CoolFace
Modelpublic

SetFit/distilbert-base-uncased__sst2__train-8-1

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face
0likes117downloads
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. -->

distilbert-base-uncased_sst2_train-8-1

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • —Loss: 0.6930
  • —Accuracy: 0.5047

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: 4
  • —evalbatchsize: 4
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 50
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation LossAccuracy
0.70821.030.70480.25
0.67612.060.72490.25
0.66533.090.74230.25
0.62124.0120.77270.25
0.59325.0150.80980.25
0.54276.0180.84960.25
0.51467.0210.89920.25
0.43568.0240.94940.25
0.42759.0270.96940.25
0.335110.0300.99680.25
0.281211.0331.00560.5

Framework versions

  • —Transformers 4.15.0
  • —Pytorch 1.10.2+cu102
  • —Datasets 1.18.2
  • —Tokenizers 0.10.3