github/tinygrad
1
1
Fork 0
mirror of https://github.com/tinygrad/tinygrad.git synced 2026-01-09 15:08:02 -05:00
Code Issues Packages Projects Releases Wiki Activity

add a flag to log when beam surpassed max limit [pr] (#9533)

Browse Source
This commit is contained in:
chenyu
2025-03-21 13:37:02 -04:00
committed by GitHub
parent eb95825eea
commit b46b8ee15e
5 changed files with 10 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_green/dev_beam.sh
View File

@@ -6,6 +6,7 @@ export DEFAULT_FLOAT="HALF" SUM_DTYPE="HALF" GPUS=6 BS=96 EVAL_BS=96
export BEAM=4 BEAM_UOPS_MAX=3000 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"
export RESET_STEP=1

2
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_green/run_and_time.sh
View File

@@ -17,7 +17,7 @@ DATETIME=$(date "+%m%d%H%M")
LOGFILE="bert_green_${DATETIME}_${SEED}.log"
# init
BENCHMARK=10 INITMLPERF=1 RESET_STEP=1 python3 examples/mlperf/model_train.py | tee $LOGFILE
BENCHMARK=10 INITMLPERF=1 RESET_STEP=1 BEAM_LOG_SURPASS_MAX=1 python3 examples/mlperf/model_train.py | tee $LOGFILE
# run
PARALLEL=0 RUNMLPERF=1 python3 examples/mlperf/model_train.py | tee -a $LOGFILE

1
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_red/dev_beam.sh
View File

@@ -6,6 +6,7 @@ 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 IGNORE_JIT_FIRST_BEAM=1
export BEAM_LOG_SURPASS_MAX=1
export BASEDIR="/raid/datasets/wiki"
export RESET_STEP=1

2
examples/mlperf/training_submission_v5.0/tinycorp/benchmarks/bert/implementations/tinybox_red/run_and_time.sh
View File

@@ -17,7 +17,7 @@ DATETIME=$(date "+%m%d%H%M")
LOGFILE="bert_red_${DATETIME}_${SEED}.log"
# init
BENCHMARK=10 INITMLPERF=1 RESET_STEP=1 python3 examples/mlperf/model_train.py | tee $LOGFILE
BENCHMARK=10 INITMLPERF=1 RESET_STEP=1 BEAM_LOG_SURPASS_MAX=1 python3 examples/mlperf/model_train.py | tee $LOGFILE
# run
PARALLEL=0 RUNMLPERF=1 python3 examples/mlperf/model_train.py | tee -a $LOGFILE