diff --git "a/20240825_104447/20240825_104447.log" "b/20240825_104447/20240825_104447.log" new file mode 100644--- /dev/null +++ "b/20240825_104447/20240825_104447.log" @@ -0,0 +1,1110 @@ +2024/08/25 10:44:47 - mmengine - DEBUG - An `DeepSpeedStrategy` instance is built from registry, and its implementation can be found in xtuner.engine._strategy.deepspeed +2024/08/25 10:44:47 - mmengine - DEBUG - An `DeepSpeedStrategy` instance is built from registry, and its implementation can be found in xtuner.engine._strategy.deepspeed +2024/08/25 10:44:48 - 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: 850064668 + 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: + launcher: none + randomness: {'seed': None, 'deterministic': False} + cudnn_benchmark: False + mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} + dist_cfg: {'backend': 'nccl'} + seed: None + deterministic: False + Distributed launcher: none + Distributed training: False + GPU number: 1 +------------------------------------------------------------ + +2024/08/25 10:44:48 - 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: 1607702960 + 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: + launcher: none + randomness: {'seed': None, 'deterministic': False} + cudnn_benchmark: False + mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} + dist_cfg: {'backend': 'nccl'} + seed: None + deterministic: False + Distributed launcher: none + Distributed training: False + GPU number: 1 +------------------------------------------------------------ + +2024/08/25 10:44:48 - 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( + optimizer=dict( + betas=( + 0.9, + 0.999, + ), + lr=2e-05, + type='torch.optim.AdamW', + weight_decay=0.1), + type='DeepSpeedOptimWrapper') +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 +runner_type = 'FlexibleRunner' +save_steps = 1000 +save_total_limit = -1 +strategy = dict( + config=dict( + bf16=dict(enabled=True), + fp16=dict(enabled=False, initial_scale_power=16), + gradient_accumulation_steps='auto', + gradient_clipping='auto', + train_micro_batch_size_per_gpu='auto', + zero_allow_untested_optimizer=True, + zero_force_ds_cpu_optimizer=False, + zero_optimization=dict(overlap_comm=True, stage=2)), + exclude_frozen_parameters=True, + gradient_accumulation_steps=4, + gradient_clipping=1, + sequence_parallel_size=1, + train_micro_batch_size_per_gpu=4, + type='xtuner.engine.DeepSpeedStrategy') +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 10:44:48 - mmengine - DEBUG - An `TensorboardVisBackend` instance is built from registry, and its implementation can be found in mmengine.visualization.vis_backend +2024/08/25 10:44:48 - 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( + optimizer=dict( + betas=( + 0.9, + 0.999, + ), + lr=2e-05, + type='torch.optim.AdamW', + weight_decay=0.1), + type='DeepSpeedOptimWrapper') +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 +runner_type = 'FlexibleRunner' +save_steps = 1000 +save_total_limit = -1 +strategy = dict( + config=dict( + bf16=dict(enabled=True), + fp16=dict(enabled=False, initial_scale_power=16), + gradient_accumulation_steps='auto', + gradient_clipping='auto', + train_micro_batch_size_per_gpu='auto', + zero_allow_untested_optimizer=True, + zero_force_ds_cpu_optimizer=False, + zero_optimization=dict(overlap_comm=True, stage=2)), + exclude_frozen_parameters=True, + gradient_accumulation_steps=4, + gradient_clipping=1, + sequence_parallel_size=1, + train_micro_batch_size_per_gpu=4, + type='xtuner.engine.DeepSpeedStrategy') +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 10:44:48 - mmengine - DEBUG - An `TensorboardVisBackend` instance is built from registry, and its implementation can be found in mmengine.visualization.vis_backend +2024/08/25 10:44:48 - mmengine - DEBUG - An `Visualizer` instance is built from registry, and its implementation can be found in mmengine.visualization.visualizer +2024/08/25 10:44:48 - mmengine - DEBUG - An `Visualizer` instance is built from registry, and its implementation can be found in mmengine.visualization.visualizer +2024/08/25 10:44:48 - mmengine - DEBUG - Attribute `_env_initialized` is not defined in or `._env_initialized is False, `_init_env` will be called and ._env_initialized will be set to True +2024/08/25 10:44:48 - mmengine - DEBUG - Attribute `_env_initialized` is not defined in or `._env_initialized is False, `_init_env` will be called and ._env_initialized will be set to True +2024/08/25 10:44:49 - mmengine - DEBUG - Get class `RuntimeInfoHook` from "hook" registry in "mmengine" +2024/08/25 10:44:49 - mmengine - DEBUG - An `RuntimeInfoHook` instance is built from registry, and its implementation can be found in mmengine.hooks.runtime_info_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `IterTimerHook` instance is built from registry, and its implementation can be found in mmengine.hooks.iter_timer_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `DistSamplerSeedHook` instance is built from registry, and its implementation can be found in mmengine.hooks.sampler_seed_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `LoggerHook` instance is built from registry, and its implementation can be found in mmengine.hooks.logger_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `ParamSchedulerHook` instance is built from registry, and its implementation can be found in mmengine.hooks.param_scheduler_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `CheckpointHook` instance is built from registry, and its implementation can be found in mmengine.hooks.checkpoint_hook +2024/08/25 10:44:49 - mmengine - WARNING - Failed to search registry with scope "mmengine" in the "builder" registry tree. As a workaround, the current "builder" registry in "xtuner" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmengine" is a correct scope, or whether the registry is initialized. +2024/08/25 10:44:49 - mmengine - DEBUG - Get class `RuntimeInfoHook` from "hook" registry in "mmengine" +2024/08/25 10:44:49 - mmengine - DEBUG - An `RuntimeInfoHook` instance is built from registry, and its implementation can be found in mmengine.hooks.runtime_info_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `IterTimerHook` instance is built from registry, and its implementation can be found in mmengine.hooks.iter_timer_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `DistSamplerSeedHook` instance is built from registry, and its implementation can be found in mmengine.hooks.sampler_seed_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `LoggerHook` instance is built from registry, and its implementation can be found in mmengine.hooks.logger_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `ParamSchedulerHook` instance is built from registry, and its implementation can be found in mmengine.hooks.param_scheduler_hook +2024/08/25 10:44:49 - mmengine - DEBUG - An `CheckpointHook` instance is built from registry, and its implementation can be found in mmengine.hooks.checkpoint_hook +2024/08/25 10:44:49 - mmengine - WARNING - Failed to search registry with scope "mmengine" in the "builder" registry tree. As a workaround, the current "builder" registry in "xtuner" is used to build instance. This may cause unexpected failure when running the built modules. Please check whether "mmengine" is a correct scope, or whether the registry is initialized. +2024/08/25 10:44:49 - mmengine - DEBUG - An `from_pretrained` instance is built from registry, and its implementation can be found in transformers.models.auto.tokenization_auto +2024/08/25 10:44:49 - mmengine - DEBUG - An `DatasetInfoHook` instance is built from registry, and its implementation can be found in xtuner.engine.hooks.dataset_info_hook +2024/08/25 10:44:49 - mmengine - INFO - Hooks will be executed in the following order: +before_run: +(VERY_HIGH ) RuntimeInfoHook +(BELOW_NORMAL) LoggerHook + -------------------- +before_train: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(NORMAL ) DatasetInfoHook +(VERY_LOW ) CheckpointHook + -------------------- +before_train_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(NORMAL ) DistSamplerSeedHook + -------------------- +before_train_iter: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook + -------------------- +after_train_iter: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +after_train_epoch: +(NORMAL ) IterTimerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +before_val: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) DatasetInfoHook + -------------------- +before_val_epoch: +(NORMAL ) IterTimerHook + -------------------- +before_val_iter: +(NORMAL ) IterTimerHook + -------------------- +after_val_iter: +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_val_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +after_val: +(VERY_HIGH ) RuntimeInfoHook + -------------------- +after_train: +(VERY_HIGH ) RuntimeInfoHook +(VERY_LOW ) CheckpointHook + -------------------- +before_test: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) DatasetInfoHook + -------------------- +before_test_epoch: +(NORMAL ) IterTimerHook + -------------------- +before_test_iter: +(NORMAL ) IterTimerHook + -------------------- +after_test_iter: +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_test_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_test: +(VERY_HIGH ) RuntimeInfoHook + -------------------- +after_run: +(BELOW_NORMAL) LoggerHook + -------------------- +2024/08/25 10:44:49 - mmengine - DEBUG - An `from_pretrained` instance is built from registry, and its implementation can be found in transformers.models.auto.tokenization_auto +2024/08/25 10:44:49 - mmengine - DEBUG - An `DatasetInfoHook` instance is built from registry, and its implementation can be found in xtuner.engine.hooks.dataset_info_hook +2024/08/25 10:44:49 - mmengine - INFO - Hooks will be executed in the following order: +before_run: +(VERY_HIGH ) RuntimeInfoHook +(BELOW_NORMAL) LoggerHook + -------------------- +before_train: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(NORMAL ) DatasetInfoHook +(VERY_LOW ) CheckpointHook + -------------------- +before_train_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(NORMAL ) DistSamplerSeedHook + -------------------- +before_train_iter: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook + -------------------- +after_train_iter: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +after_train_epoch: +(NORMAL ) IterTimerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +before_val: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) DatasetInfoHook + -------------------- +before_val_epoch: +(NORMAL ) IterTimerHook + -------------------- +before_val_iter: +(NORMAL ) IterTimerHook + -------------------- +after_val_iter: +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_val_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook +(LOW ) ParamSchedulerHook +(VERY_LOW ) CheckpointHook + -------------------- +after_val: +(VERY_HIGH ) RuntimeInfoHook + -------------------- +after_train: +(VERY_HIGH ) RuntimeInfoHook +(VERY_LOW ) CheckpointHook + -------------------- +before_test: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) DatasetInfoHook + -------------------- +before_test_epoch: +(NORMAL ) IterTimerHook + -------------------- +before_test_iter: +(NORMAL ) IterTimerHook + -------------------- +after_test_iter: +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_test_epoch: +(VERY_HIGH ) RuntimeInfoHook +(NORMAL ) IterTimerHook +(BELOW_NORMAL) LoggerHook + -------------------- +after_test: +(VERY_HIGH ) RuntimeInfoHook + -------------------- +after_run: +(BELOW_NORMAL) LoggerHook + -------------------- +2024/08/25 10:44:49 - mmengine - DEBUG - An `FlexibleRunner` instance is built from registry, its implementation can be found inmmengine.runner._flexible_runner +2024/08/25 10:44:49 - mmengine - DEBUG - An `FlexibleRunner` instance is built from registry, its implementation can be found inmmengine.runner._flexible_runner +2024/08/25 10:44:50 - mmengine - INFO - Starting to loading data and calc length +2024/08/25 10:44:50 - mmengine - INFO - =======Starting to process /root/data/screenshot_od/layout_ocr_multi.json ======= +2024/08/25 10:44:50 - mmengine - INFO - Starting to loading data and calc length +2024/08/25 10:44:50 - mmengine - INFO - =======Starting to process /root/data/screenshot_od/layout_ocr_multi.json ======= +2024/08/25 10:44:56 - mmengine - INFO - =======total 4806 samples of /root/data/screenshot_od/layout_ocr_multi.json======= +2024/08/25 10:44:56 - mmengine - INFO - end loading data and calc length +2024/08/25 10:44:56 - mmengine - INFO - =======total 4806 samples======= +2024/08/25 10:44:56 - mmengine - DEBUG - An `InternVL_V1_5_Dataset` instance is built from registry, and its implementation can be found in xtuner.dataset.internvl_dataset +2024/08/25 10:44:56 - mmengine - INFO - LengthGroupedSampler is used. +2024/08/25 10:44:56 - mmengine - INFO - LengthGroupedSampler construction is complete, and the selected attribute is modality_length +2024/08/25 10:44:56 - mmengine - DEBUG - An `LengthGroupedSampler` instance is built from registry, and its implementation can be found in xtuner.dataset.samplers.length_grouped +2024/08/25 10:44:56 - mmengine - WARNING - Dataset InternVL_V1_5_Dataset has no metainfo. ``dataset_meta`` in visualizer will be None. +2024/08/25 10:44:56 - mmengine - INFO - =======total 4806 samples of /root/data/screenshot_od/layout_ocr_multi.json======= +2024/08/25 10:44:56 - mmengine - INFO - end loading data and calc length +2024/08/25 10:44:56 - mmengine - INFO - =======total 4806 samples======= +2024/08/25 10:44:56 - mmengine - DEBUG - An `InternVL_V1_5_Dataset` instance is built from registry, and its implementation can be found in xtuner.dataset.internvl_dataset +2024/08/25 10:44:56 - mmengine - DEBUG - An `TrainLoop` instance is built from registry, and its implementation can be found in xtuner.engine.runner.loops +2024/08/25 10:44:56 - mmengine - INFO - Start to load InternVL_V1_5 model. +2024/08/25 10:44:56 - mmengine - DEBUG - Get class `BaseDataPreprocessor` from "model" registry in "mmengine" +2024/08/25 10:44:56 - mmengine - DEBUG - An `BaseDataPreprocessor` instance is built from registry, and its implementation can be found in mmengine.model.base_model.data_preprocessor +2024/08/25 10:44:56 - mmengine - INFO - LengthGroupedSampler is used. +2024/08/25 10:44:56 - mmengine - INFO - LengthGroupedSampler construction is complete, and the selected attribute is modality_length +2024/08/25 10:44:56 - mmengine - DEBUG - An `LengthGroupedSampler` instance is built from registry, and its implementation can be found in xtuner.dataset.samplers.length_grouped +2024/08/25 10:44:56 - mmengine - WARNING - Dataset InternVL_V1_5_Dataset has no metainfo. ``dataset_meta`` in visualizer will be None. +2024/08/25 10:44:56 - mmengine - DEBUG - An `TrainLoop` instance is built from registry, and its implementation can be found in xtuner.engine.runner.loops +2024/08/25 10:44:56 - mmengine - INFO - Start to load InternVL_V1_5 model. +2024/08/25 10:44:56 - mmengine - DEBUG - Get class `BaseDataPreprocessor` from "model" registry in "mmengine" +2024/08/25 10:44:56 - mmengine - DEBUG - An `BaseDataPreprocessor` instance is built from registry, and its implementation can be found in mmengine.model.base_model.data_preprocessor +2024/08/25 10:45:04 - mmengine - DEBUG - An `LoraConfig` instance is built from registry, and its implementation can be found in peft.tuners.lora.config +2024/08/25 10:45:04 - mmengine - DEBUG - An `LoraConfig` instance is built from registry, and its implementation can be found in peft.tuners.lora.config +2024/08/25 10:45:05 - mmengine - INFO - InternVL_V1_5( + (data_preprocessor): BaseDataPreprocessor() + (model): InternVLChatModel( + (vision_model): InternVisionModel( + (embeddings): InternVisionEmbeddings( + (patch_embedding): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14)) + ) + (encoder): InternVisionEncoder( + (layers): ModuleList( + (0-23): 24 x InternVisionEncoderLayer( + (attn): InternAttention( + (qkv): Linear(in_features=1024, out_features=3072, bias=True) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (mlp): InternMLP( + (act): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + ) + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path1): Identity() + (drop_path2): Identity() + ) + ) + ) + ) + (language_model): PeftModelForCausalLM( + (base_model): LoraModel( + (model): InternLM2ForCausalLM( + (model): InternLM2Model( + (tok_embeddings): Embedding(92553, 2048, padding_idx=2) + (layers): ModuleList( + (0-23): 24 x InternLM2DecoderLayer( + (attention): InternLM2Attention( + (wqkv): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=4096, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=4096, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (wo): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=2048, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=2048, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (rotary_emb): InternLM2DynamicNTKScalingRotaryEmbedding() + ) + (feed_forward): InternLM2MLP( + (w1): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=8192, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=8192, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (w3): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=8192, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=8192, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (w2): lora.Linear( + (base_layer): Linear4bit(in_features=8192, out_features=2048, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=8192, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=2048, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (act_fn): SiLU() + ) + (attention_norm): InternLM2RMSNorm() + (ffn_norm): InternLM2RMSNorm() + ) + ) + (norm): InternLM2RMSNorm() + ) + (output): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=92553, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=92553, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + ) + ) + ) + (mlp1): Sequential( + (0): LayerNorm((4096,), eps=1e-05, elementwise_affine=True) + (1): Linear(in_features=4096, out_features=2048, bias=True) + (2): GELU(approximate='none') + (3): Linear(in_features=2048, out_features=2048, bias=True) + ) + ) +) +2024/08/25 