bart-base-vn-re-attention-vn-tokenizer

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

• Loss: 2.4481
• Rouge1: 18.0845
• Rouge2: 8.2722
• Rougel: 15.4154
• Rougelsum: 16.6591
• Bleu-1: 0.0007
• Bleu-2: 0.0004
• Bleu-3: 0.0002
• Bleu-4: 0.0001
• Gen Len: 19.811

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	Rouge1	Rouge2	Rougel	Rougelsum	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Gen Len
2.6584	1.0	10886	2.4481	18.0845	8.2722	15.4154	16.6591	0.0007	0.0004	0.0002	0.0001	19.811

Framework versions

• Transformers 4.35.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.14.1