代码运行问题 about lilt HOT 8 CLOSED

我的transformers库是4.25.1的

from lilt.

你好，我是东华大学的一名研究生。 很荣幸能够阅读你这么优秀的文章，并进行复现。现在我在运行你的实例代码时，碰到了一些问题： 希望你能抽空看看，解决一下。十分感谢！

transformer库的问题，改一下/LiLT/LiLTfinetune里面的init文件就行

from collections import OrderedDict
import types
from transformers import CONFIG_MAPPING, MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, MODEL_NAMES_MAPPING, TOKENIZER_MAPPING
from transformers.convert_slow_tokenizer import SLOW_TO_FAST_CONVERTERS, BertConverter, RobertaConverter, XLMRobertaConverter
try:
    from transformers.models.auto.modeling_auto import auto_class_factory
except:
    from transformers.models.auto.modeling_auto import _BaseAutoModelClass, auto_class_update

from .models.LiLTRobertaLike import (
    LiLTRobertaLikeConfig,
    LiLTRobertaLikeForRelationExtraction,
    LiLTRobertaLikeForTokenClassification,
    LiLTRobertaLikeTokenizer,
    LiLTRobertaLikeTokenizerFast,
)

CONFIG_MAPPING.update([("liltrobertalike", LiLTRobertaLikeConfig),])
MODEL_NAMES_MAPPING.update([("liltrobertalike", "LiLTRobertaLike"),])
TOKENIZER_MAPPING.update(
    [
        (LiLTRobertaLikeConfig, (LiLTRobertaLikeTokenizer, LiLTRobertaLikeTokenizerFast)),
    ]
)

with open('tag.txt', 'r') as tagf:
    TAG = tagf.read().lower()
assert TAG == 'monolingual' or TAG == 'multilingual', 'TAG is wrong. It should be monolingual or multilingual.'
if TAG == 'monolingual':
    SLOW_TO_FAST_CONVERTERS.update({"LiLTRobertaLikeTokenizer": RobertaConverter,})
elif TAG == 'multilingual':
    SLOW_TO_FAST_CONVERTERS.update({"LiLTRobertaLikeTokenizer": XLMRobertaConverter,})

MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING.update(
    [(LiLTRobertaLikeConfig, LiLTRobertaLikeForTokenClassification),]
)

MODEL_FOR_RELATION_EXTRACTION_MAPPING = OrderedDict(
    [(LiLTRobertaLikeConfig, LiLTRobertaLikeForRelationExtraction),]
)

try:
    AutoModelForTokenClassification = auto_class_factory(
        "AutoModelForTokenClassification", MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, head_doc="token classification")
except:
    cls = types.new_class("AutoModelForTokenClassification", (_BaseAutoModelClass,))
    cls._model_mapping = MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING
    cls.__name__ = "AutoModelForTokenClassification"

    AutoModelForTokenClassification = auto_class_update(cls, head_doc="token classification")


try:
    AutoModelForRelationExtraction = auto_class_factory(
        "AutoModelForRelationExtraction", MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, head_doc="relation extraction")
except:
    cls = types.new_class("AutoModelForRelationExtraction", (_BaseAutoModelClass,))
    cls._model_mapping = MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING
    cls.__name__ = "AutoModelForRelationExtraction"

    AutoModelForRelationExtraction = auto_class_update(cls, head_doc="relation extraction")

# AutoModelForTokenClassification = auto_class_factory(
#     "AutoModelForTokenClassification", MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, head_doc="token classification"
# )

# AutoModelForRelationExtraction = auto_class_factory(
#     "AutoModelForRelationExtraction", MODEL_FOR_RELATION_EXTRACTION_MAPPING, head_doc="relation extraction"
# )

第19行和20行，这里是为了更新transformer内的定义，因为transformer==4.5.1时，还没有lilt模型。

CONFIG_MAPPING.update([("liltrobertalike", LiLTRobertaLikeConfig),("lilt", LiLTRobertaLikeConfig),])
MODEL_NAMES_MAPPING.update([("liltrobertalike", "LiLTRobertaLike"),("lilt", "LiLTRobertaLike"),])

另外，楼主原本的问题，是packaging包的版本造成的，降级到packaging==21.0即可

from lilt.

