metadata

license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: robbert_testrun
    results: []

robbert_testrun

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: 0.5609
Precisions: 0.8558
Recall: 0.8234
F-measure: 0.8375
Accuracy: 0.9294

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: 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: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Precisions	Recall	F-measure	Accuracy
0.4449	1.0	285	0.3985	0.8120	0.6963	0.7240	0.8907
0.19	2.0	570	0.3572	0.8522	0.7715	0.8031	0.9118
0.0946	3.0	855	0.3966	0.8331	0.7816	0.8013	0.9168
0.0492	4.0	1140	0.4321	0.8295	0.8127	0.8189	0.9187
0.034	5.0	1425	0.4523	0.8123	0.8122	0.8097	0.9241
0.0221	6.0	1710	0.5082	0.8111	0.8109	0.8097	0.9222
0.015	7.0	1995	0.5375	0.8587	0.7934	0.8194	0.9212
0.0121	8.0	2280	0.5233	0.8542	0.8256	0.8373	0.9292
0.0077	9.0	2565	0.5259	0.8277	0.8235	0.8246	0.9286
0.0063	10.0	2850	0.5609	0.8558	0.8234	0.8375	0.9294
0.003	11.0	3135	0.5672	0.8176	0.8197	0.8169	0.9271
0.002	12.0	3420	0.5968	0.8555	0.8184	0.8347	0.9294
0.0021	13.0	3705	0.5846	0.8315	0.8222	0.8263	0.9269
0.0016	14.0	3990	0.5905	0.8352	0.8167	0.8251	0.9263

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1