nerugm-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: 0.1728
• Location Precision: 0.7241
• Location Recall: 0.8873
• Location F1: 0.7975
• Location Number: 71
• Organization Precision: 0.6023
• Organization Recall: 0.8154
• Organization F1: 0.6928
• Organization Number: 65
• Person Precision: 0.8447
• Person Recall: 0.9067
• Person F1: 0.8746
• Person Number: 150
• Quantity Precision: 0.7073
• Quantity Recall: 0.8788
• Quantity F1: 0.7838
• Quantity Number: 33
• Time Precision: 0.9231
• Time Recall: 0.8571
• Time F1: 0.8889
• Time Number: 28
• Overall Precision: 0.7568
• Overall Recall: 0.8790
• Overall F1: 0.8133
• Overall Accuracy: 0.9581

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	Quantity Precision	Quantity Recall	Quantity F1	Quantity Number	Time Precision	Time Recall	Time F1	Time Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.9441	1.0	106	0.6185	0.0	0.0	0.0	71	0.0	0.0	0.0	65	0.3333	0.0067	0.0131	150	0.0	0.0	0.0	33	0.0	0.0	0.0	28	0.3333	0.0029	0.0057	0.8414
0.5645	2.0	212	0.4194	0.44	0.1549	0.2292	71	0.0571	0.0308	0.04	65	0.4709	0.6467	0.5449	150	0.0	0.0	0.0	33	0.5556	0.3571	0.4348	28	0.4225	0.3458	0.3803	0.8877
0.3968	3.0	318	0.3094	0.4565	0.5915	0.5153	71	0.3509	0.3077	0.3279	65	0.5753	0.84	0.6829	150	0.1875	0.1818	0.1846	33	0.875	0.75	0.8077	28	0.5071	0.6196	0.5577	0.9202
0.2937	4.0	424	0.2223	0.4653	0.6620	0.5465	71	0.5172	0.4615	0.4878	65	0.7443	0.8733	0.8037	150	0.4186	0.5455	0.4737	33	0.8519	0.8214	0.8364	28	0.6148	0.7176	0.6622	0.9370
0.2294	5.0	530	0.1804	0.5930	0.7183	0.6497	71	0.5429	0.5846	0.5630	65	0.7738	0.8667	0.8176	150	0.4565	0.6364	0.5316	33	0.9231	0.8571	0.8889	28	0.6667	0.7608	0.7106	0.9428
0.1955	6.0	636	0.1957	0.5980	0.8592	0.7052	71	0.4851	0.7538	0.5904	65	0.7472	0.8867	0.8110	150	0.4444	0.7273	0.5517	33	0.7667	0.8214	0.7931	28	0.6237	0.8357	0.7143	0.9396
0.1799	7.0	742	0.1606	0.6629	0.8310	0.7375	71	0.5875	0.7231	0.6483	65	0.7706	0.8733	0.8187	150	0.5510	0.8182	0.6585	33	0.8	0.8571	0.8276	28	0.6890	0.8300	0.7529	0.9469
0.1628	8.0	848	0.1527	0.6421	0.8592	0.7349	71	0.5556	0.7692	0.6452	65	0.7811	0.88	0.8276	150	0.6	0.8182	0.6923	33	0.8276	0.8571	0.8421	28	0.6869	0.8473	0.7587	0.9510
0.1528	9.0	954	0.1416	0.6941	0.8310	0.7564	71	0.5663	0.7231	0.6351	65	0.8086	0.8733	0.8397	150	0.6429	0.8182	0.7200	33	0.8621	0.8929	0.8772	28	0.7207	0.8329	0.7727	0.9522
0.1466	10.0	1060	0.1407	0.6706	0.8028	0.7308	71	0.5696	0.6923	0.625	65	0.8125	0.8667	0.8387	150	0.6512	0.8485	0.7368	33	0.8333	0.8929	0.8621	28	0.7179	0.8213	0.7661	0.9522
