|
--- |
|
license: mit |
|
base_model: DTAI-KULeuven/robbert-2023-dutch-large |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: robbert-2023-dutch-large-ft-lcn |
|
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-ft-lcn |
|
|
|
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: 1.8711 |
|
|
|
## 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: 6e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 12 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3132 | 1.0 | 69 | 2.1302 | |
|
| 2.1372 | 2.0 | 138 | 2.0750 | |
|
| 2.0204 | 3.0 | 207 | 1.9985 | |
|
| 1.9231 | 4.0 | 276 | 1.9298 | |
|
| 1.8671 | 5.0 | 345 | 1.9031 | |
|
| 1.764 | 6.0 | 414 | 1.9241 | |
|
| 1.7491 | 7.0 | 483 | 1.9061 | |
|
| 1.7057 | 8.0 | 552 | 1.9247 | |
|
| 1.6751 | 9.0 | 621 | 1.8435 | |
|
| 1.5922 | 10.0 | 690 | 1.8714 | |
|
| 1.5859 | 11.0 | 759 | 1.8203 | |
|
| 1.5551 | 12.0 | 828 | 1.8823 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|