my_awesome_ner-token_classification_v1.0

This model is a fine-tuned version of NlpHUST/ner-vietnamese-electra-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.7184
• Precision: 0.5603
• Recall: 0.6333
• F1: 0.5946
• Accuracy: 0.8261

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: cosine
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.478	1.9991	2313	0.5109	0.5864	0.5956	0.5910	0.8411
0.3927	3.9983	4626	0.5095	0.5834	0.6186	0.6005	0.8401
0.3111	5.9974	6939	0.5813	0.5434	0.6335	0.5850	0.8258
0.2339	7.9965	9252	0.6137	0.5515	0.6312	0.5887	0.8261
0.1983	9.9957	11565	0.6743	0.5719	0.6243	0.5969	0.8305
0.1565	11.9948	13878	0.7044	0.5594	0.6372	0.5958	0.8250
0.1657	13.9939	16191	0.7184	0.5603	0.6333	0.5946	0.8261

Framework versions

• Transformers 4.41.2
• Pytorch 2.1.2
• Datasets 2.19.2
• Tokenizers 0.19.1