robingeibel's picture
update model card README.md
c89fb7a
|
raw
history blame
1.48 kB
metadata
tags:
  - generated_from_trainer
datasets:
  - big_patent
model-index:
  - name: reformer-finetuned-big_patent
    results: []

reformer-finetuned-big_patent

This model is a fine-tuned version of robingeibel/reformer-finetuned-big_patent on the big_patent dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0000

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: 64
  • eval_batch_size: 64
  • 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
0.0 1.0 5973 0.0000
0.0 2.0 11946 0.0000
0.0 3.0 17919 0.0000

Framework versions

  • Transformers 4.20.1
  • Pytorch 1.11.0+cu113
  • Datasets 2.3.2
  • Tokenizers 0.12.1