NLLB-en_tags-hi-HVG-3

hrithikgupt/NLLB-en_tags-hi-HVG-3

NLLB-en_tags-hi-HVG-3 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

16% 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: Jul 3, 2023
Updated: Jul 4, 2023
SHA: b57d1e71

Try a prompt

Model card

From the Hugging Face model README

NLLB-en_tags-hi-HVG-3

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: 1.4224
Bleu: 50.2464

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
0.8383	1.0	905	0.5937	48.0047
0.4588	2.0	1810	0.5747	49.4888
0.3836	3.0	2715	0.5860	49.0906
0.3197	4.0	3620	0.6010	49.6233
0.2765	5.0	4525	0.6133	49.6139
0.2329	6.0	5430	0.6458	49.7150
0.2018	7.0	6335	0.6673	49.7623
0.1733	8.0	7240	0.6798	49.3782
0.1526	9.0	8145	0.7211	49.4226
0.1317	10.0	9050	0.7413	49.8865
0.1115	11.0	9955	0.7609	49.1985
0.0965	12.0	10860	0.7979	49.3173
0.0882	13.0	11765	0.8332	49.7166
0.0787	14.0	12670	0.8386	50.1672
0.0718	15.0	13575	0.8547	50.0704
0.0635	16.0	14480	0.8909	49.6800
0.0551	17.0	15385	0.9103	49.3905
0.0501	18.0	16290	0.9101	50.8256
0.0471	19.0	17195	0.9442	49.0775
0.0441	20.0	18100	0.9513	48.4543
0.0418	21.0	19005	0.9805	48.7676
0.0354	22.0	19910	0.9941	49.7009
0.0336	23.0	20815	0.9991	49.3838
0.0322	24.0	21720	1.0307	49.6475
0.0286	25.0	22625	1.0561	50.3584
0.0276	26.0	23530	1.0411	49.6683
0.0235	27.0	24435	1.0556	49.0866
0.0232	28.0	25340	1.0851	49.4716
0.0224	29.0	26245	1.0750	50.1579
0.022	30.0	27150	1.0934	49.3374
0.0207	31.0	28055	1.0967	49.7173
0.0181	32.0	28960	1.0945	49.7657
0.0169	33.0	29865	1.1407	50.0030
0.0171	34.0	30770	1.1189	50.4127
0.0159	35.0	31675	1.1346	50.2506
0.0162	36.0	32580	1.1489	49.8176
0.0141	37.0	33485	1.1928	50.6360
0.0134	38.0	34390	1.1727	49.8416
0.0133	39.0	35295	1.1773	49.8876
0.0125	40.0	36200	1.1953	49.8122
0.0122	41.0	37105	1.2067	50.4785
0.0118	42.0	38010	1.1981	50.3467
0.0105	43.0	38915	1.2002	49.8224
0.0102	44.0	39820	1.2111	50.5699
0.0093	45.0	40725	1.2399	49.7683
0.0098	46.0	41630	1.2272	50.7580
0.0097	47.0	42535	1.2473	50.5611
0.0098	48.0	43440	1.2589	50.3284
0.0084	49.0	44345	1.2460	50.2871
0.0091	50.0	45250	1.2286	49.4469
0.0085	51.0	46155	1.2587	49.7388
0.0086	52.0	47060	1.2461	50.4568
0.0079	53.0	47965	1.2544	49.9404
0.0077	54.0	48870	1.2834	49.9716
0.0071	55.0	49775	1.2862	49.7437
0.0066	56.0	50680	1.2875	50.2184
0.0073	57.0	51585	1.2698	50.8421
0.0063	58.0	52490	1.2939	50.6062
0.0069	59.0	53395	1.3216	50.0915
0.0063	60.0	54300	1.2951	49.8986
0.0063	61.0	55205	1.3120	48.8698
0.0065	62.0	56110	1.3206	49.8809
0.0061	63.0	57015	1.3223	50.0771
0.0052	64.0	57920	1.3319	49.3782
0.0056	65.0	58825	1.3218	49.7072
0.0057	66.0	59730	1.3311	49.7683
0.0051	67.0	60635	1.3272	49.8843
0.0056	68.0	61540	1.3430	49.9421
0.0048	69.0	62445	1.3404	50.1666
0.0044	70.0	63350	1.3396	50.6629
0.0048	71.0	64255	1.3425	50.1145
0.0045	72.0	65160	1.3617	50.3237
0.0047	73.0	66065	1.3594	49.8087
0.0039	74.0	66970	1.3565	49.6365
0.0042	75.0	67875	1.3577	49.6644
0.004	76.0	68780	1.3751	49.9209
0.004	77.0	69685	1.3741	49.6684
0.0039	78.0	70590	1.3628	50.3882
0.0042	79.0	71495	1.3650	50.2353
0.0039	80.0	72400	1.3726	50.4128
0.0035	81.0	73305	1.3787	50.0809
0.0035	82.0	74210	1.3817	49.9331
0.0036	83.0	75115	1.3826	50.3345
0.0037	84.0	76020	1.3914	50.4378
0.0034	85.0	76925	1.3957	50.3504
0.0031	86.0	77830	1.4006	50.3621
0.003	87.0	78735	1.4092	50.1707
0.0035	88.0	79640	1.3886	50.3511
0.0032	89.0	80545	1.4077	50.3015
0.0032	90.0	81450	1.3998	50.5452
0.0032	91.0	82355	1.4127	50.4971
0.0029	92.0	83260	1.4081	50.3431
0.0029	93.0	84165	1.4134	50.1356
0.0033	94.0	85070	1.4101	50.4153
0.0028	95.0	85975	1.4193	50.4722
0.0028	96.0	86880	1.4122	50.1081
0.0025	97.0	87785	1.4161	50.3480
0.0027	98.0	88690	1.4246	50.2260
0.0027	99.0	89595	1.4231	50.2785
0.0024	100.0	90500	1.4224	50.2464

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 3, 2023
Updated: Jul 4, 2023