This model is a fine-tuned version of google/long-t5-tglobal-base on the gov_report_summarization_dataset dataset. It achieves the following results on the evaluation set:

Loss: 1.4052
Rouge1: 0.0432
Rouge2: 0.0217
Rougel: 0.0378
Rougelsum: 0.0408

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: 4e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 32
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
15.9484	0.99	31	2.7412	0.0382	0.0142	0.0319	0.0354
3.0143	1.98	62	1.7096	0.0385	0.0144	0.032	0.0355
2.1893	2.98	93	1.4976	0.0376	0.0138	0.0313	0.0347
1.6128	4.0	125	1.4406	0.041	0.0174	0.0354	0.0387
1.5438	4.99	156	1.4292	0.043	0.0203	0.0368	0.0408
1.5015	5.98	187	1.4220	0.0427	0.0205	0.0367	0.0405
1.4723	6.98	218	1.4071	0.0431	0.0215	0.0376	0.0408
1.4707	8.0	250	1.4089	0.0427	0.0212	0.0373	0.0405
1.4447	8.99	281	1.4046	0.0431	0.0216	0.0379	0.0408
1.4884	9.92	310	1.4052	0.0432	0.0217	0.0378	0.0408

Framework versions

Transformers 4.37.0
Pytorch 2.1.2
Datasets 2.1.0
Tokenizers 0.15.1

RMWeerasinghe/long-t5-tglobal-base-finetuned-govReport-4096

long-t5-tglobal-base-finetuned-govReport-4096

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

RMWeerasinghe/
long-t5-tglobal-base-finetuned-govReport-4096