sunbird-medical-luganda-bidirectional-v3-kaggle

This model is a fine-tuned version of Sunbird/translate-nllb-1.3b-salt on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.1054
• Bleu: 21.1119
• Chrf: 40.1257

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: 16
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 128
• 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: linear
• lr_scheduler_warmup_steps: 100
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Chrf
0.7411	3.5110	400	1.4134	20.4264	41.7565
0.3377	7.0176	800	1.1662	18.2353	35.6653
0.2665	10.5286	1200	1.1054	21.1119	40.1257

Framework versions

• PEFT 0.16.0
• Transformers 4.57.3
• Pytorch 2.9.0+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1