metadata

tags:
  - generated_from_trainer
model-index:
  - name: icdar23-entrydetector_plaintext
    results: []

icdar23-entrydetector_plaintext

This model is a fine-tuned version of HueyNemud/das22-10-camembert_pretrained on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0337
Ebegin: {'precision': 0.9737045630317092, 'recall': 0.9469725460699511, 'f1': 0.9601525262154433, 'number': 2659}
Eend: {'precision': 0.9644312708410523, 'recall': 0.9727204783258595, 'f1': 0.9685581395348838, 'number': 2676}
Overall Precision: 0.9690
Overall Recall: 0.9599
Overall F1: 0.9644
Overall Accuracy: 0.9931

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	0.07	300	0.0380	0.9713	0.9691	0.9702	0.9942
0.1537	0.14	600	0.0318	0.9933	0.9550	0.9738	0.9947
0.1537	0.21	900	0.0185	0.9842	0.9780	0.9811	0.9962
0.0262	0.29	1200	0.0176	0.9883	0.9754	0.9818	0.9963
0.0171	0.36	1500	0.0174	0.9915	0.9650	0.9781	0.9955
0.0171	0.43	1800	0.0139	0.9869	0.9787	0.9828	0.9965
0.0151	0.5	2100	0.0142	0.9845	0.9814	0.9830	0.9965
0.0151	0.57	2400	0.0185	0.9894	0.9713	0.9803	0.9960
0.0144	0.64	2700	0.0150	0.9864	0.9789	0.9827	0.9965
0.0134	0.72	3000	0.0197	0.9848	0.9734	0.9791	0.9957
0.0134	0.79	3300	0.0201	0.9809	0.9804	0.9806	0.9960
0.012	0.86	3600	0.0163	0.9794	0.9832	0.9813	0.9961