看样子是某个库版本对不上

检查一下当前的环境配置，按照README里面的要求重新安装一下conda环境

from lilt.

就是按照readme里面的步骤安装的，出现了一样的问题

from lilt.

你好，我是东华大学的一名研究生。 很荣幸能够阅读你这么优秀的文章，并进行复现。现在我在运行你的实例代码时，碰到了一些问题： 希望你能抽空看看，解决一下。十分感谢！

transformer库的问题，改一下/LiLT/LiLTfinetune里面的init文件就行

from collections import OrderedDict
import types
from transformers import CONFIG_MAPPING, MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, MODEL_NAMES_MAPPING, TOKENIZER_MAPPING
from transformers.convert_slow_tokenizer import SLOW_TO_FAST_CONVERTERS, BertConverter, RobertaConverter, XLMRobertaConverter
try:
    from transformers.models.auto.modeling_auto import auto_class_factory
except:
    from transformers.models.auto.modeling_auto import _BaseAutoModelClass, auto_class_update

from .models.LiLTRobertaLike import (
    LiLTRobertaLikeConfig,
    LiLTRobertaLikeForRelationExtraction,
    LiLTRobertaLikeForTokenClassification,
    LiLTRobertaLikeTokenizer,
    LiLTRobertaLikeTokenizerFast,
)

CONFIG_MAPPING.update([("liltrobertalike", LiLTRobertaLikeConfig),])
MODEL_NAMES_MAPPING.update([("liltrobertalike", "LiLTRobertaLike"),])
TOKENIZER_MAPPING.update(
    [
        (LiLTRobertaLikeConfig, (LiLTRobertaLikeTokenizer, LiLTRobertaLikeTokenizerFast)),
    ]
)

with open('tag.txt', 'r') as tagf:
    TAG = tagf.read().lower()
assert TAG == 'monolingual' or TAG == 'multilingual', 'TAG is wrong. It should be monolingual or multilingual.'
if TAG == 'monolingual':
    SLOW_TO_FAST_CONVERTERS.update({"LiLTRobertaLikeTokenizer": RobertaConverter,})
elif TAG == 'multilingual':
    SLOW_TO_FAST_CONVERTERS.update({"LiLTRobertaLikeTokenizer": XLMRobertaConverter,})

MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING.update(
    [(LiLTRobertaLikeConfig, LiLTRobertaLikeForTokenClassification),]
)

MODEL_FOR_RELATION_EXTRACTION_MAPPING = OrderedDict(
    [(LiLTRobertaLikeConfig, LiLTRobertaLikeForRelationExtraction),]
)

try:
    AutoModelForTokenClassification = auto_class_factory(
        "AutoModelForTokenClassification", MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, head_doc="token classification")
except:
    cls = types.new_class("AutoModelForTokenClassification", (_BaseAutoModelClass,))
    cls._model_mapping = MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING
    cls.__name__ = "AutoModelForTokenClassification"

    AutoModelForTokenClassification = auto_class_update(cls, head_doc="token classification")


try:
    AutoModelForRelationExtraction = auto_class_factory(
        "AutoModelForRelationExtraction", MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, head_doc="relation extraction")
except:
    cls = types.new_class("AutoModelForRelationExtraction", (_BaseAutoModelClass,))
    cls._model_mapping = MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING
    cls.__name__ = "AutoModelForRelationExtraction"

    AutoModelForRelationExtraction = auto_class_update(cls, head_doc="relation extraction")

# AutoModelForTokenClassification = auto_class_factory(
#     "AutoModelForTokenClassification", MODEL_FOR_TOKEN_CLASSIFICATION_MAPPING, head_doc="token classification"
# )

# AutoModelForRelationExtraction = auto_class_factory(
#     "AutoModelForRelationExtraction", MODEL_FOR_RELATION_EXTRACTION_MAPPING, head_doc="relation extraction"
# )

from lilt.

