Medical-NER-finetuned-ner

This model is a fine-tuned version of Clinical-AI-Apollo/Medical-NER on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3114
• Precision: 0.7903
• Recall: 0.9005
• F1: 0.8418
• Accuracy: 0.9313

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	90	0.9174	0.4239	0.3613	0.3901	0.7448
No log	2.0	180	0.6814	0.5257	0.5521	0.5386	0.7899
No log	3.0	270	0.6262	0.5383	0.7265	0.6184	0.7974
No log	4.0	360	0.4934	0.6065	0.7291	0.6622	0.8434
No log	5.0	450	0.5071	0.6102	0.7946	0.6903	0.8431
0.7847	6.0	540	0.4195	0.6863	0.7963	0.7372	0.8744
0.7847	7.0	630	0.4215	0.6850	0.8386	0.7541	0.8816
0.7847	8.0	720	0.3807	0.7287	0.8440	0.7822	0.8985
0.7847	9.0	810	0.3474	0.7383	0.8479	0.7893	0.9079
0.7847	10.0	900	0.3259	0.7583	0.8679	0.8094	0.9135
0.7847	11.0	990	0.3428	0.7595	0.8812	0.8158	0.9151
0.2288	12.0	1080	0.3469	0.7568	0.8821	0.8147	0.9147
0.2288	13.0	1170	0.3211	0.7790	0.8880	0.8299	0.9257
0.2288	14.0	1260	0.3217	0.7847	0.8909	0.8344	0.9271
0.2288	15.0	1350	0.2944	0.7952	0.8941	0.8418	0.9321
0.2288	16.0	1440	0.3244	0.7822	0.8986	0.8364	0.9275
0.1273	17.0	1530	0.3153	0.7911	0.9012	0.8426	0.9307
0.1273	18.0	1620	0.3198	0.7874	0.9005	0.8402	0.9298
0.1273	19.0	1710	0.3109	0.7911	0.9012	0.8426	0.9315
0.1273	20.0	1800	0.3114	0.7903	0.9005	0.8418	0.9313

Framework versions

• Transformers 4.30.0
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.13.3