youtube-bert / README.md
flboehm's picture
update model card README.md
e68d230
metadata
license: apache-2.0
tags:
  - generated_from_trainer
model-index:
  - name: youtube-bert
    results: []

youtube-bert

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: 2.4771

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
2.691 1.0 1077 2.5445
2.5768 2.0 2154 2.5226
2.5227 3.0 3231 2.5027

Framework versions

  • Transformers 4.15.0
  • Pytorch 1.10.0+cu113
  • Datasets 1.17.0
  • Tokenizers 0.10.3