pima-diabetes

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

• Loss: 0.1017
• Rouge1: 87.4026
• Rouge2: 76.1364
• Rougel: 87.2727
• Rougelsum: 87.2727
• Gen Len: 6.8442

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	39	0.1038	86.7532	75.1623	86.7532	86.7532	7.0
No log	2.0	78	0.1191	86.7532	75.1623	86.7532	86.7532	7.0
No log	3.0	117	0.1026	86.7532	75.1623	86.7532	86.7532	7.0
No log	4.0	156	0.1027	86.7532	75.1623	86.7532	86.7532	7.0
No log	5.0	195	0.1026	86.7532	75.1623	86.7532	86.7532	7.0
No log	6.0	234	0.1025	86.4935	74.6753	86.4935	86.4935	6.9870
No log	7.0	273	0.1030	86.7532	75.1623	86.7532	86.7532	7.0
No log	8.0	312	0.1031	83.6364	69.3182	83.6364	83.6364	6.5325
No log	9.0	351	0.1024	86.4935	74.6753	86.4935	86.4935	6.9610
No log	10.0	390	0.1017	87.4026	76.1364	87.2727	87.2727	6.8442

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.0
• Datasets 2.14.5
• Tokenizers 0.13.3