Merge branch 'main' of https://github.com/NVIDIA/Megatron-LM

examples/finetune_mnli_distributed.sh

+#!/bin/bash
+
+WORLD_SIZE=8
+
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+
+TRAIN_DATA="data/glue_data/MNLI/train.tsv"
+VALID_DATA="data/glue_data/MNLI/dev_matched.tsv \
+            data/glue_data/MNLI/dev_mismatched.tsv"
+PRETRAINED_CHECKPOINT=checkpoints/bert_345m
+VOCAB_FILE=bert-vocab.txt
+CHECKPOINT_PATH=checkpoints/bert_345m_mnli
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
+               --task MNLI \
+               --seed 1234 \
+               --train-data $TRAIN_DATA \
+               --valid-data $VALID_DATA \
+               --tokenizer-type BertWordPieceLowerCase \
+               --vocab-file $VOCAB_FILE \
+               --epochs 5 \
+               --pretrained-checkpoint $PRETRAINED_CHECKPOINT \
+               --tensor-model-parallel-size 1 \
+               --num-layers 24 \
+               --hidden-size 1024 \
+               --num-attention-heads 16 \
+               --micro-batch-size 8 \
+               --activations-checkpoint-method uniform \
+               --lr 5.0e-5 \
+               --lr-decay-style linear \
+               --lr-warmup-fraction 0.065 \
+               --seq-length 512 \
+               --max-position-embeddings 512 \
+               --save-interval 500000 \
+               --save $CHECKPOINT_PATH \
+               --log-interval 10 \
+               --eval-interval 100 \
+               --eval-iters 50 \
+               --weight-decay 1.0e-1 \
+               --fp16

examples/finetune_race_distributed.sh

+#!/bin/bash
+
+WORLD_SIZE=8
+
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+
+TRAIN_DATA="data/RACE/train/middle"
+VALID_DATA="data/RACE/dev/middle \
+            data/RACE/dev/high"
+VOCAB_FILE=bert-vocab.txt
+PRETRAINED_CHECKPOINT=checkpoints/bert_345m
+CHECKPOINT_PATH=checkpoints/bert_345m_race
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
+               --task RACE \
+               --seed 1234 \
+               --train-data $TRAIN_DATA \
+               --valid-data $VALID_DATA \
+               --tokenizer-type BertWordPieceLowerCase \
+               --vocab-file $VOCAB_FILE \
+               --epochs 3 \
+               --pretrained-checkpoint $PRETRAINED_CHECKPOINT \
+               --tensor-model-parallel-size 1 \
+               --num-layers 24 \
+               --hidden-size 1024 \
+               --num-attention-heads 16 \
+               --micro-batch-size 4 \
+               --activations-checkpoint-method uniform \
+               --lr 1.0e-5 \
+               --lr-decay-style linear \
+               --lr-warmup-fraction 0.06 \
+               --seq-length 512 \
+               --max-position-embeddings 512 \
+               --save-interval 100000 \
+               --save $CHECKPOINT_PATH \
+               --log-interval 10 \
+               --eval-interval 100 \
+               --eval-iters 50 \
+               --weight-decay 1.0e-1 \
+               --clip-grad 1.0 \
+               --hidden-dropout 0.1 \
+               --attention-dropout 0.1 \
+               --fp16

