NLLB_DoRA

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: 1.2708
• Bleu: 32.802
• Rouge: 0.6028
• Gen Len: 17.4444

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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
1.3937	1.0	2000	1.3115	32.2196	0.5954	17.6569
1.3309	2.0	4000	1.2781	32.6752	0.6011	17.4931
1.3234	3.0	6000	1.2708	32.802	0.6028	17.4444

Framework versions

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