Team Ai
Modelpublic

agi-css/distilroberta-base-mrl

sourceHugging Faceapache-2.0updated 4y 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. -->

distilroberta-base-mrl

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

  • —Loss: 0.0170
  • —Accuracy: 0.9967
  • —F1: 0.9967

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: 2.1821851463909416e-05
  • —trainbatchsize: 400
  • —evalbatchsize: 400
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 9

Training results

Training LossEpochStepValidation LossAccuracyF1
No log1.0480.02650.99460.9946
No log2.0960.01800.99620.9962
No log3.01440.01630.99620.9962
No log4.01920.01940.99460.9946
No log5.02400.01930.99420.9942
No log6.02880.01720.99670.9967
No log7.03360.02060.99540.9954
No log8.03840.01830.99620.9962
No log9.04320.01700.99670.9967

Framework versions

  • —Transformers 4.18.0
  • —Pytorch 1.11.0+cu113
  • —Datasets 2.1.0
  • —Tokenizers 0.12.1