bart-base-vn-re-attention

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

• Loss: 1.7789
• Rouge1: 19.0028
• Rouge2: 7.9076
• Rougel: 15.8936
• Rougelsum: 17.5193
• Bleu-1: 0.003
• Bleu-2: 0.0018
• Bleu-3: 0.001
• Bleu-4: 0.0006
• Gen Len: 19.9959

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu-1	Bleu-2	Bleu-3	Bleu-4	Gen Len
1.9746	1.0	10886	1.7789	19.0028	7.9076	15.8936	17.5193	0.003	0.0018	0.001	0.0006	19.9959

Framework versions

• Transformers 4.33.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.13.3