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: 0.5895
Precisions: 0.8184
Recall: 0.7998
F-measure: 0.8078
Accuracy: 0.9148

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: 8e-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
0.5957	1.0	236	0.4045	0.8529	0.6860	0.6940	0.8784
0.3024	2.0	472	0.3456	0.7564	0.7584	0.7471	0.8964
0.1843	3.0	708	0.3792	0.8188	0.7691	0.7741	0.9087
0.1163	4.0	944	0.4231	0.8317	0.7678	0.7878	0.9060
0.0753	5.0	1180	0.4595	0.8051	0.7846	0.7911	0.9070
0.0496	6.0	1416	0.4942	0.8188	0.7803	0.7960	0.9087
0.0321	7.0	1652	0.5121	0.7966	0.7927	0.7900	0.9103
0.0246	8.0	1888	0.5057	0.8155	0.7959	0.8030	0.9148
0.0156	9.0	2124	0.5445	0.8039	0.7924	0.7967	0.9109
0.0118	10.0	2360	0.5646	0.8151	0.7948	0.8032	0.9140
0.0083	11.0	2596	0.5911	0.8387	0.7872	0.8075	0.9138
0.0052	12.0	2832	0.5895	0.8184	0.7998	0.8078	0.9148
0.0038	13.0	3068	0.5839	0.8193	0.7987	0.8078	0.9149
0.0026	14.0	3304	0.5911	0.8195	0.7926	0.8041	0.9135

Framework versions

Transformers 4.34.0
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.14.0