NLLB_LoRA

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: 1.3291
• Bleu: 32.6379
• Rouge: 0.5923
• Gen Len: 17.375

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: 2e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge	Gen Len
2.714	1.0	875	1.3916	31.9042	0.5851	17.4015
1.457	2.0	1750	1.3379	32.3993	0.5916	17.4175
1.4281	3.0	2625	1.3291	32.6379	0.5923	17.375

Framework versions

• PEFT 0.12.0
• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1