Tensorride's picture
update model card README.md
2f40980
metadata
license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: censorship_classifier_transformer
    results: []

censorship_classifier_transformer

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: 0.6150
  • Accuracy: 0.7727

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: 4

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 2 0.6542 0.5909
No log 2.0 4 0.6344 0.5909
No log 3.0 6 0.6212 0.6364
No log 4.0 8 0.6150 0.7727

Framework versions

  • Transformers 4.30.2
  • Pytorch 2.0.1+cpu
  • Datasets 2.13.1
  • Tokenizers 0.13.3