Hugging Face's logo

simonycl
/
bert-base-uncased-sst-2-32-13-30

Text Classification
Transformers
PyTorch
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
1
bert-base-uncased-sst-2-32-13-30 / README.md
simonycl's picture
simonycl
update model card README.md
0e99a3d
preview code
|
raw
history blame
3.22 kB
metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: bert-base-uncased-sst-2-32-13-30
    results: []

bert-base-uncased-sst-2-32-13-30

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: 0.5860
  • Accuracy: 0.7344

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: 1.5e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 2 0.7504 0.4844
No log 2.0 4 0.7296 0.4844
No log 3.0 6 0.7038 0.4688
No log 4.0 8 0.6848 0.5
0.6775 5.0 10 0.6753 0.5312
0.6775 6.0 12 0.6666 0.5625
0.6775 7.0 14 0.6533 0.5938
0.6775 8.0 16 0.6361 0.6406
0.6775 9.0 18 0.6181 0.6562
0.4471 10.0 20 0.6136 0.6406
0.4471 11.0 22 0.6116 0.6875
0.4471 12.0 24 0.6051 0.7031
0.4471 13.0 26 0.5977 0.7031
0.4471 14.0 28 0.5903 0.7031
0.2163 15.0 30 0.5855 0.7031
0.2163 16.0 32 0.5839 0.7031
0.2163 17.0 34 0.5831 0.7031
0.2163 18.0 36 0.5821 0.7031
0.2163 19.0 38 0.5822 0.7188
0.1269 20.0 40 0.5819 0.7188
0.1269 21.0 42 0.5826 0.7188
0.1269 22.0 44 0.5844 0.7344
0.1269 23.0 46 0.5848 0.7344
0.1269 24.0 48 0.5841 0.75
0.0961 25.0 50 0.5841 0.7344
0.0961 26.0 52 0.5848 0.7344
0.0961 27.0 54 0.5854 0.7344
0.0961 28.0 56 0.5858 0.7344
0.0961 29.0 58 0.5859 0.7344
0.0833 30.0 60 0.5860 0.7344

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.4.0
  • Tokenizers 0.13.3