nerui-seq_bn-3

This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0541
• Location Precision: 0.9022
• Location Recall: 0.9651
• Location F1: 0.9326
• Location Number: 86
• Organization Precision: 0.9006
• Organization Recall: 0.9157
• Organization F1: 0.9081
• Organization Number: 178
• Person Precision: 0.9766
• Person Recall: 0.9766
• Person F1: 0.9766
• Person Number: 128
• Overall Precision: 0.9252
• Overall Recall: 0.9464
• Overall F1: 0.9357
• Overall Accuracy: 0.9857

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: 16
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100.0

Training results

Training Loss	Epoch	Step	Validation Loss	Location Precision	Location Recall	Location F1	Location Number	Organization Precision	Organization Recall	Organization F1	Organization Number	Person Precision	Person Recall	Person F1	Person Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.834	1.0	96	0.5200	0.0	0.0	0.0	86	0.3333	0.0112	0.0217	178	0.0	0.0	0.0	128	0.25	0.0051	0.0100	0.8437
0.4501	2.0	192	0.3053	0.4524	0.2209	0.2969	86	0.3739	0.4831	0.4216	178	0.3445	0.5625	0.4273	128	0.3680	0.4515	0.4055	0.9042
0.309	3.0	288	0.2180	0.5714	0.5116	0.5399	86	0.6212	0.6910	0.6543	178	0.6646	0.8203	0.7343	128	0.6282	0.6939	0.6594	0.9425
0.2169	4.0	384	0.1387	0.6633	0.7558	0.7065	86	0.75	0.7416	0.7458	178	0.8696	0.9375	0.9023	128	0.7694	0.8087	0.7886	0.9625
0.145	5.0	480	0.1083	0.7228	0.8488	0.7807	86	0.7424	0.8258	0.7819	178	0.9179	0.9609	0.9389	128	0.7921	0.875	0.8315	0.9671
0.1191	6.0	576	0.0931	0.7048	0.8605	0.7749	86	0.8249	0.8202	0.8225	178	0.9318	0.9609	0.9462	128	0.8285	0.875	0.8511	0.9703
0.1063	7.0	672	0.0904	0.7130	0.8953	0.7938	86	0.7989	0.8483	0.8229	178	0.9265	0.9844	0.9545	128	0.8176	0.9031	0.8582	0.9698
0.0947	8.0	768	0.0734	0.7624	0.8953	0.8235	86	0.8242	0.8427	0.8333	178	0.9535	0.9609	0.9572	128	0.8495	0.8929	0.8706	0.9768
0.085	9.0	864	0.0692	0.7959	0.9070	0.8478	86	0.8449	0.8876	0.8658	178	0.9466	0.9688	0.9575	128	0.8654	0.9184	0.8911	0.9789
0.082	10.0	960	0.0669	0.7959	0.9070	0.8478	86	0.8579	0.8820	0.8698	178	0.9615	0.9766	0.9690	128	0.8759	0.9184	0.8966	0.9789
0.0769	11.0	1056	0.0632	0.8182	0.9419	0.8757	86	0.8548	0.8933	0.8736	178	0.9612	0.9688	0.9650	128	0.8792	0.9286	0.9032	0.9803
0.0749	12.0	1152	0.0609	0.8421	0.9302	0.8840	86	0.8717	0.9157	0.8932	178	0.9690	0.9766	0.9728	128	0.8954	0.9388	0.9166	0.9819
0.0648	13.0	1248	0.0569	0.8316	0.9186	0.8729	86	0.8736	0.8933	0.8833	178	0.9612	0.9688	0.9650	128	0.8916	0.9235	0.9073	0.9811
0.0639	14.0	1344	0.0598	0.8211	0.9070	0.8619	86	0.9012	0.8708	0.8857	178	0.9612	0.9688	0.9650	128	0.9015	0.9107	0.9061	0.9811
0.0627	15.0	1440	0.0537	0.8495	0.9186	0.8827	86	0.8757	0.9101	0.8926	178	0.9843	0.9766	0.9804	128	0.9037	0.9337	0.9184	0.9819
