metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: distilbert-base-uncased-three_v2
    results: []

distilbert-base-uncased-three_v2

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1119
Overall Precision: 0.6887
Overall Recall: 0.7043
Overall F1: 0.6964
Overall Accuracy: 0.9661
Accountname F1: 0.9754
Accountnumber F1: 0.9909
Age F1: 0.8968
Amount F1: 0.9696
Bic F1: 0.8958
Bitcoinaddress F1: 0.9558
Buildingnumber F1: 0.6231
City F1: 0.4939
Companyname F1: 0.7855
County F1: 0.9636
Creditcardcvv F1: 0.8203
Creditcardissuer F1: 0.9870
Creditcardnumber F1: 0.8612
Currency F1: 0.7425
Currencycode F1: 0.7627
Currencyname F1: 0.0982
Currencysymbol F1: 0.9107
Date F1: 0.7740
Dob F1: 0.5599
Email F1: 0.6672
Ethereumaddress F1: 1.0
Eyecolor F1: 0.9311
Firstname F1: 0.9272
Gender F1: 0.9687
Height F1: 0.9770
Iban F1: 0.9728
Ip F1: 0.3270
Ipv4 F1: 0.8654
Ipv6 F1: 0.7183
Jobarea F1: 0.9173
Jobtitle F1: 0.6473
Jobtype F1: 0.9296
Lastname F1: 0.4612
Litecoinaddress F1: 0.8625
Mac F1: 0.9881
Maskednumber F1: 0.8622
Middlename F1: 0.9260
Nearbygpscoordinate F1: 0.6963
Ordinaldirection F1: 0.9745
Password F1: 0.4805
Phoneimei F1: 0.9862
Phonenumber F1: 0.6201
Pin F1: 0.8720
Prefix F1: 0.9302
Secondaryaddress F1: 0.5961
Sex F1: 0.6282
Ssn F1: 0.5050
State F1: 0.5606
Street F1: 0.7082
Time F1: 0.5796
Url F1: 0.9878
Useragent F1: 0.9852
Username F1: 0.7521
Vehiclevin F1: 0.9646
Vehiclevrm F1: 0.9668
Zipcode F1: 0.5227