examples/finetune_retriever_distributed.sh

+#!/bin/bash
+
+# Finetune a BERT or pretrained ICT model using Google natural question data 
+# Datasets can be downloaded from the following link:
+# https://github.com/facebookresearch/DPR/blob/master/data/download_data.py
+
+WORLD_SIZE=8
+
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+
+CHECKPOINT_PATH=<Specify path for the finetuned retriever model>
+
+# Load either of the below
+BERT_LOAD_PATH=<Path of BERT pretrained model>
+PRETRAINED_CHECKPOINT=<Path of Pretrained ICT model>
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/main.py \
+        --task RET-FINETUNE-NQ \
+        --train-with-neg \
+        --train-hard-neg 1 \
+        --pretrained-checkpoint ${PRETRAINED_CHECKPOINT} \
+        --num-layers 12 \
+        --hidden-size 768 \
+        --num-attention-heads 12 \
+        --tensor-model-parallel-size 1 \
+        --tokenizer-type BertWordPieceLowerCase \
+        --train-data nq-train.json \
+        --valid-data nq-dev.json \
+        --save ${CHECKPOINT_PATH} \
+        --load ${CHECKPOINT_PATH} \
+        --vocab-file bert-vocab.txt \
+        --bert-load ${BERT_LOAD_PATH} \
+        --save-interval 5000 \
+        --log-interval 10 \
+        --eval-interval 20000 \
+        --eval-iters 100 \
+        --indexer-log-interval 1000 \
+        --faiss-use-gpu \
+        --DDP-impl torch \
+        --fp16 \
+        --retriever-report-topk-accuracies 1 5 10 20 100 \
+        --seq-length 512 \
+        --retriever-seq-length 256 \
+        --max-position-embeddings 512 \
+        --retriever-score-scaling \
+        --epochs 80 \
+        --micro-batch-size 8 \
+        --eval-micro-batch-size 16 \
+        --indexer-batch-size 128 \
+        --lr 2e-5 \
+        --lr-warmup-fraction 0.01 \
+        --weight-decay 1e-1

examples/merge_mp_bert.sh

+#!/bin/bash
+
+TENSOR_MODEL_PARALLEL_SIZE=2
+
+VOCAB_FILE=bert-vocab.txt
+CHECKPOINT_PATH=checkpoints/bert_345m
+
+WORLD_SIZE=$TENSOR_MODEL_PARALLEL_SIZE python tools/merge_mp_partitions.py \
+                                --model-type BERT \
+                                --tensor-model-parallel-size $TENSOR_MODEL_PARALLEL_SIZE \
+                                --tokenizer-type BertWordPieceLowerCase \
+                                --vocab-file $VOCAB_FILE \
+                                --num-layers 24 \
+                                --hidden-size 1024 \
+                                --num-attention-heads 16 \
+                                --seq-length 512 \
+                                --max-position-embeddings 512 \
+                                --load $CHECKPOINT_PATH

examples/msdp/README.md

+
+# Multi-Stage Prompting for Knowledgeable Dialogue Generation
+
+This directory contains all the scripts of multi-stage prompting for knowledgeable dialogue generation that includes data preparation, and knowledge and response generations. More details are available on [`knowledgeable task directory`](../../tasks/msdp).
+

