NLP-HIBA_DisTEMIST_fine_tuned_ClinicalBERT-pretrained-model

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: 0.2557
• Precision: 0.4943
• Recall: 0.5046
• F1: 0.4994
• Accuracy: 0.9407

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	71	0.2423	0.1951	0.1433	0.1653	0.9109
No log	2.0	142	0.2177	0.2905	0.3474	0.3164	0.9138
No log	3.0	213	0.1822	0.3912	0.3701	0.3804	0.9325
No log	4.0	284	0.1845	0.3839	0.4367	0.4086	0.9298
No log	5.0	355	0.2033	0.4533	0.4271	0.4398	0.9367
No log	6.0	426	0.2005	0.4535	0.4736	0.4633	0.9365
No log	7.0	497	0.2297	0.4352	0.5155	0.4720	0.9321
0.1436	8.0	568	0.2236	0.4854	0.4656	0.4753	0.9395
0.1436	9.0	639	0.2335	0.4935	0.5101	0.5016	0.9397
0.1436	10.0	710	0.2413	0.4829	0.5075	0.4949	0.9405
0.1436	11.0	781	0.2557	0.4849	0.5239	0.5036	0.9383
0.1436	12.0	852	0.2557	0.4943	0.5046	0.4994	0.9407

Framework versions

• Transformers 4.35.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.6
• Tokenizers 0.14.1