metadata
license: mit
base_model: DTAI-KULeuven/robbert-2023-dutch-large
tags:
- generated_from_trainer
model-index:
- name: robbert-2023-dutch-large-ft-lcn
results: []
robbert-2023-dutch-large-ft-lcn
This model is a fine-tuned version of DTAI-KULeuven/robbert-2023-dutch-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0170
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 30
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4518 | 1.0 | 69 | 2.2797 |
| 2.2185 | 2.0 | 138 | 2.1987 |
| 2.0898 | 3.0 | 207 | 2.0697 |
| 1.9864 | 4.0 | 276 | 2.0990 |
| 1.9536 | 5.0 | 345 | 2.0931 |
| 1.9179 | 6.0 | 414 | 2.0926 |
| 1.8327 | 7.0 | 483 | 2.0360 |
| 1.8026 | 8.0 | 552 | 2.0184 |
| 1.7421 | 9.0 | 621 | 2.0204 |
| 1.718 | 10.0 | 690 | 2.0213 |
| 1.629 | 11.0 | 759 | 1.9758 |
| 1.6068 | 12.0 | 828 | 1.9624 |
| 1.5701 | 13.0 | 897 | 2.0252 |
| 1.5413 | 14.0 | 966 | 2.0177 |
| 1.5081 | 15.0 | 1035 | 1.9927 |
| 1.4819 | 16.0 | 1104 | 2.0139 |
| 1.4276 | 17.0 | 1173 | 2.0395 |
| 1.3509 | 18.0 | 1242 | 1.9635 |
| 1.3773 | 19.0 | 1311 | 2.0046 |
| 1.3482 | 20.0 | 1380 | 1.9418 |
| 1.2942 | 21.0 | 1449 | 1.9375 |
| 1.2545 | 22.0 | 1518 | 1.9260 |
| 1.2211 | 23.0 | 1587 | 2.0129 |
| 1.1984 | 24.0 | 1656 | 1.9790 |
| 1.195 | 25.0 | 1725 | 2.0265 |
| 1.1825 | 26.0 | 1794 | 1.9964 |
| 1.1437 | 27.0 | 1863 | 1.9897 |
| 1.1351 | 28.0 | 1932 | 1.9511 |
| 1.1142 | 29.0 | 2001 | 1.9283 |
| 1.1011 | 30.0 | 2070 | 1.9966 |
Framework versions
- Transformers 4.31.0
- Pytorch 1.11.0+cu113
- Datasets 2.14.4
- Tokenizers 0.13.3