0.138	11.0	1166	0.1406	0.6966	0.8732	0.775	71	0.5976	0.7538	0.6667	65	0.8075	0.8667	0.8360	150	0.6512	0.8485	0.7368	33	0.8333	0.8929	0.8621	28	0.7259	0.8473	0.7819	0.9537
0.1314	12.0	1272	0.1420	0.6966	0.8732	0.775	71	0.5747	0.7692	0.6579	65	0.8049	0.88	0.8408	150	0.6512	0.8485	0.7368	33	0.75	0.8571	0.8000	28	0.7133	0.8530	0.7769	0.9534
0.1285	13.0	1378	0.1342	0.6628	0.8028	0.7261	71	0.5618	0.7692	0.6494	65	0.8148	0.88	0.8462	150	0.6667	0.8485	0.7467	33	0.9259	0.8929	0.9091	28	0.7192	0.8415	0.7756	0.9549
0.1301	14.0	1484	0.1278	0.7229	0.8451	0.7792	71	0.5455	0.6462	0.5915	65	0.8199	0.88	0.8489	150	0.7179	0.8485	0.7778	33	0.8333	0.8929	0.8621	28	0.7359	0.8271	0.7788	0.9564
0.1197	15.0	1590	0.1395	0.7045	0.8732	0.7799	71	0.6067	0.8308	0.7013	65	0.8110	0.8867	0.8471	150	0.6136	0.8182	0.7013	33	0.8	0.8571	0.8276	28	0.7229	0.8646	0.7874	0.9539
0.1147	16.0	1696	0.1355	0.7381	0.8732	0.8	71	0.6282	0.7538	0.6853	65	0.8148	0.88	0.8462	150	0.6087	0.8485	0.7089	33	0.75	0.8571	0.8000	28	0.7338	0.8501	0.7877	0.9556
0.1134	17.0	1802	0.1294	0.7349	0.8592	0.7922	71	0.6216	0.7077	0.6619	65	0.8160	0.8867	0.8498	150	0.6279	0.8182	0.7105	33	0.8276	0.8571	0.8421	28	0.7423	0.8386	0.7876	0.9564
0.1103	18.0	1908	0.1350	0.7381	0.8732	0.8	71	0.6386	0.8154	0.7162	65	0.8121	0.8933	0.8508	150	0.6512	0.8485	0.7368	33	0.8276	0.8571	0.8421	28	0.7450	0.8674	0.8016	0.9568
0.1078	19.0	2014	0.1308	0.7439	0.8592	0.7974	71	0.6386	0.8154	0.7162	65	0.8160	0.8867	0.8498	150	0.6429	0.8182	0.7200	33	0.8571	0.8571	0.8571	28	0.7487	0.8588	0.8000	0.9578
0.1051	20.0	2120	0.1283	0.7294	0.8732	0.7949	71	0.6571	0.7077	0.6815	65	0.8272	0.8933	0.8590	150	0.7179	0.8485	0.7778	33	0.8889	0.8571	0.8727	28	0.7676	0.8473	0.8055	0.9588
0.1013	21.0	2226	0.1331	0.7381	0.8732	0.8	71	0.6463	0.8154	0.7211	65	0.8121	0.8933	0.8508	150	0.6512	0.8485	0.7368	33	0.8889	0.8571	0.8727	28	0.7506	0.8674	0.8048	0.9585
0.1015	22.0	2332	0.1462	0.6854	0.8592	0.7625	71	0.5957	0.8615	0.7044	65	0.8072	0.8933	0.8481	150	0.6512	0.8485	0.7368	33	0.8571	0.8571	0.8571	28	0.7214	0.8732	0.7901	0.9530
0.0952	23.0	2438	0.1262	0.7654	0.8732	0.8158	71	0.6842	0.8	0.7376	65	0.8210	0.8867	0.8526	150	0.7179	0.8485	0.7778	33	0.9231	0.8571	0.8889	28	0.7786	0.8617	0.8181	0.9612
0.0957	24.0	2544	0.1411	0.7262	0.8592	0.7871	71	0.6207	0.8308	0.7105	65	0.8024	0.8933	0.8454	150	0.6512	0.8485	0.7368	33	0.8571	0.8571	0.8571	28	0.7359	0.8674	0.7963	0.9556
0.0913	25.0	2650	0.1381	0.7561	0.8732	0.8105	71	0.6790	0.8462	0.7534	65	0.8133	0.9	0.8544	150	0.6364	0.8485	0.7273	33	0.8276	0.8571	0.8421	28	0.7562	0.8761	0.8117	0.9583
