LED_multi_lexsum_peft

This model is a fine-tuned version of pszemraj/led-large-book-summary on an allenai/multi_lexsum dataset. It achieves the following results on the evaluation set:

• Loss: 4.2303
• Rouge1: 0.3156
• Rouge2: 0.1258
• Rougel: 0.1548
• Rougelsum: 0.185
• Bert Precision: 0.8468
• Bert Recall: 0.887
• Bert F1: 0.8664
• Gen Len: 949.968

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: 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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bert Precision	Bert Recall	Bert F1	Gen Len
6.2726	1.0	850	4.2979	0.3208	0.1202	0.1551	0.185	0.8724	0.8797	0.876	906.8
4.5041	2.0	1700	4.2303	0.3156	0.1258	0.1548	0.185	0.8468	0.887	0.8664	949.968

Framework versions

• PEFT 0.10.0
• Transformers 4.38.2
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2