update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,86 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: DTAI-KULeuven/robbert-2023-dutch-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: robbert-2023-dutch-large-ft-lcn
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# robbert-2023-dutch-large-ft-lcn
|
| 15 |
+
|
| 16 |
+
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.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 2.0170
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 32
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 30
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 2.4518 | 1.0 | 69 | 2.2797 |
|
| 50 |
+
| 2.2185 | 2.0 | 138 | 2.1987 |
|
| 51 |
+
| 2.0898 | 3.0 | 207 | 2.0697 |
|
| 52 |
+
| 1.9864 | 4.0 | 276 | 2.0990 |
|
| 53 |
+
| 1.9536 | 5.0 | 345 | 2.0931 |
|
| 54 |
+
| 1.9179 | 6.0 | 414 | 2.0926 |
|
| 55 |
+
| 1.8327 | 7.0 | 483 | 2.0360 |
|
| 56 |
+
| 1.8026 | 8.0 | 552 | 2.0184 |
|
| 57 |
+
| 1.7421 | 9.0 | 621 | 2.0204 |
|
| 58 |
+
| 1.718 | 10.0 | 690 | 2.0213 |
|
| 59 |
+
| 1.629 | 11.0 | 759 | 1.9758 |
|
| 60 |
+
| 1.6068 | 12.0 | 828 | 1.9624 |
|
| 61 |
+
| 1.5701 | 13.0 | 897 | 2.0252 |
|
| 62 |
+
| 1.5413 | 14.0 | 966 | 2.0177 |
|
| 63 |
+
| 1.5081 | 15.0 | 1035 | 1.9927 |
|
| 64 |
+
| 1.4819 | 16.0 | 1104 | 2.0139 |
|
| 65 |
+
| 1.4276 | 17.0 | 1173 | 2.0395 |
|
| 66 |
+
| 1.3509 | 18.0 | 1242 | 1.9635 |
|
| 67 |
+
| 1.3773 | 19.0 | 1311 | 2.0046 |
|
| 68 |
+
| 1.3482 | 20.0 | 1380 | 1.9418 |
|
| 69 |
+
| 1.2942 | 21.0 | 1449 | 1.9375 |
|
| 70 |
+
| 1.2545 | 22.0 | 1518 | 1.9260 |
|
| 71 |
+
| 1.2211 | 23.0 | 1587 | 2.0129 |
|
| 72 |
+
| 1.1984 | 24.0 | 1656 | 1.9790 |
|
| 73 |
+
| 1.195 | 25.0 | 1725 | 2.0265 |
|
| 74 |
+
| 1.1825 | 26.0 | 1794 | 1.9964 |
|
| 75 |
+
| 1.1437 | 27.0 | 1863 | 1.9897 |
|
| 76 |
+
| 1.1351 | 28.0 | 1932 | 1.9511 |
|
| 77 |
+
| 1.1142 | 29.0 | 2001 | 1.9283 |
|
| 78 |
+
| 1.1011 | 30.0 | 2070 | 1.9966 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
+
### Framework versions
|
| 82 |
+
|
| 83 |
+
- Transformers 4.31.0
|
| 84 |
+
- Pytorch 1.11.0+cu113
|
| 85 |
+
- Datasets 2.14.4
|
| 86 |
+
- Tokenizers 0.13.3
|