finetuned-gpt2-hatexplainV2

This model is a fine-tuned version of gpt2 on the hatexplain dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8927
  • Accuracy: 0.6788
  • Precision: 0.6745
  • Recall: 0.6788
  • F1: 0.6752

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: 3e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • 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: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
0.7476 1.0 962 0.7423 0.6785 0.6724 0.6785 0.6695
0.6276 2.0 1924 0.7384 0.6878 0.6798 0.6878 0.6815
0.5859 3.0 2886 0.7771 0.6790 0.6774 0.6790 0.6762
0.3921 4.0 3848 0.8746 0.6795 0.6752 0.6795 0.6768
0.4358 5.0 4810 0.9455 0.6769 0.6724 0.6769 0.6739

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu118
  • Datasets 3.1.0
  • Tokenizers 0.21.0
Downloads last month
39
Safetensors
Model size
124M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for uboza10300/finetuned-gpt2-hatexplainV2

Finetuned
(1265)
this model

Dataset used to train uboza10300/finetuned-gpt2-hatexplainV2

Evaluation results