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: 1.3909
• Rouge1: 43.9584
• Rouge2: 34.6235
• Rougel: 42.6933
• Rougelsum: 42.1079
• Gen Len: 19.0

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	22	2.4403	25.3933	13.7472	24.1753	25.139	18.6279
No log	2.0	44	1.7941	44.8683	34.5587	43.0041	42.8714	19.0
No log	3.0	66	1.5390	43.9584	34.6235	42.6933	42.1079	19.0
No log	4.0	88	1.4240	43.9584	34.6235	42.6933	42.1079	19.0
No log	5.0	110	1.3909	43.9584	34.6235	42.6933	42.1079	19.0

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0