CoolFace
Modelpublic

Mozart-coder/BERT_Jan-6_tokenized

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes20downloads
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. -->

BERTJan-6tokenized

This model is a fine-tuned version of armheb/DNA_bert_6 on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.0369

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: 64
  • —evalbatchsize: 64
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 10
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
0.06951.01870.0404
0.03982.03740.0388
0.03863.05610.0362
0.03854.07480.0378
0.03765.09350.0358
0.03776.011220.0357
0.03787.013090.0377
0.03698.014960.0383
0.03749.016830.0364
0.035910.018700.0335

Framework versions

  • —Transformers 4.23.1
  • —Pytorch 1.12.1+cu113
  • —Datasets 2.6.1
  • —Tokenizers 0.13.1