CoolFace
Modelpublic

gokuls/HBERTv1_48_L12_H512_A8_emotion

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes7downloads
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. -->

HBERTv148L12H512A8_emotion

This model is a fine-tuned version of gokuls/HBERTv1_48_L12_H512_A8 on the emotion dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.3811
  • —Accuracy: 0.8965

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
  • —trainbatchsize: 64
  • —evalbatchsize: 64
  • —seed: 33
  • —distributed_type: multi-GPU
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10

Training results

Training LossEpochStepValidation LossAccuracy
0.82771.02500.43430.852
0.38762.05000.35350.877
0.2973.07500.29430.887
0.2294.010000.29670.891
0.17945.012500.29580.891
0.1326.015000.32390.8915
0.10187.017500.38110.8965
0.07118.020000.45570.892
0.05049.022500.50290.894
0.03410.025000.56070.8935

Framework versions

  • —Transformers 4.34.0
  • —Pytorch 1.14.0a0+410ce96
  • —Datasets 2.14.5
  • —Tokenizers 0.14.0