Modelpublic

alexandrualexandru/my-final-v1-text-to-sparql-combined-dataset-t5-small-2023-05-10_07-44

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face

0likes6downloads

Model Card

my-final-v1-text-to-sparql-combined-dataset-t5-small-2023-05-10_07-44

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

—Loss: 0.4073
—Gen Len: 19.0
—Bertscorer-p: 0.4980
—Bertscorer-r: 0.1017
—Bertscorer-f1: 0.2920
—Sacrebleu-score: 5.8855
—Sacrebleu-precisions: [77.05727215080417, 62.5240589596784, 50.651199136696, 44.790044963147636]
—Bleu-bp: 0.1024

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: 0.0003
—trainbatchsize: 8
—evalbatchsize: 8
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Gen Len	Bertscorer-p	Bertscorer-r	Bertscorer-f1	Sacrebleu-score	Sacrebleu-precisions	Bleu-bp
0.5032	1.0	7822	0.4629	19.0	0.4897	0.1066	0.2908	5.9440	[75.58761664102093, 59.98349638586719, 47.124791651568955, 40.69508501229539]	0.1095
0.4506	2.0	15644	0.4219	19.0	0.4843	0.1024	0.2861	5.5345	[76.04556633170597, 61.69371447400939, 49.49361223273979, 43.50113197496338]	0.0982
0.4333	3.0	23466	0.4073	19.0	0.4980	0.1017	0.2920	5.8855	[77.05727215080417, 62.5240589596784, 50.651199136696, 44.790044963147636]	0.1024

Framework versions

—Transformers 4.28.1
—Pytorch 2.0.0+cu118
—Datasets 2.12.0
—Tokenizers 0.13.3