long-t5-tglobal-base-german-law – AI Model by hmueller25 | AlphaNeural AI

You can deploy this model and start earning money today!

hmueller25/
long-t5-tglobal-base-german-law

like

0

text2text-generation

generated_from_trainer

google/long-t5-tglobal-base

endpoints_compatible

Views

No views yet

long-t5-tglobal-base-german-law

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

Loss: 3.4575
Rouge1: 0.072
Rouge2: 0.0236
Rougel: 0.0631
Rougelsum: 0.0631
Gen Len: 20.0

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: 1
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
5.5906	1.0	49	9.5684	0.0375	0.0103	0.0369	0.0377	20.0
4.6503	2.0	98	3.8125	0.0634	0.0206	0.0555	0.0568	20.0
3.6625	3.0	147	3.4575	0.072	0.0236	0.0631	0.0631	20.0
3.1628	4.0	196	3.3466	0.0693	0.0202	0.0626	0.0633	20.0

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 3.6.0
Tokenizers 0.21.1