mimba/mbart50-fra2ngiemboon

This model is a fine-tuned version of mimba/mbart50-fra2ngiemboon on the mimba/text2text dataset. It achieves the following results on the evaluation set:

• Loss: 1.0451
• Chrf: 36.9332
• Chrf Plus Plus: 36.9332

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf	Chrf Plus Plus
0.7397	1.0	2405	1.1243	36.2989	36.2989
0.8331	2.0	4810	1.0451	36.9332	36.9332

Framework versions

• Transformers 4.57.6
• Pytorch 2.10.0+cu126
• Datasets 4.5.0
• Tokenizers 0.22.2