flan-t5-small

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

• Loss: 2.1038
• Rouge1: 68.104
• Rouge2: 62.8731
• Rougel: 64.5026
• Rougelsum: 64.9706
• Gen Len: 18.2857

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	8	2.2508	50.6686	41.7234	40.6222	39.9018	14.5714
No log	2.0	16	2.1618	67.043	61.7975	59.6406	59.8096	18.0
No log	3.0	24	2.1275	68.4011	63.5573	65.3917	65.8837	18.2857
No log	4.0	32	2.1100	67.547	62.8731	64.5026	64.9706	18.2857
No log	5.0	40	2.1038	68.104	62.8731	64.5026	64.9706	18.2857

Framework versions

• Transformers 4.33.1
• Pytorch 1.13.1
• Datasets 2.14.5
• Tokenizers 0.13.3