forked from bigscience-workshop/Megatron-DeepSpeed
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pretrain_bert_distributed_with_mp.sh
executable file
·46 lines (42 loc) · 1.33 KB
/
pretrain_bert_distributed_with_mp.sh
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
#!/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
VOCAB_FILE=<Specify path to vocab.txt>
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 \
--tensor-model-parallel-size 2 \
--pipeline-model-parallel-size 2 \
--num-layers 24 \
--hidden-size 1024 \
--num-attention-heads 16 \
--micro-batch-size 2 \
--global-batch-size 16 \
--max-position-embeddings 512 \
--train-iters 1000000 \
--save $CHECKPOINT_PATH \
--load $CHECKPOINT_PATH \
--data-path $DATA_PATH \
--vocab-file $VOCAB_FILE \
--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 \
--lr-warmup-fraction .01 \
--log-interval 100 \
--save-interval 10000 \
--eval-interval 1000 \
--eval-iters 10 \
--fp16