8.0 | 1200 | 0.6132 | 1.0 | 1.0 | 1.0 | 0.8521 | |
|
| 0.1257 | 9.0 | 1350 | 0.6580 | 1.0 | 1.0 | 1.0 | 0.8639 | |
|
| 0.0448 | 10.0 | 1500 | 0.6727 | 1.0 | 1.0 | 1.0 | 0.8629 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
