Modelpublic

aditnnda/machine_translation_informal2formal

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes40downloads

Model Card

aditnnda/machinetranslationinformal2formal

This model is a fine-tuned version of Helsinki-NLP/opus-mt-id-en on STIF Indonesia dataset. It achieves the following results on the evaluation set:

—Train Loss: 0.0077
—Validation Loss: 1.2870
—Epoch: 99

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:

—optimizer: {'name': 'AdamWeightDecay', 'learningrate': {'module': 'keras.optimizers.schedules', 'classname': 'PolynomialDecay', 'config': {'initiallearningrate': 5e-05, 'decaysteps': 6000, 'endlearningrate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registeredname': None}, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weightdecayrate': 0.01}
—training_precision: float32

Training results

Train Loss	Validation Loss	Epoch
3.4298	2.4070	0
2.1508	1.8031	1
1.6301	1.5249	2
1.3013	1.3417	3
1.0752	1.2465	4
0.9119	1.1651	5
0.7778	1.1213	6
0.6763	1.0813	7
0.5907	1.0542	8
0.5162	1.0289	9
0.4573	1.0265	10
0.4057	1.0115	11
0.3645	1.0096	12
0.3227	1.0037	13
0.2864	1.0016	14
0.2598	1.0121	15
0.2291	1.0079	16
0.2069	1.0199	17
0.1876	1.0247	18
0.1717	1.0199	19
0.1544	1.0283	20
0.1393	1.0416	21
0.1285	1.0370	22
0.1171	1.0430	23
0.1069	1.0593	24
0.0990	1.0670	25
0.0915	1.0655	26
0.0827	1.0818	27
0.0781	1.0903	28
0.0729	1.0998	29
0.0678	1.0932	30
0.0639	1.1051	31
0.0592	1.1125	32
0.0556	1.1240	33
0.0509	1.1177	34
0.0512	1.1355	35
0.0438	1.1405	36
0.0453	1.1322	37
0.0443	1.1419	38
0.0407	1.1419	39
0.0397	1.1495	40
0.0386	1.1609	41
0.0346	1.1619	42
0.0351	1.1638	43
0.0344	1.1711	44
0.0302	1.1782	45
0.0470	1.1836	46
0.0330	1.1913	47
0.0284	1.1963	48
0.0268	1.1964	49
0.0255	1.2017	50
0.0236	1.2092	51
0.0241	1.2104	52
0.0234	1.2170	53
0.0216	1.2192	54
0.0209	1.2317	55
0.0205	1.2289	56
0.0193	1.2363	57
0.0191	1.2295	58
0.0184	1.2306	59
0.0185	1.2352	60
0.0184	1.2415	61
0.0174	1.2389	62
0.0166	1.2392	63
0.0167	1.2469	64
0.0166	1.2457	65
0.0147	1.2456	66
0.0146	1.2511	67
0.0147	1.2552	68
0.0147	1.2493	69
0.0133	1.2532	70
0.0135	1.2561	71
0.0136	1.2609	72
0.0130	1.2602	73
0.0119	1.2629	74
0.0123	1.2667	75
0.0114	1.2675	76
0.0122	1.2673	77
0.0111	1.2649	78
0.0099	1.2722	79
0.0109	1.2693	80
0.0101	1.2727	81
0.0101	1.2746	82
0.0096	1.2739	83
0.0103	1.2734	84
0.0096	1.2805	85
0.0093	1.2799	86
0.0097	1.2823	87
0.0093	1.2826	88
0.0095	1.2808	89
0.0091	1.2875	90
0.0081	1.2849	91
0.0084	1.2849	92
0.0083	1.2838	93
0.0089	1.2866	94
0.0084	1.2851	95
0.0082	1.2870	96
0.0078	1.2871	97
0.0078	1.2872	98
0.0077	1.2870	99

Framework versions

—Transformers 4.35.2
—TensorFlow 2.14.0
—Datasets 2.15.0
—Tokenizers 0.15.0