nllb-peft-2-way-enta

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 6.6779
• Sacrebleu: 14.6250

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: 0.0001
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu
6.7496	1.0	11250	6.6810	14.3659
6.737	2.0	22500	6.6785	14.5979
6.7405	3.0	33750	6.6779	14.6250

Framework versions

• PEFT 0.12.0
• Transformers 4.45.0.dev0
• Pytorch 2.1.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1