CoolFace
Modelpublic

Realgon/N_bert_sst5_padding50model

sourceHugging Faceapache-2.0updated 3y agoView on Hugging Face
0likes6downloads
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. -->

Nbertsst5_padding50model

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

  • —Loss: 4.1996
  • —Accuracy: 0.5235

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: 16
  • —evalbatchsize: 16
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 20

Training results

Training LossEpochStepValidation LossAccuracy
1.27571.05341.21100.4475
0.96392.010681.07630.5271
0.73283.016021.18460.5394
0.56164.021361.41740.5199
0.39285.026701.72410.5217
0.27496.032042.06800.5086
0.20267.037382.33540.5
0.15568.042722.61140.5172
0.1369.048062.89870.5172
0.109810.053403.11500.5271
0.090811.058743.38660.5339
0.075912.064083.58790.5262
0.046113.069423.79970.5376
0.04314.074763.94150.5208
0.031315.080103.99360.5249
0.020616.085444.05120.5240
0.020217.090784.13040.5267
0.013118.096124.15580.5281
0.011419.0101464.17410.5249
0.009220.0106804.19960.5235

Framework versions

  • —Transformers 4.33.2
  • —Pytorch 2.0.1+cu117
  • —Datasets 2.14.5
  • —Tokenizers 0.13.3