mode_tuned_peft

This model is a fine-tuned version of facebook/bart-large-cnn on the samsum dataset. It achieves the following results on the evaluation set:

• Loss: 0.5220
• Rouge1: 40.6099
• Rouge2: 20.4138
• Rougel: 31.1095
• Rougelsum: 37.6804
• Gen Len: 58.11

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.5144	1.0	14732	0.5494	39.171	19.3682	29.7493	36.2965	58.6773
0.5694	2.0	29464	0.5357	40.1584	20.0293	30.5791	37.1361	58.0648
0.3497	3.0	44196	0.5277	41.0391	20.7891	31.5244	38.1502	58.0086
0.3444	4.0	58928	0.5255	40.6698	20.543	31.2399	37.8126	58.3716
0.3495	5.0	73660	0.5220	40.6099	20.4138	31.1095	37.6804	58.11

Framework versions

• PEFT 0.4.0
• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1