search

InternLM / Tutorial

LLM Tutorial
1.06k stars 451 forks source link

importlib.metadata.PackageNotFoundError: No package metadata was found for xtuner #282

Open Aorg opened 6 months ago

Aorg commented 6 months ago

反复按照教程安装出现这个问题： (xtuner0.1.9) root@intern-studio:~/xtuner019/xtuner# xtuner Traceback (most recent call last): File "/root/.local/bin/xtuner", line 33, in sys.exit(load_entry_point('xtuner', 'console_scripts', 'xtuner')()) File "/root/.local/bin/xtuner", line 22, in importlib_load_entry_point for entry_point in distribution(dist_name).entry_points File "/share/conda_envs/internlm-base/lib/python3.10/importlib/metadata/init.py", line 969, in distribution return Distribution.from_name(distribution_name) File "/share/conda_envs/internlm-base/lib/python3.10/importlib/metadata/init.py", line 548, in from_name raise PackageNotFoundError(name) importlib.metadata.PackageNotFoundError: No package metadata was found for xtuner

之前可以训练，后来更换参数和数据报以下错误，就直接尝试在base环境里安装就出现上面的错误。 nohup: ignoring input [2024-01-11 19:09:22,787] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-01-11 19:10:00,577] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect) 01/11 19:10:22 - 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 numpy_random_seed: 716082487 GPU 0: NVIDIA A100-SXM4-80GB CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.7, V11.7.99 GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0 PyTorch: 2.0.1 PyTorch compiling details: PyTorch built with:

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

01/11 19:10:22 - mmengine - INFO - Config: SYSTEM = '' accumulative_counts = 16 batch_size = 1 betas = ( 0.9, 0.999, ) custom_hooks = [ dict( tokenizer=dict( padding_side='right', pretrained_model_name_or_path= '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b', trust_remote_code=True, type='transformers.AutoTokenizer.from_pretrained'), type='xtuner.engine.DatasetInfoHook'), dict( evaluation_inputs=[ '请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai', ], every_n_iters=500, prompt_template='xtuner.utils.PROMPT_TEMPLATE.internlm_chat', system='', tokenizer=dict( padding_side='right', pretrained_model_name_or_path= '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b', trust_remote_code=True, type='transformers.AutoTokenizer.from_pretrained'), type='xtuner.engine.EvaluateChatHook'), ] data_path = '/root/code/xturn/grade-school-math/grade_school_math/data/new' dataloader_num_workers = 0 default_hooks = dict( checkpoint=dict(interval=1, type='mmengine.hooks.CheckpointHook'), logger=dict(interval=10, 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)) evaluation_freq = 500 evaluation_inputs = [ '请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai', ] launcher = 'none' load_from = None log_level = 'INFO' lr = 0.0002 max_epochs = 3 max_length = 2048 max_norm = 1 model = dict( llm=dict( pretrained_model_name_or_path= '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b', quantization_config=dict( bnb_4bit_compute_dtype='torch.float16', bnb_4bit_quant_type='nf4', bnb_4bit_use_double_quant=True, llm_int8_has_fp16_weight=False, llm_int8_threshold=6.0, load_in_4bit=True, load_in_8bit=False, type='transformers.BitsAndBytesConfig'), torch_dtype='torch.float16', trust_remote_code=True, type='transformers.AutoModelForCausalLM.from_pretrained'), lora=dict( bias='none', lora_alpha=16, lora_dropout=0.1, r=64, task_type='CAUSAL_LM', type='peft.LoraConfig'), type='xtuner.model.SupervisedFinetune') optim_type = 'bitsandbytes.optim.PagedAdamW32bit' optim_wrapper = dict( optimizer=dict( betas=( 0.9, 0.999, ), lr=0.0002, type='bitsandbytes.optim.PagedAdamW32bit', weight_decay=0), type='DeepSpeedOptimWrapper') pack_to_max_length = True param_scheduler = dict( T_max=3, by_epoch=True, convert_to_iter_based=True, eta_min=0.0, type='mmengine.optim.CosineAnnealingLR') pretrained_model_name_or_path = '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b' prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.internlm_chat' randomness = dict(deterministic=False, seed=None) resume = False runner_type = 'FlexibleRunner' 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=16, gradient_clipping=1, train_micro_batch_size_per_gpu=1, type='DeepSpeedStrategy') tokenizer = dict( padding_side='right', pretrained_model_name_or_path= '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b', trust_remote_code=True, type='transformers.AutoTokenizer.from_pretrained') train_cfg = dict(by_epoch=True, max_epochs=3, val_interval=1) train_dataloader = dict( batch_size=1, collate_fn=dict(type='xtuner.dataset.collate_fns.default_collate_fn'), dataset=dict( dataset=dict( path= '/root/code/xturn/grade-school-math/grade_school_math/data/new', type='datasets.load_dataset'), dataset_map_fn='xtuner.dataset.map_fns.oasst1_map_fn', max_length=2048, pack_to_max_length=True, remove_unused_columns=True, shuffle_before_pack=True, template_map_fn=dict( template='xtuner.utils.PROMPT_TEMPLATE.internlm_chat', type='xtuner.dataset.map_fns.template_map_fn_factory'), tokenizer=dict( padding_side='right', pretrained_model_name_or_path= '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b', trust_remote_code=True, type='transformers.AutoTokenizer.from_pretrained'), type='xtuner.dataset.process_hf_dataset'), num_workers=0, sampler=dict(shuffle=True, type='mmengine.dataset.DefaultSampler')) train_dataset = dict( dataset=dict( path='/root/code/xturn/grade-school-math/grade_school_math/data/new', type='datasets.load_dataset'), dataset_map_fn='xtuner.dataset.map_fns.oasst1_map_fn', max_length=2048, pack_to_max_length=True, remove_unused_columns=True, shuffle_before_pack=True, template_map_fn=dict( template='xtuner.utils.PROMPT_TEMPLATE.internlm_chat', type='xtuner.dataset.map_fns.template_map_fn_factory'), tokenizer=dict( padding_side='right', pretrained_model_name_or_path= '/root/model/Shanghai_AI_Laboratory/internlm-chat-7b', trust_remote_code=True, type='transformers.AutoTokenizer.from_pretrained'), type='xtuner.dataset.process_hf_dataset') visualizer = None weight_decay = 0 work_dir = './work_dirs/internlm_chat_7b_qlora_oasst1_e3_copy'

