---
tags:
- generated_from_trainer
datasets:
- big_patent
model-index:
- name: reformer-finetuned-big_patent-16384
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# reformer-finetuned-big_patent-16384

This model is a fine-tuned version of [google/reformer-crime-and-punishment](https://huggingface.co/google/reformer-crime-and-punishment) on the big_patent dataset.
It achieves the following results on the evaluation set:
- Loss: 4.2238

## 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 |
|:-------------:|:-----:|:-----:|:---------------:|
| 4.2727        | 1.0   | 17979 | 4.2608          |
| 4.2425        | 2.0   | 35958 | 4.2382          |
| 4.2341        | 3.0   | 53937 | 4.2238          |


### Framework versions

- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.3.2
- Tokenizers 0.12.1