Hugging Face's logo

HuggingFaceTB
/
stack-edu-classifier-sql

Text Classification
Transformers
Safetensors
code
bert
Generated from Trainer
Model card Files
xet
Community
stack-edu-classifier-sql / README.md
loubnabnl's picture
loubnabnl HF Staff
Model save
5ebf0e7 verified
preview code
|
raw
history blame
5.07 kB
metadata
base_model: bigcode/starencoder
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - accuracy
model-index:
  - name: classifier-llama3-sql-500k
    results: []

classifier-llama3-sql-500k

This model is a fine-tuned version of bigcode/starencoder on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4719
  • Precision: 0.6074
  • Recall: 0.4618
  • F1 Macro: 0.4864
  • Accuracy: 0.5478
  • F1 Binary Minimum3: 0.8854
  • F1 Binary Minimum2: 0.9418

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: 0.0001
  • train_batch_size: 16
  • eval_batch_size: 256
  • seed: 0
  • distributed_type: multi-GPU
  • num_devices: 8
  • total_train_batch_size: 128
  • total_eval_batch_size: 2048
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 200
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Macro Accuracy F1 Binary Minimum3 F1 Binary Minimum2
No log 0 0 8.5378 0.0326 0.2 0.0561 0.1632 0 0
0.5231 1.2837 1000 0.5326 0.5973 0.4176 0.4388 0.5192 0.8777 0.9339
0.5041 2.5674 2000 0.5038 0.6039 0.4350 0.4533 0.5348 0.8824 0.9392
0.5062 3.8511 3000 0.4965 0.6035 0.4452 0.4652 0.5402 0.8829 0.9411
0.498 5.1348 4000 0.4916 0.6036 0.4445 0.4634 0.5398 0.8848 0.9404
0.5036 6.4185 5000 0.4894 0.5963 0.4531 0.4789 0.5397 0.8842 0.9396
0.4968 7.7022 6000 0.4880 0.6082 0.4402 0.4595 0.5347 0.8826 0.9396
0.498 8.9859 7000 0.4835 0.6032 0.4592 0.4843 0.5440 0.8837 0.9413
0.4849 10.2696 8000 0.4816 0.6168 0.4555 0.4799 0.5442 0.8844 0.9412
0.4925 11.5533 9000 0.4821 0.5868 0.4595 0.4861 0.5422 0.8843 0.9405
0.477 12.8370 10000 0.4800 0.6117 0.4472 0.4688 0.5404 0.8849 0.9403
0.4753 14.1207 11000 0.4790 0.6111 0.4533 0.4737 0.5444 0.8842 0.9420
0.4863 15.4044 12000 0.4809 0.5849 0.4593 0.4858 0.5426 0.8847 0.9402
0.4794 16.6881 13000 0.4761 0.6116 0.4565 0.4820 0.5442 0.8844 0.9410
0.4684 17.9718 14000 0.4766 0.6044 0.4533 0.4756 0.5444 0.8852 0.9412
0.4814 19.2555 15000 0.4748 0.6093 0.4614 0.4842 0.5496 0.8844 0.9427
0.4993 20.5392 16000 0.4746 0.5977 0.4620 0.4879 0.5464 0.8849 0.9415
0.4788 21.8228 17000 0.4739 0.6125 0.4592 0.4809 0.5482 0.8860 0.9426
0.4857 23.1065 18000 0.4747 0.6190 0.4546 0.4771 0.5457 0.8858 0.9414
0.4709 24.3902 19000 0.4728 0.6132 0.4566 0.4800 0.5462 0.8850 0.9417
0.4803 25.6739 20000 0.4754 0.5999 0.4585 0.4858 0.5435 0.8856 0.9397
0.4731 26.9576 21000 0.4725 0.6100 0.4575 0.4805 0.5470 0.8859 0.9415
0.4788 28.2413 22000 0.4725 0.6087 0.4609 0.4861 0.5478 0.8861 0.9415
0.4594 29.5250 23000 0.4719 0.6074 0.4618 0.4864 0.5478 0.8854 0.9418

Framework versions

  • Transformers 4.43.4
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1