InternLM
执行 NPROC_PER_NODE=2 xtuner train /root/StableDiffusionGPT/config/internlm2_1_8b_qlora_alpaca_e3_copy.py --work-dir /root/test/ft/train --deepspeed deepspeed_zero2 指令运行报错
error log： Generating train split: 3457 examples [00:00, 14292.20 examples/s] Map (num_proc=32): 0%| | 0/3457 [00:00<?, ? examples/s] [rank0]: multiprocess.pool.RemoteTraceback: [rank0]: """ [rank0]: Traceback (most recent call last): [rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/multiprocess/pool.py", line 125, in worker [rank0]: result = (True, func(*args, **kwds)) [rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/utils/py_utils.py", line 623, in _write_generator_to_queue [rank0]: for i, result in enumerate(func(**kwargs)): [rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3458, in _map_single [rank0]: example = apply_function_on_filtered_inputs(example, i, offset=offset) [rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3361, in apply_function_on_filtered_inputs [rank0]: processed_inputs = function(*fn_args, *additional_args, **fn_kwargs) [rank0]: File "/root/test/xtuner/xtuner/dataset/map_fns/dataset_map_fns/openai_map_fn.py", line 22, in openai_map_fn [rank0]: messages = example['messages'] [rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/formatting/formatting.py", line 270, in getitem [rank0]: value = self.data[key] [rank0]: KeyError: 'messages' [rank0]: """
[rank0]: The above exception was the direct cause of the following exception:
[rank0]: Traceback (most recent call last):
[rank0]: File "/root/test/xtuner/xtuner/tools/train.py", line 360, in
[rank0]: main()
[rank0]: File "/root/test/xtuner/xtuner/tools/train.py", line 356, in main
[rank0]: runner.train()
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 1160, in train
[rank0]: self._train_loop = self.build_train_loop(
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 958, in build_train_loop
[rank0]: loop = LOOPS.build(
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
[rank0]: return self.build_func(cfg, *args, **kwargs, registry=self)
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
[rank0]: obj = obj_cls(**args) # type: ignore
[rank0]: File "/root/test/xtuner/xtuner/engine/runner/loops.py", line 32, in init
[rank0]: dataloader = runner.build_dataloader(
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 824, in build_dataloader
[rank0]: dataset = DATASETS.build(dataset_cfg)
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
[rank0]: return self.build_func(cfg, *args, **kwargs, registry=self)
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
[rank0]: obj = obj_cls(**args) # type: ignore
[rank0]: File "/root/test/xtuner/xtuner/dataset/huggingface.py", line 308, in process_hf_dataset
[rank0]: dataset = process(**kwargs)
[rank0]: File "/root/test/xtuner/xtuner/dataset/huggingface.py", line 179, in process
[rank0]: dataset = map_dataset(dataset, dataset_map_fn, map_num_proc)
[rank0]: File "/root/test/xtuner/xtuner/dataset/huggingface.py", line 50, in map_dataset
[rank0]: dataset = dataset.map(dataset_map_fn, num_proc=map_num_proc)
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 593, in wrapper
[rank0]: out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 558, in wrapper
[rank0]: out: Union["Dataset", "DatasetDict"] = func(self, *args, **kwargs)
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/arrow_dataset.py", line 3197, in map
[rank0]: for rank, done, content in iflatmap_unordered(
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/utils/py_utils.py", line 663, in iflatmap_unordered
[rank0]: [async_result.get(timeout=0.05) for async_result in async_results]
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/datasets/utils/py_utils.py", line 663, in
[rank0]: [async_result.get(timeout=0.05) for async_result in async_results]
[rank0]: File "/root/.conda/envs/test/lib/python3.10/site-packages/multiprocess/pool.py", line 774, in get
[rank0]: raise self._value
[rank0]: KeyError: 'messages'
[rank1]:[E ProcessGroupGloo.cpp:144] Rank 1 successfully reached monitoredBarrier, but received errors while waiting for send/recv from rank 0. Please check rank 0 logs for faulty rank.
