godsofheaven's picture
End of training
cfa2092 verified
metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - jigsaw_toxicity_pred
metrics:
  - f1
  - accuracy
model-index:
  - name: final_model_toxicity_classification
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: jigsaw_toxicity_pred
          type: jigsaw_toxicity_pred
          config: default
          split: test
          args: default
        metrics:
          - name: F1
            type: f1
            value: 0.6775510204081633
          - name: Accuracy
            type: accuracy
            value: 0.921

final_model_toxicity_classification

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

  • Loss: 0.2702
  • F1: 0.6776
  • Accuracy: 0.921

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: 4.910748967246961e-05
  • train_batch_size: 32
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 2
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss F1 Accuracy
0.0959 1.0 4987 0.1663 0.7248 0.94
0.0527 2.0 9974 0.2702 0.6776 0.921

Framework versions

  • Transformers 4.52.4
  • Pytorch 2.6.0+cu124
  • Datasets 3.6.0
  • Tokenizers 0.21.1