Training related issues

[ioir123ju]

When I trained qwen2vl-2B with your data, I could achieve an accuracy of 73 with 10k of data, but could only achieve an accuracy of 49 with the entire dataset. I don't know why this is happening.

[boyugou]

Hi, thanks for the feedback. Could you provide more details about the settings and configuration? I haven’t received any similar feedback before.

[Joywanglulu]

hi i have an error assert "factor" in rope_scaling

[KevinBreet]

Hi, I also have an error: assert "factor" in rope_scaling.

my conda env:
Package Version Editable project location

---

absl-py 2.1.0
accelerate 1.3.0
addict 2.4.0
aiofiles 23.2.1
aiohappyeyeballs 2.4.3
aiohttp 3.10.10
aiosignal 1.3.1
aliyun-python-sdk-core 2.16.0
aliyun-python-sdk-kms 2.16.5
annotated-types 0.7.0
anyio 4.6.2.post1
async-timeout 4.0.3
attrdict 2.0.1
attrs 24.2.0
av 13.1.0
binpacking 1.5.2
Brotli 1.0.9
certifi 2024.8.30
cffi 1.17.1
chardet 4.0.0
charset-normalizer 3.3.2
click 8.1.7
cloudpickle 3.1.1
contourpy 1.3.0
cpm-kernels 1.0.11
crcmod 1.7
cryptography 43.0.3
cycler 0.12.1
dacite 1.8.1
datasets 3.0.1
decord 0.6.0
deepspeed 0.15.3+unknown
dill 0.3.8
diskcache 5.6.3
distro 1.9.0
docstring_parser 0.16
easydict 1.13
einops 0.8.0
exceptiongroup 1.2.2
fastapi 0.115.2
ffmpy 0.4.0
filelock 3.13.1
fonttools 4.54.1
frozenlist 1.4.1
fsspec 2024.6.1
future 1.0.0
gguf 0.9.1
gmpy2 2.1.2
gradio 5.1.0
gradio_client 1.4.0
grpcio 1.67.0
h11 0.14.0
hjson 3.1.0
httpcore 1.0.6
httptools 0.6.4
httpx 0.27.2
huggingface-hub 0.26.0
idna 3.10
importlib_metadata 8.5.0
interegular 0.3.3
janus 1.0.0
jieba 0.42.1
Jinja2 3.1.4
jiter 0.6.1
jmespath 0.10.0
joblib 1.4.2
jsonschema 4.25.0
jsonschema-specifications 2025.4.1
kiwisolver 1.4.7
lark 1.2.2
llvmlite 0.44.0
lm-format-enforcer 0.10.6
Markdown 3.7
markdown-it-py 3.0.0
MarkupSafe 2.1.3
matplotlib 3.9.2
mdurl 0.1.2
mistral_common 1.8.1
mkl_fft 1.3.10
mkl_random 1.2.7
mkl-service 2.4.0
modelscope 1.22.3
mpmath 1.3.0
ms-swift 3.1.0
msgpack 1.1.0
msgspec 0.19.0
multidict 6.1.0
multiprocess 0.70.16
nest-asyncio 1.6.0
networkx 3.2.1
ninja 1.11.1.1
nltk 3.9.1
numba 0.61.2
numpy 1.26.4
nvidia-cublas-cu12 12.1.3.1
nvidia-cuda-cupti-cu12 12.1.105
nvidia-cuda-nvrtc-cu12 12.1.105
nvidia-cuda-runtime-cu12 12.1.105
nvidia-cudnn-cu12 9.1.0.70
nvidia-cufft-cu12 11.0.2.54
nvidia-curand-cu12 10.3.2.106
nvidia-cusolver-cu12 11.4.5.107
nvidia-cusparse-cu12 12.1.0.106
nvidia-ml-py 12.560.30
nvidia-nccl-cu12 2.20.5
nvidia-nvjitlink-cu12 12.9.86
nvidia-nvtx-cu12 12.1.105
openai 1.52.0
opencv-python 4.10.0.84
orjson 3.10.9
oss2 2.19.0
outlines 0.0.46
packaging 24.1
pandas 2.2.3
partial-json-parser 0.2.1.1.post6
peft 0.12.0
pillow 10.4.0
pip 25.0.1
prometheus_client 0.22.1
prometheus-fastapi-instrumentator 7.1.0
propcache 0.2.0
protobuf 5.28.2
psutil 6.1.0
py-cpuinfo 9.0.0
pyairports 2.1.1
pyarrow 17.0.0
pycountry 24.6.1
pycparser 2.22
pycryptodome 3.21.0
pydantic 2.9.2
pydantic_core 2.23.4
pydantic-extra-types 2.10.5
pydub 0.25.1
Pygments 2.18.0
pyparsing 3.2.0
PySocks 1.7.1
python-dateutil 2.9.0.post0
python-dotenv 1.1.1
python-multipart 0.0.12
pytz 2024.2
PyYAML 6.0.2
pyzmq 27.0.0
qwen-vl-utils 0.0.8
ray 2.48.0
referencing 0.36.2
regex 2024.9.11
requests 2.32.3
rich 13.9.2
rouge 1.0.1
rpds-py 0.26.0
ruff 0.7.0
safetensors 0.4.5
scipy 1.14.1
semantic-version 2.10.0
sentencepiece 0.2.0
setuptools 69.5.1
shellingham 1.5.4
shtab 1.7.1
simplejson 3.19.3
six 1.16.0
sniffio 1.3.1
sortedcontainers 2.4.0
starlette 0.40.0
sympy 1.13.2
tensorboard 2.18.0
tensorboard-data-server 0.7.2
tiktoken 0.8.0
timm 1.0.11
tokenizers 0.21.0
tomlkit 0.12.0
torch 2.4.0+cu121
torchaudio 2.3.0
torchvision 0.19.0+cu121
tqdm 4.66.5
transformers 4.49.0.dev0 /root/transformers
transformers-stream-generator 0.0.5
triton 3.0.0
trl 0.14.0
typer 0.12.5
typing_extensions 4.11.0
tyro 0.8.13
tzdata 2024.2
urllib3 2.2.3
uvicorn 0.32.0
uvloop 0.21.0
vllm 0.6.1
vllm-flash-attn 2.6.1
watchfiles 1.1.0
websockets 12.0
Werkzeug 3.0.4
wheel 0.44.0
xformers 0.0.27.post2
xxhash 3.5.0
yarl 1.15.5
zipp 3.20.2
zstandard 0.23.0

