metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: robbert2809_lrate7.5
results: []
robbert2809_lrate7.5
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: 0.3477
- Precision: 0.7368
- Recall: 0.7716
- F1: 0.7538
- Accuracy: 0.9017
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: 7.5e-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 | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 118 | 0.3855 | 0.6721 | 0.6533 | 0.6625 | 0.8795 |
| No log | 2.0 | 236 | 0.3511 | 0.6921 | 0.7284 | 0.7098 | 0.8880 |
| No log | 3.0 | 354 | 0.3477 | 0.7368 | 0.7716 | 0.7538 | 0.9017 |
| No log | 4.0 | 472 | 0.4055 | 0.7489 | 0.7628 | 0.7558 | 0.9019 |
| 0.3159 | 5.0 | 590 | 0.3930 | 0.7506 | 0.7488 | 0.7497 | 0.9035 |
| 0.3159 | 6.0 | 708 | 0.4131 | 0.7684 | 0.7716 | 0.7700 | 0.9082 |
| 0.3159 | 7.0 | 826 | 0.4382 | 0.7714 | 0.7786 | 0.7749 | 0.9093 |
| 0.3159 | 8.0 | 944 | 0.4478 | 0.7817 | 0.7698 | 0.7757 | 0.9097 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3