robbert0210_lrate2.5b8
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: 0.3692
- Precisions: 0.7993
- Recall: 0.7287
- F-measure: 0.7307
- Accuracy: 0.8915
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: 2.5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 | 471 | 0.4360 | 0.8519 | 0.6630 | 0.6789 | 0.8678 |
| 0.6455 | 2.0 | 942 | 0.3692 | 0.7993 | 0.7287 | 0.7307 | 0.8915 |
| 0.3291 | 3.0 | 1413 | 0.3768 | 0.7658 | 0.7398 | 0.7397 | 0.8986 |
| 0.2114 | 4.0 | 1884 | 0.4194 | 0.7951 | 0.7452 | 0.7532 | 0.9048 |
| 0.1457 | 5.0 | 2355 | 0.4626 | 0.7756 | 0.7536 | 0.7620 | 0.9021 |
| 0.0955 | 6.0 | 2826 | 0.5145 | 0.8075 | 0.7700 | 0.7858 | 0.9048 |
| 0.0641 | 7.0 | 3297 | 0.5118 | 0.8113 | 0.7997 | 0.8045 | 0.9100 |
| 0.0484 | 8.0 | 3768 | 0.5204 | 0.8052 | 0.7952 | 0.7995 | 0.9093 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3