nllb-200-distilled-600M-FLEURS-GL-EN

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on juanjucm/FLEURS-SpeechT-GL-EN. It achieves the following results on the evaluation set:

• Loss: 0.0877
• Bleu: 43.7516

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
No log	1.0	343	5.3970	42.8151
14.0381	2.0	686	3.4256	42.6804
6.6148	3.0	1029	1.7277	42.9270
6.6148	4.0	1372	0.6586	43.0670
2.2397	5.0	1715	0.2392	43.7306
0.532	6.0	2058	0.1265	43.0986
0.532	7.0	2401	0.0939	43.4517
0.2069	8.0	2744	0.0877	43.7516

Framework versions

• Transformers 4.47.1
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0