but when I run the grounding/uground_qwen2vl.py, this error occurs:

Traceback (most recent call last):
File "/data/qin/uground/grounding/uground_qwen2vl.py", line 106, in
eval_model(args)
File "/data/qin/uground/grounding/uground_qwen2vl.py", line 48, in eval_model
llm = LLM(
File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 178, in init
self.llm_engine = LLMEngine.from_engine_args(
File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 554, in from_engine_args
engine_config = engine_args.create_engine_config()
File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 844, in create_engine_config
model_config = self.create_model_config()
File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 782, in create_model_config
return ModelConfig(
File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/config.py", line 227, in init
self.max_model_len = _get_and_verify_max_len(
File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/config.py", line 1740, in _get_and_verify_max_len
assert "factor" in rope_scaling

[yjlself]

Hi, I also have an error: assert "factor" in rope_scaling.嗨，我也有一个错误：assert "factor" in rope_scaling。

my conda env:  我的 conda 环境： Package Version Editable project location Package Version 可编辑项目位置

absl-py 2.1.0 accelerate 1.3.0 addict 2.4.0 aiofiles 23.2.1 aiohappyeyeballs 2.4.3 aiohttp 3.10.10  aiosignal 1.3.1  aliyun-python-sdk-core 2.16.0  aliyun-python-sdk-kms 2.16.5  annotated-types 0.7.0 anyio 4.6.2.post1 async-timeout 4.0.3 attrdict 2.0.1 attrs 24.2.0 av 13.1.0 binpacking 1.5.2 Brotli 1.0.9 certifi 2024.8.30 cffi 1.17.1 chardet 4.0.0 charset-normalizer 3.3.2 click 8.1.7  点击 8.1.7 cloudpickle 3.1.1 contourpy 1.3.0 cpm-kernels 1.0.11 crcmod 1.7 cryptography 43.0.3 cycler 0.12.1 dacite 1.8.1 datasets 3.0.1 decord 0.6.0 deepspeed 0.15.3+unknown dill 0.3.8 diskcache 5.6.3 distro 1.9.0 docstring_parser 0.16 easydict 1.13 einops 0.8.0 exceptiongroup 1.2.2 fastapi 0.115.2 ffmpy 0.4.0 filelock 3.13.1 fonttools 4.54.1 frozenlist 1.4.1 fsspec 2024.6.1 future 1.0.0 gguf 0.9.1 gmpy2 2.1.2 gradio 5.1.0 gradio_client 1.4.0 grpcio 1.67.0 h11 0.14.0 hjson 3.1.0 httpcore 1.0.6 httptools 0.6.4 httpx 0.27.2 huggingface-hub 0.26.0 idna 3.10 importlib_metadata 8.5.0 interegular 0.3.3 janus 1.0.0 jieba 0.42.1 Jinja2 3.1.4 jiter 0.6.1 