add fastmoe project

examples/transformer-xl/scripts/getdata.sh

+echo "=== Acquiring datasets ==="
+echo "---"
+
+mkdir -p ../data
+cd ../data
+
+if [[ ! -d 'wikitext-2' ]]; then
+    echo "- Downloading WikiText-2 (WT2)"
+    wget --quiet --continue https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-2-v1.zip
+    unzip -q wikitext-2-v1.zip
+    cd wikitext-2
+    mv wiki.train.tokens train.txt
+    mv wiki.valid.tokens valid.txt
+    mv wiki.test.tokens test.txt
+    cd ..
+fi
+
+echo "- Downloading WikiText-103 (WT2)"
+if [[ ! -d 'wikitext-103' ]]; then
+    wget --continue https://s3.amazonaws.com/research.metamind.io/wikitext/wikitext-103-v1.zip
+    unzip -q wikitext-103-v1.zip
+    cd wikitext-103
+    mv wiki.train.tokens train.txt
+    mv wiki.valid.tokens valid.txt
+    mv wiki.test.tokens test.txt
+    cd ..
+fi
+
+echo "- Downloading enwik8 (Character)"
+if [[ ! -d 'enwik8' ]]; then
+    mkdir -p enwik8
+    cd enwik8
+    wget --continue http://mattmahoney.net/dc/enwik8.zip
+    wget https://raw.githubusercontent.com/salesforce/awd-lstm-lm/master/data/enwik8/prep_enwik8.py
+    python3 prep_enwik8.py
+    cd ..
+fi
+
+echo "- Downloading text8 (Character)"
+if [[ ! -d 'text8' ]]; then
+    mkdir -p text8
+    cd text8
+    wget --continue http://mattmahoney.net/dc/text8.zip
+    python ../../prep_text8.py
+    cd ..
+fi
+
+echo "- Downloading Penn Treebank (PTB)"
+if [[ ! -d 'penn' ]]; then
+    wget --quiet --continue http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz
+    tar -xzf simple-examples.tgz
+
+    mkdir -p penn
+    cd penn
+    mv ../simple-examples/data/ptb.train.txt train.txt
+    mv ../simple-examples/data/ptb.test.txt test.txt
+    mv ../simple-examples/data/ptb.valid.txt valid.txt
+    cd ..
+
+    echo "- Downloading Penn Treebank (Character)"
+    mkdir -p pennchar
+    cd pennchar
+    mv ../simple-examples/data/ptb.char.train.txt train.txt
+    mv ../simple-examples/data/ptb.char.test.txt test.txt
+    mv ../simple-examples/data/ptb.char.valid.txt valid.txt
+    cd ..
+
+    rm -rf simple-examples/
+fi
+
+echo "- Downloading 1B words"
+
+if [[ ! -d 'one-billion-words' ]]; then
+    mkdir -p one-billion-words
+    cd one-billion-words
+
+    wget --no-proxy http://www.statmt.org/lm-benchmark/1-billion-word-language-modeling-benchmark-r13output.tar.gz
+    tar xzvf 1-billion-word-language-modeling-benchmark-r13output.tar.gz
+
+    path="1-billion-word-language-modeling-benchmark-r13output/heldout-monolingual.tokenized.shuffled/"
+    cat ${path}/news.en.heldout-00000-of-00050 > valid.txt
+    cat ${path}/news.en.heldout-00000-of-00050 > test.txt
+
+    wget https://github.com/rafaljozefowicz/lm/raw/master/1b_word_vocab.txt
+
+    cd ..
+fi
+
+echo "---"
+echo "Happy language modeling :)"

