olgagasowska/mbart-large-50-many-to-many-mmt-iva_mt-en-pl

iva_mt

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

• Loss: 2.4663
• Bleu: 8.2225
• Gen Len: 14.5833

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 128
• optimizer: Use 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	Bleu	Gen Len
No log	0.6154	1	2.4663	8.2225	14.5833
No log	1.8462	3	2.4663	8.2225	14.5833

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3