bert BEAM_UOPS_MAX 3000->4000 (#9603)

more stable for the final step time

green 410ms (master) -> 397ms (BEAM=4) -> 392ms (this)
red 561ms (master) -> 550ms (this)
This commit is contained in:
chenyu
2025-03-27 11:58:47 -04:00
committed by GitHub
parent 088a677e25
commit a187dfd3df
6 changed files with 6 additions and 6 deletions

View File

@@ -4,7 +4,7 @@ export PYTHONPATH="."
export MODEL="bert"
export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=24
export BEAM=5 BEAM_UOPS_MAX=3000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export BEAM=4 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
export BEAM_LOG_SURPASS_MAX=1
export BASEDIR="/raid/datasets/wiki"

View File

@@ -4,7 +4,7 @@ export PYTHONPATH="."
export MODEL="bert"
export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=24
export BEAM=5 BEAM_UOPS_MAX=3000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export BEAM=4 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
export BASEDIR="/raid/datasets/wiki"

View File

@@ -5,7 +5,7 @@ export MODEL="bert"
export SUBMISSION_PLATFORM="tinybox_green"
export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=24
export BEAM=5 BEAM_UOPS_MAX=3000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export BEAM=4 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
export BASEDIR="/raid/datasets/wiki"

View File

@@ -4,7 +4,7 @@ export PYTHONPATH="."
export MODEL="bert"
export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=96
export BEAM=3 BEAM_UOPS_MAX=3000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export BEAM=3 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
export BEAM_LOG_SURPASS_MAX=1
export BASEDIR="/raid/datasets/wiki"

View File

@@ -4,7 +4,7 @@ export PYTHONPATH="."
export MODEL="bert"
export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=96
export BEAM=3 BEAM_UOPS_MAX=3000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export BEAM=3 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
export BASEDIR="/raid/datasets/wiki"

View File

@@ -5,7 +5,7 @@ export MODEL="bert"
export SUBMISSION_PLATFORM="tinybox_red"
export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=96
export BEAM=3 BEAM_UOPS_MAX=3000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export BEAM=3 BEAM_UOPS_MAX=4000 BEAM_UPCAST_MAX=256 BEAM_LOCAL_MAX=1024 BEAM_MIN_PROGRESS=5
export IGNORE_JIT_FIRST_BEAM=1
export BASEDIR="/raid/datasets/wiki"