BulBERT-fakenews-5epochs

This model is a fine-tuned version of mor40/BulBERT-chitanka-model on the bgglue dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3487
  • Accuracy: 0.9050

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: 32
  • eval_batch_size: 32
  • 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 84 0.4732 0.7511
No log 2.0 168 0.3922 0.8552
No log 3.0 252 0.3230 0.8778
No log 4.0 336 0.3518 0.8959
No log 5.0 420 0.3487 0.9050

Framework versions

  • Transformers 4.34.1
  • Pytorch 2.1.0+cu118
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
17
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 mor40/BulBERT-fakenews-5epochs

Finetuned
(8)
this model

Collection including mor40/BulBERT-fakenews-5epochs

Evaluation results