metadata

license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: robbert1010_lrate10b16
    results: []

robbert1010_lrate10b16

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: 0.6021
Precisions: 0.8323
Recall: 0.7951
F-measure: 0.8088
Accuracy: 0.9164

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: 0.0001
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
0.6104	1.0	236	0.4304	0.8532	0.6700	0.6852	0.8707
0.32	2.0	472	0.3520	0.7761	0.7551	0.7413	0.8916
0.1989	3.0	708	0.3686	0.7500	0.7591	0.7465	0.9010
0.1331	4.0	944	0.4045	0.8289	0.7666	0.7835	0.9090
0.0784	5.0	1180	0.4307	0.8052	0.7759	0.7890	0.9092
0.0682	6.0	1416	0.4696	0.8101	0.7658	0.7770	0.9059
0.04	7.0	1652	0.5078	0.8450	0.7642	0.7820	0.9096
0.0256	8.0	1888	0.5718	0.8007	0.7830	0.7906	0.9058
0.0219	9.0	2124	0.5508	0.8078	0.7987	0.8000	0.9093
0.0162	10.0	2360	0.5786	0.8256	0.7791	0.7946	0.9141
0.0117	11.0	2596	0.5979	0.8360	0.7912	0.8046	0.9168
0.011	12.0	2832	0.6021	0.8323	0.7951	0.8088	0.9164
0.0079	13.0	3068	0.6115	0.8337	0.7956	0.8088	0.9166
0.0064	14.0	3304	0.6100	0.8305	0.7932	0.8064	0.9164

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.1