flan-t5-large-peft-mixSub

This model is a fine-tuned version of google/flan-t5-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9408
• Rouge1: 39.2511
• Rouge2: 14.4613
• Rougel: 28.6907
• Rougelsum: 35.9795
• Gen Len: 97.8269

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: 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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
2.1134	1.0	1630	1.9559	39.0131	14.3369	28.4611	35.7936	96.2081
2.0783	2.0	3260	1.9438	39.0184	14.3571	28.5375	35.7466	99.4684
2.0722	3.0	4890	1.9408	39.2511	14.4613	28.6907	35.9795	97.8269

Framework versions

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