robbert_seed34_1311

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: 0.3777
• Precisions: 0.8501
• Recall: 0.8262
• F-measure: 0.8370
• Accuracy: 0.9450

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
0.4251	1.0	236	0.2557	0.7903	0.7339	0.7510	0.9248
0.2162	2.0	472	0.3018	0.8386	0.7336	0.7532	0.9200
0.1275	3.0	708	0.2461	0.8347	0.7758	0.7858	0.9364
0.0797	4.0	944	0.2773	0.8694	0.7843	0.8114	0.9383
0.049	5.0	1180	0.2767	0.8314	0.8143	0.8200	0.9419
0.03	6.0	1416	0.3036	0.8126	0.8106	0.8104	0.9407
0.0189	7.0	1652	0.3637	0.8051	0.8146	0.8073	0.9395
0.014	8.0	1888	0.3762	0.8479	0.7926	0.8135	0.9436
0.012	9.0	2124	0.3649	0.8486	0.8019	0.8205	0.9443
0.0045	10.0	2360	0.3966	0.8530	0.8000	0.8200	0.9431
0.0057	11.0	2596	0.3856	0.8564	0.8129	0.8307	0.9441
0.0054	12.0	2832	0.3777	0.8501	0.8262	0.8370	0.9450
0.0025	13.0	3068	0.3792	0.8608	0.8207	0.8369	0.9458
0.0019	14.0	3304	0.3859	0.8581	0.8149	0.8318	0.9455

Framework versions

• Transformers 4.35.0
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1