robingeibel's picture
update model card README.md
72123ea
metadata
tags:
  - generated_from_trainer
datasets:
  - big_patent
model-index:
  - name: reformer-big_patent-16384
    results: []

reformer-big_patent-16384

This model was trained from scratch on the big_patent dataset. It achieves the following results on the evaluation set:

  • Loss: 6.0565

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: 2.5e-06
  • 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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
6.0379 1.0 17732 6.0935
5.9941 2.0 35464 6.0363
5.9831 3.0 53196 6.0565

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.12.0+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1