finetune-NLLB-600M-on-opus100-Ar2En-without-optimization

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2100
• Bleu: 34.6972
• Rouge: 0.6037
• Gen Len: 17.7144

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: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 4
• 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	Bleu	Rouge	Gen Len
1.5487	1.0	2000	1.2118	34.2974	0.6072	17.6144
1.135	2.0	4000	1.2100	34.6972	0.6037	17.7144
0.9746	3.0	6000	1.2414	34.1024	0.5995	17.6656

Framework versions

• Transformers 4.44.0
• Pytorch 2.4.0
• Datasets 2.21.0
• Tokenizers 0.19.1