timhbach/Team_Gryffindor_NER - AI Model Zoo

Team-Gryffindor-distilbert-base-finetuned-NER-creditcardcontract-100epoch

This model is a fine-tuned version of distilbert-base-uncased on the Credit card agreement dataset. It achieves the following results on the evaluation set:

Loss: 0.0470
Precision: 0.7319
Recall: 0.7064
F1: 0.7190
Accuracy: 0.9920

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0113	0.33	500	0.0443	0.6547	0.7028	0.6779	0.9908
0.0118	0.67	1000	0.0435	0.7207	0.6440	0.6802	0.9916
0.013	1.0	1500	0.0449	0.7113	0.6826	0.6966	0.9918
0.0113	1.34	2000	0.0434	0.7213	0.6697	0.6946	0.9915
0.0121	1.67	2500	0.0467	0.6955	0.6789	0.6871	0.9914
0.0125	2.01	3000	0.0417	0.7095	0.6991	0.7043	0.9920
0.0106	2.34	3500	0.0437	0.7191	0.6624	0.6896	0.9918
0.0114	2.68	4000	0.0468	0.7165	0.6679	0.6914	0.9920
0.0125	3.01	4500	0.0431	0.6888	0.6862	0.6875	0.9917
0.0107	3.35	5000	0.0446	0.7184	0.6459	0.6802	0.9913
0.0096	3.68	5500	0.0485	0.6926	0.6532	0.6723	0.9912
0.013	4.02	6000	0.0448	0.6134	0.6697	0.6404	0.9907
0.0102	4.35	6500	0.0497	0.6895	0.6642	0.6766	0.9913
0.0112	4.69	7000	0.0464	0.6759	0.6697	0.6728	0.9910
0.0117	5.02	7500	0.0484	0.7451	0.6275	0.6813	0.9916
0.0114	5.36	8000	0.0411	0.7086	0.6826	0.6953	0.9919
0.0108	5.69	8500	0.0443	0.7041	0.6679	0.6855	0.9916
0.0109	6.03	9000	0.0470	0.7228	0.6697	0.6952	0.9916
0.0099	6.36	9500	0.0471	0.7253	0.6881	0.7062	0.9913
0.0103	6.7	10000	0.0430	0.6986	0.7101	0.7043	0.9914
0.0117	7.03	10500	0.0462	0.7327	0.6991	0.7155	0.9918
0.0098	7.37	11000	0.0483	0.6910	0.6771	0.6840	0.9914
0.0107	7.7	11500	0.0468	0.7189	0.6899	0.7041	0.9916
0.0119	8.04	12000	0.0434	0.6970	0.6881	0.6925	0.9918
0.0112	8.37	12500	0.0469	0.7007	0.6917	0.6962	0.9918
0.011	8.71	13000	0.0469	0.6736	0.6514	0.6623	0.9914
0.0101	9.04	13500	0.0451	0.6691	0.6606	0.6648	0.9913
0.0099	9.38	14000	0.0462	0.7006	0.6826	0.6914	0.9918
0.0107	9.71	14500	0.0444	0.6840	0.6752	0.6796	0.9915
0.0118	10.05	15000	0.0457	0.7015	0.6771	0.6891	0.9918
0.0102	10.38	15500	0.0500	0.7413	0.6679	0.7027	0.9919
0.0107	10.72	16000	0.0470	0.7319	0.7064	0.7190	0.9920

Framework versions

Transformers 4.18.0
Pytorch 1.10.0+cu111
Datasets 2.0.0
Tokenizers 0.11.6