报错FileNotFoundError: [Errno 2] No such file or directory: '/app/work_dirs/chatglm2_6b_qlora_lawyer_e3_copy/20240514_035914/vis_data/eval_outputs_iter_499.txt'

[rcejzibjks38]

修改tensorboard的日志目录后，当微调step执行到save_step时，报错FileNotFoundError: [Errno 2] No such file or directory: '/app/work_dirs/chatglm2_6b_qlora_lawyer_e3_copy/20240514_035914/vis_data/eval_outputs_iter_499.txt'.

debug发现是在到达save_step后，xtuner调用evaluate_chat_hook.py的_save_eval_output方法：

def _save_eval_output(self, runner, eval_outputs):
    save_path = os.path.join(runner.log_dir, 'vis_data',
                             f'eval_outputs_iter_{runner.iter}.txt')
    with open(save_path, 'w', encoding='utf-8') as f:
        for i, output in enumerate(eval_outputs):
            f.write(f'Eval output {i + 1}:\n{output}\n\n')

在该方法中，写死了vis_data目录，而在配置文件中改变了tensorboard的save_dir后，work_dir下的runner.log_dir不会产生vis_data目录，引起报错。

使用的复现配置文件如下：

# 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 mmengine.visualization import Visualizer, TensorboardVisBackend
from peft import LoraConfig
from torch.optim import AdamW
from transformers import (AutoModelForCausalLM, AutoTokenizer,
                          BitsAndBytesConfig)

from xtuner.dataset import ConcatDataset, process_hf_dataset
from xtuner.dataset.collate_fns import default_collate_fn
from xtuner.dataset.map_fns import (crime_kg_assitant_map_fn,
                                    law_reference_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.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE

#######################################################################
#                          PART 1  Settings                           #
#######################################################################
# Model
pretrained_model_name_or_path = '../weights/model-update/chatglm2-6b'
use_varlen_attn = False

# Data
# download data from https://github.com/LiuHC0428/LAW-GPT
crime_kg_assitant_path = '../datasets/Chinese-Lawyer/CrimeKgAssitant清洗后_52k.json'
law_reference_data_path = '../datasets/Chinese-Lawyer/训练数据_带法律依据_92k.json'
prompt_template = PROMPT_TEMPLATE.chatglm2
max_length = 1024
pack_to_max_length = True

# Scheduler & Optimizer
batch_size = 8  # per_device
accumulative_counts = 16
dataloader_num_workers = 16
max_epochs = 3
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 = 50
save_total_limit = 2  # Maximum checkpoints to keep (-1 means unlimited)

# Evaluate the generation performance during the training
evaluation_freq = 10
SYSTEM = SYSTEM_TEMPLATE.lawyer
evaluation_inputs = ['危害公共安全将受到什么惩罚？', '非法占有他人财物构成什么罪，将受到什么惩罚？']

#######################################################################
#                      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='left')

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                   #
#######################################################################
crime_kg_assitant = dict(
    type=process_hf_dataset,
    dataset=dict(
        type=load_dataset,
        path='json',
        data_files=dict(train=crime_kg_assitant_path)),
    tokenizer=tokenizer,
    max_length=max_length,
    dataset_map_fn=crime_kg_assitant_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)

law_reference_data = dict(
    type=process_hf_dataset,
    dataset=dict(
        type=load_dataset,
        path='json',
        data_files=dict(train=law_reference_data_path)),
    tokenizer=tokenizer,
    max_length=max_length,
    dataset_map_fn=law_reference_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)

train_dataset = dict(
    type=ConcatDataset, datasets=[crime_kg_assitant, law_reference_data])

train_dataloader = dict(
    batch_size=batch_size,
    num_workers=dataloader_num_workers,
    dataset=train_dataset,
    sampler=dict(type=DefaultSampler, 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 = dict(
    type=Visualizer,
    vis_backends=[dict(type=TensorboardVisBackend, save_dir='/task/events')]
)

# 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)

[HIT-cwh]

多谢您帮忙指出问题！这里确实是我们疏忽了。

如果您方便，能否帮忙提个 pr 修一下这个 bug，我们会尽快合入！非常感谢