Hugging Face's logo

mousaazari
/
t5-text2sql

Text2Text Generation
Transformers
PyTorch
TensorBoard
t5
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
5
t5-text2sql / README.md
mousaazari's picture
mousaazari
update model card README.md
57a33ab
preview code
|
raw
history blame
4.47 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: t5-text2sql
    results: []

t5-text2sql

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

  • Loss: 0.1189
  • Rouge2 Precision: 0.9177
  • Rouge2 Recall: 0.4311
  • Rouge2 Fmeasure: 0.5617

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: 5e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure
No log 1.0 11 0.1481 0.8982 0.4224 0.5515
No log 2.0 22 0.1409 0.939 0.4393 0.5736
No log 3.0 33 0.1352 0.939 0.4393 0.5736
No log 4.0 44 0.1279 0.9294 0.4353 0.5679
No log 5.0 55 0.1244 0.9192 0.4307 0.5633
No log 6.0 66 0.1294 0.9331 0.4379 0.5716
No log 7.0 77 0.1358 0.939 0.4393 0.5736
No log 8.0 88 0.1304 0.9331 0.4379 0.5716
No log 9.0 99 0.1312 0.9177 0.4311 0.5617
No log 10.0 110 0.1291 0.9177 0.4311 0.5617
No log 11.0 121 0.1319 0.9138 0.4311 0.5616
No log 12.0 132 0.1264 0.9113 0.4273 0.5586
No log 13.0 143 0.1273 0.907 0.4246 0.555
No log 14.0 154 0.1181 0.9113 0.4273 0.5586
No log 15.0 165 0.1196 0.9113 0.4273 0.5586
No log 16.0 176 0.1168 0.907 0.4246 0.555
No log 17.0 187 0.1190 0.9232 0.4348 0.5672
No log 18.0 198 0.1162 0.9113 0.4273 0.5586
No log 19.0 209 0.1160 0.907 0.4246 0.555
No log 20.0 220 0.1188 0.9113 0.4246 0.5554
No log 21.0 231 0.1200 0.9113 0.4246 0.5554
No log 22.0 242 0.1226 0.9113 0.4246 0.5554
No log 23.0 253 0.1235 0.9155 0.4273 0.5592
No log 24.0 264 0.1206 0.9177 0.4311 0.5617
No log 25.0 275 0.1189 0.9177 0.4311 0.5617
No log 26.0 286 0.1197 0.9177 0.4311 0.5617
No log 27.0 297 0.1202 0.9177 0.4311 0.5617
No log 28.0 308 0.1199 0.9177 0.4311 0.5617
No log 29.0 319 0.1192 0.9177 0.4311 0.5617
No log 30.0 330 0.1189 0.9177 0.4311 0.5617

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1