my_awesome_billsum_model – AI Model by ASEDISH | AlphaNeural AI

You can deploy this model and start earning money today!

ASEDISH/
my_awesome_billsum_model

like

0

text2text-generation

generated_from_trainer

google-t5/t5-small

text-generation-inference

endpoints_compatible

Views

No views yet

my_awesome_billsum_model

This model is a fine-tuned version of t5-small on the billsum dataset. It achieves the following results on the evaluation set:

Loss: 2.5377
Rouge1: 0.1439
Rouge2: 0.0497
Rougel: 0.1155
Rougelsum: 0.1154
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: 2e-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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	62	2.8300	0.1234	0.0337	0.1019	0.102	19.0
No log	2.0	124	2.6177	0.1362	0.0458	0.1114	0.1111	19.0
No log	3.0	186	2.5542	0.142	0.0497	0.1146	0.1145	19.0
No log	4.0	248	2.5377	0.1439	0.0497	0.1155	0.1154	19.0

Framework versions

Transformers 4.33.1
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3