examples/msdp/data_processing.sh

+#!/bin/bash
+
+# Data preparation for our framework: preprocessing the WoW and WoI datasets
+# The datasets can be downloaded through the following links:
+# WoW: https://parl.ai/projects/wizard_of_wikipedia/
+# WoI: https://parl.ai/projects/sea/
+
+DIR=`pwd`
+# Before running the preprocessing, please download 
+# the wizard of wikipedia and wizard datasets
+WOW_DATA_FOLDER=<PATH_OF_WIZARD_OF_WIKIPEDIA_DATA_FOLDER>
+WOI_DATA_FOLDER=<PATH_OF_WIZARD_OF_INTERNET_DATA_FOLDER>
+
+# We provide examples for processing the raw data from Wizard of Wikipedia
+# Processing the train dataset (train.json)
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func process_wow_dataset \
+        --raw_file ${WOW_DATA_FOLDER}/train.json \
+        --processed_file ${WOW_DATA_FOLDER}/train_processed.txt
+
+# Processing test seen dataset (test_random_split.json)
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func process_wow_dataset \
+        --raw_file ${WOW_DATA_FOLDER}/test_random_split.json \
+        --processed_file ${WOW_DATA_FOLDER}/testseen_processed.txt \
+        --knwl_ref_file ${WOW_DATA_FOLDER}/output_testseen_knowledge_reference.txt \
+        --resp_ref_file ${WOW_DATA_FOLDER}/output_testseen_response_reference.txt
+
+# processing test unseen dataset (test_topic_split.json)
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func process_wow_dataset \
+        --raw_file ${WOW_DATA_FOLDER}/test_topic_split.json \
+        --processed_file ${WOW_DATA_FOLDER}/testunseen_processed.txt \
+        --knwl_ref_file ${WOW_DATA_FOLDER}/output_testunseen_knowledge_reference.txt \
+        --resp_ref_file ${WOW_DATA_FOLDER}/output_testunseen_response_reference.txt
+
+
+# We provide the following script to process the raw data from Wizard of Internet
+# Processing the test dataset (test.jsonl)
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func process_woi_dataset \
+        --raw_file ${WOI_DATA_FOLDER}/test.jsonl \
+        --processed_file ${WOI_DATA_FOLDER}/test_processed.txt \
+        --knwl_ref_file ${WOI_DATA_FOLDER}/output_test_knowledge_reference.txt \
+        --resp_ref_file ${WOI_DATA_FOLDER}/output_test_response_reference.txt
+
+
+# Get the knowledge generation prompts for the each test dataset in WoW and WoI
+MODEL_FILE=<PATH_OF_THE_FINETUNED_DPR_MODEL> 
+# WoW test seen
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func get_knwl_gen_prompts \
+        --test_file ${WOW_DATA_FOLDER}/testseen_processed.txt \
+        --train_file ${WOW_DATA_FOLDER}/train_processed.txt \
+        --model_file ${MODEL_FILE} \
+        --processed_file ${WOW_DATA_FOLDER}/output_testseen_knowledge_prompts.json \
+        --data_type wow_seen
+
+# WoW test unseen
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func get_knwl_gen_prompts \
+        --test_file ${WOW_DATA_FOLDER}/testunseen_processed.txt \
+        --train_file ${WOW_DATA_FOLDER}/train_processed.txt \
+        --model_file ${MODEL_FILE} \
+        --processed_file ${WOW_DATA_FOLDER}/output_testunseen_knowledge_prompts.json \
+        --data_type wow_unseen
+
+# WoI
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func get_knwl_gen_prompts \
+        --test_file ${WOI_DATA_FOLDER}/test_processed.txt \
+        --train_file ${WOW_DATA_FOLDER}/train_processed.txt \
+        --model_file ${MODEL_FILE} \
+        --processed_file ${WOI_DATA_FOLDER}/output_test_knowledge_prompts.json \
+        --data_type woi
+
+
+# Get the response generation prompts (can be applied for all the test datasets)
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func get_resp_gen_prompts \
+        --train_file ${WOW_DATA_FOLDER}/train_processed.txt \
+        --processed_file ${WOW_DATA_FOLDER}/output_response_prompts.txt
+

examples/msdp/eval_knwl_generation.sh

+#!/bin/bash
+
+#########################
+# Evaluate the F1 scores.
+#########################
+
+WORLD_SIZE=1
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+                  
+MODEL_GEN_PATH=<PATH_OF_THE_KNOWLEDGE_GENERATION> \ 
+        (e.g., /testseen_knowledge_generations.txt)
+GROUND_TRUTH_PATH=<PATH_OF_THE_GROUND_TRUTH_KNOWLEDGE> \ 
+        (e.g., /testseen_knowledge_reference.txt)
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
+        --num-layers 24 \
+        --hidden-size 1024 \
+        --num-attention-heads 16 \
+        --seq-length 2048 \
+        --max-position-embeddings 2048 \
+        --micro-batch-size 4 \
+        --task MSDP-EVAL-F1 \
+        --guess-file ${MODEL_GEN_PATH} \
+        --answer-file ${GROUND_TRUTH_PATH}
+
+
+############################################
+# Evaluate BLEU, METEOR, and ROUGE-L scores.
+############################################
+
+# We follow the nlg-eval (https://github.com/Maluuba/nlg-eval) to 
+# evaluate the BLEU, METEOR, and ROUGE-L scores. 
+
+# To evaluate on these metrics, please setup the environments based on 
+# the nlg-eval github, and run the corresponding evaluation commands.
+
+nlg-eval \
+    --hypothesis=<PATH_OF_THE_KNOWLEDGE_GENERATION> \
+    --references=<PATH_OF_THE_GROUND_TRUTH_KNOWLEDGE>