0.0567	16.0	1536	0.0549	0.8247	0.9302	0.8743	86	0.8656	0.9045	0.8846	178	0.9615	0.9766	0.9690	128	0.8862	0.9337	0.9093	0.9792
0.0546	17.0	1632	0.0511	0.8696	0.9302	0.8989	86	0.8757	0.9101	0.8926	178	0.9843	0.9766	0.9804	128	0.9084	0.9362	0.9221	0.9830
0.0527	18.0	1728	0.0529	0.8454	0.9535	0.8962	86	0.9029	0.8876	0.8952	178	0.9688	0.9688	0.9688	128	0.91	0.9286	0.9192	0.9827
0.0492	19.0	1824	0.0535	0.8602	0.9302	0.8939	86	0.8977	0.8876	0.8927	178	0.9688	0.9688	0.9688	128	0.9118	0.9235	0.9176	0.9822
0.0474	20.0	1920	0.0501	0.8617	0.9419	0.9000	86	0.9061	0.9213	0.9136	178	0.9843	0.9766	0.9804	128	0.9204	0.9439	0.9320	0.9827
0.0447	21.0	2016	0.0528	0.8660	0.9767	0.9180	86	0.9045	0.9045	0.9045	178	0.9843	0.9766	0.9804	128	0.9204	0.9439	0.9320	0.9835
0.0453	22.0	2112	0.0522	0.8137	0.9651	0.8830	86	0.9056	0.9157	0.9106	178	0.9843	0.9766	0.9804	128	0.9071	0.9464	0.9263	0.9819
0.039	23.0	2208	0.0494	0.8384	0.9651	0.8973	86	0.92	0.9045	0.9122	178	0.9766	0.9766	0.9766	128	0.9179	0.9413	0.9295	0.9835
0.0414	24.0	2304	0.0537	0.83	0.9651	0.8925	86	0.9143	0.8989	0.9065	178	0.9766	0.9766	0.9766	128	0.9132	0.9388	0.9258	0.9819
0.038	25.0	2400	0.0514	0.8632	0.9535	0.9061	86	0.9191	0.8933	0.9060	178	0.9843	0.9766	0.9804	128	0.9266	0.9337	0.9301	0.9838
0.038	26.0	2496	0.0505	0.875	0.9767	0.9231	86	0.9244	0.8933	0.9086	178	0.9766	0.9766	0.9766	128	0.9293	0.9388	0.9340	0.9833
0.037	27.0	2592	0.0508	0.8469	0.9651	0.9022	86	0.9195	0.8989	0.9091	178	0.9843	0.9766	0.9804	128	0.9223	0.9388	0.9305	0.9825
0.0375	28.0	2688	0.0482	0.875	0.9767	0.9231	86	0.9101	0.9101	0.9101	178	0.9843	0.9766	0.9804	128	0.9252	0.9464	0.9357	0.9841
0.0342	29.0	2784	0.0484	0.8830	0.9651	0.9222	86	0.9096	0.9045	0.9070	178	0.9766	0.9766	0.9766	128	0.9248	0.9413	0.9330	0.9833
0.0314	30.0	2880	0.0489	0.8557	0.9651	0.9071	86	0.8913	0.9213	0.9061	178	0.9767	0.9844	0.9805	128	0.9098	0.9515	0.9302	0.9841
0.0308	31.0	2976	0.0522	0.8660	0.9767	0.9180	86	0.9029	0.8876	0.8952	178	0.9766	0.9766	0.9766	128	0.9175	0.9362	0.9268	0.9825
0.0284	32.0	3072	0.0507	0.875	0.9767	0.9231	86	0.9143	0.8989	0.9065	178	0.9766	0.9766	0.9766	128	0.9248	0.9413	0.9330	0.9833
0.029	33.0	3168	0.0519	0.8485	0.9767	0.9081	86	0.9133	0.8876	0.9003	178	0.9766	0.9766	0.9766	128	0.9175	0.9362	0.9268	0.9819
0.0273	34.0	3264	0.0514	0.8660	0.9767	0.9180	86	0.92	0.9045	0.9122	178	0.9766	0.9766	0.9766	128	0.925	0.9439	0.9343	0.9827
0.0273	35.0	3360	0.0535	0.8660	0.9767	0.9180	86	0.9133	0.8876	0.9003	178	0.9766	0.9766	0.9766	128	0.9221	0.9362	0.9291	0.9827
0.0275	36.0	3456	0.0519	0.8384	0.9651	0.8973	86	0.8895	0.9045	0.8969	178	0.9615	0.9766	0.9690	128	0.9	0.9413	0.9202	0.9814
