robbert0210_lrate5b32
This model is a fine-tuned version of pdelobelle/robbert-v2-dutch-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3497
- Precisions: 0.8168
- Recall: 0.7629
- F-measure: 0.7745
- Accuracy: 0.9044
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: 5e-05
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precisions | Recall | F-measure | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 118 | 0.4100 | 0.8801 | 0.6728 | 0.6931 | 0.8747 |
| No log | 2.0 | 236 | 0.3638 | 0.7841 | 0.7186 | 0.7176 | 0.8871 |
| No log | 3.0 | 354 | 0.3533 | 0.8013 | 0.7568 | 0.7535 | 0.8967 |
| No log | 4.0 | 472 | 0.3497 | 0.8168 | 0.7629 | 0.7745 | 0.9044 |
| 0.3409 | 5.0 | 590 | 0.3781 | 0.7928 | 0.7789 | 0.7814 | 0.9046 |
| 0.3409 | 6.0 | 708 | 0.4072 | 0.8013 | 0.7836 | 0.7884 | 0.9073 |
| 0.3409 | 7.0 | 826 | 0.4193 | 0.8047 | 0.8026 | 0.8012 | 0.9082 |
| 0.3409 | 8.0 | 944 | 0.4197 | 0.8121 | 0.8021 | 0.8049 | 0.9103 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3