metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: VaccinChatSentenceClassifierDutch_fromBERTje2_DAdialogQonly09
results: []
VaccinChatSentenceClassifierDutch_fromBERTje2_DAdialogQonly09
This model is a fine-tuned version of outputDAQonly09/ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8105
- Accuracy: 0.8757
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: 1e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 330 | 3.9924 | 0.2230 |
| 4.3795 | 2.0 | 660 | 3.1812 | 0.3958 |
| 4.3795 | 3.0 | 990 | 2.5904 | 0.5512 |
| 3.2046 | 4.0 | 1320 | 2.1536 | 0.6408 |
| 2.3683 | 5.0 | 1650 | 1.8079 | 0.7130 |
| 2.3683 | 6.0 | 1980 | 1.5420 | 0.7687 |
| 1.8065 | 7.0 | 2310 | 1.3434 | 0.8053 |
| 1.373 | 8.0 | 2640 | 1.1882 | 0.8254 |
| 1.373 | 9.0 | 2970 | 1.0700 | 0.8400 |
| 1.0931 | 10.0 | 3300 | 0.9791 | 0.8510 |
| 0.8714 | 11.0 | 3630 | 0.9202 | 0.8620 |
| 0.8714 | 12.0 | 3960 | 0.8641 | 0.8684 |
| 0.7428 | 13.0 | 4290 | 0.8372 | 0.8748 |
| 0.6531 | 14.0 | 4620 | 0.8168 | 0.8766 |
| 0.6531 | 15.0 | 4950 | 0.8105 | 0.8757 |
Framework versions
- Transformers 4.13.0.dev0
- Pytorch 1.10.0
- Datasets 1.16.1
- Tokenizers 0.10.3