mbart-en-translation

This model is a fine-tuned version of facebook/mbart-large-50 on watermelonhydro/es_en_2999 dataset. It achieves the following results on the evaluation set:

• Loss: 1.2646
• Bleu: 51.3603
• Gen Len: 51.072

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: 5.6e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	282	1.0701	46.0434	49.7947
1.2218	2.0	564	0.9959	49.3118	50.584
1.2218	3.0	846	1.0847	50.359	51.352
0.311	4.0	1128	1.2012	50.6484	50.9733
0.311	5.0	1410	1.2646	51.3603	51.072

Framework versions

• Transformers 4.38.0
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2