0.0244	37.0	3552	0.0511	0.8438	0.9419	0.8901	86	0.8989	0.8989	0.8989	178	0.9766	0.9766	0.9766	128	0.9104	0.9337	0.9219	0.9819
0.0272	38.0	3648	0.0563	0.8660	0.9767	0.9180	86	0.9029	0.8876	0.8952	178	0.9766	0.9766	0.9766	128	0.9175	0.9362	0.9268	0.9827
0.028	39.0	3744	0.0517	0.875	0.9767	0.9231	86	0.9101	0.9101	0.9101	178	0.9766	0.9766	0.9766	128	0.9229	0.9464	0.9345	0.9835
0.0236	40.0	3840	0.0525	0.8723	0.9535	0.9111	86	0.9056	0.9157	0.9106	178	0.9766	0.9766	0.9766	128	0.9204	0.9439	0.9320	0.9833
0.0223	41.0	3936	0.0547	0.8901	0.9419	0.9153	86	0.9157	0.9157	0.9157	178	0.9766	0.9766	0.9766	128	0.9295	0.9413	0.9354	0.9835
0.0228	42.0	4032	0.0505	0.8804	0.9419	0.9101	86	0.9011	0.9213	0.9111	178	0.9766	0.9766	0.9766	128	0.9204	0.9439	0.9320	0.9841
0.0233	43.0	4128	0.0556	0.8646	0.9651	0.9121	86	0.9061	0.9213	0.9136	178	0.9766	0.9766	0.9766	128	0.9185	0.9490	0.9335	0.9835
0.0219	44.0	4224	0.0529	0.8571	0.9767	0.9130	86	0.8865	0.9213	0.9036	178	0.9690	0.9766	0.9728	128	0.9053	0.9515	0.9279	0.9835
0.0194	45.0	4320	0.0572	0.8660	0.9767	0.9180	86	0.9195	0.8989	0.9091	178	0.9766	0.9766	0.9766	128	0.9248	0.9413	0.9330	0.9819
0.0212	46.0	4416	0.0550	0.8454	0.9535	0.8962	86	0.8919	0.9270	0.9091	178	0.9615	0.9766	0.9690	128	0.9029	0.9490	0.9254	0.9827
0.019	47.0	4512	0.0515	0.8511	0.9302	0.8889	86	0.8967	0.9270	0.9116	178	0.9690	0.9766	0.9728	128	0.9091	0.9439	0.9262	0.9843
0.0182	48.0	4608	0.0524	0.8632	0.9535	0.9061	86	0.9006	0.9157	0.9081	178	0.9766	0.9766	0.9766	128	0.9158	0.9439	0.9296	0.9841
0.0185	49.0	4704	0.0523	0.8830	0.9651	0.9222	86	0.9148	0.9045	0.9096	178	0.9766	0.9766	0.9766	128	0.9271	0.9413	0.9342	0.9843
0.0181	50.0	4800	0.0539	0.875	0.9767	0.9231	86	0.9	0.9101	0.9050	178	0.9766	0.9766	0.9766	128	0.9183	0.9464	0.9322	0.9838
0.0181	51.0	4896	0.0564	0.8925	0.9651	0.9274	86	0.9205	0.9101	0.9153	178	0.9766	0.9766	0.9766	128	0.9320	0.9439	0.9379	0.9841
0.0177	52.0	4992	0.0585	0.8830	0.9651	0.9222	86	0.9314	0.9157	0.9235	178	0.9766	0.9766	0.9766	128	0.9345	0.9464	0.9404	0.9835
0.0168	53.0	5088	0.0541	0.8333	0.9302	0.8791	86	0.8877	0.9326	0.9096	178	0.9690	0.9766	0.9728	128	0.9005	0.9464	0.9229	0.9835
0.0172	54.0	5184	0.0514	0.8696	0.9302	0.8989	86	0.8930	0.9382	0.9151	178	0.9690	0.9766	0.9728	128	0.9118	0.9490	0.9300	0.9846
0.0165	55.0	5280	0.0504	0.9022	0.9651	0.9326	86	0.9111	0.9213	0.9162	178	0.9843	0.9766	0.9804	128	0.9323	0.9490	0.9406	0.9854
0.017	56.0	5376	0.0514	0.8830	0.9651	0.9222	86	0.9081	0.9438	0.9256	178	0.9766	0.9766	0.9766	128	0.9238	0.9592	0.9412	0.9852
0.0153	57.0	5472	0.0513	0.8737	0.9651	0.9171	86	0.8777	0.9270	0.9016	178	0.9766	0.9766	0.9766	128	0.9075	0.9515	0.9290	0.9865
0.0157	58.0	5568	0.0568	0.8936	0.9767	0.9333	86	0.9195	0.8989	0.9091	178	0.9766	0.9766	0.9766	128	0.9318	0.9413	0.9365	0.9841
