mbart-50-lora-cb-en

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.8461
• Bleu: 45.1801

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 800
• num_epochs: 8
• label_smoothing_factor: 0.1

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
3.007	1.8394	500	2.9616	45.1801
2.9084	3.6774	1000	2.8873	100.0000
2.8383	5.5154	1500	2.8542	45.1801
2.8091	7.3534	2000	2.8461	45.1801

Framework versions

• PEFT 0.17.1
• Transformers 4.57.1
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1