diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml index ca88b7b8b0..cdc253d6ae 100644 --- a/.github/workflows/benchmark.yml +++ b/.github/workflows/benchmark.yml @@ -115,7 +115,7 @@ jobs: - name: Run GPT2 w HALF/BEAM run: CUDA=1 JIT=1 HALF=1 BEAM=2 CACHELEVEL=0 CAST_BEFORE_VIEW=0 python3 examples/gpt2.py --count 10 --temperature 0 --timing | tee gpt2_half_beam.txt - name: Run full CIFAR training - run: time CUDA=1 HALF=1 LATEWINO=1 STEPS=1000 TARGET_EVAL_ACC_PCT=93.5 python3 examples/hlb_cifar10.py | tee train_cifar_one_gpu.txt + run: time CUDA=1 HALF=1 LATEWINO=1 STEPS=1000 TARGET_EVAL_ACC_PCT=93.3 python3 examples/hlb_cifar10.py | tee train_cifar_one_gpu.txt - uses: actions/upload-artifact@v4 with: name: Speed (NVIDIA) @@ -229,9 +229,9 @@ jobs: - name: Run 10 CIFAR training steps w HALF run: HSA=1 STEPS=10 HALF=1 python3 examples/hlb_cifar10.py | tee train_cifar_half.txt - name: Run full CIFAR training w 1 GPU - run: time HSA=1 HALF=1 LATEWINO=1 STEPS=1000 TARGET_EVAL_ACC_PCT=93.5 python3 examples/hlb_cifar10.py | tee train_cifar_one_gpu.txt + run: time HSA=1 HALF=1 LATEWINO=1 STEPS=1000 TARGET_EVAL_ACC_PCT=93.3 python3 examples/hlb_cifar10.py | tee train_cifar_one_gpu.txt - name: Run full CIFAR training steps w 6 GPUS - run: time HSA=1 HALF=1 STEPS=350 BS=1536 GPUS=6 TARGET_EVAL_ACC_PCT=93.5 python3 examples/hlb_cifar10.py | tee train_cifar_six_gpu.txt + run: time HSA=1 HALF=1 STEPS=350 BS=1536 GPUS=6 TARGET_EVAL_ACC_PCT=93.3 python3 examples/hlb_cifar10.py | tee train_cifar_six_gpu.txt - name: Run MLPerf resnet eval on training data run: time HSA=1 MODEL=resnet python3 examples/mlperf/model_eval.py - name: Run 10 MLPerf ResNet50 training steps (1 gpu)