aha_classification / README.md
djsull's picture
djsull/aha_classification
b56ef07 verified
|
raw
history blame
2.19 kB
metadata
base_model: monologg/kobigbird-bert-base
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: aha_classification
    results: []

aha_classification

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

  • Loss: 0.0276
  • F1: 1.0
  • Roc Auc: 1.0
  • Accuracy: 1.0

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
  • 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
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss F1 Roc Auc Accuracy
No log 1.0 50 0.2740 0.9906 0.9930 0.9857
No log 2.0 100 0.1222 0.9938 0.9962 0.9857
No log 3.0 150 0.0663 0.9969 0.9981 0.9929
No log 4.0 200 0.0423 0.9969 0.9981 0.9929
No log 5.0 250 0.0276 1.0 1.0 1.0
No log 6.0 300 0.0208 1.0 1.0 1.0
No log 7.0 350 0.0165 1.0 1.0 1.0
No log 8.0 400 0.0135 1.0 1.0 1.0
No log 9.0 450 0.0114 1.0 1.0 1.0
0.1025 10.0 500 0.0101 1.0 1.0 1.0

Framework versions

  • Transformers 4.42.3
  • Pytorch 2.3.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.19.1