examples/msdp/eval_resp_generation.sh

+#!/bin/bash
+
+#########################
+# Evaluate the F1 scores.
+#########################
+
+WORLD_SIZE=1
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+                  
+MODEL_GEN_PATH=<PATH_OF_THE_RESPONSE_GENERATION> \ 
+        (e.g., /testseen_response_generations.txt)
+GROUND_TRUTH_PATH=<PATH_OF_THE_GROUND_TRUTH_RESPONSE> \ 
+        (e.g., /testseen_response_reference.txt)
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
+        --num-layers 24 \
+        --hidden-size 1024 \
+        --num-attention-heads 16 \
+        --seq-length 2048 \
+        --max-position-embeddings 2048 \
+        --micro-batch-size 4 \
+        --task MSDP-EVAL-F1 \
+        --guess-file ${MODEL_GEN_PATH} \
+        --answer-file ${GROUND_TRUTH_PATH}
+
+
+##########################
+# Evaluate the KF1 scores.
+##########################
+                  
+MODEL_GEN_PATH=<PATH_OF_THE_RESPONSE_GENERATION> \ 
+        (e.g., /testseen_response_generations.txt)
+GROUND_TRUTH_PATH=<PATH_OF_THE_GROUND_TRUTH_KNOWLEDGE> \ 
+        (e.g., /testseen_knowledge_reference.txt)
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
+        --num-layers 24 \
+        --hidden-size 1024 \
+        --num-attention-heads 16 \
+        --seq-length 2048 \
+        --max-position-embeddings 2048 \
+        --micro-batch-size 4 \
+        --task MSDP-EVAL-F1 \
+        --guess-file ${MODEL_GEN_PATH} \
+        --answer-file ${GROUND_TRUTH_PATH}
+
+
+############################################
+# Evaluate BLEU, METEOR, and ROUGE-L scores.
+############################################
+
+# We follow the nlg-eval (https://github.com/Maluuba/nlg-eval) to 
+# evaluate the BLEU, METEOR, and ROUGE-L scores. 
+
+# To evaluate on these metrics, please setup the environments based on 
+# the nlg-eval github, and run the corresponding evaluation commands.
+
+nlg-eval \
+    --hypothesis=<PATH_OF_THE_RESPONSE_GENERATION> \
+    --references=<PATH_OF_THE_GROUND_TRUTH_RESPONSE>

examples/msdp/prep_resp_gen.sh

+#!/bin/bash
+
+# Preparing the input file for the response generation (second-stage prompting)
+
+DIR=`pwd`
+
+TEST_FILE=<PATH_OF_PROCESSED_TEST_DATA> \
+        (e.g., /testseen_processed.txt)
+KNOWLEDGE_FILE=<PATH_OF_GENERATED_KNOWLEDGE_DATA> \
+        (e.g., /testseen_knowledge_generations.txt)
+PROCESSED_FILE=<PATH_OF_INPUT_FILE_FOR_RESPONSE_GENERATION> \
+        (e.g., /testseen_processed_with_generated_knowledge.txt)
+
+python ${DIR}/tasks/msdp/preprocessing.py \
+        --func prepare_input \
+        --test_file ${TEST_FILE} \
+        --knwl_gen_file ${KNOWLEDGE_FILE} \
+        --processed_file ${PROCESSED_FILE}

