detect-femicide-news-bert-nl-None

This model is a fine-tuned version of GroNLP/bert-base-dutch-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.8162
• Accuracy: 0.75
• Precision Neg: 0.8235
• Precision Pos: 0.6364
• Recall Neg: 0.7778
• Recall Pos: 0.7
• F1 Score Neg: 0.8000
• F1 Score Pos: 0.6667

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: 1e-05
• train_batch_size: 24
• eval_batch_size: 8
• seed: 1996
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision Neg	Precision Pos	Recall Neg	Recall Pos	F1 Score Neg	F1 Score Pos
0.6636	1.0	23	0.6474	0.6429	0.8333	0.5	0.5556	0.8	0.6667	0.6154
0.572	2.0	46	0.5653	0.6071	0.6842	0.4444	0.7222	0.4	0.7027	0.4211
0.502	3.0	69	0.5601	0.6786	0.8462	0.5333	0.6111	0.8	0.7097	0.64
0.4576	4.0	92	0.5199	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.3803	5.0	115	0.5219	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.3466	6.0	138	0.5125	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.3325	7.0	161	0.4930	0.75	0.7895	0.6667	0.8333	0.6	0.8108	0.6316
0.3022	8.0	184	0.5144	0.75	0.7895	0.6667	0.8333	0.6	0.8108	0.6316
0.2854	9.0	207	0.5588	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2797	10.0	230	0.5700	0.6786	0.7647	0.5455	0.7222	0.6	0.7429	0.5714
0.2645	11.0	253	0.5806	0.6786	0.7647	0.5455	0.7222	0.6	0.7429	0.5714
0.2411	12.0	276	0.5642	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2554	13.0	299	0.6364	0.6786	0.8	0.5385	0.6667	0.7	0.7273	0.6087
0.2682	14.0	322	0.5656	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2429	15.0	345	0.6249	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2368	16.0	368	0.5914	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2398	17.0	391	0.7456	0.6786	0.8462	0.5333	0.6111	0.8	0.7097	0.64
0.251	18.0	414	0.5602	0.75	0.7895	0.6667	0.8333	0.6	0.8108	0.6316
0.2403	19.0	437	0.5803	0.75	0.7895	0.6667	0.8333	0.6	0.8108	0.6316
0.2237	20.0	460	0.8165	0.6786	0.9091	0.5294	0.5556	0.9	0.6897	0.6667
0.2481	21.0	483	0.6195	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2357	22.0	506	0.7081	0.6429	0.75	0.5	0.6667	0.6	0.7059	0.5455
0.2227	23.0	529	0.6786	0.6786	0.8	0.5385	0.6667	0.7	0.7273	0.6087
0.2137	24.0	552	0.6567	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.2216	25.0	575	0.7286	0.7143	0.8571	0.5714	0.6667	0.8	0.75	0.6667
0.2289	26.0	598	0.6146	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2268	27.0	621	0.6721	0.6786	0.8	0.5385	0.6667	0.7	0.7273	0.6087
0.2208	28.0	644	0.6894	0.6786	0.8	0.5385	0.6667	0.7	0.7273	0.6087
0.2252	29.0	667	0.5986	0.7857	0.8	0.75	0.8889	0.6	0.8421	0.6667
0.2127	30.0	690	0.6868	0.6429	0.75	0.5	0.6667	0.6	0.7059	0.5455
0.2259	31.0	713	0.6682	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2253	32.0	736	0.8906	0.6786	0.9091	0.5294	0.5556	0.9	0.6897	0.6667
0.2421	33.0	759	0.6461	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2181	34.0	782	0.7014	0.6786	0.7647	0.5455	0.7222	0.6	0.7429	0.5714
0.2199	35.0	805	0.7655	0.6786	0.8	0.5385	0.6667	0.7	0.7273	0.6087
0.201	36.0	828	0.7356	0.6429	0.75	0.5	0.6667	0.6	0.7059	0.5455
0.2192	37.0	851	0.6958	0.6786	0.7647	0.5455	0.7222	0.6	0.7429	0.5714
0.2164	38.0	874	0.7475	0.6429	0.75	0.5	0.6667	0.6	0.7059	0.5455
0.22	39.0	897	0.6847	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2177	40.0	920	0.6463	0.7857	0.8	0.75	0.8889	0.6	0.8421	0.6667
0.2126	41.0	943	0.6793	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2069	42.0	966	0.7303	0.7143	0.8125	0.5833	0.7222	0.7	0.7647	0.6364
0.2099	43.0	989	0.6598	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2104	44.0	1012	0.7276	0.6786	0.7647	0.5455	0.7222	0.6	0.7429	0.5714
0.213	45.0	1035	0.7099	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2083	46.0	1058	0.7545	0.6786	0.8	0.5385	0.6667	0.7	0.7273	0.6087
0.1958	47.0	1081	0.6533	0.75	0.7895	0.6667	0.8333	0.6	0.8108	0.6316
0.2096	48.0	1104	0.7141	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2134	49.0	1127	0.7008	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.203	50.0	1150	0.6557	0.75	0.7895	0.6667	0.8333	0.6	0.8108	0.6316
0.2024	51.0	1173	0.7348	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.2095	52.0	1196	0.7708	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1997	53.0	1219	0.7106	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2048	54.0	1242	0.7530	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1963	55.0	1265	0.7520	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2039	56.0	1288	0.7230	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2023	57.0	1311	0.7644	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.2022	58.0	1334	0.7666	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1898	59.0	1357	0.7961	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.2155	60.0	1380	0.7763	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1948	61.0	1403	0.7545	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.2124	62.0	1426	0.7344	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1979	63.0	1449	0.7676	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1958	64.0	1472	0.7567	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1946	65.0	1495	0.7349	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1888	66.0	1518	0.7472	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1889	67.0	1541	0.7202	0.7857	0.8	0.75	0.8889	0.6	0.8421	0.6667
0.2077	68.0	1564	0.7193	0.7857	0.8	0.75	0.8889	0.6	0.8421	0.6667
0.1882	69.0	1587	0.7541	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1903	70.0	1610	0.8058	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.2017	71.0	1633	0.7862	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1929	72.0	1656	0.8000	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.192	73.0	1679	0.8199	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1903	74.0	1702	0.8044	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1953	75.0	1725	0.7943	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1908	76.0	1748	0.7805	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1975	77.0	1771	0.7595	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1943	78.0	1794	0.7908	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.192	79.0	1817	0.8389	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1879	80.0	1840	0.7925	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1933	81.0	1863	0.8149	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1867	82.0	1886	0.7925	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1906	83.0	1909	0.8118	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1895	84.0	1932	0.8108	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1925	85.0	1955	0.7962	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1851	86.0	1978	0.7942	0.7143	0.7778	0.6	0.7778	0.6	0.7778	0.6
0.1952	87.0	2001	0.8104	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1821	88.0	2024	0.8187	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1946	89.0	2047	0.8378	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1904	90.0	2070	0.8407	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1931	91.0	2093	0.8351	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1883	92.0	2116	0.8269	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1845	93.0	2139	0.8110	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1883	94.0	2162	0.8209	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1991	95.0	2185	0.8194	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.187	96.0	2208	0.8182	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1842	97.0	2231	0.8168	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1837	98.0	2254	0.8164	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.1849	99.0	2277	0.8173	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667
0.189	100.0	2300	0.8162	0.75	0.8235	0.6364	0.7778	0.7	0.8000	0.6667

Framework versions

• Transformers 4.16.2
• Pytorch 1.10.2+cu113
• Datasets 1.18.3
• Tokenizers 0.11.0