mBART-large-50-si-2

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

• Loss: 0.0337
• Bleu: 64.7407
• Exact Match: 0.4607

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: 32
• eval_batch_size: 16
• seed: 42
• 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Exact Match
0.0436	0.8278	500	0.0407	58.7860	0.3622
0.0278	1.6556	1000	0.0311	56.6939	0.4049
0.0188	2.4834	1500	0.0295	63.7207	0.4437
0.0106	3.3113	2000	0.0318	63.6282	0.4451
0.0072	4.1391	2500	0.0333	64.3830	0.4582
0.0065	4.9669	3000	0.0337	64.7407	0.4607

Framework versions

• Transformers 5.0.0
• Pytorch 2.8.0+cu128
• Datasets 4.5.0
• Tokenizers 0.22.2