01/11 19:10:23 - 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. 01/11 19:10:24 - 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
(NORMAL ) EvaluateChatHook
(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
(NORMAL ) EvaluateChatHook
(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
(NORMAL ) EvaluateChatHook

after_train: (VERY_HIGH ) RuntimeInfoHook
(NORMAL ) EvaluateChatHook
(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

01/11 19:10:26 - mmengine - WARNING - Dataset Dataset has no metainfo. dataset_meta in visualizer will be None. quantization_config convert to <class 'transformers.utils.quantization_config.BitsAndBytesConfig'>

Loading checkpoint shards: 0%| | 0/8 [00:00<?, ?it/s] Loading checkpoint shards: 12%|█▎ | 1/8 [00:03<00:23, 3.34s/it] Loading checkpoint shards: 25%|██▌ | 2/8 [00:06<00:19, 3.30s/it] Loading checkpoint shards: 38%|███▊ | 3/8 [00:09<00:16, 3.25s/it] Loading checkpoint shards: 50%|█████ | 4/8 [00:12<00:12, 3.17s/it] Loading checkpoint shards: 62%|██████▎ | 5/8 [00:16<00:09, 3.20s/it] Loading checkpoint shards: 75%|███████▌ | 6/8 [00:20<00:07, 3.65s/it] Loading checkpoint shards: 88%|████████▊ | 7/8 [00:23<00:03, 3.43s/it] Loading checkpoint shards: 100%|██████████| 8/8 [00:24<00:00, 2.55s/it] Loading checkpoint shards: 100%|██████████| 8/8 [00:24<00:00, 3.04s/it] 01/11 19:10:53 - mmengine - INFO - dispatch internlm attn forward 01/11 19:10:53 - mmengine - WARNING - Due to the implementation of the PyTorch version of flash attention, even when the output_attentions flag is set to True, it is not possible to return the attn_weights. [2024-01-11 19:11:48,486] [INFO] [logging.py:96:log_dist] [Rank -1] DeepSpeed info: version=0.12.6, git-hash=unknown, git-branch=unknown [2024-01-11 19:11:48,486] [INFO] [comm.py:637:init_distributed] cdb=None [2024-01-11 19:11:48,486] [INFO] [comm.py:652:init_distributed] Not using the DeepSpeed or dist launchers, attempting to detect MPI environment... [2024-01-11 19:11:48,653] [INFO] [comm.py:702:mpi_discovery] Discovered MPI settings of world_rank=0, local_rank=0, world_size=1, master_addr=192.168.237.56, master_port=29500 [2024-01-11 19:11:48,653] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl [2024-01-11 19:11:49,014] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False [2024-01-11 19:11:49,019] [INFO] [logging.py:96:log_dist] [Rank 0] Using client Optimizer as basic optimizer [2024-01-11 19:11:49,019] [INFO] [logging.py:96:log_dist] [Rank 0] Removing param_group that has no 'params' in the basic Optimizer [2024-01-11 19:11:49,089] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Basic Optimizer = PagedAdamW32bit [2024-01-11 19:11:49,089] [INFO] [utils.py:56:is_zero_supported_optimizer] Checking ZeRO support for optimizer=PagedAdamW32bit type=<class 'bitsandbytes.optim.adamw.PagedAdamW32bit'> [2024-01-11 19:11:49,089] [WARNING] [engine.py:1166:_do_optimizer_sanity_check] ** You are using ZeRO with an untested optimizer, proceed with caution ***** [2024-01-11 19:11:49,089] [INFO] [logging.py:96:log_dist] [Rank 0] Creating torch.bfloat16 ZeRO stage 2 optimizer [2024-01-11 19:11:49,090] [INFO] [stage_1_and_2.py:148:init] Reduce bucket size 500,000,000 [2024-01-11 19:11:49,090] [INFO] [stage_1_and_2.py:149:init] Allgather bucket size 500,000,000 [2024-01-11 19:11:49,090] [INFO] [stage_1_and_2.py:150:init] CPU Offload: False [2024-01-11 19:11:49,090] [INFO] [stage_1_and_2.py:151:init] Round robin gradient partitioning: False [2024-01-11 19:11:51,497] [INFO] [utils.py:791:see_memory_usage] Before initializing optimizer states [2024-01-11 19:11:51,498] [INFO] [utils.py:792:see_memory_usage] MA 5.63 GB Max_MA 5.93 GB CA 6.31 GB Max_CA 6 GB [2024-01-11 19:11:51,498] [INFO] [utils.py:799:see_memory_usage] CPU Virtual Memory: used = 105.09 GB, percent = 5.2% [2024-01-11 19:11:51,748] [INFO] [utils.py:791:see_memory_usage] After initializing optimizer states [2024-01-11 19:11:51,748] [INFO] [utils.py:792:see_memory_usage] MA 5.63 GB Max_MA 6.23 GB CA 6.91 GB Max_CA 7 GB [2024-01-11 19:11:51,749] [INFO] [utils.py:799:see_memory_usage] CPU Virtual Memory: used = 105.32 GB, percent = 5.2% [2024-01-11 19:11:51,749] [INFO] [stage_1_and_2.py:516:init] optimizer state initialized [2024-01-11 19:11:51,870] [INFO] [utils.py:791:see_memory_usage] After initializing ZeRO optimizer [2024-01-11 19:11:51,871] [INFO] [utils.py:792:see_memory_usage] MA 5.63 GB Max_MA 5.63 GB CA 6.91 GB Max_CA 7 GB [2024-01-11 19:11:51,871] [INFO] [utils.py:799:see_memory_usage] CPU Virtual Memory: used = 105.39 GB, percent = 5.2% [2024-01-11 19:11:51,882] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Final Optimizer = PagedAdamW32bit [2024-01-11 19:11:51,882] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed using client LR scheduler [2024-01-11 19:11:51,882] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed LR Scheduler = None [2024-01-11 19:11:51,882] [INFO] [logging.py:96:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0002], mom=[(0.9, 0.999)] [2024-01-11 19:11:51,886] [INFO] [config.py:984:print] DeepSpeedEngine configuration: [2024-01-11 19:11:51,886] [INFO] [config.py:988:print] activation_checkpointing_config { "partition_activations": false, "contiguous_memory_optimization": false, "cpu_checkpointing": false, "number_checkpoints": null, "synchronize_checkpoint_boundary": false, "profile": false } [2024-01-11 19:11:51,886] [INFO] [config.py:988:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} [2024-01-11 19:11:51,886] [INFO] [config.py:988:print] amp_enabled .................. False [2024-01-11 19:11:51,886] [INFO] [config.py:988:print] amp_params ................... