NLLB-en_tags-hi-HVG-4

hrithikgupt/NLLB-en_tags-hi-HVG-4

NLLB-en_tags-hi-HVG-4 is a translation model from hrithikgupt. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as cc-by-nc-4.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

12% of all-time downloads

All-time downloads

Public

Repo size

71.4 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin5.5 GB · 100%

At a glance

Task: Translation
Library: transformers
License: cc-by-nc-4.0
Model type: m2m_100
Access: Public
Created: Jul 4, 2023
Updated: Jul 5, 2023
SHA: ca665ea5

Try a prompt

Model card

From the Hugging Face model README

NLLB-en_tags-hi-HVG-4

This model is a fine-tuned version of facebook/nllb-200-distilled-1.3B on the None dataset. It achieves the following results on the evaluation set:

Loss: 1.5967
Bleu: 49.9441

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 100
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.4813	1.0	1809	0.5902	48.6510
0.3359	2.0	3618	0.5961	50.4673
0.2513	3.0	5427	0.6304	49.8793
0.1803	4.0	7236	0.6917	48.8100
0.139	5.0	9045	0.7407	49.4996
0.1099	6.0	10854	0.7885	49.0436
0.0848	7.0	12663	0.8299	50.0973
0.0686	8.0	14472	0.8799	49.6841
0.0569	9.0	16281	0.8960	49.4942
0.0475	10.0	18090	0.9470	49.0631
0.0404	11.0	19899	0.9839	50.0242
0.0355	12.0	21708	1.0104	49.7374
0.0332	13.0	23517	1.0201	49.7865
0.03	14.0	25326	1.0488	49.5754
0.0265	15.0	27135	1.0466	50.0790
0.0244	16.0	28944	1.0873	50.3815
0.0229	17.0	30753	1.0970	50.6232
0.0216	18.0	32562	1.1129	50.0035
0.0202	19.0	34371	1.1537	49.2957
0.0188	20.0	36180	1.1436	49.4308
0.0175	21.0	37989	1.1438	49.6689
0.0171	22.0	39798	1.1774	49.3337
0.0159	23.0	41607	1.1991	49.7659
0.015	24.0	43416	1.1940	49.7935
0.0153	25.0	45225	1.1859	49.1999
0.0139	26.0	47034	1.1935	50.7531
0.0123	27.0	48843	1.1926	49.5786
0.0131	28.0	50652	1.2150	49.8876
0.0123	29.0	52461	1.2355	49.8494
0.0122	30.0	54270	1.2254	50.1757
0.012	31.0	56079	1.2938	49.8082
0.0111	32.0	57888	1.2779	50.7888
0.0113	33.0	59697	1.2764	51.5388
0.0108	34.0	61506	1.2775	50.0114
0.0101	35.0	63315	1.2818	49.7846
0.0097	36.0	65124	1.2923	50.2888
0.0095	37.0	66933	1.3320	49.8109
0.0091	38.0	68742	1.2959	49.7810
0.0087	39.0	70551	1.3117	49.3185
0.0092	40.0	72360	1.3425	49.5479
0.009	41.0	74169	1.3635	49.5754
0.0089	42.0	75978	1.3495	50.1936
0.008	43.0	77787	1.3229	50.0721
0.0087	44.0	79596	1.3395	49.4060
0.0077	45.0	81405	1.3563	49.9498
0.0079	46.0	83214	1.3860	50.5139
0.0074	47.0	85023	1.3701	50.2424
0.0079	48.0	86832	1.3847	49.8723
0.0073	49.0	88641	1.3801	50.0133
0.0073	50.0	90450	1.4012	49.7632
0.0072	51.0	92259	1.3536	50.3370
0.0067	52.0	94068	1.4024	50.0111
0.0064	53.0	95877	1.3833	50.3144
0.0061	54.0	97686	1.4155	50.1808
0.0059	55.0	99495	1.4212	49.3615
0.0062	56.0	101304	1.4160	50.1105
0.0061	57.0	103113	1.4164	50.4343
0.006	58.0	104922	1.4349	50.7254
0.0063	59.0	106731	1.4371	49.4904
0.0059	60.0	108540	1.4392	50.1641
0.006	61.0	110349	1.4660	49.2518
0.0059	62.0	112158	1.4411	49.6985
0.0056	63.0	113967	1.4775	50.1533
0.0054	64.0	115776	1.4853	50.0788
0.0056	65.0	117585	1.4755	50.2000
0.0057	66.0	119394	1.4831	49.6236
0.0053	67.0	121203	1.4668	49.8398
0.0056	68.0	123012	1.4780	50.3374
0.0053	69.0	124821	1.4855	50.1800
0.0055	70.0	126630	1.4980	50.8824
0.0049	71.0	128439	1.4849	49.9084
0.0051	72.0	130248	1.5116	50.1776
0.005	73.0	132057	1.5060	49.8619
0.005	74.0	133866	1.5237	50.6154
0.0049	75.0	135675	1.5418	49.6692
0.0049	76.0	137484	1.5356	50.1683
0.0048	77.0	139293	1.5145	50.8463
0.0047	78.0	141102	1.5401	49.8162
0.0044	79.0	142911	1.5209	50.2556
0.0047	80.0	144720	1.5383	49.8232
0.0049	81.0	146529	1.5492	49.9976
0.0046	82.0	148338	1.5417	49.9741
0.0043	83.0	150147	1.5548	50.0999
0.0044	84.0	151956	1.5541	50.4247
0.0042	85.0	153765	1.5524	50.6283
0.0043	86.0	155574	1.5746	50.5471
0.0043	87.0	157383	1.5640	49.6041
0.0042	88.0	159192	1.5716	50.4354
0.0043	89.0	161001	1.5762	50.3046
0.0041	90.0	162810	1.5777	50.1317
0.0041	91.0	164619	1.5739	50.0471
0.004	92.0	166428	1.5700	50.2259
0.0038	93.0	168237	1.5761	49.9065
0.0039	94.0	170046	1.5755	50.0105
0.0037	95.0	171855	1.5802	50.3069
0.0037	96.0	173664	1.5934	50.0489
0.0036	97.0	175473	1.5991	50.1203
0.0037	98.0	177282	1.5969	49.7518
0.0035	99.0	179091	1.5978	49.8365
0.0034	100.0	180900	1.5967	49.9441

Framework versions

Transformers 4.27.3
Pytorch 2.0.0
Datasets 2.10.1
Tokenizers 0.13.2

Task: Translation
Library: transformers
Type: m2m_100
License: cc-by-nc-4.0
Created: Jul 4, 2023
Updated: Jul 5, 2023