metadata

license: apache-2.0
base_model: t5-small
tags:
  - generated_from_trainer
datasets:
  - billsum
metrics:
  - rouge
model-index:
  - name: my_awesome_billsum_model
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: billsum
          type: billsum
          config: default
          split: ca_test
          args: default
        metrics:
          - name: Rouge1
            type: rouge
            value: 0.2014

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: 2.2453
Rouge1: 0.2014
Rouge2: 0.1012
Rougel: 0.1696
Rougelsum: 0.1698
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: 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	124	2.5661	0.1328	0.0422	0.1082	0.1083	19.0
No log	2.0	248	2.4215	0.1686	0.0704	0.139	0.1391	19.0
No log	3.0	372	2.3551	0.1994	0.0994	0.1669	0.1667	19.0
No log	4.0	496	2.3135	0.2021	0.1018	0.1701	0.17	19.0
2.7983	5.0	620	2.2911	0.2019	0.103	0.1703	0.1705	19.0
2.7983	6.0	744	2.2719	0.2015	0.1023	0.1707	0.1708	19.0
2.7983	7.0	868	2.2597	0.2008	0.1013	0.1691	0.1693	19.0
2.7983	8.0	992	2.2515	0.2016	0.1016	0.1695	0.1697	19.0
2.4664	9.0	1116	2.2467	0.2017	0.1016	0.1696	0.1698	19.0
2.4664	10.0	1240	2.2453	0.2014	0.1012	0.1696	0.1698	19.0

Framework versions

Transformers 4.33.3
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3