Home

Awesome

LSTM and QRNN Language Model Toolkit

This repository contains the code used for two Salesforce Research papers:

The model comes with instructions to train:

The model can be composed of an LSTM or a Quasi-Recurrent Neural Network (QRNN) which is two or more times faster than the cuDNN LSTM in this setup while achieving equivalent or better accuracy.

If you use this code or our results in your research, please cite as appropriate:

@article{merityRegOpt,
  title={{Regularizing and Optimizing LSTM Language Models}},
  author={Merity, Stephen and Keskar, Nitish Shirish and Socher, Richard},
  journal={arXiv preprint arXiv:1708.02182},
  year={2017}
}
@article{merityAnalysis,
  title={{An Analysis of Neural Language Modeling at Multiple Scales}},
  author={Merity, Stephen and Keskar, Nitish Shirish and Socher, Richard},
  journal={arXiv preprint arXiv:1803.08240},
  year={2018}
}

Update (June/13/2018)

The codebase is now PyTorch 0.4 compatible for most use cases (a big shoutout to https://github.com/shawntan for a fairly comprehensive PR https://github.com/salesforce/awd-lstm-lm/pull/43). Mild readjustments to hyperparameters may be necessary to obtain quoted performance. If you desire exact reproducibility (or wish to run on PyTorch 0.3 or lower), we suggest using an older commit of this repository. We are still working on pointer, finetune and generate functionalities.

Software Requirements

Python 3 and PyTorch 0.4 are required for the current codebase.

Included below are hyper parameters to get equivalent or better results to those included in the original paper.

If you need to use an earlier version of the codebase, the original code and hyper parameters accessible at the PyTorch==0.1.12 release, with Python 3 and PyTorch 0.1.12 are required. If you are using Anaconda, installation of PyTorch 0.1.12 can be achieved via: conda install pytorch=0.1.12 -c soumith.

Experiments

The codebase was modified during the writing of the paper, preventing exact reproduction due to minor differences in random seeds or similar. We have also seen exact reproduction numbers change when changing underlying GPU. The guide below produces results largely similar to the numbers reported.

For data setup, run ./getdata.sh. This script collects the Mikolov pre-processed Penn Treebank and the WikiText-2 datasets and places them in the data directory.

Next, decide whether to use the QRNN or the LSTM as the underlying recurrent neural network model. The QRNN is many times faster than even Nvidia's cuDNN optimized LSTM (and dozens of times faster than a naive LSTM implementation) yet achieves similar or better results than the LSTM for many word level datasets. At the time of writing, the QRNN models use the same number of parameters and are slightly deeper networks but are two to four times faster per epoch and require less epochs to converge.

The QRNN model uses a QRNN with convolutional size 2 for the first layer, allowing the model to view discrete natural language inputs (i.e. "New York"), while all other layers use a convolutional size of 1.

Finetuning Note: Fine-tuning modifies the original saved model model.pt file - if you wish to keep the original weights you must copy the file.

Pointer note: BPTT just changes the length of the sequence pushed onto the GPU but won't impact the final result.

Character level enwik8 with LSTM

Character level Penn Treebank (PTB) with LSTM

Word level WikiText-103 (WT103) with QRNN

Word level Penn Treebank (PTB) with LSTM

The instruction below trains a PTB model that without finetuning achieves perplexities of approximately 61.2 / 58.8 (validation / testing), with finetuning achieves perplexities of approximately 58.8 / 56.5, and with the continuous cache pointer augmentation achieves perplexities of approximately 53.2 / 52.5.

Word level Penn Treebank (PTB) with QRNN

The instruction below trains a QRNN model that without finetuning achieves perplexities of approximately 60.6 / 58.3 (validation / testing), with finetuning achieves perplexities of approximately 59.1 / 56.7, and with the continuous cache pointer augmentation achieves perplexities of approximately 53.4 / 52.6.

Word level WikiText-2 (WT2) with LSTM

The instruction below trains a PTB model that without finetuning achieves perplexities of approximately 68.7 / 65.6 (validation / testing), with finetuning achieves perplexities of approximately 67.4 / 64.7, and with the continuous cache pointer augmentation achieves perplexities of approximately 52.2 / 50.6.

Word level WikiText-2 (WT2) with QRNN

The instruction below will a QRNN model that without finetuning achieves perplexities of approximately 69.3 / 66.8 (validation / testing), with finetuning achieves perplexities of approximately 68.5 / 65.9, and with the continuous cache pointer augmentation achieves perplexities of approximately 53.6 / 52.1. Better numbers are likely achievable but the hyper parameters have not been extensively searched. These hyper parameters should serve as a good starting point however.

Speed

For speed regarding character-level PTB and enwik8 or word-level WikiText-103, refer to the relevant paper.

The default speeds for the models during training on an NVIDIA Quadro GP100:

The default QRNN models can be far faster than the cuDNN LSTM model, with the speed-ups depending on how much of a bottleneck the RNN is. The majority of the model time above is now spent in softmax or optimization overhead (see PyTorch QRNN discussion on speed).

Speeds are approximately three times slower on a K80. On a K80 or other memory cards with less memory you may wish to enable the cap on the maximum sampled sequence length to prevent out-of-memory (OOM) errors, especially for WikiText-2.

If speed is a major issue, SGD converges more quickly than our non-monotonically triggered variant of ASGD though achieves a worse overall perplexity.

Details of the QRNN optimization

For full details, refer to the PyTorch QRNN repository.

Details of the LSTM optimization

All the augmentations to the LSTM, including our variant of DropConnect (Wan et al. 2013) termed weight dropping which adds recurrent dropout, allow for the use of NVIDIA's cuDNN LSTM implementation. PyTorch will automatically use the cuDNN backend if run on CUDA with cuDNN installed. This ensures the model is fast to train even when convergence may take many hundreds of epochs.