[rank1]: Traceback (most recent call last):
[rank1]: File "/root/test/xtuner/xtuner/tools/train.py", line 360, in
[rank1]: main()
[rank1]: File "/root/test/xtuner/xtuner/tools/train.py", line 356, in main
[rank1]: runner.train()
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 1160, in train
[rank1]: self._train_loop = self.build_train_loop(
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 958, in build_train_loop
[rank1]: loop = LOOPS.build(
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
[rank1]: return self.build_func(cfg, *args, **kwargs, registry=self)
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
[rank1]: obj = obj_cls(**args) # type: ignore
[rank1]: File "/root/test/xtuner/xtuner/engine/runner/loops.py", line 32, in init
[rank1]: dataloader = runner.build_dataloader(
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/runner/_flexible_runner.py", line 824, in build_dataloader
[rank1]: dataset = DATASETS.build(dataset_cfg)
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/registry.py", line 570, in build
[rank1]: return self.build_func(cfg, *args, **kwargs, registry=self)
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg
[rank1]: obj = obj_cls(**args) # type: ignore
[rank1]: File "/root/test/xtuner/xtuner/dataset/huggingface.py", line 313, in process_hf_dataset
[rank1]: dist.monitored_barrier(group=group_gloo, timeout=xtuner_dataset_timeout)
[rank1]: File "/root/.conda/envs/test/lib/python3.10/site-packages/torch/distributed/distributed_c10d.py", line 3763, in monitored_barrier
[rank1]: return group_to_use.monitored_barrier(timeout, wait_all_ranks=wait_all_ranks)
[rank1]: RuntimeError: Rank 1 successfully reached monitoredBarrier, but received errors while waiting for send/recv from rank 0. Please check rank 0 logs for faulty rank.
[rank1]: Original exception:
[rank1]: [../third_party/gloo/gloo/transport/tcp/pair.cc:534] Connection closed by peer [192.168.239.202]:35230
E0526 11:02:25.394000 139939038151872 torch/distributed/elastic/multiprocessing/api.py:826] failed (exitcode: 1) local_rank: 0 (pid: 7090) of binary: /root/.conda/envs/test/bin/python
Traceback (most recent call last):
File "/root/.conda/envs/test/bin/torchrun", line 8, in
sys.exit(main())
File "/root/.conda/envs/test/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/init.py", line 347, in wrapper
return f(*args, **kwargs)
File "/root/.conda/envs/test/lib/python3.10/site-packages/torch/distributed/run.py", line 879, in main
run(args)
File "/root/.conda/envs/test/lib/python3.10/site-packages/torch/distributed/run.py", line 870, in run
elastic_launch(
File "/root/.conda/envs/test/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 132, in call
return launch_agent(self._config, self._entrypoint, list(args))
File "/root/.conda/envs/test/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 263, in launch_agent
raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError:
/root/test/xtuner/xtuner/tools/train.py FAILED
Failures: [1]: time : 2024-05-26_11:02:25 host : intern-studio-083870 rank : 1 (local_rank: 1) exitcode : 1 (pid: 7091) error_file: <N/A> traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
Root Cause (first observed failure): [0]: time : 2024-05-26_11:02:25 host : intern-studio-083870 rank : 0 (local_rank: 0) exitcode : 1 (pid: 7090) error_file: <N/A> traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
配置有做啥更改吗？我看错误信息是：
[rank0]: value = self.data[key]
[rank0]: KeyError: 'messages'
配置有做啥更改吗？我看错误信息是：
[rank0]: value = self.data[key] [rank0]: KeyError: 'messages'
this config ↓ ↓
Copyright (c) OpenMMLab. All rights reserved.
import torch from datasets import load_dataset from mmengine.dataset import DefaultSampler from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook, LoggerHook, ParamSchedulerHook) from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR from peft import LoraConfig from torch.optim import AdamW from transformers import (AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig)
from xtuner.dataset import process_hf_dataset from xtuner.dataset.collate_fns import default_collate_fn from xtuner.dataset.map_fns import openai_map_fn, template_map_fn_factory from xtuner.engine.hooks import (DatasetInfoHook, EvaluateChatHook, VarlenAttnArgsToMessageHubHook) from xtuner.engine.runner import TrainLoop from xtuner.model import SupervisedFinetune from xtuner.parallel.sequence import SequenceParallelSampler from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE
#######################################################################
PART 1 Settings
#######################################################################
Model
pretrained_model_name_or_path = '/root/Test/ft/model/18b' use_varlen_attn = False
Data
alpaca_en_path = '/root/Test/ft/data/personal_assistant.json' prompt_template = PROMPT_TEMPLATE.default max_length = 2048 pack_to_max_length = True
parallel
