|
|
--- |
|
|
license: mit |
|
|
base_model: pdelobelle/robbert-v2-dutch-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- recall |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: robbert_testrun |
|
|
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. --> |
|
|
|
|
|
# robbert_testrun |
|
|
|
|
|
This model is a fine-tuned version of [pdelobelle/robbert-v2-dutch-base](https://huggingface.co/pdelobelle/robbert-v2-dutch-base) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3318 |
|
|
- Precisions: 0.8562 |
|
|
- Recall: 0.8095 |
|
|
- F-measure: 0.8293 |
|
|
- Accuracy: 0.9476 |
|
|
|
|
|
## 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: 7.5e-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: 14 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:----------:|:------:|:---------:|:--------:| |
|
|
| 0.4465 | 1.0 | 269 | 0.3166 | 0.8058 | 0.6865 | 0.6693 | 0.9046 | |
|
|
| 0.2204 | 2.0 | 538 | 0.2474 | 0.8108 | 0.7990 | 0.7979 | 0.9295 | |
|
|
| 0.133 | 3.0 | 807 | 0.2529 | 0.8072 | 0.7719 | 0.7830 | 0.9357 | |
|
|
| 0.087 | 4.0 | 1076 | 0.2601 | 0.8462 | 0.7886 | 0.8012 | 0.9415 | |
|
|
| 0.0578 | 5.0 | 1345 | 0.2896 | 0.8286 | 0.8106 | 0.8186 | 0.9418 | |
|
|
| 0.0307 | 6.0 | 1614 | 0.3017 | 0.8474 | 0.8065 | 0.8240 | 0.9433 | |
|
|
| 0.0257 | 7.0 | 1883 | 0.3435 | 0.8488 | 0.8129 | 0.8270 | 0.9407 | |
|
|
| 0.0159 | 8.0 | 2152 | 0.3318 | 0.8562 | 0.8095 | 0.8293 | 0.9476 | |
|
|
| 0.0086 | 9.0 | 2421 | 0.3629 | 0.8433 | 0.8065 | 0.8224 | 0.9451 | |
|
|
| 0.0067 | 10.0 | 2690 | 0.3700 | 0.8648 | 0.8020 | 0.8272 | 0.9451 | |
|
|
| 0.0064 | 11.0 | 2959 | 0.3835 | 0.8328 | 0.8108 | 0.8203 | 0.9425 | |
|
|
| 0.0041 | 12.0 | 3228 | 0.3625 | 0.8454 | 0.8094 | 0.8255 | 0.9447 | |
|
|
| 0.0028 | 13.0 | 3497 | 0.3734 | 0.8450 | 0.8097 | 0.8254 | 0.9451 | |
|
|
| 0.0021 | 14.0 | 3766 | 0.3706 | 0.8469 | 0.8119 | 0.8274 | 0.9462 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.34.0 |
|
|
- Pytorch 2.0.1+cu118 |
|
|
- Datasets 2.14.5 |
|
|
- Tokenizers 0.14.1 |
|
|
|
