metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- recall
- accuracy
model-index:
- name: robbert0210_lrate2.5b16
results: []
robbert0210_lrate2.5b16
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: 0.3449
- Precisions: 0.7846
- Recall: 0.7358
- F-measure: 0.7356
- Accuracy: 0.8988
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: 16
- eval_batch_size: 16
- 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 | 236 | 0.4364 | 0.8256 | 0.6672 | 0.6709 | 0.8658 |
| No log | 2.0 | 472 | 0.3745 | 0.6875 | 0.7116 | 0.6970 | 0.8839 |
| 0.5514 | 3.0 | 708 | 0.3449 | 0.7846 | 0.7358 | 0.7356 | 0.8988 |
| 0.5514 | 4.0 | 944 | 0.3625 | 0.8042 | 0.7487 | 0.7552 | 0.9000 |
| 0.2255 | 5.0 | 1180 | 0.3987 | 0.8037 | 0.7541 | 0.7618 | 0.9000 |
| 0.2255 | 6.0 | 1416 | 0.4315 | 0.8049 | 0.7549 | 0.7636 | 0.9010 |
| 0.1211 | 7.0 | 1652 | 0.4060 | 0.8170 | 0.7633 | 0.7785 | 0.9034 |
| 0.1211 | 8.0 | 1888 | 0.4146 | 0.8162 | 0.7813 | 0.7927 | 0.9070 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3