update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: BertjeWDialDataALLQonly03
|
| 6 |
+
results: []
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# BertjeWDialDataALLQonly03
|
| 13 |
+
|
| 14 |
+
This model is a fine-tuned version of [GroNLP/bert-base-dutch-cased](https://huggingface.co/GroNLP/bert-base-dutch-cased) on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 1.9995
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 16
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- gradient_accumulation_steps: 8
|
| 40 |
+
- total_train_batch_size: 128
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 24.0
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
| 49 |
+
| No log | 1.0 | 435 | 2.0751 |
|
| 50 |
+
| 2.1982 | 2.0 | 870 | 2.0465 |
|
| 51 |
+
| 2.0841 | 3.0 | 1305 | 2.0420 |
|
| 52 |
+
| 2.0374 | 4.0 | 1740 | 2.0325 |
|
| 53 |
+
| 1.9731 | 5.0 | 2175 | 2.0075 |
|
| 54 |
+
| 1.9248 | 6.0 | 2610 | 2.0219 |
|
| 55 |
+
| 1.8848 | 7.0 | 3045 | 1.9770 |
|
| 56 |
+
| 1.8848 | 8.0 | 3480 | 2.0093 |
|
| 57 |
+
| 1.8419 | 9.0 | 3915 | 2.0298 |
|
| 58 |
+
| 1.804 | 10.0 | 4350 | 1.9681 |
|
| 59 |
+
| 1.7817 | 11.0 | 4785 | 1.9938 |
|
| 60 |
+
| 1.7472 | 12.0 | 5220 | 1.9654 |
|
| 61 |
+
| 1.7075 | 13.0 | 5655 | 1.9797 |
|
| 62 |
+
| 1.6976 | 14.0 | 6090 | 1.9691 |
|
| 63 |
+
| 1.6748 | 15.0 | 6525 | 1.9568 |
|
| 64 |
+
| 1.6748 | 16.0 | 6960 | 1.9618 |
|
| 65 |
+
| 1.6528 | 17.0 | 7395 | 1.9843 |
|
| 66 |
+
| 1.6335 | 18.0 | 7830 | 1.9265 |
|
| 67 |
+
| 1.6179 | 19.0 | 8265 | 1.9598 |
|
| 68 |
+
| 1.5992 | 20.0 | 8700 | 1.9331 |
|
| 69 |
+
| 1.583 | 21.0 | 9135 | 1.9795 |
|
| 70 |
+
| 1.5699 | 22.0 | 9570 | 2.0073 |
|
| 71 |
+
| 1.5703 | 23.0 | 10005 | 1.9308 |
|
| 72 |
+
| 1.5703 | 24.0 | 10440 | 1.9285 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.13.0.dev0
|
| 78 |
+
- Pytorch 1.10.0
|
| 79 |
+
- Datasets 1.16.1
|
| 80 |
+
- Tokenizers 0.10.3
|