examples/msdp/prompt_knwl_gen.sh

+#!/bin/bash
+
+# Stage-1: Prompt a pretrained language model to generate the context-relevant knowledge
+# The input contains prompts and current dialogue context, the output is the relevant knowledge
+# The size of the pretrained language model is 357M
+
+WORLD_SIZE=8
+
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+
+CHECKPOINT_PATH=<PATH_OF_LANGUAGE_MODEL> (e.g., /357m)
+VOCAB_PATH=<PATH_OF_VOCAB_FILE> (e.g., /gpt2-vocab.json)
+MERGE_PATH=<PATH_OF_MERGE_FILE> (e.g., /gpt2-merges.txt)
+INPUT_PATH=<PATH_OF_PROCESSED_TEST_DATA_FILE> \ 
+        (e.g., /testseen_processed.txt)
+PROMPT_PATH=<PATH_OF_KNOWLEDGE_GENERATION_PROMPTS> \
+        (e.g., /testseen_knowledge_prompts.json)
+OUTPUT_PATH=<PATH_OF_OUTPUT_GENERATION_FILE> \
+        (e.g., /testseen_knowledge_generations.txt)
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
+        --num-layers 24 \
+        --hidden-size 1024 \
+        --num-attention-heads 16 \
+        --seq-length 2048 \
+        --max-position-embeddings 2048 \
+        --micro-batch-size 1 \
+        --vocab-file ${VOCAB_PATH} \
+        --merge-file ${MERGE_PATH} \
+        --load ${CHECKPOINT_PATH} \
+        --fp16 \
+        --DDP-impl torch \
+        --tokenizer-type GPT2BPETokenizer \
+        --sample-input-file ${INPUT_PATH} \
+        --sample-output-file ${OUTPUT_PATH} \
+        --prompt-file ${PROMPT_PATH} \
+        --prompt-type knowledge \
+        --num-prompt-examples 10 \
+        --task MSDP-PROMPT 
+
+# NOTE: If you use api for the model generation, please use 
+# the "--api-prompt" flag (setting this value as True). 

examples/msdp/prompt_resp_gen.sh

+#!/bin/bash
+
+# Stage-2: Prompt a pretrained language model to generate the corresponding response
+# The input contains prompts, current dialogue context, and generated knowledge in Stage-1
+# The output is the corresponding response.
+# The size of the pretrained language model is 357M
+
+WORLD_SIZE=8
+
+DISTRIBUTED_ARGS="--nproc_per_node $WORLD_SIZE \
+                  --nnodes 1 \
+                  --node_rank 0 \
+                  --master_addr localhost \
+                  --master_port 6000"
+
+CHECKPOINT_PATH=<PATH_OF_LANGUAGE_MODEL> (e.g., /357m)
+VOCAB_PATH=<PATH_OF_VOCAB_FILE> (e.g., /gpt2-vocab.json)
+MERGE_PATH=<PATH_OF_MERGE_FILE> (e.g., /gpt2-merges.txt)
+INPUT_PATH=<PATH_OF_INPUT_TEST_DATA_FILE> (e.g., /testseen_processed.txt)
+PROMPT_PATH=<PATH_OF_RESPONSE_GENERATION_PROMPTS> \
+        (e.g., /response_prompts.txt)
+OUTPUT_PATH=<PATH_OF_OUTPUT_GENERATION_FILE> \
+        (e.g., /output_testseen_response_generations.txt)
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS ./tasks/msdp/main.py \
+        --num-layers 24 \
+        --hidden-size 1024 \
+        --num-attention-heads 16 \
+        --seq-length 2048 \
+        --max-position-embeddings 2048 \
+        --micro-batch-size 1 \
+        --vocab-file ${VOCAB_PATH} \
+        --merge-file ${MERGE_PATH} \
+        --load ${CHECKPOINT_PATH} \
+        --fp16 \
+        --DDP-impl torch \
+        --tokenizer-type GPT2BPETokenizer \
+        --sample-input-file ${INPUT_PATH} \
+        --sample-output-file ${OUTPUT_PATH} \
+        --prompt-file ${PROMPT_PATH} \
+        --prompt-type response \
+        --num-prompt-examples 20 \
+        --task MSDP-PROMPT 
+
+# NOTE: If you use api for the model generation, please use 
+# the "--api-prompt" flag (setting this value as True). 