0.091	26.0	2756	0.1377	0.7176	0.8592	0.7821	71	0.6709	0.8154	0.7361	65	0.8204	0.9133	0.8644	150	0.6222	0.8485	0.7179	33	0.8889	0.8571	0.8727	28	0.7519	0.8732	0.808	0.9576
0.0902	27.0	2862	0.1440	0.7093	0.8592	0.7771	71	0.6429	0.8308	0.7248	65	0.8084	0.9	0.8517	150	0.5652	0.7879	0.6582	33	0.8	0.8571	0.8276	28	0.7264	0.8646	0.7895	0.9547
0.087	28.0	2968	0.1355	0.75	0.8451	0.7947	71	0.6180	0.8462	0.7143	65	0.8282	0.9	0.8626	150	0.7179	0.8485	0.7778	33	0.9231	0.8571	0.8889	28	0.7607	0.8703	0.8118	0.9583
0.0849	29.0	3074	0.1335	0.7349	0.8592	0.7922	71	0.5934	0.8308	0.6923	65	0.8121	0.8933	0.8508	150	0.6923	0.8182	0.7500	33	0.9231	0.8571	0.8889	28	0.7426	0.8646	0.7989	0.9585
0.0815	30.0	3180	0.1338	0.7439	0.8592	0.7974	71	0.6625	0.8154	0.7310	65	0.8395	0.9067	0.8718	150	0.6829	0.8485	0.7568	33	0.9231	0.8571	0.8889	28	0.7724	0.8703	0.8184	0.9612
0.0838	31.0	3286	0.1372	0.7176	0.8592	0.7821	71	0.6471	0.8462	0.7333	65	0.8253	0.9133	0.8671	150	0.6829	0.8485	0.7568	33	0.9231	0.8571	0.8889	28	0.7568	0.8790	0.8133	0.9588
0.076	32.0	3392	0.1505	0.7093	0.8592	0.7771	71	0.6022	0.8615	0.7089	65	0.8204	0.9133	0.8644	150	0.6087	0.8485	0.7089	33	0.8889	0.8571	0.8727	28	0.7303	0.8818	0.7990	0.9549
0.0775	33.0	3498	0.1308	0.7561	0.8732	0.8105	71	0.6944	0.7692	0.7299	65	0.8395	0.9067	0.8718	150	0.7568	0.8485	0.8000	33	0.9231	0.8571	0.8889	28	0.7916	0.8646	0.8264	0.9634
0.0768	34.0	3604	0.1335	0.7561	0.8732	0.8105	71	0.6667	0.8615	0.7517	65	0.8385	0.9	0.8682	150	0.7179	0.8485	0.7778	33	0.9231	0.8571	0.8889	28	0.7781	0.8790	0.8254	0.9612
0.0746	35.0	3710	0.1394	0.7262	0.8592	0.7871	71	0.6628	0.8769	0.7550	65	0.8447	0.9067	0.8746	150	0.7	0.8485	0.7671	33	0.9231	0.8571	0.8889	28	0.7708	0.8818	0.8226	0.9588
0.0724	36.0	3816	0.1419	0.7294	0.8732	0.7949	71	0.6044	0.8462	0.7051	65	0.8107	0.9133	0.8589	150	0.7632	0.8788	0.8169	33	0.8889	0.8571	0.8727	28	0.7488	0.8847	0.8111	0.9578
0.0703	37.0	3922	0.1566	0.6932	0.8592	0.7673	71	0.6022	0.8615	0.7089	65	0.8303	0.9133	0.8698	150	0.6	0.8182	0.6923	33	0.8889	0.8571	0.8727	28	0.7297	0.8790	0.7974	0.9517
0.07	38.0	4028	0.1458	0.7093	0.8592	0.7771	71	0.6627	0.8462	0.7432	65	0.8415	0.92	0.8790	150	0.5870	0.8182	0.6835	33	0.8571	0.8571	0.8571	28	0.7494	0.8790	0.8090	0.9571
0.0688	39.0	4134	0.1449	0.7011	0.8592	0.7722	71	0.6087	0.8615	0.7134	65	0.8415	0.92	0.8790	150	0.7436	0.8788	0.8056	33	0.9231	0.8571	0.8889	28	0.7549	0.8876	0.8159	0.9583
0.0691	40.0	4240	0.1356	0.7381	0.8732	0.8	71	0.675	0.8308	0.7448	65	0.8415	0.92	0.8790	150	0.7368	0.8485	0.7887	33	0.9231	0.8571	0.8889	28	0.7806	0.8818	0.8281	0.9614
