Edit model card

EN_mrm8488_spider

This model is a fine-tuned version of mrm8488/t5-small-finetuned-wikiSQL on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1002
  • Rouge2 Precision: 0.0364
  • Rouge2 Recall: 0.0288
  • Rouge2 Fmeasure: 0.0266

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Rouge2 Precision Rouge2 Recall Rouge2 Fmeasure
No log 1.0 438 0.4103 0.3532 0.1547 0.194
0.9639 2.0 876 0.2544 0.189 0.086 0.1038
0.3388 3.0 1314 0.1954 0.1365 0.0641 0.0768
0.2255 4.0 1752 0.1614 0.0644 0.0377 0.0407
0.1673 5.0 2190 0.1412 0.0675 0.0443 0.0467
0.1356 6.0 2628 0.1344 0.0528 0.0361 0.0366
0.1148 7.0 3066 0.1255 0.0476 0.0333 0.0338
0.0998 8.0 3504 0.1167 0.0513 0.0389 0.0374
0.0998 9.0 3942 0.1107 0.0619 0.0447 0.0439
0.088 10.0 4380 0.1092 0.0529 0.0412 0.0384
0.0816 11.0 4818 0.1047 0.0478 0.0358 0.0334
0.0742 12.0 5256 0.1015 0.0386 0.0306 0.028
0.071 13.0 5694 0.1018 0.0384 0.0301 0.0281
0.0674 14.0 6132 0.1004 0.0344 0.0279 0.0256
0.0674 15.0 6570 0.1002 0.0364 0.0288 0.0266

Framework versions

  • Transformers 4.26.1
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.7.dev0
  • Tokenizers 0.13.3
Downloads last month
2