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
f080ac9
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: 0.6080
  • Accuracy: 0.6875

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 0.7378 0.4844
No log 2.0 4 0.7276 0.4844
No log 3.0 6 0.7104 0.4844
No log 4.0 8 0.6924 0.5469
0.7068 5.0 10 0.6837 0.5625
0.7068 6.0 12 0.6782 0.5938
0.7068 7.0 14 0.6755 0.5781
0.7068 8.0 16 0.6701 0.625
0.7068 9.0 18 0.6644 0.625
0.5803 10.0 20 0.6574 0.6406
0.5803 11.0 22 0.6505 0.625
0.5803 12.0 24 0.6436 0.6875
0.5803 13.0 26 0.6370 0.6562
0.5803 14.0 28 0.6316 0.6719
0.4412 15.0 30 0.6267 0.6875
0.4412 16.0 32 0.6232 0.6719
0.4412 17.0 34 0.6205 0.6875
0.4412 18.0 36 0.6175 0.6875
0.4412 19.0 38 0.6141 0.6875
0.3438 20.0 40 0.6113 0.6875
0.3438 21.0 42 0.6099 0.6875
0.3438 22.0 44 0.6109 0.6875
0.3438 23.0 46 0.6112 0.6875
0.3438 24.0 48 0.6107 0.6875
0.2832 25.0 50 0.6097 0.6875
0.2832 26.0 52 0.6088 0.6875
0.2832 27.0 54 0.6082 0.6875
0.2832 28.0 56 0.6080 0.6875
0.2832 29.0 58 0.6080 0.6875
0.2532 30.0 60 0.6080 0.6875

Framework versions

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