0.0673	41.0	4346	0.1531	0.7011	0.8592	0.7722	71	0.5914	0.8462	0.6962	65	0.8303	0.9133	0.8698	150	0.6136	0.8182	0.7013	33	0.8571	0.8571	0.8571	28	0.7290	0.8761	0.7958	0.9539
0.0663	42.0	4452	0.1425	0.7381	0.8732	0.8	71	0.6364	0.8615	0.7320	65	0.8333	0.9	0.8654	150	0.6667	0.8485	0.7467	33	0.9231	0.8571	0.8889	28	0.7587	0.8790	0.8144	0.9581
0.0639	43.0	4558	0.1413	0.7294	0.8732	0.7949	71	0.68	0.7846	0.7286	65	0.8221	0.8933	0.8562	150	0.7	0.8485	0.7671	33	0.8889	0.8571	0.8727	28	0.7667	0.8617	0.8114	0.9593
0.064	44.0	4664	0.1402	0.7561	0.8732	0.8105	71	0.6279	0.8308	0.7152	65	0.8303	0.9133	0.8698	150	0.7179	0.8485	0.7778	33	0.9231	0.8571	0.8889	28	0.7663	0.8790	0.8188	0.9605
0.0615	45.0	4770	0.1534	0.7011	0.8592	0.7722	71	0.625	0.8462	0.7190	65	0.8457	0.9133	0.8782	150	0.6	0.8182	0.6923	33	0.8889	0.8571	0.8727	28	0.7433	0.8761	0.8042	0.9554
0.0614	46.0	4876	0.1427	0.7561	0.8732	0.8105	71	0.6322	0.8462	0.7237	65	0.8395	0.9067	0.8718	150	0.7368	0.8485	0.7887	33	0.9231	0.8571	0.8889	28	0.7722	0.8790	0.8221	0.9612
0.0595	47.0	4982	0.1540	0.7159	0.8873	0.7925	71	0.6364	0.8615	0.7320	65	0.8364	0.92	0.8762	150	0.7	0.8485	0.7671	33	0.8571	0.8571	0.8571	28	0.7555	0.8905	0.8175	0.9573
0.0594	48.0	5088	0.1491	0.7241	0.8873	0.7975	71	0.625	0.8462	0.7190	65	0.8344	0.9067	0.8690	150	0.7073	0.8788	0.7838	33	0.8889	0.8571	0.8727	28	0.7562	0.8847	0.8154	0.9588
0.0579	49.0	5194	0.1488	0.7241	0.8873	0.7975	71	0.6190	0.8	0.6980	65	0.8354	0.9133	0.8726	150	0.6667	0.8485	0.7467	33	0.8889	0.8571	0.8727	28	0.7525	0.8761	0.8096	0.9578
0.0561	50.0	5300	0.1435	0.7470	0.8732	0.8052	71	0.6118	0.8	0.6933	65	0.8395	0.9067	0.8718	150	0.7368	0.8485	0.7887	33	0.9231	0.8571	0.8889	28	0.7665	0.8703	0.8151	0.9605
0.056	51.0	5406	0.1516	0.7159	0.8873	0.7925	71	0.6145	0.7846	0.6892	65	0.8253	0.9133	0.8671	150	0.7179	0.8485	0.7778	33	0.8889	0.8571	0.8727	28	0.7519	0.8732	0.808	0.9573
0.0547	52.0	5512	0.1511	0.7470	0.8732	0.8052	71	0.6163	0.8154	0.7020	65	0.8438	0.9	0.8710	150	0.6585	0.8182	0.7297	33	0.8889	0.8571	0.8727	28	0.7582	0.8674	0.8091	0.9588
0.0534	53.0	5618	0.1615	0.7241	0.8873	0.7975	71	0.6087	0.8615	0.7134	65	0.8253	0.9133	0.8671	150	0.6429	0.8182	0.7200	33	0.8889	0.8571	0.8727	28	0.7415	0.8847	0.8068	0.9554
0.0526	54.0	5724	0.1521	0.7381	0.8732	0.8	71	0.6	0.8308	0.6968	65	0.8395	0.9067	0.8718	150	0.7436	0.8788	0.8056	33	0.9231	0.8571	0.8889	28	0.7606	0.8790	0.8155	0.9581
0.0538	55.0	5830	0.1600	0.7079	0.8873	0.7875	71	0.6044	0.8462	0.7051	65	0.8395	0.9067	0.8718	150	0.6	0.8182	0.6923	33	0.8889	0.8571	0.8727	28	0.7367	0.8790	0.8016	0.9551
0.0529	56.0	5936	0.1579	0.7241	0.8873	0.7975	71	0.6111	0.8462	0.7097	65	0.8354	0.9133	0.8726	150	0.6429	0.8182	0.7200	33	0.9231	0.8571	0.8889	28	0.7482	0.8818	0.8095	0.9571