examples/pretrain_bert.sh

+#!/bin/bash
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/bert-vocab.txt
+DATA_PATH=<Specify path and file prefix>_text_sentence
+
+BERT_ARGS="
+    --num-layers 24 \
+    --hidden-size 1024 \
+    --num-attention-heads 16 \
+    --seq-length 512 \
+    --max-position-embeddings 512 \
+    --micro-batch-size 4 \
+    --global-batch-size 8 \
+    --lr 0.0001 \
+    --train-iters 2000000 \
+    --lr-decay-iters 990000 \
+    --lr-decay-style linear \
+    --min-lr 0.00001 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun pretrain_bert.py \
+    $BERT_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH

examples/pretrain_bert_distributed.sh

+#!/bin/bash
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+GPUS_PER_NODE=8
+# Change for multinode config
+MASTER_ADDR=localhost
+MASTER_PORT=6000
+NNODES=1
+NODE_RANK=0
+WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/bert-vocab.txt
+DATA_PATH=<Specify path and file prefix>_text_sentence
+
+DISTRIBUTED_ARGS="
+    --nproc_per_node $GPUS_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $NODE_RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT
+"
+
+BERT_ARGS="
+    --num-layers 24 \
+    --hidden-size 1024 \
+    --num-attention-heads 16 \
+    --seq-length 512 \
+    --max-position-embeddings 512 \
+    --micro-batch-size 4 \
+    --global-batch-size 32 \
+    --lr 0.0001 \
+    --train-iters 1000000 \
+    --lr-decay-iters 990000 \
+    --lr-decay-style linear \
+    --min-lr 1.0e-5 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun $DISTRIBUTED_ARGS pretrain_bert.py \
+    $BERT_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --distributed-backend nccl \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH

examples/pretrain_bert_distributed_with_mp.sh

+#!/bin/bash
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+GPUS_PER_NODE=8
+# Change for multinode config
+MASTER_ADDR=localhost
+MASTER_PORT=6000
+NNODES=1
+NODE_RANK=0
+WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/bert-vocab.txt
+DATA_PATH=<Specify path and file prefix>_text_sentence
+
+DISTRIBUTED_ARGS="
+    --nproc_per_node $GPUS_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $NODE_RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT
+"
+
+BERT_ARGS="
+    --tensor-model-parallel-size 2 \
+    --pipeline-model-parallel-size 2 \
+    --num-layers 24 \
+    --hidden-size 1024 \
+    --num-attention-heads 16 \
+    --seq-length 512 \
+    --max-position-embeddings 512 \
+    --micro-batch-size 2 \
+    --global-batch-size 16 \
+    --lr 0.0001 \
+    --train-iters 1000000 \
+    --lr-decay-iters 990000 \
+    --lr-decay-style linear \
+    --min-lr 1.0e-5 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun $DISTRIBUTED_ARGS pretrain_bert.py \
+    $BERT_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --distributed-backend nccl \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH

examples/pretrain_gpt.sh

+#!/bin/bash
+
+# Runs the "345M" parameter model
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/gpt2-vocab.json
+MERGE_FILE=<Specify path to file>/gpt2-merges.txt
+DATA_PATH=<Specify path and file prefix>_text_document
+
+GPT_ARGS="
+    --num-layers 24 \
+    --hidden-size 1024 \
+    --num-attention-heads 16 \
+    --seq-length 1024 \
+    --max-position-embeddings 1024 \
+    --micro-batch-size 4 \
+    --global-batch-size 8 \
+    --lr 0.00015 \
+    --train-iters 500000 \
+    --lr-decay-iters 320000 \
+    --lr-decay-style cosine \
+    --min-lr 1.0e-5 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --merge-file $MERGE_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun pretrain_gpt.py \
+    $GPT_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH

