Hypert / README.md
HeroGeonil's picture
Update README.md
f1b6285
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: Hypernymy-Aware-BERT-v4
    results: []

Hypert

This model is a fine-tuned version of bert-base-uncased on an unknown dataset.

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: 5e-05
  • train_batch_size: 36
  • eval_batch_size: 24
  • seed: 42
  • gradient_accumulation_steps: 6
  • total_train_batch_size: 216
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 500
  • training_steps: 10000

Training results

Framework versions

  • Transformers 4.21.0
  • Pytorch 1.10.1+cu111
  • Datasets 2.10.1
  • Tokenizers 0.12.1