CoolFace
Modelpublic

gokuls/HBERTv1_48_L10_H512_A8_massive

sourceHugging Faceupdated 3y agoView on Hugging Face
0likes10downloads
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. -->

HBERTv148L10H512A8_massive

This model is a fine-tuned version of gokuls/HBERTv1_48_L10_H512_A8 on the massive dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.8593
  • —Accuracy: 0.8583

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: 15

Training results

Training LossEpochStepValidation LossAccuracy
2.65361.01801.32120.6542
1.06962.03600.83840.7777
0.7013.05400.75140.8082
0.51814.07200.73760.8096
0.39585.09000.67640.8269
0.30316.010800.69550.8382
0.23787.012600.71730.8392
0.17198.014400.72890.8401
0.12949.016200.76090.8485
0.09610.018000.77440.8465
0.076911.019800.82060.8490
0.0512.021600.80850.8564
0.03413.023400.85370.8534
0.021814.025200.84800.8564
0.013915.027000.85930.8583

Framework versions

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