| [1/4] /home/ludaze/usr/local/cuda/cuda-11.8/bin/nvcc --generate-dependencies-with-compile --dependency-output fast_lsh_cumulation_cuda.cuda.o.d -DTORCH_EXTENSION_NAME=fast_lsh_cumulation -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/TH -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/THC -isystem /home/ludaze/usr/local/cuda/cuda-11.8/include -isystem /home/ludaze/.conda/envs/axolotl/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++17 -c /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/transformers/kernels/yoso/fast_lsh_cumulation_cuda.cu -o fast_lsh_cumulation_cuda.cuda.o | |
| [2/4] c++ -MMD -MF fast_lsh_cumulation_torch.o.d -DTORCH_EXTENSION_NAME=fast_lsh_cumulation -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/TH -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/THC -isystem /home/ludaze/usr/local/cuda/cuda-11.8/include -isystem /home/ludaze/.conda/envs/axolotl/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -fPIC -std=c++17 -c /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/transformers/kernels/yoso/fast_lsh_cumulation_torch.cpp -o fast_lsh_cumulation_torch.o | |
| [3/4] /home/ludaze/usr/local/cuda/cuda-11.8/bin/nvcc --generate-dependencies-with-compile --dependency-output fast_lsh_cumulation.cuda.o.d -DTORCH_EXTENSION_NAME=fast_lsh_cumulation -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/torch/csrc/api/include -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/TH -isystem /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/include/THC -isystem /home/ludaze/usr/local/cuda/cuda-11.8/include -isystem /home/ludaze/.conda/envs/axolotl/include/python3.10 -D_GLIBCXX_USE_CXX11_ABI=0 -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_BFLOAT16_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr -gencode=arch=compute_86,code=compute_86 -gencode=arch=compute_86,code=sm_86 --compiler-options '-fPIC' -std=c++17 -c /home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/transformers/kernels/yoso/fast_lsh_cumulation.cu -o fast_lsh_cumulation.cuda.o | |
| [4/4] c++ fast_lsh_cumulation_torch.o fast_lsh_cumulation.cuda.o fast_lsh_cumulation_cuda.cuda.o -shared -L/home/ludaze/.conda/envs/axolotl/lib/python3.10/site-packages/torch/lib -lc10 -lc10_cuda -ltorch_cpu -ltorch_cuda -ltorch -ltorch_python -L/home/ludaze/usr/local/cuda/cuda-11.8/lib64 -lcudart -o fast_lsh_cumulation.so | |
| {'loss': 1.3875, 'grad_norm': 0.290032297372818, 'learning_rate': 4.708318749270797e-05, 'epoch': 0.18} | |
| {'loss': 1.387, 'grad_norm': 0.24705088138580322, 'learning_rate': 4.416637498541594e-05, 'epoch': 0.35} | |
| {'loss': 1.387, 'grad_norm': 0.2913823425769806, 'learning_rate': 4.124956247812391e-05, 'epoch': 0.53} | |
| {'loss': 1.3867, 'grad_norm': 0.2294648140668869, 'learning_rate': 3.8332749970831875e-05, 'epoch': 0.7} | |
| {'loss': 1.3868, 'grad_norm': 0.25805965065956116, 'learning_rate': 3.5415937463539846e-05, 'epoch': 0.88} | |