bert-base-arabert-BioNER-EN-AR

This model is a fine-tuned version of StivenLancheros/bert-base-arabert-BioNER-EN on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4250
• Precision: 0.7143
• Recall: 0.8209
• F1: 0.7639
• Accuracy: 0.9197

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: 3e-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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.6376	1.0	680	0.7457	0.4379	0.6384	0.5195	0.8242
0.4549	2.0	1360	0.7120	0.4878	0.7113	0.5787	0.8346
0.3214	3.0	2040	0.5576	0.5676	0.7529	0.6473	0.8749
0.2883	4.0	2720	0.5304	0.5916	0.7745	0.6708	0.8808
0.2596	5.0	3400	0.4942	0.6117	0.7884	0.6889	0.8906
0.2168	6.0	4080	0.5229	0.6204	0.7977	0.6979	0.8898
0.2105	7.0	4760	0.4630	0.6501	0.7935	0.7147	0.8999
0.1889	8.0	5440	0.5048	0.6407	0.8066	0.7141	0.8958
0.1714	9.0	6120	0.4538	0.6909	0.7986	0.7409	0.9105
0.1626	10.0	6800	0.4433	0.6912	0.8070	0.7446	0.9130
0.1559	11.0	7480	0.4282	0.7006	0.8054	0.7493	0.9144
0.1451	12.0	8160	0.4475	0.6978	0.8150	0.7519	0.9135
0.1384	13.0	8840	0.4535	0.6928	0.8215	0.7517	0.9145
0.1331	14.0	9520	0.4250	0.7143	0.8209	0.7639	0.9197
0.1282	15.0	10200	0.4350	0.7108	0.8237	0.7631	0.9200
0.1216	16.0	10880	0.4385	0.7096	0.8231	0.7621	0.9188
0.1195	17.0	11560	0.4376	0.7134	0.8275	0.7662	0.9204
0.1187	18.0	12240	0.4461	0.7092	0.8297	0.7647	0.9183
0.1159	19.0	12920	0.4359	0.7215	0.8264	0.7704	0.9219
0.1121	20.0	13600	0.4358	0.7198	0.8264	0.7694	0.9217

Framework versions

• Transformers 4.27.2
• Pytorch 1.13.0+cu117
• Datasets 2.7.1
• Tokenizers 0.13.2