在修改过__Init__.py文件，并将transformers库版本更新到4.25.1后。
我重新运行Semantic Entity Recognition on FUNSD的shell脚本文件
CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 examples/run_funsd.py \ --model_name_or_path lilt-roberta-en-base \ --tokenizer_name roberta-base \ --output_dir ser_funsd_lilt-roberta-en-base \ --do_train \ --do_predict \ --max_steps 2000 \ --per_device_train_batch_size 8 \ --warmup_ratio 0.1 \ --fp16
出现以下报错，貌似是程序中的关键字中断了程序运行。
`*****************************************
Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed.

WARNING:main:Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: True
INFO:main:Training/evaluation parameters TrainingArguments(
_n_gpu=1,
adafactor=False,
adam_beta1=0.9,
adam_beta2=0.999,
adam_epsilon=1e-08,
auto_find_batch_size=False,
bf16=False,
bf16_full_eval=False,
data_seed=None,
dataloader_drop_last=False,
dataloader_num_workers=0,
dataloader_pin_memory=True,
ddp_bucket_cap_mb=None,
ddp_find_unused_parameters=None,
ddp_timeout=1800,
debug=[],
deepspeed=None,
disable_tqdm=False,
do_eval=False,
do_predict=True,
do_train=True,
eval_accumulation_steps=None,
eval_delay=0,
eval_steps=None,
evaluation_strategy=no,
fp16=True,
fp16_backend=auto,
fp16_full_eval=False,
fp16_opt_level=O1,
fsdp=[],
fsdp_min_num_params=0,
fsdp_transformer_layer_cls_to_wrap=None,
full_determinism=False,
gradient_accumulation_steps=1,
gradient_checkpointing=False,
greater_is_better=None,
group_by_length=False,
half_precision_backend=auto,
hub_model_id=None,
hub_private_repo=False,
hub_strategy=every_save,
hub_token=<HUB_TOKEN>,
ignore_data_skip=False,
include_inputs_for_metrics=False,
jit_mode_eval=False,
label_names=None,
label_smoothing_factor=0.0,
learning_rate=5e-05,
length_column_name=length,
load_best_model_at_end=False,
local_rank=0,
log_level=passive,
log_level_replica=passive,
log_on_each_node=True,
logging_dir=ser_funsd_lilt-roberta-en-base/runs/Feb20_16-07-29_dgx,
logging_first_step=False,
logging_nan_inf_filter=True,
logging_steps=500,
logging_strategy=steps,
lr_scheduler_type=linear,
max_grad_norm=1.0,
max_steps=2000,
metric_for_best_model=None,
mp_parameters=,
no_cuda=False,
num_train_epochs=3.0,
optim=adamw_hf,
optim_args=None,
output_dir=ser_funsd_lilt-roberta-en-base,
overwrite_output_dir=False,
past_index=-1,
per_device_eval_batch_size=8,
per_device_train_batch_size=8,
prediction_loss_only=False,
push_to_hub=False,
push_to_hub_model_id=None,
push_to_hub_organization=None,
push_to_hub_token=<PUSH_TO_HUB_TOKEN>,
ray_scope=last,
remove_unused_columns=True,
report_to=['tensorboard'],
resume_from_checkpoint=None,
run_name=ser_funsd_lilt-roberta-en-base,
save_on_each_node=False,
save_steps=500,
save_strategy=steps,
save_total_limit=None,
seed=42,
sharded_ddp=[],
skip_memory_metrics=True,
tf32=None,
torchdynamo=None,
tpu_metrics_debug=False,
tpu_num_cores=None,
use_ipex=False,
use_legacy_prediction_loop=False,
use_mps_device=False,
warmup_ratio=0.1,
warmup_steps=0,
weight_decay=0.0,
xpu_backend=None,
)
Downloading and preparing dataset funsd/funsd (download: Unknown size, generated: Unknown size, post-processed: Unknown size, total: Unknown size) to /home/pm-gaojun/.cache/huggingface/datasets/funsd/funsd/1.0.0/f64b3b868c231da8090a3d527c1376c082b0afb5873ddb1e65e9f1005c919106...
WARNING:main:Process rank: 2, device: cuda:2, n_gpu: 1distributed training: True, 16-bits training: True
WARNING:main:Process rank: 1, device: cuda:1, n_gpu: 1distributed training: True, 16-bits training: True
WARNING:main:Process rank: 3, device: cuda:3, n_gpu: 1distributed training: True, 16-bits training: True
Downloading: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16.8M/16.8M [09:12<00:00, 30.5kB/s]
Dataset funsd downloaded and prepared to /home/pm-gaojun/.cache/huggingface/datasets/funsd/funsd/1.0.0/f64b3b868c231da8090a3d527c1376c082b0afb5873ddb1e65e9f1005c919106. Subsequent calls will reuse this data.
WARNING:datasets.builder:Reusing dataset funsd (/home/pm-gaojun/.cache/huggingface/datasets/funsd/funsd/1.0.0/f64b3b868c231da8090a3d527c1376c082b0afb5873ddb1e65e9f1005c919106)
WARNING:datasets.builder:Reusing dataset funsd (/home/pm-gaojun/.cache/huggingface/datasets/funsd/funsd/1.0.0/f64b3b868c231da8090a3d527c1376c082b0afb5873ddb1e65e9f1005c919106)
[INFO|configuration_utils.py:652] 2023-02-20 16:16:54,487 >> loading configuration file lilt-roberta-en-base/config.json
Traceback (most recent call last):
File "examples/run_funsd.py", line 369, in
main()
File "examples/run_funsd.py", line 135, in main
use_auth_token=True if model_args.use_auth_token else None,
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 829, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 536, in getitem
raise KeyError(key)
KeyError: 'liltrobertalike'
Traceback (most recent call last):
Traceback (most recent call last):
File "examples/run_funsd.py", line 369, in
File "examples/run_funsd.py", line 369, in
main()main()

