Merge branch 'deepspeed-branch' into 'main'

Deepspeed branch

See merge request dcutoolkit/deeplearing/dlexamples_new!22

Deepspeed/Megatron-LM-v1.1.5-ZeRO3/examples/generate_text.sh

+#!/bin/bash
+
+CHECKPOINT_PATH=checkpoints/gpt2_345m
+VOCAB_FILE=gpt2-vocab.json
+MERGE_FILE=gpt2-merges.txt
+
+python tools/generate_samples_gpt2.py \
+       --model-parallel-size 1 \
+       --num-layers 24 \
+       --hidden-size 1024 \
+       --load $CHECKPOINT_PATH \
+       --num-attention-heads 16 \
+       --max-position-embeddings 1024 \
+       --tokenizer-type GPT2BPETokenizer \
+       --fp16 \
+       --batch-size 2 \
+       --seq-length 1024 \
+       --out-seq-length 1024 \
+       --temperature 1.0 \
+       --vocab-file $VOCAB_FILE \
+       --merge-file $MERGE_FILE \
+       --genfile unconditional_samples.json \
+       --num-samples 2 \
+       --top_p 0.9 \
+       --recompute

Deepspeed/Megatron-LM-v1.1.5-ZeRO3/examples/merge_mp_bert.sh

+#!/bin/bash
+
+MODEL_PARALLEL_SIZE=2
+
+VOCAB_FILE=bert-vocab.txt
+CHECKPOINT_PATH=checkpoints/bert_345m
+
+WORLD_SIZE=$MODEL_PARALLEL_SIZE python tools/merge_mp_partitions.py \
+                                --model-type BERT \
+                                --model-parallel-size $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

Deepspeed/Megatron-LM-v1.1.5-ZeRO3/examples/pretrain_bert.sh

+#!/bin/bash
+
+RANK=0
+WORLD_SIZE=1
+DATA_PATH=<Specify path and file prefix>_text_sentence
+CHECKPOINT_PATH=<Specify path>
+
+python pretrain_bert.py \
+       --num-layers 24 \
+       --hidden-size 1024 \
+       --num-attention-heads 16 \
+       --batch-size 4 \
+       --seq-length 512 \
+       --max-position-embeddings 512 \
+       --train-iters 2000000 \
+       --save $CHECKPOINT_PATH \
+       --load $CHECKPOINT_PATH \
+       --data-path $DATA_PATH \
+       --vocab-file bert-vocab.txt \
+       --data-impl mmap \
+       --split 949,50,1 \
+       --distributed-backend nccl \
+       --lr 0.0001 \
+       --min-lr 0.00001 \
+       --lr-decay-style linear \
+       --lr-decay-iters 990000 \
+       --weight-decay 1e-2 \
+       --clip-grad 1.0 \
+       --warmup .01 \
+       --log-interval 100 \
+       --save-interval 10000 \
+       --eval-interval 1000 \
+       --eval-iters 10 \
+       --fp16
+

Deepspeed/Megatron-LM-v1.1.5-ZeRO3/examples/pretrain_bert_distributed.sh

+#!/bin/bash
+
+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))
+
+DATA_PATH=<Specify path and file prefix>_text_sentence
+CHECKPOINT_PATH=<Specify path>
+
+DISTRIBUTED_ARGS="--nproc_per_node $GPUS_PER_NODE --nnodes $NNODES --node_rank $NODE_RANK --master_addr $MASTER_ADDR --master_port $MASTER_PORT"
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS \
+       pretrain_bert.py \
+       --model-parallel-size 1 \
+       --num-layers 24 \
+       --hidden-size 1024 \
+       --num-attention-heads 16 \
+       --batch-size 4 \
+       --seq-length 512 \
+       --max-position-embeddings 512 \
+       --train-iters 1000000 \
+       --save $CHECKPOINT_PATH \
+       --load $CHECKPOINT_PATH \
+       --data-path $DATA_PATH \
+       --vocab-file bert-vocab.txt \
+       --data-impl mmap \
+       --split 949,50,1 \
+       --distributed-backend nccl \
+       --lr 0.0001 \
+       --lr-decay-style linear \
+       --min-lr 1.0e-5 \
+       --lr-decay-iters 990000 \
+       --weight-decay 1e-2 \
+       --clip-grad 1.0 \
+       --warmup .01 \
+       --log-interval 100 \
+       --save-interval 10000 \
+       --eval-interval 1000 \
+       --eval-iters 10 \
+       --fp16

Deepspeed/Megatron-LM-v1.1.5-ZeRO3/examples/pretrain_gpt2.sh

+#! /bin/bash
+
+# Runs the "345M" parameter model
+
+RANK=0
+WORLD_SIZE=1
+
+DATA_PATH=<Specify path and file prefix>_text_document
+CHECKPOINT_PATH=<Specify path>
+
+
+python pretrain_gpt2.py \
+       --num-layers 24 \
+       --hidden-size 1024 \
+       --num-attention-heads 16 \
+       --batch-size 8 \
+       --seq-length 1024 \
+       --max-position-embeddings 1024 \
+       --train-iters 500000 \
+       --lr-decay-iters 320000 \
+       --save $CHECKPOINT_PATH \
+       --load $CHECKPOINT_PATH \
+       --data-path $DATA_PATH \
+       --vocab-file gpt2-vocab.json \
+       --merge-file gpt2-merges.txt \
+       --data-impl mmap \
+       --split 949,50,1 \
+       --distributed-backend nccl \
+       --lr 0.00015 \
+       --min-lr 1.0e-5 \
+       --lr-decay-style cosine \
+       --weight-decay 1e-2 \
+       --clip-grad 1.0 \
+       --warmup .01 \
+       --checkpoint-activations \
+       --log-interval 100 \
+       --save-interval 10000 \
+       --eval-interval 1000 \
+       --eval-iters 10 \
+       --fp16
+
+
+set +x

Deepspeed/Megatron-LM-v1.1.5-ZeRO3/examples/pretrain_gpt2_distributed.sh

+#! /bin/bash
+
+# Runs the "345M" parameter model
+
+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))
+
+DATA_PATH=<Specify path and file prefix>_text_document
+CHECKPOINT_PATH=<Specify path>
+
+DISTRIBUTED_ARGS="--nproc_per_node $GPUS_PER_NODE --nnodes $NNODES --node_rank $NODE_RANK --master_addr $MASTER_ADDR --master_port $MASTER_PORT"
+
+python -m torch.distributed.launch $DISTRIBUTED_ARGS \
+       pretrain_gpt2.py \
+       --model-parallel-size 1 \
+       --num-layers 24 \
+       --hidden-size 1024 \
+       --num-attention-heads 16 \
+       --batch-size 8 \
+       --seq-length 1024 \
+       --max-position-embeddings 1024 \
+       --train-iters 500000 \
+       --lr-decay-iters 320000 \
+       --save $CHECKPOINT_PATH \
+       --load $CHECKPOINT_PATH \
+       --data-path $DATA_PATH \
+       --vocab-file gpt2-vocab.json \
+       --merge-file gpt2-merges.txt \
+       --data-impl mmap \
+       --split 949,50,1 \
+       --distributed-backend nccl \
+       --lr 0.00015 \
+       --lr-decay-style cosine \
+       --min-lr 1.0e-5 \
+       --weight-decay 1e-2 \
+       --clip-grad 1.0 \
+       --warmup .01 \
+       --checkpoint-activations \
+       --log-interval 100 \
+       --save-interval 10000 \
+       --eval-interval 1000 \
+       --eval-iters 10 \
+       --fp16
+
+
+
+set +x