nllb-200-distilled-600M-en-to-dz

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: 1.4130
• Bleu: 3.9043
• Gen Len: 16.5447

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: 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: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.7451	1.0	1688	1.5913	2.285	17.3937
1.5595	2.0	3376	1.4808	1.9817	16.787
1.429	3.0	5064	1.4367	2.7438	16.802
1.3653	4.0	6752	1.4180	4.3181	16.5257
1.3291	5.0	8440	1.4130	3.9043	16.6407

Framework versions

• Transformers 4.29.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.11.0
• Tokenizers 0.13.3