examples/transformer-xl/scripts/run_enwik8_base.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/enwik8/ \
+        --dataset enwik8 \
+        --n_layer 12 \
+        --d_model 512 \
+        --n_head 8 \
+        --d_head 64 \
+        --d_inner 2048 \
+        --dropout 0.1 \
+        --dropatt 0.0 \
+        --optim adam \
+        --lr 0.00025 \
+        --warmup_step 0 \
+        --max_step 400000 \
+        --tgt_len 512 \
+        --mem_len 512 \
+        --eval_tgt_len 128 \
+        --batch_size 22 \
+        --multi_gpu \
+        --gpu0_bsz 4 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/enwik8/ \
+        --dataset enwik8 \
+        --tgt_len 80 \
+        --mem_len 2100 \
+        --clamp_len 820 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_enwik8_base_moe.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/enwik8/ \
+        --dataset enwik8 \
+        --n_layer 12 \
+        --d_model 512 \
+        --n_head 8 \
+        --d_head 64 \
+        --d_inner 1024 \
+        --dropout 0.1 \
+        --dropatt 0.0 \
+        --optim adam \
+        --lr 0.00025 \
+        --warmup_step 0 \
+        --max_step 400000 \
+        --tgt_len 512 \
+        --mem_len 512 \
+        --eval_tgt_len 128 \
+        --batch_size 22 \
+        --multi_gpu \
+        --gpu0_bsz 4 \
+        --moe --moe-num-expert 64 --moe-top-k 2 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/enwik8/ \
+        --dataset enwik8 \
+        --tgt_len 80 \
+        --mem_len 2100 \
+        --clamp_len 820 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_enwik8_large.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/enwik8/ \
+        --dataset enwik8 \
+        --n_layer 24 \
+        --d_model 1024 \
+        --n_head 8 \
+        --d_head 128 \
+        --d_inner 3072 \
+        --dropout 0.15 \
+        --dropatt 0.15 \
+        --optim adam \
+        --lr 0.00025 \
+        --warmup_step 4000 \
+        --max_step 400000 \
+        --tgt_len 768 \
+        --mem_len 768 \
+        --eval_tgt_len 128 \
+        --batch_size 64 \
+        --multi_gpu \
+        --gpu0_bsz 0 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/enwik8/ \
+        --dataset enwik8 \
+        --tgt_len 128 \
+        --mem_len 3800 \
+        --clamp_len 1000 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_lm1b_base.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/one-billion-words/ \
+        --dataset lm1b \
+        --adaptive \
+        --n_layer 18 \
+        --d_model 1024 \
+        --div_val 4 \
+        --n_head 8 \
+        --d_head 128 \
+        --d_inner 4096 \
+        --dropout 0.0 \
+        --dropatt 0.0 \
+        --optim adam \
+        --warmup_step 20000 \
+        --max_step 500000 \
+        --lr 0.00025 \
+        --tgt_len 32 \
+        --mem_len 32 \
+        --eval_tgt_len 32 \
+        --batch_size 224 \
+        --multi_gpu \
+        --gpu0_bsz 32 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/one-billion-words/ \
+        --dataset lm1b \
+        --batch_size 64 \
+        --tgt_len 32 \
+        --mem_len 128 \
+        --split test \
+        --same_length \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_lm1b_large.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/one-billion-words/ \
+        --dataset lm1b \
+        --adaptive \
+        --div_val 4 \
+        --n_layer 24 \
+        --d_model 1280 \
+        --n_head 16 \
+        --d_head 80 \
+        --d_inner 8192 \
+        --dropout 0.05 \
+        --dropatt 0.05 \
+        --optim adam \
+        --warmup_step 30000 \
+        --max_step 1200000 \
+        --lr 0.00025 \
+        --tgt_len 32 \
+        --mem_len 32 \
+        --eval_tgt_len 32 \
+        --batch_size 512 \
+        --multi_gpu \
+        --gpu0_bsz 0 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/one-billion-words/ \
+        --dataset lm1b \
+        --batch_size 8 \
+        --tgt_len 32 \
+        --mem_len 128 \
+        --split test \
+        --same_length \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_text8_base.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/text8/ \
+        --dataset text8 \
+        --n_layer 12 \
+        --d_model 512 \
+        --n_head 8 \
+        --d_head 64 \
+        --d_inner 2048 \
+        --dropout 0.1 \
+        --dropatt 0.0 \
+        --optim adam \
+        --lr 0.00025 \
+        --warmup_step 0 \
+        --max_step 400000 \
+        --tgt_len 512 \
+        --mem_len 512 \
+        --eval_tgt_len 128 \
+        --batch_size 22 \
+        --multi_gpu \
+        --gpu0_bsz 4 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/text8/ \
+        --dataset text8 \
+        --tgt_len 80 \
+        --mem_len 2100 \
+        --clamp_len 820 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_text8_large.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/text8/ \
+        --dataset text8 \
+        --n_layer 24 \
+        --d_model 1024 \
+        --n_head 8 \
+        --d_head 128 \
+        --d_inner 3072 \
+        --dropout 0.15 \
+        --dropatt 0.15 \
+        --optim adam \
+        --lr 0.00025 \
+        --tgt_len 768 \
+        --mem_len 768 \
+        --eval_tgt_len 128 \
+        --batch_size 64 \
+        --max_step 400000 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/text8/ \
+        --dataset text8 \
+        --tgt_len 128 \
+        --mem_len 3800 \
+        --clamp_len 1000 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_wt103_base.sh

+#!/bin/bash
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python train.py \
+        --cuda \
+        --data ../data/wikitext-103/ \
+        --dataset wt103 \
+        --adaptive \
+        --n_layer 16 \
+        --d_model 410 \
+        --n_head 10 \
+        --d_head 41 \
+        --d_inner 2100 \
+        --dropout 0.1 \
+        --dropatt 0.0 \
+        --optim adam \
+        --lr 0.00025 \
+        --warmup_step 0 \
+        --max_step 200000 \
+        --tgt_len 150 \
+        --mem_len 150 \
+        --eval_tgt_len 150 \
+        --batch_size 60 \
+        --multi_gpu \
+        --gpu0_bsz 4 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/wikitext-103/ \
+        --dataset wt103 \
+        --tgt_len 64 \
+        --mem_len 640 \
+        --clamp_len 400 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi

examples/transformer-xl/scripts/run_wt103_large.sh

+#!/bin/bash
+export PYTHONPATH=$PWD/cuda/build/lib.linux-x86_64-3.7
+
+if [[ $1 == 'train' ]]; then
+    echo 'Run training...'
+    python3 train.py \
+        --cuda \
+        --data ../data/wikitext-103/ \
+        --dataset wt103 \
+        --adaptive \
+        --div_val 4 \
+        --n_layer 18 \
+        --d_model 1024 \
+        --n_head 16 \
+        --d_head 64 \
+        --d_inner 4096 \
+        --dropout 0.2 \
+        --dropatt 0.2 \
+        --optim adam \
+        --lr 0.00025 \
+        --warmup_step 16000 \
+        --max_step 4000000 \
+        --tgt_len 384 \
+        --mem_len 384 \
+        --eval_tgt_len 128 \
+        --batch_size 128 \
+        --multi_gpu \
+        --gpu0_bsz 0 \
+        ${@:2}
+elif [[ $1 == 'eval' ]]; then
+    echo 'Run evaluation...'
+    python eval.py \
+        --cuda \
+        --data ../data/wikitext-103/ \
+        --dataset wt103 \
+        --tgt_len 128 \
+        --mem_len 1600 \
+        --clamp_len 1000 \
+        --same_length \
+        --split test \
+        ${@:2}
+else
+    echo 'unknown argment 1'
+fi