kinleyrabgay/nllb-200-600M-dzo-eng-50k

NLLB-200-600M Dzongkha-English Translation Model

This model is a fine-tuned version of kinleyrabgay/nllb-200-600M-dzo-eng-30k on kinleyrabgay/dz_to_en dataset. It achieves the following results on the evaluation set:

• Loss: 0.05
• Bleu: 65.0623

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: 3e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.0647	1.0	2500	0.0582	63.7979
0.0514	2.0	5000	0.0583	64.4264
0.0417	3.0	7500	0.0598	65.0520
0.0338	4.0	10000	0.0621	65.1574
0.0278	5.0	12500	0.0637	65.9515

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1