CoolFace
Modelpublic

sachiray27/esm2_t6_8M_UR50D-finetuned-cytosol-membrane-classification

sourceHugging Facemitupdated 1y agoView on Hugging Face
0likes4downloads
Model Card

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

esm2t68M_UR50D-finetuned-cytosol-membrane-classification

This model is a fine-tuned version of facebook/esm2_t6_8M_UR50D on an unknown dataset. It achieves the following results on the evaluation set:

  • —Train Loss: 0.0025
  • —Train Accuracy: 0.9995
  • —Validation Loss: 0.3043
  • —Validation Accuracy: 0.9430
  • —Epoch: 9

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:

  • —optimizer: {'name': 'AdamWeightDecay', 'learningrate': 2e-05, 'decay': 0.0, 'beta1': 0.9, 'beta2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weightdecay_rate': 0.0}
  • —training_precision: float32

Training results

Train LossTrain AccuracyValidation LossValidation AccuracyEpoch
0.26080.92410.17990.94760
0.17050.94930.17790.94611
0.13770.95520.17900.94382
0.09800.96840.19910.93913
0.05600.98230.19140.93534
0.03880.98790.21570.94305
0.02580.99230.22020.94616
0.01390.99670.25960.94147
0.00380.99900.28230.94078
0.00250.99950.30430.94309

Framework versions

  • —Transformers 4.51.3
  • —TensorFlow 2.18.0
  • —Datasets 2.14.4
  • —Tokenizers 0.21.1