thedavidhackett's picture
End of training
c74cedb
|
raw
history blame
1.66 kB
metadata
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: distilbert-police-mission-statement
    results: []

distilbert-police-mission-statement

This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3287
  • Accuracy: 0.9290

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: 16
  • eval_batch_size: 16
  • 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
No log 1.0 198 0.3337 0.8864
No log 2.0 396 0.2290 0.9205
0.2112 3.0 594 0.3053 0.9261
0.2112 4.0 792 0.3026 0.9318
0.2112 5.0 990 0.3287 0.9290

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.0