BARTBana_Translation_Delete_v0

This model is a fine-tuned version of IAmSkyDra/BARTBana_v4 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.1618
• Sacrebleu: 14.9084

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: 100
• eval_batch_size: 100
• seed: 42
• 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: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Sacrebleu
0.3784	1.0	7467	0.2997	9.0338
0.2439	2.0	14934	0.1859	13.6216
0.2086	3.0	22401	0.1618	14.9084

Framework versions

• Transformers 4.48.1
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0