You can deploy this model and start earning money today!

KMayanja/
sunbird-medical-luganda-bidirectional

Name: sunbird-medical-luganda-bidirectional
Availability: InStock

Sunbird/translate-nllb-1.3b-salt

Views

No views yet

sunbird-medical-luganda-bidirectional

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: 1.2232
Bleu: 20.2494
Chrf: 36.398

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: 8
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
optimizer: Use 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
2.5386	0.9434	400	2.7346	23.3038	42.4517
1.5123	1.8868	800	2.0047	22.8899	42.332
1.2933	2.8302	1200	1.8325	22.0526	42.144
1.0617	3.7736	1600	1.6657	22.1939	42.7281
0.8517	4.7170	2000	1.4932	20.1487	40.7975
0.6754	5.6604	2400	1.3601	15.4695	30.9355
0.6044	6.6038	2800	1.2990	18.2295	34.0916
0.5291	7.5472	3200	1.2658	19.1868	35.2587
0.5034	8.4906	3600	1.2454	19.9832	36.1208
0.4905	9.4340	4000	1.2341	20.1341	36.2599
0.4737	10.3774	4400	1.2263	20.2801	36.3278
0.4717	11.3208	4800	1.2232	20.2494	36.398

Framework versions

PEFT 0.17.1
Transformers 4.56.2
Pytorch 2.8.0
Datasets 4.1.1
Tokenizers 0.22.1

KMayanja/sunbird-medical-luganda-bidirectional

sunbird-medical-luganda-bidirectional

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

KMayanja/
sunbird-medical-luganda-bidirectional