Hugging Face's logo

mousaazari
/
t5-text2sql_v1

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
1
t5-text2sql_v1 / README.md
mousaazari's picture
mousaazari
update model card README.md
2e23e24
preview code
|
raw
history blame
4.48 kB
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: t5-text2sql_v1
    results: []

t5-text2sql_v1

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

  • Loss: 0.0747
  • Rouge2 Precision: 0.9499
  • Rouge2 Recall: 0.3287
  • Rouge2 Fmeasure: 0.4614

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 2.1363 0.0465 0.0105 0.017
No log 2.0 22 1.3415 0.0475 0.0105 0.017
No log 3.0 33 0.8590 0.0445 0.0119 0.0181
No log 4.0 44 0.5496 0.2211 0.0848 0.1182
No log 5.0 55 0.3879 0.4371 0.1923 0.2529
No log 6.0 66 0.2915 0.7201 0.259 0.3604
No log 7.0 77 0.2325 0.7942 0.2704 0.3838
No log 8.0 88 0.1910 0.8412 0.288 0.4067
No log 9.0 99 0.1734 0.8399 0.2964 0.4132
No log 10.0 110 0.1453 0.8902 0.3211 0.4448
No log 11.0 121 0.1276 0.8749 0.3121 0.434
No log 12.0 132 0.1236 0.8486 0.304 0.423
No log 13.0 143 0.1173 0.8369 0.301 0.4178
No log 14.0 154 0.1085 0.8935 0.3147 0.4411
No log 15.0 165 0.1001 0.9154 0.3216 0.452
No log 16.0 176 0.0971 0.8822 0.3155 0.4402
No log 17.0 187 0.0931 0.9071 0.3247 0.4525
No log 18.0 198 0.0870 0.9029 0.3174 0.4453
No log 19.0 209 0.0838 0.9286 0.323 0.4545
No log 20.0 220 0.0842 0.9539 0.3328 0.4667
No log 21.0 231 0.0824 0.9539 0.3328 0.4667
No log 22.0 242 0.0801 0.9539 0.3311 0.465
No log 23.0 253 0.0789 0.9316 0.321 0.4507
No log 24.0 264 0.0778 0.9316 0.321 0.4507
No log 25.0 275 0.0768 0.9316 0.3194 0.449
No log 26.0 286 0.0762 0.9338 0.3222 0.4523
No log 27.0 297 0.0755 0.9499 0.3287 0.4614
No log 28.0 308 0.0752 0.9499 0.3287 0.4614
No log 29.0 319 0.0749 0.9499 0.3287 0.4614
No log 30.0 330 0.0747 0.9499 0.3287 0.4614

Framework versions

  • Transformers 4.21.2
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1