0.05	57.0	6042	0.1494	0.7381	0.8732	0.8	71	0.6447	0.7538	0.6950	65	0.8447	0.9067	0.8746	150	0.7436	0.8788	0.8056	33	0.9231	0.8571	0.8889	28	0.7772	0.8646	0.8186	0.9602
0.0512	58.0	6148	0.1474	0.7294	0.8732	0.7949	71	0.6494	0.7692	0.7042	65	0.8395	0.9067	0.8718	150	0.7368	0.8485	0.7887	33	0.9231	0.8571	0.8889	28	0.7732	0.8646	0.8163	0.9597
0.047	59.0	6254	0.1532	0.7126	0.8732	0.7848	71	0.6429	0.8308	0.7248	65	0.8457	0.9133	0.8782	150	0.7179	0.8485	0.7778	33	0.9231	0.8571	0.8889	28	0.7663	0.8790	0.8188	0.9595
0.047	60.0	6360	0.1539	0.7294	0.8732	0.7949	71	0.6111	0.8462	0.7097	65	0.8438	0.9	0.8710	150	0.7632	0.8788	0.8169	33	0.9231	0.8571	0.8889	28	0.7644	0.8790	0.8177	0.9590
0.0465	61.0	6466	0.1599	0.7159	0.8873	0.7925	71	0.6207	0.8308	0.7105	65	0.8354	0.9133	0.8726	150	0.7368	0.8485	0.7887	33	0.9231	0.8571	0.8889	28	0.7593	0.8818	0.816	0.9585
0.045	62.0	6572	0.1569	0.7381	0.8732	0.8	71	0.6092	0.8154	0.6974	65	0.8405	0.9133	0.8754	150	0.7436	0.8788	0.8056	33	0.9231	0.8571	0.8889	28	0.7644	0.8790	0.8177	0.9595
0.0468	63.0	6678	0.1519	0.7561	0.8732	0.8105	71	0.6310	0.8154	0.7114	65	0.8438	0.9	0.8710	150	0.7368	0.8485	0.7887	33	0.9231	0.8571	0.8889	28	0.7744	0.8703	0.8195	0.9612
0.0446	64.0	6784	0.1547	0.7349	0.8592	0.7922	71	0.6667	0.8	0.7273	65	0.8457	0.9133	0.8782	150	0.7105	0.8182	0.7606	33	0.9231	0.8571	0.8889	28	0.7778	0.8674	0.8202	0.9610
0.0452	65.0	6890	0.1631	0.7294	0.8732	0.7949	71	0.6044	0.8462	0.7051	65	0.8509	0.9133	0.8810	150	0.6829	0.8485	0.7568	33	0.9231	0.8571	0.8889	28	0.7574	0.8818	0.8149	0.9576
0.0442	66.0	6996	0.1616	0.7294	0.8732	0.7949	71	0.6044	0.8462	0.7051	65	0.8562	0.9133	0.8839	150	0.7073	0.8788	0.7838	33	0.8889	0.8571	0.8727	28	0.7599	0.8847	0.8176	0.9578
0.0431	67.0	7102	0.1608	0.7209	0.8732	0.7898	71	0.6163	0.8154	0.7020	65	0.8344	0.9067	0.8690	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7562	0.8761	0.8117	0.9583
0.0427	68.0	7208	0.1687	0.7159	0.8873	0.7925	71	0.6180	0.8462	0.7143	65	0.8344	0.9067	0.8690	150	0.6136	0.8182	0.7013	33	0.8889	0.8571	0.8727	28	0.7421	0.8790	0.8047	0.9556
0.043	69.0	7314	0.1637	0.7159	0.8873	0.7925	71	0.6067	0.8308	0.7013	65	0.8395	0.9067	0.8718	150	0.725	0.8788	0.7945	33	0.9231	0.8571	0.8889	28	0.7556	0.8818	0.8138	0.9573
0.0426	70.0	7420	0.1629	0.7241	0.8873	0.7975	71	0.6136	0.8308	0.7059	65	0.8395	0.9067	0.8718	150	0.725	0.8788	0.7945	33	0.9231	0.8571	0.8889	28	0.7593	0.8818	0.816	0.9581
0.0439	71.0	7526	0.1787	0.6966	0.8732	0.775	71	0.5938	0.8769	0.7081	65	0.8466	0.92	0.8818	150	0.6744	0.8788	0.7632	33	0.9231	0.8571	0.8889	28	0.7434	0.8934	0.8115	0.9542
