bart-base-finetuned-ro-to-en-clean

This model is a fine-tuned version of facebook/bart-base on the wmt16 dataset. It achieves the following results on the evaluation set:

• Loss: 1.5226
• Bleu: 15.7437
• Gen Len: 18.4167

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.0182	1.0	38145	1.5226	15.7437	18.4167

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1+cu121
• Datasets 2.15.0
• Tokenizers 0.15.0