finetuned_BioClinicalBERT

This model is a fine-tuned version of emilyalsentzer/Bio_ClinicalBERT on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4147
• F1: 0.9143

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	F1
0.5879	1.0	24	0.4997	0.8767
0.52	2.0	48	0.4386	0.8889
0.3865	3.0	72	0.4487	0.7797
0.4456	4.0	96	0.5242	0.8
0.2789	5.0	120	0.4147	0.9143
0.2035	6.0	144	0.5301	0.8710
0.124	7.0	168	0.6356	0.8923
0.1422	8.0	192	0.9593	0.8308
0.123	9.0	216	2.0378	0.5833
0.0296	10.0	240	1.1534	0.8197
0.0047	11.0	264	0.6878	0.9254
0.0739	12.0	288	1.2483	0.8387
0.0016	13.0	312	1.9790	0.7143
0.0017	14.0	336	0.9967	0.8615
0.0015	15.0	360	2.0558	0.7143
0.0008	16.0	384	1.2408	0.8696
0.0006	17.0	408	1.6653	0.8
0.0003	18.0	432	1.1586	0.875
0.0002	19.0	456	1.1180	0.8955
0.0002	20.0	480	1.1362	0.8955
0.0002	21.0	504	1.1670	0.8955
0.0002	22.0	528	1.1915	0.8955
0.0002	23.0	552	1.2127	0.8955
0.0002	24.0	576	1.2162	0.8955
0.0002	25.0	600	1.2291	0.8955
0.0002	26.0	624	1.2454	0.8955
0.0002	27.0	648	1.2608	0.8955
0.0002	28.0	672	1.2348	0.8923
0.0002	29.0	696	1.2444	0.8923
0.0001	30.0	720	1.2437	0.8923

Framework versions

• Transformers 4.48.0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0