Edit model card

finetuned-bert-piqa

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

  • Loss: 0.6603
  • Accuracy: 0.6518

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 251 0.6751 0.6115
0.6628 2.0 502 0.6556 0.6534
0.6628 3.0 753 0.6603 0.6518

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1
Downloads last month
94
Model state unknown

Dataset used to train sledz08/finetuned-bert-piqa