File "examples/run_funsd.py", line 135, in main
File "examples/run_funsd.py", line 135, in main
use_auth_token=True if model_args.use_auth_token else None,
use_auth_token=True if model_args.use_auth_token else None, File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 829, in from_pretrained

File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 829, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 536, in getitem
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 536, in getitem
raise KeyError(key)raise KeyError(key)

KeyError: KeyError'liltrobertalike'
: 'liltrobertalike'
WARNING:datasets.builder:Reusing dataset funsd (/home/pm-gaojun/.cache/huggingface/datasets/funsd/funsd/1.0.0/f64b3b868c231da8090a3d527c1376c082b0afb5873ddb1e65e9f1005c919106)
Traceback (most recent call last):
File "examples/run_funsd.py", line 369, in
main()
File "examples/run_funsd.py", line 135, in main
use_auth_token=True if model_args.use_auth_token else None,
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 829, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/transformers/models/auto/configuration_auto.py", line 536, in getitem
raise KeyError(key)
KeyError: 'liltrobertalike'
Killing subprocess 132879
Killing subprocess 132880
Killing subprocess 132881
Killing subprocess 132882
Traceback (most recent call last):
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/runpy.py", line 193, in _run_module_as_main
"main", mod_spec)
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/runpy.py", line 85, in _run_code
exec(code, run_globals)
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/torch/distributed/launch.py", line 340, in
main()
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/torch/distributed/launch.py", line 326, in main
sigkill_handler(signal.SIGTERM, None) # not coming back
File "/home/pm-gaojun/anaconda3/envs/lilt/lib/python3.7/site-packages/torch/distributed/launch.py", line 301, in sigkill_handler
raise subprocess.CalledProcessError(returncode=last_return_code, cmd=cmd)
subprocess.CalledProcessError: Command '['/home/pm-gaojun/anaconda3/envs/lilt/bin/python', '-u', 'examples/run_funsd.py', '--local_rank=3', '--model_name_or_path', 'lilt-roberta-en-base', '--tokenizer_name', 'roberta-base', '--output_dir', 'ser_funsd_lilt-roberta-en-base', '--do_train', '--do_predict', '--max_steps', '2000', '--per_device_train_batch_size', '8', '--warmup_ratio', '0.1', '--fp16']' returned non-zero exit status 1.
`

from lilt.

请问后来解决关键字的问题了吗，我最近在尝试用这个模型， 但是也有同样的问题

from lilt.

pip install packaging==21.3 ok

from lilt.