temp_attack / README.md
davidgaofc's picture
End of training
3e99066
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: training
    results: []

training

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

  • Loss: 0.8713
  • Accuracy: 0.5183
  • F1: 0.5192
  • Precision: 0.5219
  • Recall: 0.5183

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: 20
  • eval_batch_size: 20
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
No log 1.0 66 0.7083 0.4970 0.4093 0.5891 0.4970
No log 2.0 132 0.7447 0.4939 0.4486 0.5338 0.4939
No log 3.0 198 0.7978 0.5 0.4814 0.5239 0.5
No log 4.0 264 0.8450 0.5091 0.5100 0.5136 0.5091
No log 5.0 330 0.8713 0.5183 0.5192 0.5219 0.5183

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.1+cu121
  • Datasets 2.15.0
  • Tokenizers 0.15.0