IndoBert-large-ler

jafarabdurrohman/IndoBert-large-ler

IndoBert-large-ler is a token classification model from jafarabdurrohman. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.

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

Downloads · 30 days

3% of all-time downloads

All-time downloads

204

Public

Repo size

22.7 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin1.3 GB · 100%

At a glance

Task: Token Classification
Library: transformers
License: mit
Model type: bert
Access: Public
Created: Jun 8, 2023
Updated: Aug 2, 2023
SHA: b27c440e

Try a prompt

Model card

From the Hugging Face model README

IndoBert-large-ler

This model is a fine-tuned version of indobenchmark/indobert-large-p1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.0280
Overall Precision: 0.8514
Overall Recall: 0.8391
Overall F1: 0.8452
Overall Accuracy: 0.9965
Jenis amar F1: 0.9373
Jenis dakwaan F1: 0.8619
Jenis perkara F1: 0.8023
Melanggar uu (dakwaan) F1: 0.6952
Melanggar uu (pertimbangan hukum) F1: 0.5805
Melanggar uu (tuntutan) F1: 0.8052
Nama hakim anggota F1: 0.9106
Nama hakim ketua F1: 0.8938
Nama jaksa F1: 0.9034
Nama panitera F1: 0.9078
Nama pengacara F1: 0.7839
Nama pengadilan F1: 0.9964
Nama saksi F1: 0.8391
Nama terdakwa F1: 0.8208
Nomor putusan F1: 0.9346
Putusan hukuman F1: 0.7023
Tanggal kejadian F1: 0.4252
Tanggal putusan F1: 0.9267
Tingkat kasus F1: 0.9725
Tuntutan hukuman F1: 0.8329

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
max_sequence_length: 128
stride: 0%
decay_rate: 0.01
num_epochs: 16