0.0409	72.0	7632	0.1614	0.7349	0.8592	0.7922	71	0.6207	0.8308	0.7105	65	0.8447	0.9067	0.8746	150	0.725	0.8788	0.7945	33	0.9231	0.8571	0.8889	28	0.7657	0.8761	0.8172	0.9590
0.0404	73.0	7738	0.1655	0.7241	0.8873	0.7975	71	0.6023	0.8154	0.6928	65	0.8395	0.9067	0.8718	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7550	0.8790	0.8123	0.9578
0.0399	74.0	7844	0.1669	0.7412	0.8873	0.8077	71	0.5955	0.8154	0.6883	65	0.8395	0.9067	0.8718	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7568	0.8790	0.8133	0.9585
0.04	75.0	7950	0.1640	0.7241	0.8873	0.7975	71	0.6207	0.8308	0.7105	65	0.85	0.9067	0.8774	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7631	0.8818	0.8182	0.9583
0.0402	76.0	8056	0.1683	0.7159	0.8873	0.7925	71	0.6067	0.8308	0.7013	65	0.8395	0.9067	0.8718	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7537	0.8818	0.8127	0.9578
0.0402	77.0	8162	0.1702	0.7079	0.8873	0.7875	71	0.6235	0.8154	0.7067	65	0.8344	0.9067	0.8690	150	0.6829	0.8485	0.7568	33	0.9231	0.8571	0.8889	28	0.7525	0.8761	0.8096	0.9576
0.0379	78.0	8268	0.1694	0.7159	0.8873	0.7925	71	0.6023	0.8154	0.6928	65	0.8333	0.9	0.8654	150	0.725	0.8788	0.7945	33	0.9231	0.8571	0.8889	28	0.7525	0.8761	0.8096	0.9583
0.0371	79.0	8374	0.1731	0.7159	0.8873	0.7925	71	0.5955	0.8154	0.6883	65	0.8509	0.9133	0.8810	150	0.6829	0.8485	0.7568	33	0.8889	0.8571	0.8727	28	0.7512	0.8790	0.8101	0.9576
0.0375	80.0	8480	0.1701	0.7326	0.8873	0.8025	71	0.5955	0.8154	0.6883	65	0.8509	0.9133	0.8810	150	0.7	0.8485	0.7671	33	0.9231	0.8571	0.8889	28	0.7587	0.8790	0.8144	0.9576
0.0367	81.0	8586	0.1683	0.7209	0.8732	0.7898	71	0.5955	0.8154	0.6883	65	0.8354	0.9133	0.8726	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7512	0.8790	0.8101	0.9576
0.0369	82.0	8692	0.1746	0.7241	0.8873	0.7975	71	0.5824	0.8154	0.6795	65	0.8519	0.92	0.8846	150	0.7073	0.8788	0.7838	33	0.8889	0.8571	0.8727	28	0.7525	0.8847	0.8132	0.9571
0.0382	83.0	8798	0.1662	0.7126	0.8732	0.7848	71	0.6163	0.8154	0.7020	65	0.8344	0.9067	0.8690	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7543	0.8761	0.8107	0.9581
0.0376	84.0	8904	0.1694	0.7241	0.8873	0.7975	71	0.6092	0.8154	0.6974	65	0.8457	0.9133	0.8782	150	0.6829	0.8485	0.7568	33	0.9231	0.8571	0.8889	28	0.7568	0.8790	0.8133	0.9583
0.0372	85.0	9010	0.1741	0.7241	0.8873	0.7975	71	0.5978	0.8462	0.7006	65	0.8509	0.9133	0.8810	150	0.7	0.8485	0.7671	33	0.8889	0.8571	0.8727	28	0.7543	0.8847	0.8143	0.9571
0.0351	86.0	9116	0.1718	0.7159	0.8873	0.7925	71	0.6023	0.8154	0.6928	65	0.8447	0.9067	0.8746	150	0.7073	0.8788	0.7838	33	0.8889	0.8571	0.8727	28	0.7531	0.8790	0.8112	0.9578