0.0139	59.0	5664	0.0530	0.9101	0.9419	0.9257	86	0.8944	0.9045	0.8994	178	0.9766	0.9766	0.9766	128	0.9244	0.9362	0.9303	0.9838
0.0156	60.0	5760	0.0518	0.8646	0.9651	0.9121	86	0.8804	0.9101	0.8950	178	0.9690	0.9766	0.9728	128	0.9046	0.9439	0.9238	0.9841
0.0134	61.0	5856	0.0491	0.9101	0.9419	0.9257	86	0.9027	0.9382	0.9201	178	0.9690	0.9766	0.9728	128	0.9256	0.9515	0.9384	0.9852
0.0128	62.0	5952	0.0513	0.8913	0.9535	0.9213	86	0.8770	0.9213	0.8986	178	0.9690	0.9766	0.9728	128	0.9093	0.9464	0.9275	0.9843
0.0126	63.0	6048	0.0512	0.9121	0.9651	0.9379	86	0.8919	0.9270	0.9091	178	0.9690	0.9766	0.9728	128	0.9210	0.9515	0.9360	0.9854
0.0134	64.0	6144	0.0520	0.9011	0.9535	0.9266	86	0.8956	0.9157	0.9056	178	0.9766	0.9766	0.9766	128	0.9227	0.9439	0.9332	0.9843
0.0128	65.0	6240	0.0494	0.9022	0.9651	0.9326	86	0.8783	0.9326	0.9046	178	0.9690	0.9766	0.9728	128	0.9122	0.9541	0.9327	0.9860
0.0119	66.0	6336	0.0511	0.8830	0.9651	0.9222	86	0.8811	0.9157	0.8981	178	0.9690	0.9766	0.9728	128	0.9093	0.9464	0.9275	0.9852
0.012	67.0	6432	0.0549	0.8830	0.9651	0.9222	86	0.92	0.9045	0.9122	178	0.9766	0.9766	0.9766	128	0.9295	0.9413	0.9354	0.9852
0.0124	68.0	6528	0.0523	0.8913	0.9535	0.9213	86	0.8865	0.9213	0.9036	178	0.9690	0.9766	0.9728	128	0.9138	0.9464	0.9298	0.9838
0.0139	69.0	6624	0.0550	0.8817	0.9535	0.9162	86	0.9096	0.9045	0.9070	178	0.9690	0.9766	0.9728	128	0.9223	0.9388	0.9305	0.9841
0.0121	70.0	6720	0.0528	0.9022	0.9651	0.9326	86	0.8871	0.9270	0.9066	178	0.9690	0.9766	0.9728	128	0.9165	0.9515	0.9337	0.9852
0.0113	71.0	6816	0.0500	0.8901	0.9419	0.9153	86	0.8730	0.9270	0.8992	178	0.9690	0.9766	0.9728	128	0.9071	0.9464	0.9263	0.9857
0.0114	72.0	6912	0.0560	0.8804	0.9419	0.9101	86	0.8811	0.9157	0.8981	178	0.9690	0.9766	0.9728	128	0.9089	0.9413	0.9248	0.9843
0.01	73.0	7008	0.0532	0.8737	0.9651	0.9171	86	0.8871	0.9270	0.9066	178	0.9690	0.9766	0.9728	128	0.9098	0.9515	0.9302	0.9857
0.0138	74.0	7104	0.0525	0.8925	0.9651	0.9274	86	0.8817	0.9213	0.9011	178	0.9690	0.9766	0.9728	128	0.9118	0.9490	0.9300	0.9852
0.0108	75.0	7200	0.0573	0.8646	0.9651	0.9121	86	0.9040	0.8989	0.9014	178	0.9690	0.9766	0.9728	128	0.9154	0.9388	0.9270	0.9827
0.0113	76.0	7296	0.0550	0.9022	0.9651	0.9326	86	0.8950	0.9101	0.9025	178	0.9690	0.9766	0.9728	128	0.9204	0.9439	0.9320	0.9849
0.0111	77.0	7392	0.0564	0.9121	0.9651	0.9379	86	0.9157	0.9157	0.9157	178	0.9766	0.9766	0.9766	128	0.9345	0.9464	0.9404	0.9846
0.0114	78.0	7488	0.0565	0.8737	0.9651	0.9171	86	0.8950	0.9101	0.9025	178	0.9766	0.9766	0.9766	128	0.9158	0.9439	0.9296	0.9833
0.0101	79.0	7584	0.0547	0.9022	0.9651	0.9326	86	0.9111	0.9213	0.9162	178	0.9690	0.9766	0.9728	128	0.9277	0.9490	0.9382	0.9846
