BART-finetuned-on-training-without-knowledge

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

• Loss: 2.2844
• Bleu: 2.829
• Gen Len: 19.3589

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: 3
• eval_batch_size: 3
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.6072	1.0	1679	2.3674	2.3478	19.8107
2.2177	2.0	3358	2.2844	2.829	19.3589

Framework versions

• Transformers 4.34.1
• Pytorch 2.0.1+cu117
• Datasets 2.13.0
• Tokenizers 0.14.1