nllb-tamazight-finetuned-v3

This model is a fine-tuned version of facebook/nllb-200-3.3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.6156

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: 2
• eval_batch_size: 8
• seed: 42
• 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
5.2004	1.0	50	4.7242
3.433	2.0	100	3.1314
2.8056	3.0	150	2.6156

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.0+cu118
• Datasets 3.6.0
• Tokenizers 0.15.2