You can deploy this model and start earning money today!

GJATT/
CLstageDEC17-nllb-1-sentence-punjabi

Name: CLstageDEC17-nllb-1-sentence-punjabi
Availability: InStock

generated_from_trainer

facebook/nllb-200-distilled-600M

finetune

cc-by-nc-4.0

endpoints_compatible

Views

No views yet

CLstageDEC17-nllb-1-sentence-punjabi

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.4637

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: 8
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 300
num_epochs: 30
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.2256	1.0	146	1.9084
1.9315	2.0	292	1.6233
1.8011	3.0	438	1.4219
1.6703	4.0	584	1.2829
1.552	5.0	730	1.1708
1.5023	6.0	876	1.0786
1.3737	7.0	1022	0.9996
1.2745	8.0	1168	0.9256
1.2833	9.0	1314	0.8643
1.1382	10.0	1460	0.8074
1.079	11.0	1606	0.7575
1.071	12.0	1752	0.7110
0.9769	13.0	1898	0.6729
0.9625	14.0	2044	0.6376
0.9301	15.0	2190	0.6068
0.8925	16.0	2336	0.5787
0.8436	17.0	2482	0.5554
0.8595	18.0	2628	0.5363
0.8292	19.0	2774	0.5185
0.7902	20.0	2920	0.5056
0.8046	21.0	3066	0.4936
0.7998	22.0	3212	0.4851
0.7376	23.0	3358	0.4780
0.826	24.0	3504	0.4726
0.7632	25.0	3650	0.4689
0.7595	26.0	3796	0.4662
0.7342	27.0	3942	0.4648
0.7196	28.0	4088	0.4640
0.723	29.0	4234	0.4638
0.7946	30.0	4380	0.4637

Framework versions

Transformers 4.57.3
Pytorch 2.9.0+cu126
Datasets 4.4.1
Tokenizers 0.22.1

GJATT/CLstageDEC17-nllb-1-sentence-punjabi

CLstageDEC17-nllb-1-sentence-punjabi

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

GJATT/
CLstageDEC17-nllb-1-sentence-punjabi