metadata

license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: robdataaugmentation1511
    results: []

robdataaugmentation1511

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: 0.4187
Precisions: 0.8503
Recall: 0.8197
F-measure: 0.8320
Accuracy: 0.9446

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: 34
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
0.4276	1.0	284	0.2688	0.8001	0.7195	0.7402	0.9200
0.1871	2.0	568	0.2595	0.8183	0.7803	0.7948	0.9308
0.0942	3.0	852	0.2800	0.8083	0.8047	0.8042	0.9366
0.0542	4.0	1136	0.2841	0.8228	0.8232	0.8212	0.9402
0.0365	5.0	1420	0.3355	0.8472	0.8056	0.8224	0.9393
0.0228	6.0	1704	0.3860	0.8501	0.8009	0.8211	0.9405
0.0141	7.0	1988	0.3997	0.8320	0.8175	0.8233	0.9409
0.0132	8.0	2272	0.4225	0.8478	0.8025	0.8164	0.9397
0.0077	9.0	2556	0.3890	0.8258	0.8410	0.8312	0.9429
0.006	10.0	2840	0.3954	0.8354	0.8150	0.8235	0.9402
0.0045	11.0	3124	0.4266	0.8441	0.8136	0.8246	0.9424
0.0037	12.0	3408	0.4171	0.8364	0.8174	0.8245	0.9426
0.0021	13.0	3692	0.4221	0.8461	0.8192	0.8294	0.9434
0.0018	14.0	3976	0.4187	0.8503	0.8197	0.8320	0.9446

Framework versions

Transformers 4.35.1
Pytorch 2.1.0+cu118
Datasets 2.14.7
Tokenizers 0.14.1