| 2024/08/25 18:15:54 - mmengine - INFO - | |
| ------------------------------------------------------------ | |
| System environment: | |
| sys.platform: linux | |
| Python: 3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0] | |
| CUDA available: True | |
| MUSA available: False | |
| numpy_random_seed: 698415529 | |
| GPU 0,1: NVIDIA A100-SXM4-80GB | |
| CUDA_HOME: /usr/local/cuda | |
| NVCC: Cuda compilation tools, release 12.2, V12.2.140 | |
| GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 | |
| PyTorch: 2.3.1+cu121 | |
| PyTorch compiling details: PyTorch built with: | |
| - GCC 9.3 | |
| - C++ Version: 201703 | |
| - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications | |
| - Intel(R) MKL-DNN v3.3.6 (Git Hash 86e6af5974177e513fd3fee58425e1063e7f1361) | |
| - OpenMP 201511 (a.k.a. OpenMP 4.5) | |
| - LAPACK is enabled (usually provided by MKL) | |
| - NNPACK is enabled | |
| - CPU capability usage: AVX512 | |
| - CUDA Runtime 12.1 | |
| - NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90 | |
| - CuDNN 8.9.2 | |
| - Magma 2.6.1 | |
| - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=12.1, CUDNN_VERSION=8.9.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.3.1, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, | |
| TorchVision: 0.18.1+cu121 | |
| OpenCV: 4.9.0 | |
| MMEngine: 0.10.3 | |
| Runtime environment: | |
| cudnn_benchmark: False | |
| mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} | |
| dist_cfg: {'backend': 'nccl'} | |
| seed: 698415529 | |
| deterministic: False | |
| Distributed launcher: none | |
| Distributed training: False | |
| GPU number: 1 | |
| ------------------------------------------------------------ | |
| 2024/08/25 18:15:54 - mmengine - INFO - Config: | |
| accumulative_counts = 4 | |
| batch_size = 4 | |
| betas = ( | |
| 0.9, | |
| 0.999, | |
| ) | |
| custom_hooks = [ | |
| dict( | |
| tokenizer=dict( | |
| pretrained_model_name_or_path='/root/models/InternVL2_2B', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.engine.hooks.DatasetInfoHook'), | |
| ] | |
| data_path = '/root/data/screenshot_od/layout_ocr_multi.json' | |
| data_root = '/root/data/extracted_images' | |
| dataloader_num_workers = 4 | |
| default_hooks = dict( | |
| checkpoint=dict( | |
| by_epoch=False, | |
| interval=1000, | |
| max_keep_ckpts=-1, | |
| save_optimizer=False, | |
| type='mmengine.hooks.CheckpointHook'), | |
| logger=dict( | |
| interval=10, | |
| log_metric_by_epoch=False, | |
| type='mmengine.hooks.LoggerHook'), | |
| param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'), | |
| sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'), | |
| timer=dict(type='mmengine.hooks.IterTimerHook')) | |
| env_cfg = dict( | |
| cudnn_benchmark=False, | |
| dist_cfg=dict(backend='nccl'), | |
| mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) | |
| image_folder = '/root/data/extracted_imagesscreenshot_od/images' | |
| launcher = 'none' | |
| llava_dataset = dict( | |
| data_paths='/root/data/screenshot_od/layout_ocr_multi.json', | |
| image_folders='/root/data/extracted_imagesscreenshot_od/images', | |
| max_length=8192, | |
| model_path='/root/models/InternVL2_2B', | |
| template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat', | |
| type='xtuner.dataset.InternVL_V1_5_Dataset') | |
| load_from = None | |
| log_level = 'DEBUG' | |
| log_processor = dict(by_epoch=False) | |
| lr = 2e-05 | |
| max_epochs = 4 | |
