distilbert-base-uncased-ner-invoiceSenderRecipient-all-inv-26-12

Lilya/distilbert-base-uncased-ner-invoiceSenderRecipient-all-inv-26-12

distilbert-base-uncased-ner-invoiceSenderRecipient-all-inv-26-12 is a token classification model from Lilya. Use it when you need labels on individual words, such as names. It is set up for transformers.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

1% of all-time downloads

All-time downloads

474

Public

Repo size

7.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin266 MB · 100%

At a glance

Task: Token Classification
Library: transformers
Model type: distilbert
Access: Public
Created: Dec 27, 2022
Updated: Jan 2, 2023
SHA: 54740163

Try a prompt

Model card

From the Hugging Face model README

distilbert-base-uncased-ner-invoiceSenderRecipient-all-inv-26-12

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0245
Precision: 0.8602
Recall: 0.9015
F1: 0.8804
Accuracy: 0.9921

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.0157	0.06	500	0.0286	0.8569	0.8605	0.8587	0.9908
0.0156	0.11	1000	0.0287	0.8340	0.8940	0.8630	0.9910
0.0141	0.17	1500	0.0296	0.8368	0.8853	0.8604	0.9908
0.014	0.23	2000	0.0296	0.8356	0.8915	0.8627	0.9910
0.0144	0.28	2500	0.0306	0.8310	0.8896	0.8593	0.9906
0.0136	0.34	3000	0.0290	0.8384	0.8842	0.8607	0.9910
0.0134	0.4	3500	0.0306	0.8514	0.8779	0.8645	0.9912
0.0138	0.46	4000	0.0307	0.8475	0.8790	0.8630	0.9910
0.0139	0.51	4500	0.0301	0.8208	0.9002	0.8587	0.9908
0.014	0.57	5000	0.0320	0.8307	0.8981	0.8631	0.9909
0.0155	0.63	5500	0.0307	0.8329	0.8992	0.8648	0.9909
0.0154	0.68	6000	0.0268	0.8403	0.8971	0.8677	0.9913
0.0178	0.74	6500	0.0269	0.8548	0.8869	0.8705	0.9916
0.0177	0.8	7000	0.0268	0.8552	0.8904	0.8725	0.9917
0.0178	0.85	7500	0.0267	0.8498	0.8972	0.8729	0.9917
0.017	0.91	8000	0.0259	0.8517	0.8969	0.8737	0.9917
0.0176	0.97	8500	0.0249	0.8523	0.8921	0.8717	0.9916
0.0157	1.02	9000	0.0274	0.8535	0.8990	0.8757	0.9918
0.0134	1.08	9500	0.0293	0.8375	0.9060	0.8704	0.9913
0.0132	1.14	10000	0.0278	0.8648	0.8864	0.8755	0.9919
0.0135	1.19	10500	0.0273	0.8540	0.8958	0.8744	0.9917
0.0133	1.25	11000	0.0277	0.8442	0.9034	0.8728	0.9917
0.0138	1.31	11500	0.0276	0.8484	0.9035	0.8751	0.9917
0.0141	1.37	12000	0.0274	0.8501	0.9016	0.8751	0.9918
0.0137	1.42	12500	0.0274	0.8529	0.9010	0.8763	0.9918
0.014	1.48	13000	0.0269	0.8509	0.9022	0.8758	0.9919
0.0141	1.54	13500	0.0260	0.8653	0.8926	0.8787	0.9920
0.0149	1.59	14000	0.0258	0.8521	0.9048	0.8777	0.9919
0.0149	1.65	14500	0.0257	0.8607	0.8980	0.8790	0.9921
0.0152	1.71	15000	0.0257	0.8596	0.9001	0.8794	0.9920
0.015	1.76	15500	0.0257	0.8556	0.9032	0.8788	0.9920
0.0157	1.82	16000	0.0248	0.8620	0.8993	0.8802	0.9922
0.0158	1.88	16500	0.0251	0.8573	0.9036	0.8798	0.9921
0.0163	1.93	17000	0.0248	0.8579	0.9034	0.8800	0.9921
0.017	1.99	17500	0.0245	0.8602	0.9015	0.8804	0.9921

Framework versions

Transformers 4.15.0
Pytorch 1.10.0
Datasets 2.3.2
Tokenizers 0.10.3

Task: Token Classification
Library: transformers
Type: distilbert
Created: Dec 27, 2022
Updated: Jan 2, 2023