xlm-roberta-base-finetuned-Conll2003-ner-2024_08_05

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1404
• Precision: 0.9004
• Recall: 0.9163
• F1: 0.9083
• Accuracy: 0.9780

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: 2e-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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0838	0.3326	292	0.1220	0.8779	0.8841	0.8810	0.9730
0.0807	0.6651	584	0.1345	0.8695	0.8934	0.8813	0.9728
0.0711	0.9977	876	0.1336	0.8728	0.8986	0.8855	0.9733
0.0467	1.3303	1168	0.1443	0.8817	0.9090	0.8951	0.9748
0.0452	1.6629	1460	0.1311	0.8887	0.9138	0.9011	0.9759
0.0383	1.9954	1752	0.1324	0.9021	0.9146	0.9083	0.9776
0.026	2.3280	2044	0.1352	0.9024	0.9180	0.9101	0.9784
0.0245	2.6606	2336	0.1431	0.9010	0.9172	0.9090	0.9778
0.0235	2.9932	2628	0.1403	0.9004	0.9163	0.9083	0.9780

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1