reformer-finetuned-big_patent-16384

This model is a fine-tuned version of robingeibel/reformer-finetuned-big_patent-wikipedia-arxiv-16384 on the big_patent dataset. It achieves the following results on the evaluation set:

• Loss: 6.7382

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
6.7398	1.0	53286	6.7243
6.7449	2.0	106572	6.7388
6.7534	3.0	159858	6.7382

Framework versions

• Transformers 4.20.1
• Pytorch 1.12.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1