examples/pretrain_gpt3_175B.sh

+#!/bin/bash
+
+
+#SBATCH <SLURM OPTIONS> --nodes=128 --exclusive --ntasks-per-node=8 --job-name=megatron_gpt3_175b
+
+
+DIR=`pwd`
+DATETIME=`date +'date_%y-%m-%d_time_%H-%M-%S'`
+mkdir -p $DIR/logs
+
+
+DATASET_1="<PATH TO THE FIRST DATASET>"
+DATASET_2="<PATH TO THE SECOND DATASET>"
+DATASET_3="<PATH TO THE THIRD DATASET>"
+DATASET="0.2 ${DATASET_1} 0.3 ${DATASET_2} 0.5 ${DATASET_3}"
+
+
+options=" \
+	--tensor-model-parallel-size 8 \
+	--pipeline-model-parallel-size 16 \
+        --num-layers 96 \
+        --hidden-size 12288 \
+        --num-attention-heads 96 \
+        --seq-length 2048 \
+        --max-position-embeddings 2048 \
+	--micro-batch-size 1 \
+	--global-batch-size 1536 \
+	--rampup-batch-size 16 16 5859375 \
+	--train-samples 146484375 \
+       	--lr-decay-samples 126953125 \
+        --lr-warmup-samples 183105 \
+        --lr 6.0e-5 \
+	--min-lr 6.0e-6 \
+        --lr-decay-style cosine \
+        --log-interval 10 \
+        --eval-iters 40 \
+        --eval-interval 1000 \
+	--data-path ${DATASET} \
+	--vocab-file <PATH TO gpt-vocab.json> \
+	--merge-file <PATH TO gpt-merges.txt> \
+	--save-interval 1000 \
+	--save <PATH TO CHECKPOINTS DIRECTORY> \
+	--load <PATH TO CHECKPOINTS DIRECTORY> \
+        --split 98,2,0 \
+        --clip-grad 1.0 \
+	--weight-decay 0.1 \
+	--adam-beta1 0.9 \
+	--adam-beta2 0.95 \
+	--init-method-std 0.006 \
+	--tensorboard-dir <TENSORBOARD DIRECTORY> \
+        --fp16 \
+	--activations-checkpoint-method uniform "
+
+
+run_cmd="python -u ${DIR}/pretrain_gpt.py $@ ${options}"
+
+
+srun -l \
+     --container-image "nvcr.io/nvidia/pytorch:20.12-py3" \
+     --container-mounts "<DIRECTORIES TO MOUNT>" \
+     --output=$DIR/logs/%x_%j_$DATETIME.log sh -c "${run_cmd}"
+
+
+set +x
+

examples/pretrain_gpt_distributed.sh

+#!/bin/bash
+
+# Runs the "345M" parameter model
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+GPUS_PER_NODE=8
+# Change for multinode config
+MASTER_ADDR=localhost
+MASTER_PORT=6000
+NNODES=1
+NODE_RANK=0
+WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/gpt2-vocab.json
+MERGE_FILE=<Specify path to file>/gpt2-merges.txt
+DATA_PATH=<Specify path and file prefix>_text_document
+
+DISTRIBUTED_ARGS="
+    --nproc_per_node $GPUS_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $NODE_RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT
+"
+
+GPT_ARGS="
+    --num-layers 24 \
+    --hidden-size 1024 \
+    --num-attention-heads 16 \
+    --seq-length 1024 \
+    --max-position-embeddings 1024 \
+    --micro-batch-size 8 \
+    --global-batch-size 64 \
+    --lr 0.00015 \
+    --train-iters 500000 \
+    --lr-decay-iters 320000 \
+    --lr-decay-style cosine \
+    --min-lr 1.0e-5 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --merge-file $MERGE_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun $DISTRIBUTED_ARGS pretrain_gpt.py \
+    $GPT_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --distributed-backend nccl \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH

examples/pretrain_gpt_distributed_with_mp.sh

+#!/bin/bash
+
+# Runs the "345M" parameter model
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+GPUS_PER_NODE=8
+# Change for multinode config
+MASTER_ADDR=localhost
+MASTER_PORT=6000
+NNODES=1
+NODE_RANK=0
+WORLD_SIZE=$(($GPUS_PER_NODE*$NNODES))
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/gpt2-vocab.json
+MERGE_FILE=<Specify path to file>/gpt2-merges.txt
+DATA_PATH=<Specify path and file prefix>_text_document
+
+DISTRIBUTED_ARGS="
+    --nproc_per_node $GPUS_PER_NODE \
+    --nnodes $NNODES \
+    --node_rank $NODE_RANK \
+    --master_addr $MASTER_ADDR \
+    --master_port $MASTER_PORT
+"
+
+GPT_ARGS="
+    --tensor-model-parallel-size 2 \
+    --pipeline-model-parallel-size 2 \
+    --sequence-parallel \
+    --num-layers 24 \
+    --hidden-size 1024 \
+    --num-attention-heads 16 \
+    --seq-length 1024 \
+    --max-position-embeddings 1024 \
+    --micro-batch-size 4 \
+    --global-batch-size 16 \
+    --lr 0.00015 \
+    --train-iters 500000 \
+    --lr-decay-iters 320000 \
+    --lr-decay-style cosine \
+    --min-lr 1.0e-5 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --merge-file $MERGE_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun $DISTRIBUTED_ARGS pretrain_gpt.py \
+    $GPT_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --distributed-backend nccl \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH
+