sequence_parallel_size = 1
Scheduler & Optimizer
batch_size = 1 # per_device accumulative_counts = 16 accumulative_counts *= sequence_parallel_size dataloader_num_workers = 0 max_epochs = 2 optim_type = AdamW lr = 2e-4 betas = (0.9, 0.999) weight_decay = 0 max_norm = 1 # grad clip warmup_ratio = 0.03
Save
save_steps = 300 save_total_limit = 3 # Maximum checkpoints to keep (-1 means unlimited)
Evaluate the generation performance during the training
evaluation_freq = 300 SYSTEM = '' evaluation_inputs = [ '请介绍一下你自己', '帮我生成一个小男孩坐在椅子上看向电脑','一个小女孩坐在楼梯上','一只狸花猫趴在阳光下的沙滩上' ]
#######################################################################
PART 2 Model & Tokenizer
####################################################################### tokenizer = dict( type=AutoTokenizer.from_pretrained, pretrained_model_name_or_path=pretrained_model_name_or_path, trust_remote_code=True, padding_side='right')
model = dict( type=SupervisedFinetune, use_varlen_attn=use_varlen_attn, llm=dict( type=AutoModelForCausalLM.from_pretrained, pretrained_model_name_or_path=pretrained_model_name_or_path, trust_remote_code=True, torch_dtype=torch.float16, quantization_config=dict( type=BitsAndBytesConfig, load_in_4bit=True, load_in_8bit=False, llm_int8_threshold=6.0, llm_int8_has_fp16_weight=False, bnb_4bit_compute_dtype=torch.float16, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type='nf4')), lora=dict( type=LoraConfig, r=64, lora_alpha=16, lora_dropout=0.1, bias='none', task_type='CAUSAL_LM'))
#######################################################################
PART 3 Dataset & Dataloader
####################################################################### alpaca_en = dict( type=process_hf_dataset, dataset=dict(type=load_dataset, path='json', data_files=dict(train=alpaca_en_path)), tokenizer=tokenizer, max_length=max_length, dataset_map_fn=openai_map_fn, template_map_fn=dict( type=template_map_fn_factory, template=prompt_template), remove_unused_columns=True, shuffle_before_pack=True, pack_to_max_length=pack_to_max_length, use_varlen_attn=use_varlen_attn)
sampler = SequenceParallelSampler
if sequence_parallel_size > 1 else DefaultSampler
train_dataloader = dict(
batch_size=batch_size,
num_workers=dataloader_num_workers,
dataset=alpaca_en,
sampler=dict(type=sampler, shuffle=True),
collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn))
#######################################################################
PART 4 Scheduler & Optimizer
#######################################################################
optimizer
optim_wrapper = dict( type=AmpOptimWrapper, optimizer=dict( type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay), clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False), accumulative_counts=accumulative_counts, loss_scale='dynamic', dtype='float16')
learning policy
More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501
param_scheduler = [ dict( type=LinearLR, start_factor=1e-5, by_epoch=True, begin=0, end=warmup_ratio * max_epochs, convert_to_iter_based=True), dict( type=CosineAnnealingLR, eta_min=0.0, by_epoch=True, begin=warmup_ratio * max_epochs, end=max_epochs, convert_to_iter_based=True) ]
train, val, test setting
train_cfg = dict(type=TrainLoop, max_epochs=max_epochs)
#######################################################################
PART 5 Runtime
#######################################################################
Log the dialogue periodically during the training process, optional
custom_hooks = [ dict(type=DatasetInfoHook, tokenizer=tokenizer), dict( type=EvaluateChatHook, tokenizer=tokenizer, every_n_iters=evaluation_freq, evaluation_inputs=evaluation_inputs, system=SYSTEM, prompt_template=prompt_template) ]
if use_varlen_attn: custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)]
configure default hooks
default_hooks = dict(
# record the time of every iteration.
timer=dict(type=IterTimerHook),
# print log every 10 iterations.
logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10),
# enable the parameter scheduler.
param_scheduler=dict(type=ParamSchedulerHook),
# save checkpoint per save_steps.
checkpoint=dict(
type=CheckpointHook,
by_epoch=False,
interval=save_steps,
max_keep_ckpts=save_total_limit),
# set sampler seed in distributed evrionment.
sampler_seed=dict(type=DistSamplerSeedHook),
)
configure environment
env_cfg = dict( # whether to enable cudnn benchmark cudnn_benchmark=False, # set multi process parameters mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), # set distributed parameters dist_cfg=dict(backend='nccl'), )
set visualizer
visualizer = None
set log level
log_level = 'INFO'
load from which checkpoint
load_from = None
whether to resume training from the loaded checkpoint
resume = False
Defaults to use random seed and disable deterministic
randomness = dict(seed=None, deterministic=False)
set log processor
log_processor = dict(by_epoch=False)