t5-small-finetuned-webnlg-mt-2.0e-04-multicorp – AI Model by vente | AlphaNeural AI

You can deploy this model and start earning money today!

vente/
t5-small-finetuned-webnlg-mt-2.0e-04-multicorp

like

0

text2text-generation

generated_from_trainer

text-generation-inference

endpoints_compatible

Views

No views yet

t5-small-finetuned-webnlg-mt-2.0e-04-multicorp

This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3764
Rouge1: 0.8196
Rouge2: 0.6426
Rougel: 0.6983
Rougelsum: 0.7239
Gen Len: 44.2931

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: 0.0002
train_batch_size: 64
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.8444	1.23	1500	0.4807	0.7814	0.5860	0.6585	0.6825	43.3923
0.7098	2.47	3000	0.4127	0.8047	0.6206	0.6824	0.7074	43.5941
0.678	3.7	4500	0.3856	0.8151	0.6363	0.6933	0.7181	44.1976
0.651	4.93	6000	0.3764	0.8196	0.6426	0.6983	0.7239	44.2931

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu117
Datasets 2.14.5
Tokenizers 0.13.3