Training results

Training Loss	Epoch	Step	Validation Loss	Overall Precision	Overall Recall	Overall F1	Overall Accuracy	Jenis amar F1	Jenis dakwaan F1	Jenis perkara F1	Melanggar uu (dakwaan) F1	Melanggar uu (pertimbangan hukum) F1	Melanggar uu (tuntutan) F1	Nama hakim anggota F1	Nama hakim ketua F1	Nama jaksa F1	Nama panitera F1	Nama pengacara F1	Nama pengadilan F1	Nama saksi F1	Nama terdakwa F1	Nomor putusan F1	Putusan hukuman F1	Tanggal kejadian F1	Tanggal putusan F1	Tingkat kasus F1	Tuntutan hukuman F1
0.0166	1.0	2748	0.0249	0.7758	0.7067	0.7396	0.9936	0.8423	0.1685	0.5932	0.5248	0.5367	0.6792	0.8378	0.8500	0.8651	0.8257	0.1235	0.9474	0.7851	0.8169	0.8446	0.5196	0.3771	0.6203	0.8691	0.4773
0.0142	2.0	5496	0.0174	0.7433	0.7866	0.7643	0.9953	0.8768	0.7126	0.7329	0.6098	0.5700	0.7270	0.6293	0.3585	0.8772	0.8900	0.6534	0.9964	0.8461	0.8220	0.9333	0.5072	0.3842	0.6283	0.9580	0.7159
0.0107	3.0	8244	0.0209	0.7960	0.8236	0.8096	0.9948	0.8627	0.7920	0.4613	0.6199	0.5762	0.6600	0.8954	0.8941	0.8941	0.8980	0.6855	0.9856	0.8192	0.7853	0.9395	0.6171	0.4233	0.9384	0.9708	0.7573
0.0084	4.0	10992	0.0148	0.8054	0.8351	0.8200	0.9962	0.8912	0.7805	0.7989	0.6511	0.5696	0.7557	0.88	0.8964	0.8900	0.8820	0.4533	0.9821	0.8314	0.7595	0.9331	0.5484	0.4451	0.8849	0.9668	0.7673
0.0069	5.0	13740	0.0155	0.8370	0.8155	0.8261	0.9963	0.9191	0.8512	0.7623	0.6756	0.5732	0.7616	0.8632	0.8410	0.8791	0.8608	0.6745	0.9910	0.8442	0.7191	0.9303	0.6130	0.4351	0.9225	0.9761	0.7955
0.0059	6.0	16488	0.0175	0.8275	0.8302	0.8288	0.9960	0.9276	0.8049	0.7938	0.6219	0.5088	0.7215	0.8839	0.8760	0.8831	0.9057	0.7259	0.9910	0.8389	0.8276	0.9410	0.5837	0.3982	0.9328	0.9779	0.8022
0.0052	7.0	19236	0.0171	0.8260	0.8216	0.8238	0.9963	0.9171	0.8367	0.7810	0.6305	0.5604	0.7232	0.8284	0.8767	0.8149	0.8513	0.6970	0.9964	0.8430	0.8277	0.9390	0.5832	0.4070	0.9403	0.9761	0.7783
0.1431	8.0	21984	0.0192	0.8253	0.8308	0.8281	0.9961	0.8596	0.8175	0.7848	0.6045	0.5592	0.6472	0.8952	0.88	0.8824	0.8912	0.7492	0.9731	0.8562	0.8538	0.9379	0.5667	0.3996	0.9265	0.9761	0.7778
0.0036	9.0	24732	0.0164	0.8209	0.8462	0.8334	0.9961	0.9193	0.8456	0.8104	0.6787	0.5545	0.7774	0.9022	0.8822	0.8929	0.9006	0.7464	0.9910	0.8549	0.8479	0.9415	0.6494	0.3990	0.9149	0.9798	0.6811
0.0032	10.0	27480	0.0194	0.8392	0.8437	0.8414	0.9964	0.9257	0.8246	0.8007	0.6742	0.5632	0.7942	0.9032	0.8925	0.8934	0.8966	0.7579	0.9964	0.8432	0.8340	0.9445	0.6418	0.4387	0.9474	0.9761	0.8386
0.0032	11.0	30228	0.0216	0.8442	0.8332	0.8387	0.9965	0.9040	0.7774	0.8063	0.6756	0.5577	0.7815	0.9117	0.8760	0.9000	0.9019	0.7518	0.9856	0.8491	0.8318	0.9313	0.6316	0.4012	0.9286	0.9725	0.8297
0.0022	12.0	32976	0.0224	0.8353	0.8356	0.8354	0.9964	0.9298	0.8646	0.7923	0.6704	0.5808	0.7862	0.9123	0.8811	0.8913	0.8894	0.7801	0.9964	0.8345	0.7984	0.9282	0.6599	0.4072	0.9403	0.9688	0.8069
0.0013	13.0	35724	0.0229	0.8367	0.8435	0.8401	0.9963	0.9308	0.8629	0.7861	0.6681	0.5662	0.8152	0.9166	0.8932	0.8986	0.9019	0.7917	0.9875	0.8378	0.7869	0.9381	0.6543	0.4279	0.9242	0.9744	0.8398
0.0007	14.0	38472	0.0262	0.8474	0.8372	0.8423	0.9965	0.9373	0.8619	0.7910	0.6689	0.5752	0.7948	0.9111	0.8897	0.9038	0.9103	0.7758	0.9964	0.8438	0.8213	0.9333	0.6619	0.4290	0.9288	0.9670	0.8046
0.0005	15.0	41220	0.0270	0.8464	0.8400	0.8432	0.9964	0.9357	0.8609	0.7948	0.6794	0.5756	0.7987	0.9067	0.8915	0.9054	0.9076	0.7692	0.9964	0.8400	0.8275	0.9356	0.7157	0.4253	0.9217	0.9744	0.8161
0.0004	16.0	43968	0.0280	0.8514	0.8391	0.8452	0.9965	0.9373	0.8619	0.8023	0.6952	0.5805	0.8052	0.9106	0.8938	0.9034	0.9078	0.7839	0.9964	0.8391	0.8208	0.9346	0.7023	0.4252	0.9267	0.9725	0.8329

Framework versions

Transformers 4.28.1
Pytorch 2.0.1
Datasets 2.12.0
Tokenizers 0.13.3

Task: Token Classification
Library: transformers
Type: bert
License: mit
Created: Jun 8, 2023
Updated: Aug 2, 2023