10:45:05 - mmengine - INFO - InternVL_V1_5 construction is complete +2024/08/25 10:45:05 - mmengine - DEBUG - An `InternVL_V1_5` instance is built from registry, and its implementation can be found in xtuner.model.internvl +2024/08/25 10:45:05 - mmengine - DEBUG - Get class `DefaultOptimWrapperConstructor` from "optimizer wrapper constructor" registry in "mmengine" +2024/08/25 10:45:05 - mmengine - DEBUG - An `DefaultOptimWrapperConstructor` instance is built from registry, and its implementation can be found in mmengine.optim.optimizer.default_constructor +2024/08/25 10:45:05 - mmengine - DEBUG - An `AdamW` instance is built from registry, and its implementation can be found in torch.optim.adamw +2024/08/25 10:45:05 - mmengine - DEBUG - Get class `DeepSpeedOptimWrapper` from "optim_wrapper" registry in "mmengine" +2024/08/25 10:45:05 - mmengine - DEBUG - An `DeepSpeedOptimWrapper` instance is built from registry, and its implementation can be found in mmengine._strategy.deepspeed +2024/08/25 10:45:05 - mmengine - INFO - InternVL_V1_5( + (data_preprocessor): BaseDataPreprocessor() + (model): InternVLChatModel( + (vision_model): InternVisionModel( + (embeddings): InternVisionEmbeddings( + (patch_embedding): Conv2d(3, 1024, kernel_size=(14, 14), stride=(14, 14)) + ) + (encoder): InternVisionEncoder( + (layers): ModuleList( + (0-23): 24 x InternVisionEncoderLayer( + (attn): InternAttention( + (qkv): Linear(in_features=1024, out_features=3072, bias=True) + (attn_drop): Dropout(p=0.0, inplace=False) + (proj_drop): Dropout(p=0.0, inplace=False) + (proj): Linear(in_features=1024, out_features=1024, bias=True) + ) + (mlp): InternMLP( + (act): GELUActivation() + (fc1): Linear(in_features=1024, out_features=4096, bias=True) + (fc2): Linear(in_features=4096, out_features=1024, bias=True) + ) + (norm1): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (norm2): LayerNorm((1024,), eps=1e-06, elementwise_affine=True) + (drop_path1): Identity() + (drop_path2): Identity() + ) + ) + ) + ) + (language_model): PeftModelForCausalLM( + (base_model): LoraModel( + (model): InternLM2ForCausalLM( + (model): InternLM2Model( + (tok_embeddings): Embedding(92553, 2048, padding_idx=2) + (layers): ModuleList( + (0-23): 24 x InternLM2DecoderLayer( + (attention): InternLM2Attention( + (wqkv): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=4096, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=4096, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (wo): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=2048, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=2048, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (rotary_emb): InternLM2DynamicNTKScalingRotaryEmbedding() + ) + (feed_forward): InternLM2MLP( + (w1): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=8192, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=8192, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (w3): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=8192, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=8192, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (w2): lora.Linear( + (base_layer): Linear4bit(in_features=8192, out_features=2048, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=8192, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=2048, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + (act_fn): SiLU() + ) + (attention_norm): InternLM2RMSNorm() + (ffn_norm): InternLM2RMSNorm() + ) + ) + (norm): InternLM2RMSNorm() + ) + (output): lora.Linear( + (base_layer): Linear4bit(in_features=2048, out_features=92553, bias=False) + (lora_dropout): ModuleDict( + (default): Dropout(p=0.05, inplace=False) + ) + (lora_A): ModuleDict( + (default): Linear(in_features=2048, out_features=128, bias=False) + ) + (lora_B): ModuleDict( + (default): Linear(in_features=128, out_features=92553, bias=False) + ) + (lora_embedding_A): ParameterDict() + (lora_embedding_B): ParameterDict() + ) + ) + ) + ) + (mlp1): Sequential( + (0): LayerNorm((4096,), eps=1e-05, elementwise_affine=True) + (1): Linear(in_features=4096, out_features=2048, bias=True) + (2): GELU(approximate='none') + (3): Linear(in_features=2048, out_features=2048, bias=True) + ) + ) +) +2024/08/25 10:45:05 - mmengine - INFO - InternVL_V1_5 construction is complete +2024/08/25 10:45:05 - mmengine - DEBUG - An `InternVL_V1_5` instance is built from registry, and its implementation can be found in xtuner.model.internvl +2024/08/25 10:45:05 - mmengine - DEBUG - Get class `DefaultOptimWrapperConstructor` from "optimizer wrapper constructor" registry in "mmengine" +2024/08/25 10:45:05 - mmengine - DEBUG - An `DefaultOptimWrapperConstructor` instance is built from registry, and its implementation can be found in mmengine.optim.optimizer.default_constructor +2024/08/25 10:45:05 - mmengine - DEBUG - An `AdamW` instance is built from registry, and its implementation can be found in torch.optim.adamw +2024/08/25 10:45:05 - mmengine - DEBUG - Get class `DeepSpeedOptimWrapper` from "optim_wrapper" registry in "mmengine" +2024/08/25 10:45:05 - mmengine - DEBUG - An `DeepSpeedOptimWrapper` instance is built from registry, and its implementation can be found in mmengine._strategy.deepspeed +2024/08/25 10:45:07 - mmengine - DEBUG - The `end` of is not set. Use the max epochs/iters of train loop as default. +2024/08/25 10:45:07 - mmengine - DEBUG - The `end` of is not set. Use the max epochs/iters of train loop as default. +2024/08/25 10:45:07 - mmengine - INFO - Num train samples 4806 +2024/08/25 10:45:07 - mmengine - INFO - train example: +2024/08/25 10:45:07 - mmengine - INFO - <|im_start|> system +You are an AI assistant whose name is InternLM (书生·浦语).<|im_end|><|im_start|>user + +请从这张聊天截图中提取结构化信息<|im_end|><|im_start|> assistant +{ + "dialog_name": "<对方正在输入...", + "conversation": [ + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "不是", + "message_bbox": { + "min_x": 917, + "max_x": 989, + "min_y": 253, + "max_y": 289 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "在淘宝里", + "message_bbox": { + "min_x": 839, + "max_x": 987, + "min_y": 370, + "max_y": 404 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "不能发微信", + "message_bbox": { + "min_x": 801, + "max_x": 989, + "min_y": 485, + "max_y": 521 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "两字", + "message_bbox": { + "min_x": 915, + "max_x": 988, + "min_y": 601, + "max_y": 637 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "微信", + "message_bbox": { + "min_x": 916, + "max_x": 990, + "min_y": 718, + "max_y": 753 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "①微信", + "message_bbox": { + "min_x": 845, + "max_x": 988, + "min_y": 833, + "max_y": 869 + }, + "image": "", + "transfer": [], + "file": [] + } + ] +}<|im_end|> +2024/08/25 10:45:07 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io +2024/08/25 10:45:07 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. +2024/08/25 10:45:07 - mmengine - INFO - Checkpoints will be saved to /root/wangqun/work_dirs/internvl_ft_run_11_filter. +2024/08/25 10:45:07 - mmengine - DEBUG - The `end` of is not set. Use the max epochs/iters of train loop as default. +2024/08/25 10:45:07 - mmengine - DEBUG - The `end` of is not set. Use the max epochs/iters of train loop as default. +2024/08/25 10:45:07 - mmengine - INFO - Num train samples 4806 +2024/08/25 10:45:07 - mmengine - INFO - train example: +2024/08/25 10:45:08 - mmengine - INFO - <|im_start|> system +You are an AI assistant whose name is InternLM (书生·浦语).<|im_end|><|im_start|>user + +请从这张聊天截图中提取结构化信息<|im_end|><|im_start|> assistant +{ + "dialog_name": "<对方正在输入...", + "conversation": [ + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "不是", + "message_bbox": { + "min_x": 917, + "max_x": 989, + "min_y": 253, + "max_y": 289 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "在淘宝里", + "message_bbox": { + "min_x": 839, + "max_x": 987, + "min_y": 370, + "max_y": 404 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "不能发微信", + "message_bbox": { + "min_x": 801, + "max_x": 989, + "min_y": 485, + "max_y": 521 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "两字", + "message_bbox": { + "min_x": 915, + "max_x": 988, + "min_y": 601, + "max_y": 637 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "微信", + "message_bbox": { + "min_x": 916, + "max_x": 990, + "min_y": 718, + "max_y": 753 + }, + "image": "", + "transfer": [], + "file": [] + }, + { + "timestamp": "", + "speaker": "<对方正在输入...", + "content": "①微信", + "message_bbox": { + "min_x": 845, + "max_x": 988, + "min_y": 833, + "max_y": 869 + }, + "image": "", + "transfer": [], + "file": [] + } + ] +}<|im_end|> +2024/08/25 10:45:08 - mmengine - WARNING - "FileClient" will be deprecated in future. Please use io functions in https://mmengine.readthedocs.io/en/latest/api/fileio.html#file-io +2024/08/25 10:45:08 - mmengine - WARNING - "HardDiskBackend" is the alias of "LocalBackend" and the former will be deprecated in future. +2024/08/25 10:45:08 - mmengine - INFO - Checkpoints will be saved to /root/wangqun/work_dirs/internvl_ft_run_11_filter.