0.0108	80.0	7680	0.0527	0.9022	0.9651	0.9326	86	0.8865	0.9213	0.9036	178	0.9690	0.9766	0.9728	128	0.9163	0.9490	0.9323	0.9854
0.0108	81.0	7776	0.0524	0.8925	0.9651	0.9274	86	0.8877	0.9326	0.9096	178	0.9690	0.9766	0.9728	128	0.9144	0.9541	0.9338	0.9860
0.0108	82.0	7872	0.0553	0.8830	0.9651	0.9222	86	0.8901	0.9101	0.9000	178	0.9766	0.9766	0.9766	128	0.9158	0.9439	0.9296	0.9846
0.0109	83.0	7968	0.0529	0.8925	0.9651	0.9274	86	0.8907	0.9157	0.9030	178	0.9690	0.9766	0.9728	128	0.9160	0.9464	0.9310	0.9852
0.0095	84.0	8064	0.0545	0.8925	0.9651	0.9274	86	0.9	0.9101	0.9050	178	0.9766	0.9766	0.9766	128	0.9227	0.9439	0.9332	0.9846
0.0096	85.0	8160	0.0556	0.9022	0.9651	0.9326	86	0.9101	0.9101	0.9101	178	0.9766	0.9766	0.9766	128	0.9296	0.9439	0.9367	0.9841
0.0098	86.0	8256	0.0534	0.9022	0.9651	0.9326	86	0.9022	0.9326	0.9171	178	0.9690	0.9766	0.9728	128	0.9235	0.9541	0.9385	0.9854
0.0103	87.0	8352	0.0529	0.9121	0.9651	0.9379	86	0.9056	0.9157	0.9106	178	0.9690	0.9766	0.9728	128	0.9275	0.9464	0.9369	0.9854
0.0113	88.0	8448	0.0537	0.8925	0.9651	0.9274	86	0.9016	0.9270	0.9141	178	0.9766	0.9766	0.9766	128	0.9233	0.9515	0.9372	0.9857
0.0103	89.0	8544	0.0538	0.8913	0.9535	0.9213	86	0.8913	0.9213	0.9061	178	0.9690	0.9766	0.9728	128	0.9160	0.9464	0.9310	0.9852
0.0101	90.0	8640	0.0522	0.8913	0.9535	0.9213	86	0.8865	0.9213	0.9036	178	0.9690	0.9766	0.9728	128	0.9138	0.9464	0.9298	0.9849
0.0089	91.0	8736	0.0528	0.9022	0.9651	0.9326	86	0.8859	0.9157	0.9006	178	0.9690	0.9766	0.9728	128	0.9160	0.9464	0.9310	0.9852
0.0088	92.0	8832	0.0547	0.9022	0.9651	0.9326	86	0.8956	0.9157	0.9056	178	0.9690	0.9766	0.9728	128	0.9206	0.9464	0.9333	0.9849
0.0099	93.0	8928	0.0542	0.9022	0.9651	0.9326	86	0.8907	0.9157	0.9030	178	0.9690	0.9766	0.9728	128	0.9183	0.9464	0.9322	0.9849
0.0095	94.0	9024	0.0542	0.9022	0.9651	0.9326	86	0.8907	0.9157	0.9030	178	0.9690	0.9766	0.9728	128	0.9183	0.9464	0.9322	0.9849
0.0094	95.0	9120	0.0536	0.9022	0.9651	0.9326	86	0.8907	0.9157	0.9030	178	0.9766	0.9766	0.9766	128	0.9206	0.9464	0.9333	0.9857
0.0093	96.0	9216	0.0531	0.9022	0.9651	0.9326	86	0.8913	0.9213	0.9061	178	0.9766	0.9766	0.9766	128	0.9208	0.9490	0.9347	0.9862
0.009	97.0	9312	0.0536	0.9022	0.9651	0.9326	86	0.8865	0.9213	0.9036	178	0.9690	0.9766	0.9728	128	0.9163	0.9490	0.9323	0.9857
0.0099	98.0	9408	0.0538	0.9022	0.9651	0.9326	86	0.8956	0.9157	0.9056	178	0.9766	0.9766	0.9766	128	0.9229	0.9464	0.9345	0.9854
0.0089	99.0	9504	0.0541	0.9121	0.9651	0.9379	86	0.9006	0.9157	0.9081	178	0.9766	0.9766	0.9766	128	0.9275	0.9464	0.9369	0.9860
0.0107	100.0	9600	0.0541	0.9022	0.9651	0.9326	86	0.9006	0.9157	0.9081	178	0.9766	0.9766	0.9766	128	0.9252	0.9464	0.9357	0.9857

Framework versions

• Transformers 4.39.3
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.15.2