examples/pretrain_ict.sh

+#! /bin/bash
+
+# Runs the "217M" parameter biencoder model for ICT retriever
+
+RANK=0
+WORLD_SIZE=1
+
+PRETRAINED_BERT_PATH=<Specify path of pretrained BERT model>
+TEXT_DATA_PATH=<Specify path and file prefix of the text data>
+TITLE_DATA_PATH=<Specify path and file prefix od the titles>
+CHECKPOINT_PATH=<Specify path>
+
+
+python pretrain_ict.py \
+        --num-layers 12 \
+        --hidden-size 768 \
+        --num-attention-heads 12 \
+        --tensor-model-parallel-size 1 \
+        --micro-batch-size 32 \
+        --seq-length 256 \
+        --max-position-embeddings 512 \
+        --train-iters 100000 \
+        --vocab-file bert-vocab.txt \
+        --tokenizer-type BertWordPieceLowerCase \
+        --DDP-impl torch \
+        --bert-load ${PRETRAINED_BERT_PATH} \
+        --log-interval 100 \
+        --eval-interval 1000 \
+        --eval-iters 10 \
+        --retriever-report-topk-accuracies 1 5 10 20 100 \
+        --retriever-score-scaling \
+        --load $CHECKPOINT_PATH \
+        --save $CHECKPOINT_PATH \
+        --data-path ${TEXT_DATA_PATH} \
+        --titles-data-path ${TITLE_DATA_PATH} \
+        --lr 0.0001 \
+        --lr-decay-style linear \
+        --weight-decay 1e-2 \
+        --clip-grad 1.0 \
+        --lr-warmup-fraction 0.01 \
+        --save-interval 4000 \
+        --exit-interval 8000 \
+        --query-in-block-prob 0.1 \
+        --fp16

examples/pretrain_t5.sh

+#!/bin/bash
+
+export CUDA_DEVICE_MAX_CONNECTIONS=1
+
+CHECKPOINT_PATH=<Specify path>
+VOCAB_FILE=<Specify path to file>/t5-vocab.txt
+DATA_PATH=<Specify path and file prefix>_text_sentence
+
+T5_ARGS="
+    --num-layers 12 \
+    --hidden-size 768 \
+    --num-attention-heads 12 \
+    --kv-channels 64 \
+    --ffn-hidden-size 3072 \
+    --encoder-seq-length 512 \
+    --decoder-seq-length 128 \
+    --max-position-embeddings 512 \
+    --micro-batch-size 16 \
+    --global-batch-size 16 \
+    --lr 0.0001 \
+    --train-iters 1000000 \
+    --lr-decay-iters 1000000 \
+    --lr-decay-style linear \
+    --min-lr 0.00001 \
+    --weight-decay 1e-2 \
+    --lr-warmup-fraction .01 \
+    --clip-grad 1.0 \
+    --fp16 \
+    --vocab-extra-ids 100
+"
+
+DATA_ARGS="
+    --data-path $DATA_PATH \
+    --vocab-file $VOCAB_FILE \
+    --data-impl mmap \
+    --split 949,50,1
+"
+
+OUTPUT_ARGS="
+    --log-interval 100 \
+    --save-interval 10000 \
+    --eval-interval 1000 \
+    --eval-iters 10
+"
+
+torchrun pretrain_t5.py \
+    $T5_ARGS \
+    $DATA_ARGS \
+    $OUTPUT_ARGS \
+    --save $CHECKPOINT_PATH \
+    --load $CHECKPOINT_PATH