0.0348	87.0	9222	0.1713	0.7241	0.8873	0.7975	71	0.5889	0.8154	0.6839	65	0.8395	0.9067	0.8718	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7512	0.8790	0.8101	0.9581
0.0363	88.0	9328	0.1707	0.7241	0.8873	0.7975	71	0.6092	0.8154	0.6974	65	0.8447	0.9067	0.8746	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7587	0.8790	0.8144	0.9585
0.0371	89.0	9434	0.1718	0.7159	0.8873	0.7925	71	0.5955	0.8154	0.6883	65	0.8405	0.9133	0.8754	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7518	0.8818	0.8117	0.9576
0.0367	90.0	9540	0.1707	0.7326	0.8873	0.8025	71	0.6092	0.8154	0.6974	65	0.8571	0.92	0.8875	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7656	0.8847	0.8209	0.9590
0.0349	91.0	9646	0.1737	0.7241	0.8873	0.7975	71	0.6111	0.8462	0.7097	65	0.8395	0.9067	0.8718	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7562	0.8847	0.8154	0.9578
0.0357	92.0	9752	0.1690	0.7326	0.8873	0.8025	71	0.6235	0.8154	0.7067	65	0.8457	0.9133	0.8782	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.765	0.8818	0.8193	0.9590
0.0345	93.0	9858	0.1714	0.7241	0.8873	0.7975	71	0.6163	0.8154	0.7020	65	0.8457	0.9133	0.8782	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7612	0.8818	0.8171	0.9585
0.0349	94.0	9964	0.1766	0.7241	0.8873	0.7975	71	0.5889	0.8154	0.6839	65	0.8509	0.9133	0.8810	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7556	0.8818	0.8138	0.9576
0.0352	95.0	10070	0.1764	0.7241	0.8873	0.7975	71	0.5889	0.8154	0.6839	65	0.8509	0.9133	0.8810	150	0.7073	0.8788	0.7838	33	0.8889	0.8571	0.8727	28	0.7537	0.8818	0.8127	0.9576
0.0367	96.0	10176	0.1730	0.7241	0.8873	0.7975	71	0.6092	0.8154	0.6974	65	0.8457	0.9133	0.8782	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7593	0.8818	0.816	0.9583
0.0352	97.0	10282	0.1724	0.7241	0.8873	0.7975	71	0.6023	0.8154	0.6928	65	0.8562	0.9133	0.8839	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7612	0.8818	0.8171	0.9581
0.0341	98.0	10388	0.1748	0.7241	0.8873	0.7975	71	0.5824	0.8154	0.6795	65	0.8447	0.9067	0.8746	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7512	0.8790	0.8101	0.9571
0.0331	99.0	10494	0.1726	0.7241	0.8873	0.7975	71	0.6023	0.8154	0.6928	65	0.8447	0.9067	0.8746	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7568	0.8790	0.8133	0.9581
0.0347	100.0	10600	0.1728	0.7241	0.8873	0.7975	71	0.6023	0.8154	0.6928	65	0.8447	0.9067	0.8746	150	0.7073	0.8788	0.7838	33	0.9231	0.8571	0.8889	28	0.7568	0.8790	0.8133	0.9581

Framework versions

• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1