deberta-v3-base_finetuned_bluegennx_run2.19_5e

This model is a fine-tuned version of microsoft/deberta-v3-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0196
• Overall Precision: 0.9773
• Overall Recall: 0.9870
• Overall F1: 0.9822
• Overall Accuracy: 0.9957
• Aadhar Card F1: 0.9908
• Age F1: 0.9708
• City F1: 0.9879
• Country F1: 0.9825
• Creditcardcvv F1: 0.9915
• Creditcardnumber F1: 0.9428
• Date F1: 0.9626
• Dateofbirth F1: 0.9056
• Email F1: 0.9928
• Expirydate F1: 0.9898
• Organization F1: 0.9925
• Pan Card F1: 0.9866
• Person F1: 0.9887
• Phonenumber F1: 0.9880
• Pincode F1: 0.9897
• Secondaryaddress F1: 0.9891
• State F1: 0.9912
• Time F1: 0.9831
• Url F1: 0.9955

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine_with_restarts
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Aadhar Card F1	Age F1	City F1	Country F1	Creditcardcvv F1	Creditcardnumber F1	Date F1	Dateofbirth F1	Email F1	Expirydate F1	Organization F1	Pan Card F1	Person F1	Phonenumber F1	Pincode F1	Secondaryaddress F1	State F1	Time F1	Url F1
0.0356	1.0	15321	0.0383	0.9535	0.9675	0.9604	0.9915	0.9542	0.9221	0.9617	0.9816	0.9243	0.9195	0.9235	0.8262	0.9826	0.9477	0.9882	0.9529	0.9785	0.9684	0.9187	0.9734	0.9665	0.9723	0.9888
0.0231	2.0	30642	0.0265	0.9607	0.9814	0.9709	0.9937	0.9586	0.9437	0.9808	0.9821	0.9799	0.9006	0.9488	0.8788	0.9864	0.9768	0.9843	0.9837	0.9824	0.9809	0.9840	0.9820	0.9906	0.9749	0.9784
0.0182	3.0	45963	0.0219	0.9726	0.9854	0.9789	0.9951	0.9842	0.9631	0.9856	0.9843	0.9854	0.9424	0.9553	0.8962	0.9890	0.9878	0.9921	0.9869	0.9859	0.9815	0.9867	0.9884	0.9917	0.9767	0.9962
0.0106	4.0	61284	0.0196	0.9773	0.9870	0.9822	0.9957	0.9908	0.9708	0.9879	0.9825	0.9915	0.9428	0.9626	0.9056	0.9928	0.9898	0.9925	0.9866	0.9887	0.9880	0.9897	0.9891	0.9912	0.9831	0.9955
0.0044	5.0	76605	0.0214	0.9787	0.9876	0.9831	0.9959	0.9934	0.9710	0.9885	0.9846	0.9915	0.9453	0.9646	0.9125	0.9931	0.9898	0.9937	0.9875	0.9886	0.9893	0.9907	0.9903	0.9924	0.9837	0.9958

Framework versions

• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2