Finetuning Qwen2.5 with provided script, it comes out AttributeError: 'FieldInfo' object has no attribute 'required'. Did you mean: 'is_required'? #2291
Describe the bug
What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程,最好有截图)
Your hardware and system info
Write your system info like CUDA version/system/GPU/torch version here(在这里给出硬件信息和系统信息,如CUDA版本,系统,GPU型号和torch版本等)
Additional context
Add any other context about the problem here(在这里补充其他信息)
Traceback (most recent call last):
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/cli/sft.py", line 5, in
sft_main()
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/utils/run_utils.py", line 32, in x_main
result = llm_x(args, kwargs)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/llm/sft.py", line 541, in llm_sft
return trainer_train(args, model, template, train_dataset, val_dataset, callbacks=callbacks, msg=msg)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/llm/sft.py", line 491, in trainer_train
trainer.train(training_args.resume_from_checkpoint)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/trainers/mixin.py", line 479, in train
self._save_initial_model(self.args.output_dir)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/trainers/mixin.py", line 179, in _save_initial_model
model = unwrap_model(self.model)
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5237, in unwrap_model
return extract_model_from_parallel(model, kwargs)
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/accelerate/utils/other.py", line 77, in extract_model_from_parallel
from deepspeed import DeepSpeedEngine
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/init.py", line 22, in
from . import module_inject
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/module_inject/init.py", line 6, in
from .replace_module import replace_transformer_layer, revert_transformer_layer, ReplaceWithTensorSlicing, GroupQuantizer, generic_injection
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/module_inject/replace_module.py", line 567, in
from ..pipe import PipelineModule
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/pipe/init.py", line 6, in
from ..runtime.pipe import PipelineModule, LayerSpec, TiedLayerSpec
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/pipe/init.py", line 6, in
from .module import PipelineModule, LayerSpec, TiedLayerSpec
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/pipe/module.py", line 19, in
from ..activation_checkpointing import checkpointing
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/activation_checkpointing/checkpointing.py", line 26, in
from deepspeed.runtime.config import DeepSpeedConfig
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/config.py", line 29, in
from .zero.config import get_zero_config, ZeroStageEnum
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/zero/init.py", line 6, in
from .partition_parameters import ZeroParamType
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/zero/partition_parameters.py", line 709, in
class Init(InsertPostInitMethodToModuleSubClasses):
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/zero/partition_parameters.py", line 711, in Init
param_persistence_threshold = get_config_default(DeepSpeedZeroConfig, "param_persistence_threshold")
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/config_utils.py", line 116, in get_config_default
field_name).required, f"'{field_name}' is a required field and does not have a default value"
AttributeError: 'FieldInfo' object has no attribute 'required'. Did you mean: 'is_required'?
Describe the bug What the bug is, and how to reproduce, better with screenshots(描述bug以及复现过程,最好有截图)
Your hardware and system info Write your system info like CUDA version/system/GPU/torch version here(在这里给出硬件信息和系统信息,如CUDA版本,系统,GPU型号和torch版本等)
Additional context Add any other context about the problem here(在这里补充其他信息)
Traceback (most recent call last): File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/cli/sft.py", line 5, in
sft_main()
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/utils/run_utils.py", line 32, in x_main
result = llm_x(args, kwargs)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/llm/sft.py", line 541, in llm_sft
return trainer_train(args, model, template, train_dataset, val_dataset, callbacks=callbacks, msg=msg)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/llm/sft.py", line 491, in trainer_train
trainer.train(training_args.resume_from_checkpoint)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/trainers/mixin.py", line 479, in train
self._save_initial_model(self.args.output_dir)
File "/ssd4/zhuyongchi/facemoji_rephrase/SimejiUM/ms-swift/swift/trainers/mixin.py", line 179, in _save_initial_model
model = unwrap_model(self.model)
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/transformers/modeling_utils.py", line 5237, in unwrap_model
return extract_model_from_parallel(model, kwargs)
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/accelerate/utils/other.py", line 77, in extract_model_from_parallel
from deepspeed import DeepSpeedEngine
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/init.py", line 22, in
from . import module_inject
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/module_inject/init.py", line 6, in
from .replace_module import replace_transformer_layer, revert_transformer_layer, ReplaceWithTensorSlicing, GroupQuantizer, generic_injection
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/module_inject/replace_module.py", line 567, in
from ..pipe import PipelineModule
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/pipe/init.py", line 6, in
from ..runtime.pipe import PipelineModule, LayerSpec, TiedLayerSpec
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/pipe/init.py", line 6, in
from .module import PipelineModule, LayerSpec, TiedLayerSpec
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/pipe/module.py", line 19, in
from ..activation_checkpointing import checkpointing
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/activation_checkpointing/checkpointing.py", line 26, in
from deepspeed.runtime.config import DeepSpeedConfig
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/config.py", line 29, in
from .zero.config import get_zero_config, ZeroStageEnum
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/zero/init.py", line 6, in
from .partition_parameters import ZeroParamType
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/zero/partition_parameters.py", line 709, in
class Init(InsertPostInitMethodToModuleSubClasses):
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/zero/partition_parameters.py", line 711, in Init
param_persistence_threshold = get_config_default(DeepSpeedZeroConfig, "param_persistence_threshold")
File "/ssd4/zhuyongchi/anaconda3/envs/swift/lib/python3.10/site-packages/deepspeed/runtime/config_utils.py", line 116, in get_config_default
field_name).required, f"'{field_name}' is a required field and does not have a default value"
AttributeError: 'FieldInfo' object has no attribute 'required'. Did you mean: 'is_required'?