med_ner_2

This model is a fine-tuned version of prajjwal1/bert-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0295
• Overall Precision: 1.0
• Overall Recall: 0.9831
• Overall F1: 0.9915
• Overall Accuracy: 0.9977
• Age F1: 0.9888
• Yob F1: 1.0

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 250

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Age F1	Yob F1
0.0	47.62	1000	0.0364	1.0	0.9831	0.9915	0.9977	0.9888	1.0
0.0	95.24	2000	0.0363	1.0	0.9831	0.9915	0.9977	0.9888	1.0
0.0	142.86	3000	0.0279	1.0	0.9831	0.9915	0.9977	0.9888	1.0
0.0	190.48	4000	0.0265	1.0	0.9831	0.9915	0.9977	0.9888	1.0
0.0	238.1	5000	0.0295	1.0	0.9831	0.9915	0.9977	0.9888	1.0

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1