|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
base_model: distilbert-base-cased |
|
model-index: |
|
- name: distilbert-bpmn |
|
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. --> |
|
|
|
# distilbert-bpmn |
|
|
|
This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3311 |
|
- Precision: 0.7852 |
|
- Recall: 0.8375 |
|
- F1: 0.8105 |
|
- Accuracy: 0.9275 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 15 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:| |
|
| 2.0392 | 1.0 | 12 | 1.5999 | 0.2162 | 0.2333 | 0.2244 | 0.5017 | |
|
| 1.3439 | 2.0 | 24 | 1.0197 | 0.3786 | 0.4875 | 0.4262 | 0.7133 | |
|
| 0.8403 | 3.0 | 36 | 0.6398 | 0.5664 | 0.675 | 0.6160 | 0.8333 | |
|
| 0.4941 | 4.0 | 48 | 0.4637 | 0.6775 | 0.7792 | 0.7248 | 0.8765 | |
|
| 0.3227 | 5.0 | 60 | 0.3701 | 0.7262 | 0.7958 | 0.7594 | 0.9041 | |
|
| 0.2206 | 6.0 | 72 | 0.3286 | 0.75 | 0.8125 | 0.78 | 0.9231 | |
|
| 0.1762 | 7.0 | 84 | 0.3330 | 0.7597 | 0.8167 | 0.7871 | 0.9180 | |
|
| 0.1261 | 8.0 | 96 | 0.3159 | 0.7952 | 0.825 | 0.8098 | 0.9266 | |
|
| 0.1121 | 9.0 | 108 | 0.3205 | 0.7860 | 0.8417 | 0.8129 | 0.9275 | |
|
| 0.0902 | 10.0 | 120 | 0.3090 | 0.8071 | 0.8542 | 0.8300 | 0.9326 | |
|
| 0.08 | 11.0 | 132 | 0.3200 | 0.7821 | 0.8375 | 0.8089 | 0.9266 | |
|
| 0.0789 | 12.0 | 144 | 0.3226 | 0.7915 | 0.8542 | 0.8216 | 0.9283 | |
|
| 0.0654 | 13.0 | 156 | 0.3311 | 0.7852 | 0.8375 | 0.8105 | 0.9275 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
