metadata
license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: robbert2809_flow
results: []
robbert2809_flow
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: 0.3597
- Precision: 0.7239
- Recall: 0.7197
- F1: 0.7218
- Accuracy: 0.8938
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: 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 | 0.4622 | 0.6165 | 0.5828 | 0.5992 | 0.8584 |
| No log | 2.0 | 236 | 0.4044 | 0.6675 | 0.6620 | 0.6647 | 0.8772 |
| No log | 3.0 | 354 | 0.3787 | 0.6945 | 0.7220 | 0.708 | 0.8904 |
| No log | 4.0 | 472 | 0.3597 | 0.7239 | 0.7197 | 0.7218 | 0.8938 |
| 0.4344 | 5.0 | 590 | 0.3615 | 0.7273 | 0.7430 | 0.7351 | 0.8974 |
| 0.4344 | 6.0 | 708 | 0.3909 | 0.7410 | 0.7418 | 0.7414 | 0.8977 |
| 0.4344 | 7.0 | 826 | 0.3868 | 0.7394 | 0.7343 | 0.7368 | 0.8966 |
| 0.4344 | 8.0 | 944 | 0.3858 | 0.7402 | 0.7389 | 0.7396 | 0.8977 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3