nllb-200-distilled-600M-finetuned-English-to-Twi

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: 0.4246
• Rouge1: 0.5925
• Rouge2: 0.3539
• Rougel: 0.5514
• Gen Len: 27.4969

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: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
No log	1.0	240	2.0578	0.5591	0.3184	0.5159	27.4438
No log	2.0	480	0.6914	0.5779	0.3392	0.5374	27.5396
2.3488	3.0	720	0.4522	0.5901	0.3518	0.549	27.475
2.3488	4.0	960	0.4246	0.5925	0.3539	0.5514	27.4969

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1