flan-t5-base-samsum-finetuned-QMSum-01

This model is a fine-tuned version of philschmid/flan-t5-base-samsum on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4413
• Rouge1: 22.8732
• Rouge2: 8.0775
• Rougel: 18.0966
• Rougelsum: 20.3558
• Gen Len: 18.9959

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: 4
• eval_batch_size: 4
• 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	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	274	2.5086	22.3096	7.3877	17.378	19.7119	19.0
2.6028	2.0	548	2.4658	22.6907	7.9177	17.9165	20.108	19.0
2.6028	3.0	822	2.4436	22.9879	7.9476	18.0347	20.3127	19.0
2.3346	4.0	1096	2.4413	22.8732	8.0775	18.0966	20.3558	18.9959
2.3346	5.0	1370	2.4416	23.0559	8.257	18.1721	20.6307	18.9959

Framework versions

• Transformers 4.29.2
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3