small-dataset-factor

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

• Loss: 1.0342
• Rouge1: 0.7004
• Rouge2: 0.5624
• Rougel: 0.5489
• Rougelsum: 0.5489
• Gen Len: 72.0

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	1	1.4501	0.5989	0.3974	0.493	0.493	61.5
No log	2.0	2	1.4501	0.5989	0.3974	0.493	0.493	61.5
No log	3.0	3	1.2372	0.6418	0.459	0.5287	0.5287	66.5
No log	4.0	4	1.1366	0.6293	0.4495	0.5183	0.5183	68.0
No log	5.0	5	1.0768	0.6763	0.5432	0.5941	0.5941	75.0
No log	6.0	6	1.0550	0.6846	0.5503	0.5357	0.5357	74.0
No log	7.0	7	1.0425	0.6846	0.5503	0.5357	0.5357	74.0
No log	8.0	8	1.0342	0.7004	0.5624	0.5489	0.5489	72.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1