|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: bert-base-german-cased-noisy-pretrain-fine-tuned |
|
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. --> |
|
|
|
# bert-base-german-cased-noisy-pretrain-fine-tuned |
|
|
|
This model is a fine-tuned version of [tbosse/bert-base-german-cased-finetuned-subj_preTrained_with_noisyData](https://huggingface.co/tbosse/bert-base-german-cased-finetuned-subj_preTrained_with_noisyData) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2925 |
|
- Precision: 0.7933 |
|
- Recall: 0.7457 |
|
- F1: 0.7688 |
|
- Accuracy: 0.9147 |
|
|
|
## 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: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| No log | 1.0 | 33 | 0.3093 | 0.7456 | 0.6029 | 0.6667 | 0.8808 | |
|
| No log | 2.0 | 66 | 0.2587 | 0.7774 | 0.7286 | 0.7522 | 0.9078 | |
|
| No log | 3.0 | 99 | 0.2529 | 0.7775 | 0.7686 | 0.7730 | 0.9136 | |
|
| No log | 4.0 | 132 | 0.2598 | 0.8063 | 0.7257 | 0.7639 | 0.9147 | |
|
| No log | 5.0 | 165 | 0.2783 | 0.7927 | 0.7429 | 0.7670 | 0.9159 | |
|
| No log | 6.0 | 198 | 0.2899 | 0.8019 | 0.74 | 0.7697 | 0.9165 | |
|
| No log | 7.0 | 231 | 0.2925 | 0.7933 | 0.7457 | 0.7688 | 0.9147 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.19.2 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.2.1 |
|
- Tokenizers 0.12.1 |
|
|
