bbc-to-ind-nmt-v2

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

• Loss: 1.1318
• Sacrebleu: 37.7411
• Gen Len: 37.2965

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu	Gen Len
3.3872	1.0	825	1.2738	33.3267	37.8435
1.1626	2.0	1650	1.1593	36.2145	37.436
0.9846	3.0	2475	1.1289	37.2589	37.0315
0.8883	4.0	3300	1.1254	37.8219	37.216
0.832	5.0	4125	1.1318	37.7411	37.2965

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.14.6
• Tokenizers 0.19.1