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] autotuning_config ............ { "enabled": false, "start_step": null, "end_step": null, "metric_path": null, "arg_mappings": null, "metric": "throughput", "model_info": null, "results_dir": "autotuning_results", "exps_dir": "autotuning_exps", "overwrite": true, "fast": true, "start_profile_step": 3, "end_profile_step": 5, "tuner_type": "gridsearch", "tuner_early_stopping": 5, "tuner_num_trials": 50, "model_info_path": null, "mp_size": 1, "max_train_batch_size": null, "min_train_batch_size": 1, "max_train_micro_batch_size_per_gpu": 1.024000e+03, "min_train_micro_batch_size_per_gpu": 1, "num_tuning_micro_batch_sizes": 3 } [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] bfloat16_enabled ............. True [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] checkpoint_parallel_write_pipeline False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] checkpoint_tag_validation_enabled True [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] checkpoint_tag_validation_fail False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x7f0b4ba0bee0> [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] communication_data_type ...... None [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] compression_config ........... {'weight_quantization': {'shared_parameters': {'enabled': False, 'quantizer_kernel': False, 'schedule_offset': 0, 'quantize_groups': 1, 'quantize_verbose': False, 'quantization_type': 'symmetric', 'quantize_weight_in_forward': False, 'rounding': 'nearest', 'fp16_mixed_quantize': False, 'quantize_change_ratio': 0.001}, 'different_groups': {}}, 'activation_quantization': {'shared_parameters': {'enabled': False, 'quantization_type': 'symmetric', 'range_calibration': 'dynamic', 'schedule_offset': 1000}, 'different_groups': {}}, 'sparse_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'row_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'head_pruning': {'shared_parameters': {'enabled': False, 'method': 'topk', 'schedule_offset': 1000}, 'different_groups': {}}, 'channel_pruning': {'shared_parameters': {'enabled': False, 'method': 'l1', 'schedule_offset': 1000}, 'different_groups': {}}, 'layer_reduction': {'enabled': False}} [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] curriculum_enabled_legacy .... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] curriculum_params_legacy ..... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}} [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] data_efficiency_enabled ...... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] dataloader_drop_last ......... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] disable_allgather ............ False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] dump_state ................... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] dynamic_loss_scale_args ...... None [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_enabled ........... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_gas_boundary_resolution 1 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_layer_name ........ bert.encoder.layer [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_layer_num ......... 0 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_max_iter .......... 100 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_stability ......... 1e-06 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_tol ............... 0.01 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] eigenvalue_verbose ........... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] elasticity_enabled ........... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] flops_profiler_config ........ { "enabled": false, "recompute_fwd_factor": 0.0, "profile_step": 1, "module_depth": -1, "top_modules": 1, "detailed": true, "output_file": null } [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] fp16_auto_cast ............... None [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] fp16_enabled ................. False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] fp16_master_weights_and_gradients False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] global_rank .................. 0 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] grad_accum_dtype ............. None [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] gradient_accumulation_steps .. 16 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] gradient_clipping ............ 1 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] gradient_predivide_factor .... 1.0 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] graph_harvesting ............. False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] initial_dynamic_scale ........ 1 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] load_universal_checkpoint .... False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] loss_scale ................... 1.0 [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] memory_breakdown ............. False [2024-01-11 19:11:51,887] [INFO] [config.py:988:print] mics_hierarchial_params_gather False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] mics_shard_size .............. -1 [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] nebula_config ................ { "enabled": false, "persistent_storage_path": null, "persistent_time_interval": 100, "num_of_version_in_retention": 2, "enable_nebula_load": true, "load_path": null } [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] optimizer_legacy_fusion ...... False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] optimizer_name ............... None [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] optimizer_params ............. None [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0, 'pipe_partitioned': True, 'grad_partitioned': True} [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] pld_enabled .................. False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] pld_params ................... False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] prescale_gradients ........... False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] scheduler_name ............... None [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] scheduler_params ............. None [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] seq_parallel_communication_data_type torch.float32 [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] sparse_attention ............. None [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] sparse_gradients_enabled ..... False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] steps_per_print .............. 10000000000000 [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] train_batch_size ............. 16 [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] train_micro_batch_size_per_gpu 1 [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] use_data_before_expertparallel False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] use_node_local_storage ....... False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] wall_clock_breakdown ......... False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] weight_quantization_config ... None [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] world_size ................... 1 [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] zero_allow_untested_optimizer True [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] zero_config .................. stage=2 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500,000,000 use_multi_rank_bucket_allreduce=True allgather_partitions=True allgather_bucket_size=500,000,000 overlap_comm=True load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1,000,000,000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50,000,000 param_persistence_threshold=100,000 model_persistence_threshold=sys.maxsize max_live_parameters=1,000,000,000 max_reuse_distance=1,000,000,000 gather_16bit_weights_on_model_save=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False zero_hpz_partition_size=1 zero_quantized_weights=False zero_quantized_nontrainable_weights=False zero_quantized_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=True pipeline_loading_checkpoint=False override_module_apply=True [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] zero_enabled ................. True [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] zero_force_ds_cpu_optimizer .. False [2024-01-11 19:11:51,888] [INFO] [config.py:988:print] zero_optimization_stage ...... 2 [2024-01-11 19:11:51,888] [INFO] [config.py:974:print_user_config] json = { "gradient_accumulation_steps": 16, "train_micro_batch_size_per_gpu": 1, "gradient_clipping": 1, "zero_allow_untested_optimizer": true, "zero_force_ds_cpu_optimizer": false, "zero_optimization": { "stage": 2, "overlap_comm": true }, "fp16": { "enabled": false, "initial_scale_power": 16 }, "bf16": { "enabled": true }, "steps_per_print": 1.000000e+13 } Traceback (most recent call last): File "/root/xtuner019/xtuner/xtuner/tools/train.py", line 260, in main() File "/root/xtuner019/xtuner/xtuner/tools/train.py", line 256, in main runner.train() File "/root/.local/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 1182, in train self.strategy.prepare( File "/root/.local/lib/python3.10/site-packages/mmengine/_strategy/deepspeed.py", line 389, in prepare self.param_schedulers = self.build_param_scheduler( File "/root/.local/lib/python3.10/site-packages/mmengine/_strategy/base.py", line 658, in build_param_scheduler param_schedulers = self._build_param_scheduler( File "/root/.local/lib/python3.10/site-packages/mmengine/_strategy/base.py", line 563, in _build_param_scheduler PARAM_SCHEDULERS.build( File "/root/.local/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build return self.build_func(cfg, *args, kwargs, registry=self) File "/root/.local/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 294, in build_scheduler_from_cfg return scheduler_cls.build_iter_from_epoch( # type: ignore File "/root/.local/lib/python3.10/site-packages/mmengine/optim/scheduler/param_scheduler.py", line 663, in build_iter_from_epoch assert epoch_length is not None and epoch_length > 0, \ AssertionError: epoch_length must be a positive integer, but got 0. 请各位大佬看看

Guardian-in-the-WF commented 2 months ago

关于报错importlib.metadata.PackageNotFoundError: No package metadata was found for xtuner，安装xtuner所有依赖。 git clone https://github.com/InternLM/xtuner.git cd xtuner pip install -e '.[all]'