Hugging Face's logo

gates04
/
FP16-KD-NID

Text Classification
Transformers
Safetensors
distilbert
Generated from Trainer
Model card Files Community
FP16-KD-NID / README.md
gates04's picture
gates04
End of training
d2c6b6a verified
preview code
|
raw
history blame contribute delete
3.04 kB
metadata
library_name: transformers
base_model: huawei-noah/TinyBERT_General_4L_312D
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
model-index:
  - name: FP16-KD-NID
    results: []

FP16-KD-NID

This model is a fine-tuned version of huawei-noah/TinyBERT_General_4L_312D on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0424
  • Accuracy: 0.9919
  • Precision: 0.9348
  • Recall: 0.9215
  • F1 score: 0.9238

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: 650
  • eval_batch_size: 650
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1 score
0.1582 1.0 1828 0.1329 0.9827 0.8730 0.8321 0.8307
0.1112 2.0 3656 0.1033 0.9853 0.8697 0.8584 0.8529
0.0927 3.0 5484 0.0820 0.9879 0.9209 0.8790 0.8789
0.0828 4.0 7312 0.0689 0.9893 0.9233 0.8953 0.8980
0.0711 5.0 9140 0.0637 0.9898 0.9204 0.9024 0.9017
0.0673 6.0 10968 0.0595 0.9901 0.9206 0.9080 0.9051
0.0514 7.0 12796 0.0538 0.9907 0.9273 0.9084 0.9100
0.0522 8.0 14624 0.0518 0.9909 0.9266 0.9103 0.9123
0.0478 9.0 16452 0.0492 0.9911 0.9352 0.9105 0.9148
0.0478 10.0 18280 0.0463 0.9914 0.9335 0.9153 0.9185
0.0415 11.0 20108 0.0461 0.9914 0.9282 0.9171 0.9169
0.0394 12.0 21936 0.0445 0.9916 0.9328 0.9190 0.9204
0.0377 13.0 23764 0.0435 0.9917 0.9358 0.9180 0.9217
0.0342 14.0 25592 0.0429 0.9918 0.9346 0.9190 0.9214
0.0383 15.0 27420 0.0424 0.9919 0.9348 0.9215 0.9238

Framework versions

  • Transformers 4.49.0
  • Pytorch 2.6.0+cu124
  • Datasets 3.4.1
  • Tokenizers 0.21.1