CoolFace
Modelpublic

SetFit/distilbert-base-uncased__sst2__train-8-3

sourceHugging Faceapache-2.0updated 5y agoView on Hugging Face
0likes113downloads
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-8-3

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: 0.6914
  • —Accuracy: 0.5195

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
0.69311.030.70390.25
0.66152.060.71860.25
0.6533.090.73340.25
0.6014.0120.75920.25
0.55555.0150.79220.25
0.48326.0180.81790.25
0.45657.0210.82850.25
0.39968.0240.85590.25
0.36819.0270.85860.5
0.290110.0300.86460.5
0.24111.0330.85240.5

Framework versions

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