bart-pbmed-hierarchicall

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: 3.3741
• Rouge1: 23.99
• Rouge2: 3.43
• Rougel: 15.21
• Rougelsum: 21.93

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: 5e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
3.9967	0.2668	200	3.6014	0.0	0.0	0.0	0.0
3.8428	0.5337	400	3.4873	23.23	3.18	15.17	21.08
3.7321	0.8005	600	3.4202	23.41	3.18	14.28	21.41
3.6064	1.0674	800	3.3899	0.0	0.0	0.0	0.0
3.5746	1.3342	1000	3.3741	23.99	3.43	15.21	21.93

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.2.0
• Tokenizers 0.19.1