metadata
license: mit
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: robbertfinetuned1406
results: []
robbertfinetuned1406
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: 1.0350
- Precision: 0.6604
- Recall: 0.6291
- F1: 0.6444
- Accuracy: 0.8697
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: 2e-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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 73 | 1.0577 | 0.6605 | 0.6074 | 0.6328 | 0.8632 |
| No log | 2.0 | 146 | 1.1133 | 0.6470 | 0.6017 | 0.6235 | 0.8606 |
| No log | 3.0 | 219 | 1.0416 | 0.6539 | 0.6310 | 0.6423 | 0.8675 |
| No log | 4.0 | 292 | 1.0350 | 0.6604 | 0.6291 | 0.6444 | 0.8697 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3