bart-base

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

• Loss: 0.5993

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: 0.0001
• train_batch_size: 12
• 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
0.7968	1.0	4383	0.6996
0.6596	2.0	8766	0.6396
0.5531	3.0	13149	0.6133
0.4867	4.0	17532	0.5961
0.4285	5.0	21915	0.5993

Framework versions

• Transformers 4.40.0
• Pytorch 2.2.1+cu121
• Tokenizers 0.19.1