detect-femicide-news-xlmr-nl-mono-freeze2

This model is a fine-tuned version of xlm-roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6487
Accuracy: 0.6429
Precision Neg: 0.6429
Precision Pos: 0.0
Recall Neg: 1.0
Recall Pos: 0.0
F1 Score Neg: 0.7826
F1 Score Pos: 0.0

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
0.7312	1.0	23	0.7413	0.3571	0.0	0.3571	0.0	1.0	0.0	0.5263
0.7151	2.0	46	0.7177	0.3571	0.0	0.3571	0.0	1.0	0.0	0.5263
0.7049	3.0	69	0.6988	0.3571	0.0	0.3571	0.0	1.0	0.0	0.5263
0.6934	4.0	92	0.6945	0.3571	0.0	0.3571	0.0	1.0	0.0	0.5263
0.6886	5.0	115	0.6903	0.6071	0.8182	0.4706	0.5	0.8	0.6207	0.5926
0.6911	6.0	138	0.6846	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6856	7.0	161	0.6786	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6888	8.0	184	0.6783	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6862	9.0	207	0.6819	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6807	10.0	230	0.6758	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6839	11.0	253	0.6721	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6878	12.0	276	0.6708	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6799	13.0	299	0.6692	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6813	14.0	322	0.6673	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6792	15.0	345	0.6676	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6774	16.0	368	0.6683	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6807	17.0	391	0.6679	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6834	18.0	414	0.6693	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6784	19.0	437	0.6679	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.676	20.0	460	0.6698	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6791	21.0	483	0.6661	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6775	22.0	506	0.6633	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6688	23.0	529	0.6589	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6748	24.0	552	0.6580	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6771	25.0	575	0.6619	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6761	26.0	598	0.6639	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6773	27.0	621	0.6651	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6737	28.0	644	0.6656	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6721	29.0	667	0.6650	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6683	30.0	690	0.6612	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6663	31.0	713	0.6592	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6724	32.0	736	0.6576	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6739	33.0	759	0.6601	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6691	34.0	782	0.6602	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6652	35.0	805	0.6588	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6717	36.0	828	0.6596	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6637	37.0	851	0.6587	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6704	38.0	874	0.6579	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6608	39.0	897	0.6599	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6615	40.0	920	0.6580	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6662	41.0	943	0.6592	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6622	42.0	966	0.6616	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.664	43.0	989	0.6610	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.6695	44.0	1012	0.6570	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6677	45.0	1035	0.6557	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6705	46.0	1058	0.6546	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6591	47.0	1081	0.6547	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6675	48.0	1104	0.6532	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6622	49.0	1127	0.6544	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6571	50.0	1150	0.6552	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6678	51.0	1173	0.6555	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6596	52.0	1196	0.6544	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6583	53.0	1219	0.6517	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6641	54.0	1242	0.6508	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.671	55.0	1265	0.6502	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6645	56.0	1288	0.6513	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6604	57.0	1311	0.6510	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6644	58.0	1334	0.6509	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6617	59.0	1357	0.6528	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6608	60.0	1380	0.6536	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6533	61.0	1403	0.6533	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6596	62.0	1426	0.6518	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6607	63.0	1449	0.6511	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.658	64.0	1472	0.6509	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6546	65.0	1495	0.6514	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6613	66.0	1518	0.6516	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.662	67.0	1541	0.6506	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.661	68.0	1564	0.6503	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6571	69.0	1587	0.6497	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6656	70.0	1610	0.6500	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6637	71.0	1633	0.6508	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6519	72.0	1656	0.6518	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6593	73.0	1679	0.6516	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.6539	74.0	1702	0.6514	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.6568	75.0	1725	0.6506	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6581	76.0	1748	0.6504	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6557	77.0	1771	0.6499	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6542	78.0	1794	0.6500	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6557	79.0	1817	0.6498	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6637	80.0	1840	0.6493	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6603	81.0	1863	0.6490	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6568	82.0	1886	0.6485	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6561	83.0	1909	0.6490	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6665	84.0	1932	0.6499	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.655	85.0	1955	0.6492	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6509	86.0	1978	0.6493	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6549	87.0	2001	0.6493	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.655	88.0	2024	0.6489	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6576	89.0	2047	0.6493	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6612	90.0	2070	0.6492	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.6641	91.0	2093	0.6492	0.6071	0.6296	0.0	0.9444	0.0	0.7556	0.0
0.654	92.0	2116	0.6487	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6556	93.0	2139	0.6488	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6566	94.0	2162	0.6486	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6565	95.0	2185	0.6487	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6516	96.0	2208	0.6488	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6509	97.0	2231	0.6487	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6588	98.0	2254	0.6487	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6532	99.0	2277	0.6487	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0
0.6548	100.0	2300	0.6487	0.6429	0.6429	0.0	1.0	0.0	0.7826	0.0

Framework versions

Transformers 4.16.2
Pytorch 1.10.2+cu113
Datasets 1.18.3
Tokenizers 0.11.0

detect-femicide-news-xlmr-nl-mono-freeze2

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

NSDT 3DConvert

UnrealSynth

DreamTexture.js