|
--- |
|
license: mit |
|
base_model: DTAI-KULeuven/robbert-2023-dutch-large |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- f1 |
|
- accuracy |
|
model-index: |
|
- name: robbert-2023-dutch-large_ner |
|
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-2023-dutch-large_ner |
|
|
|
This model is a fine-tuned version of [DTAI-KULeuven/robbert-2023-dutch-large](https://huggingface.co/DTAI-KULeuven/robbert-2023-dutch-large) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3927 |
|
- Precision: 0.9137 |
|
- Recall: 0.9190 |
|
- F1: 0.9162 |
|
- Accuracy: 0.9515 |
|
|
|
## 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: 5e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- 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 | 438 | 0.3076 | 0.8616 | 0.8592 | 0.8581 | 0.9133 | |
|
| 0.4231 | 2.0 | 876 | 0.2583 | 0.9068 | 0.8795 | 0.8919 | 0.9338 | |
|
| 0.2222 | 3.0 | 1314 | 0.2809 | 0.8821 | 0.8940 | 0.8864 | 0.9331 | |
|
| 0.1519 | 4.0 | 1752 | 0.2549 | 0.9142 | 0.9207 | 0.9169 | 0.9505 | |
|
| 0.1094 | 5.0 | 2190 | 0.2487 | 0.9105 | 0.9145 | 0.9121 | 0.9482 | |
|
| 0.0731 | 6.0 | 2628 | 0.3406 | 0.9094 | 0.9108 | 0.9097 | 0.9473 | |
|
| 0.0445 | 7.0 | 3066 | 0.3137 | 0.9118 | 0.9164 | 0.9139 | 0.9498 | |
|
| 0.0251 | 8.0 | 3504 | 0.3178 | 0.9166 | 0.9209 | 0.9186 | 0.9526 | |
|
| 0.0251 | 9.0 | 3942 | 0.3886 | 0.9118 | 0.9170 | 0.9143 | 0.9504 | |
|
| 0.0129 | 10.0 | 4380 | 0.3927 | 0.9137 | 0.9190 | 0.9162 | 0.9515 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
