youtube-bert_10 / README.md
flboehm's picture
Update README.md
725d2cd
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: youtube-bert_10
    results: []

youtube-bert_10

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

  • Loss: 2.4456
  • Perplexity: 11.54

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: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Training results

Training Loss Epoch Step Validation Loss
2.6799 1.0 1899 2.5135
2.5736 2.0 3798 2.4612
2.5172 3.0 5697 2.4363

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu111
  • Datasets 1.17.0
  • Tokenizers 0.10.3