CoolFace
Modelpublic

netoferraz/distilbert-base-uncased-finetuned-pad-clf-corpus

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes3downloads
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. -->

distilbert-base-uncased-finetuned-pad-clf-corpus

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

  • —Loss: 0.1507
  • —Accuracy: 0.9667
  • —F1: 0.9667

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: 2e-05
  • —trainbatchsize: 256
  • —evalbatchsize: 256
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossAccuracyF1
No log1.040.66030.550.3903
No log2.080.57840.90830.9082
No log3.0120.45240.91670.9169
0.5934.0160.34000.94170.9418
0.5935.0200.26220.950.9501
0.5936.0240.20900.96670.9667
0.2637.0280.18110.96670.9667
0.2638.0320.16400.96670.9667
0.2639.0360.15440.96670.9667
0.26310.0400.15070.96670.9667

Framework versions

  • —Transformers 4.35.2
  • —Pytorch 2.1.1+cu121
  • —Datasets 2.15.0
  • —Tokenizers 0.15.0