| max_length = 8192 | |
| max_norm = 1 | |
| model = dict( | |
| freeze_llm=True, | |
| freeze_visual_encoder=True, | |
| llm_lora=dict( | |
| lora_alpha=256, | |
| lora_dropout=0.05, | |
| r=128, | |
| target_modules=None, | |
| task_type='CAUSAL_LM', | |
| type='peft.LoraConfig'), | |
| model_path='/root/models/InternVL2_2B', | |
| quantization_llm=True, | |
| quantization_vit=False, | |
| type='xtuner.model.InternVL_V1_5') | |
| optim_type = 'torch.optim.AdamW' | |
| optim_wrapper = dict( | |
| accumulative_counts=4, | |
| clip_grad=dict(error_if_nonfinite=False, max_norm=1), | |
| constructor='LearningRateDecayOptimWrapperConstructor', | |
| dtype='float16', | |
| loss_scale='dynamic', | |
| optimizer=dict( | |
| betas=( | |
| 0.9, | |
| 0.999, | |
| ), | |
| lr=2e-05, | |
| type='torch.optim.AdamW', | |
| weight_decay=0.1), | |
| paramwise_cfg=dict(layer_decay_rate=0.75), | |
| type='mmengine.optim.AmpOptimWrapper') | |
| param_scheduler = [ | |
| dict( | |
| begin=0, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| end=0.12, | |
| start_factor=1e-05, | |
| type='mmengine.optim.LinearLR'), | |
| dict( | |
| begin=0.12, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| end=4, | |
| eta_min=0.0, | |
| type='mmengine.optim.CosineAnnealingLR'), | |
| ] | |
| path = '/root/models/InternVL2_2B' | |
| prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.internlm2_chat' | |
| randomness = dict(deterministic=False, seed=None) | |
| resume = False | |
| save_steps = 1000 | |
| save_total_limit = -1 | |
| tokenizer = dict( | |
| pretrained_model_name_or_path='/root/models/InternVL2_2B', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained') | |
| train_cfg = dict(max_epochs=4, type='xtuner.engine.runner.TrainLoop') | |
| train_dataloader = dict( | |
| batch_size=4, | |
| collate_fn=dict(type='xtuner.dataset.collate_fns.default_collate_fn'), | |
| dataset=dict( | |
| data_paths='/root/data/screenshot_od/layout_ocr_multi.json', | |
| image_folders='/root/data/extracted_imagesscreenshot_od/images', | |
| max_length=8192, | |
| model_path='/root/models/InternVL2_2B', | |
| template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat', | |
| type='xtuner.dataset.InternVL_V1_5_Dataset'), | |
| num_workers=4, | |
| sampler=dict( | |
| length_property='modality_length', | |
| per_device_batch_size=16, | |
| type='xtuner.dataset.samplers.LengthGroupedSampler')) | |
| visualizer = dict( | |
| type='mmengine.visualization.Visualizer', | |
| vis_backends=[ | |
| dict(type='mmengine.visualization.TensorboardVisBackend'), | |
| ]) | |
| warmup_ratio = 0.03 | |
| weight_decay = 0.1 | |
| work_dir = '/root/wangqun/work_dirs/internvl_ft_run_11_filter' | |
| 2024/08/25 18:15:54 - mmengine - DEBUG - An `TensorboardVisBackend` instance is built from registry, and its implementation can be found in mmengine.visualization.vis_backend | |
| 2024/08/25 18:15:54 - mmengine - DEBUG - An `Visualizer` instance is built from registry, and its implementation can be found in mmengine.visualization.visualizer | |
| 2024/08/25 18:15:54 - mmengine - DEBUG - Attribute `_env_initialized` is not defined in <class 'mmengine.visualization.vis_backend.TensorboardVisBackend'> or `<class 'mmengine.visualization.vis_backend.TensorboardVisBackend'>._env_initialized is False, `_init_env` will be called and <class 'mmengine.visualization.vis_backend.TensorboardVisBackend'>._env_initialized will be set to True | |