mbart-large-50-many-to-many-mmt-finetuned-en_XX-to-ar_AR

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.7840

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: 8
• eval_batch_size: 8
• 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
No log	1.0	125	3.6828
No log	2.0	250	3.6740
No log	3.0	375	3.7099
2.7161	4.0	500	3.7553
2.7161	5.0	625	3.7840

Framework versions

• Transformers 4.45.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.20.1