metadata

license: mit
base_model: pdelobelle/robbert-v2-dutch-base
tags:
  - generated_from_trainer
metrics:
  - recall
  - accuracy
model-index:
  - name: robbert0510_lrate9b16
    results: []

robbert0510_lrate9b16

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: 0.5873
Precisions: 0.8240
Recall: 0.8030
F-measure: 0.8121
Accuracy: 0.9175

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: 9e-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
0.6115	1.0	236	0.3939	0.8592	0.6769	0.6912	0.8757
0.3166	2.0	472	0.3750	0.7447	0.7640	0.7458	0.8897
0.194	3.0	708	0.3445	0.7683	0.7462	0.7525	0.9025
0.1292	4.0	944	0.3776	0.8345	0.7570	0.7754	0.9072
0.0755	5.0	1180	0.4667	0.7897	0.8244	0.7995	0.9079
0.0556	6.0	1416	0.4879	0.8233	0.7809	0.7973	0.9086
0.0413	7.0	1652	0.4901	0.7770	0.8020	0.7846	0.9049
0.0245	8.0	1888	0.5467	0.8159	0.7679	0.7836	0.9086
0.015	9.0	2124	0.5914	0.8156	0.7858	0.7957	0.9109
0.0129	10.0	2360	0.5640	0.8041	0.8160	0.8079	0.9133
0.0055	11.0	2596	0.5848	0.8084	0.8044	0.8055	0.9142
0.0068	12.0	2832	0.5752	0.8097	0.7957	0.8017	0.9140
0.0036	13.0	3068	0.5873	0.8240	0.8030	0.8121	0.9175
0.0025	14.0	3304	0.5992	0.8217	0.7913	0.8037	0.9155

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.0