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.2
num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Accountname F1	Accountnumber F1	Age F1	Amount F1	Bic F1	Bitcoinaddress F1	Buildingnumber F1	City F1	Companyname F1	County F1	Creditcardcvv F1	Creditcardissuer F1	Creditcardnumber F1	Currency F1	Currencycode F1	Currencyname F1	Currencysymbol F1	Date F1	Dob F1	Email F1	Ethereumaddress F1	Eyecolor F1	Firstname F1	Gender F1	Height F1	Iban F1	Ip F1	Ipv4 F1	Ipv6 F1	Jobarea F1	Jobtitle F1	Jobtype F1	Lastname F1	Litecoinaddress F1	Mac F1	Maskednumber F1	Middlename F1	Nearbygpscoordinate F1	Ordinaldirection F1	Password F1	Phoneimei F1	Phonenumber F1	Pin F1	Prefix F1	Secondaryaddress F1	Sex F1	Ssn F1	State F1	Street F1	Time F1	Url F1	Useragent F1	Username F1	Vehiclevin F1	Vehiclevrm F1	Zipcode F1
0.3276	1.0	1299	0.2229	0.5230	0.5278	0.5254	0.9424	0.8919	0.9149	0.7206	0.6079	0.2076	0.6905	0.3045	0.2728	0.6735	0.5815	0.2843	0.6916	0.5830	0.5045	0.0	0.0	0.5092	0.6867	0.3329	0.5175	0.9744	0.6538	0.8146	0.6366	0.75	0.7257	0.1116	0.7353	0.5603	0.5528	0.4372	0.7134	0.3042	0.0046	0.9167	0.0822	0.0840	0.5911	0.9193	0.3094	0.9275	0.4683	0.2838	0.8967	0.4395	0.4518	0.2766	0.2903	0.5173	0.3399	0.9528	0.9380	0.6582	0.2656	0.6773	0.2881
0.1401	2.0	2598	0.1397	0.6287	0.6284	0.6286	0.9576	0.9534	0.9882	0.8765	0.9421	0.8202	0.9559	0.4994	0.4134	0.7426	0.9261	0.7804	0.9789	0.8197	0.6180	0.5220	0.0226	0.8262	0.7257	0.4362	0.6022	0.9969	0.8986	0.8847	0.9243	0.9628	0.9030	0.1979	0.7328	0.7735	0.8205	0.5473	0.8987	0.3867	0.8544	0.9810	0.7560	0.6807	0.5924	0.9677	0.3921	0.9727	0.5302	0.7728	0.9201	0.5307	0.5501	0.3863	0.4817	0.6337	0.4443	0.9813	0.9783	0.7122	0.9508	0.9258	0.4593
0.1104	3.0	3897	0.1209	0.6666	0.6776	0.6720	0.9623	0.9774	0.9856	0.8887	0.9567	0.8848	0.9471	0.5858	0.4443	0.7776	0.9477	0.8110	0.9804	0.7916	0.6610	0.7299	0.0700	0.8701	0.7609	0.5071	0.6432	1.0	0.9197	0.9088	0.9648	0.9829	0.9534	0.2609	0.8441	0.7462	0.8918	0.6040	0.9262	0.4194	0.8408	0.9834	0.8206	0.8171	0.6754	0.9698	0.4345	0.9812	0.5896	0.8501	0.9236	0.5751	0.5900	0.4748	0.5231	0.6923	0.5301	0.9915	0.9796	0.7299	0.9891	0.9447	0.5085
0.0882	4.0	5196	0.1161	0.6722	0.6965	0.6841	0.9638	0.9718	0.9900	0.8882	0.9705	0.8853	0.9543	0.6118	0.4870	0.7765	0.9591	0.8066	0.9837	0.8624	0.6333	0.7563	0.2385	0.8982	0.7557	0.5353	0.6497	1.0	0.9205	0.9180	0.9651	0.9828	0.9488	0.2940	0.8703	0.7025	0.9113	0.6163	0.9163	0.4395	0.8634	0.9881	0.8473	0.9018	0.6874	0.9721	0.4599	0.9837	0.6139	0.8307	0.9193	0.5885	0.6180	0.5164	0.5544	0.7027	0.5589	0.9897	0.9841	0.7347	0.9863	0.9614	0.4974
0.0764	5.0	6495	0.1119	0.6887	0.7043	0.6964	0.9661	0.9754	0.9909	0.8968	0.9696	0.8958	0.9558	0.6231	0.4939	0.7855	0.9636	0.8203	0.9870	0.8612	0.7425	0.7627	0.0982	0.9107	0.7740	0.5599	0.6672	1.0	0.9311	0.9272	0.9687	0.9770	0.9728	0.3270	0.8654	0.7183	0.9173	0.6473	0.9296	0.4612	0.8625	0.9881	0.8622	0.9260	0.6963	0.9745	0.4805	0.9862	0.6201	0.8720	0.9302	0.5961	0.6282	0.5050	0.5606	0.7082	0.5796	0.9878	0.9852	0.7521	0.9646	0.9668	0.5227
0.0645	6.0	7794	0.1169	0.6930	0.7174	0.7050	0.9660	0.9820	0.9910	0.8980	0.9672	0.9057	0.9633	0.6393	0.5015	0.7901	0.9679	0.8131	0.9853	0.8545	0.7083	0.8079	0.2574	0.9170	0.7833	0.5912	0.6722	1.0	0.9451	0.9257	0.9727	0.9828	0.9575	0.3424	0.8225	0.6504	0.9186	0.6527	0.9293	0.4763	0.8833	0.9858	0.8462	0.9326	0.7296	0.9745	0.4830	0.9862	0.6415	0.8363	0.9286	0.5937	0.6443	0.5362	0.5685	0.7241	0.6023	0.9859	0.9807	0.7558	0.9753	0.9692	0.5277
0.0587	7.0	9093	0.1226	0.6923	0.7183	0.7051	0.9665	0.9820	0.9937	0.9013	0.9689	0.8966	0.9621	0.6535	0.5054	0.7921	0.9671	0.8220	0.9870	0.8582	0.7063	0.7943	0.2763	0.9171	0.7839	0.5918	0.6682	1.0	0.9304	0.9302	0.9716	0.9885	0.9495	0.3493	0.8137	0.6927	0.9216	0.6595	0.9336	0.4684	0.8825	0.9835	0.8349	0.9404	0.7217	0.9769	0.4853	0.9825	0.6447	0.8384	0.9286	0.6141	0.6360	0.5324	0.5770	0.7238	0.6028	0.9859	0.9818	0.7508	0.9728	0.9618	0.5324

Framework versions

Transformers 4.40.1
Pytorch 2.2.2+cu121
Datasets 2.19.0
Tokenizers 0.19.1