CoolFace
Modelpublic

Tuyennguyen28/tiny-bert-sst2-distilled

sourceHugging Faceapache-2.0updated 2y agoView on Hugging Face
0likes114downloads
Model Card

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

tiny-bert-sst2-distilled

This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • —eval_loss: 0.3552
  • —eval_accuracy: 0.8509
  • —eval_AUC: 0.8049
  • —eval_MCC: 0.5681
  • —evalPRAUC: 0.6897
  • —eval_BAC: 0.7295
  • —eval_runtime: 29.1893
  • —evalsamplesper_second: 311.176
  • —evalstepsper_second: 9.73
  • —epoch: 1.0
  • —step: 1224

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: 1.0579519958564978e-05
  • —trainbatchsize: 32
  • —evalbatchsize: 32
  • —seed: 9
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 6

Framework versions

  • —Transformers 4.43.3
  • —Pytorch 2.3.1+cu121
  • —Datasets 2.20.0
  • —Tokenizers 0.19.1
Tuyennguyen28/tiny-bert-sst2-distilled · CoolFace