NLLB-en_tags-hi-HVG-1

hrithikgupt/NLLB-en_tags-hi-HVG-1

NLLB-en_tags-hi-HVG-1 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

9% of all-time downloads

All-time downloads

Public

Repo size

38.5 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: Jun 12, 2023
Updated: Jun 13, 2023
SHA: 668ed732

Try a prompt

Model card

From the Hugging Face model README

NLLB-en_tags-hi-HVG-1

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: 1.4166
Bleu: 51.1308

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
0.8349	1.0	905	0.5956	47.9524
0.4586	2.0	1810	0.5742	49.8959
0.3823	3.0	2715	0.5875	48.8309
0.3228	4.0	3620	0.5943	50.1381
0.2772	5.0	4525	0.6172	50.9123
0.2318	6.0	5430	0.6456	50.2484
0.2034	7.0	6335	0.6641	50.6074
0.1738	8.0	7240	0.6821	49.3567
0.1526	9.0	8145	0.7173	50.5959
0.132	10.0	9050	0.7428	50.2744
0.1124	11.0	9955	0.7596	50.1682
0.0968	12.0	10860	0.8024	50.4865
0.0888	13.0	11765	0.8297	49.6777
0.0785	14.0	12670	0.8468	50.5282
0.0715	15.0	13575	0.8705	49.9611
0.0634	16.0	14480	0.8871	50.2830
0.0549	17.0	15385	0.9014	49.2825
0.0502	18.0	16290	0.9370	50.2938
0.0471	19.0	17195	0.9511	49.9733
0.0436	20.0	18100	0.9522	50.2096
0.041	21.0	19005	0.9790	50.2865
0.0341	22.0	19910	1.0112	49.7069
0.0334	23.0	20815	1.0181	51.6405
0.032	24.0	21720	1.0303	50.0497
0.0295	25.0	22625	1.0291	49.6657
0.0275	26.0	23530	1.0641	49.7651
0.0243	27.0	24435	1.0429	50.1408
0.0241	28.0	25340	1.1037	49.7290
0.0217	29.0	26245	1.0890	50.2238
0.0214	30.0	27150	1.0872	49.7886
0.021	31.0	28055	1.0998	50.0502
0.0186	32.0	28960	1.1302	49.7725
0.0168	33.0	29865	1.1201	49.6323
0.0164	34.0	30770	1.1478	49.4450
0.0169	35.0	31675	1.1497	49.9194
0.0162	36.0	32580	1.1632	50.0551
0.0137	37.0	33485	1.1682	49.6857
0.0137	38.0	34390	1.1794	49.3643
0.0131	39.0	35295	1.1688	49.3656
0.0124	40.0	36200	1.2083	50.0818
0.0118	41.0	37105	1.2089	50.2072
0.0116	42.0	38010	1.2097	49.7730
0.0107	43.0	38915	1.2101	49.4323
0.0101	44.0	39820	1.2300	50.2415
0.0099	45.0	40725	1.2308	50.2144
0.01	46.0	41630	1.2384	50.7989
0.0096	47.0	42535	1.2218	49.9294
0.0085	48.0	43440	1.2592	50.1321
0.0092	49.0	44345	1.2522	50.3437
0.009	50.0	45250	1.2421	49.7097
0.0082	51.0	46155	1.2848	50.2705
0.0077	52.0	47060	1.2641	50.4266
0.0076	53.0	47965	1.2532	51.0484
0.0072	54.0	48870	1.2611	51.2995
0.0071	55.0	49775	1.2936	50.8519
0.0069	56.0	50680	1.2896	50.9311
0.0073	57.0	51585	1.2891	51.1463
0.0066	58.0	52490	1.2768	51.0150
0.0058	59.0	53395	1.2998	49.9774
0.0061	60.0	54300	1.3028	50.2904
0.0058	61.0	55205	1.3340	49.8758
0.0064	62.0	56110	1.3410	50.1948
0.0061	63.0	57015	1.3359	50.8980
0.0052	64.0	57920	1.3320	51.2584
0.0058	65.0	58825	1.3322	50.7374
0.0052	66.0	59730	1.3317	50.7991
0.0055	67.0	60635	1.3279	50.3025
0.0059	68.0	61540	1.3425	50.3331
0.0053	69.0	62445	1.3581	50.4416
0.0046	70.0	63350	1.3496	50.6066
0.0049	71.0	64255	1.3652	51.2156
0.005	72.0	65160	1.3556	50.6107
0.0046	73.0	66065	1.3821	50.8345
0.0046	74.0	66970	1.3507	50.6749
0.004	75.0	67875	1.3690	50.5656
0.0046	76.0	68780	1.3721	51.0060
0.0043	77.0	69685	1.3764	50.2744
0.0045	78.0	70590	1.3766	50.6455
0.0042	79.0	71495	1.3808	51.0862
0.004	80.0	72400	1.3785	50.8398
0.0036	81.0	73305	1.3923	50.6692
0.0038	82.0	74210	1.4045	50.2498
0.0037	83.0	75115	1.3903	50.5849
0.0039	84.0	76020	1.3927	50.6224
0.0034	85.0	76925	1.4024	50.8903
0.0034	86.0	77830	1.3977	50.5565
0.0036	87.0	78735	1.3953	50.7598
0.0036	88.0	79640	1.3960	50.9788
0.0033	89.0	80545	1.3969	51.0081
0.0032	90.0	81450	1.4088	51.1241
0.0031	91.0	82355	1.4058	50.8223
0.003	92.0	83260	1.4129	51.0453
0.0035	93.0	84165	1.4107	50.8884
0.0032	94.0	85070	1.4203	50.6694
0.0027	95.0	85975	1.4109	51.1179
0.003	96.0	86880	1.4099	50.8378
0.0032	97.0	87785	1.4131	50.7679
0.0033	98.0	88690	1.4138	51.0014
0.0029	99.0	89595	1.4169	51.1342
0.0029	100.0	90500	1.4166	51.1308

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: Jun 12, 2023
Updated: Jun 13, 2023