This model is a fine-tuned version of google/long-t5-tglobal-xl on the learn3r/gov_report_memsum_bp dataset. It achieves the following results on the evaluation set:

Loss: 0.9813
Rouge1: 55.1149
Rouge2: 30.149
Rougel: 31.9694
Rougelsum: 52.9549
Gen Len: 1101.6060

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: 0.001
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 64
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: constant
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1562	1.0	272	1.0105	37.2934	18.6683	24.0563	35.6575	1844.1543
0.9737	2.0	545	0.9813	55.1149	30.149	31.9694	52.9549	1101.6060
0.8395	3.0	818	0.9925	57.4498	31.9315	32.914	55.2389	1055.9784
0.7353	4.0	1091	1.0404	67.3946	39.2034	36.8583	64.9879	829.2881
0.6212	4.99	1360	1.0752	64.5433	36.9477	35.3482	62.2005	779.6152

Framework versions

Transformers 4.34.0.dev0
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3

learn3r/longt5_xl_gov_memsum_bp_5

longt5_xl_gov_memsum_bp_5

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

learn3r/
longt5_xl_gov_memsum_bp_5