jmespath 0.10.0 joblib 1.4.2 jsonschema 4.25.0 jsonschema-specifications 2025.4.1 kiwisolver 1.4.7 lark 1.2.2 llvmlite 0.44.0 lm-format-enforcer 0.10.6 Markdown 3.7 markdown-it-py 3.0.0 MarkupSafe 2.1.3 matplotlib 3.9.2 mdurl 0.1.2 mistral_common 1.8.1 mkl_fft 1.3.10 mkl_random 1.2.7 mkl-service 2.4.0 modelscope 1.22.3 mpmath 1.3.0 ms-swift 3.1.0 msgpack 1.1.0 msgspec 0.19.0 multidict 6.1.0 multiprocess 0.70.16 nest-asyncio 1.6.0 networkx 3.2.1 ninja 1.11.1.1 nltk 3.9.1 numba 0.61.2 numpy 1.26.4 nvidia-cublas-cu12 12.1.3.1 nvidia-cuda-cupti-cu12 12.1.105 nvidia-cuda-nvrtc-cu12 12.1.105 nvidia-cuda-runtime-cu12 12.1.105  nvidia-cudnn-cu12 9.1.0.70  nvidia-cufft-cu12 11.0.2.54  nvidia-curand-cu12 10.3.2.106  nvidia-cusolver-cu12 11.4.5.107 nvidia-cusparse-cu12 12.1.0.106 nvidia-ml-py 12.560.30 nvidia-nccl-cu12 2.20.5 nvidia-nvjitlink-cu12 12.9.86 nvidia-nvtx-cu12 12.1.105 openai 1.52.0 opencv-python 4.10.0.84 orjson 3.10.9  或 json 3.10.9 oss2 2.19.0 outlines 0.0.46 packaging 24.1 pandas 2.2.3 partial-json-parser 0.2.1.1.post6 peft 0.12.0 pillow 10.4.0 pip 25.0.1 prometheus_client 0.22.1 prometheus-fastapi-instrumentator 7.1.0 propcache 0.2.0 protobuf 5.28.2 psutil 6.1.0 py-cpuinfo 9.0.0 pyairports 2.1.1 pyarrow 17.0.0 pycountry 24.6.1 pycparser 2.22 pycryptodome 3.21.0 pydantic 2.9.2 pydantic_core 2.23.4 pydantic-extra-types 2.10.5 pydub 0.25.1 Pygments 2.18.0 pyparsing 3.2.0 PySocks 1.7.1 python-dateutil 2.9.0.post0 python-dotenv 1.1.1  python-multipart 0.0.12  pytz 2024.2  PyYAML 6.0.2  pyzmq 27.0.0 qwen-vl-utils 0.0.8 ray 2.48.0 referencing 0.36.2 regex 2024.9.11 requests 2.32.3 rich 13.9.2 rouge 1.0.1 rpds-py 0.26.0 ruff 0.7.0 safetensors 0.4.5 scipy 1.14.1 semantic-version 2.10.0 sentencepiece 0.2.0 setuptools 69.5.1 shellingham 1.5.4 shtab 1.7.1 simplejson 3.19.3 six 1.16.0 sniffio 1.3.1 sortedcontainers 2.4.0 starlette 0.40.0 sympy 1.13.2 tensorboard 2.18.0 tensorboard-data-server 0.7.2 tiktoken 0.8.0 timm 1.0.11 tokenizers 0.21.0 tomlkit 0.12.0 torch 2.4.0+cu121 torchaudio 2.3.0 torchvision 0.19.0+cu121 tqdm 4.66.5 transformers 4.49.0.dev0 /root/transformers transformers-stream-generator 0.0.5 triton 3.0.0 trl 0.14.0 typer 0.12.5 typing_extensions 4.11.0 tyro 0.8.13 tzdata 2024.2 urllib3 2.2.3 uvicorn 0.32.0 uvloop 0.21.0 vllm 0.6.1 vllm-flash-attn 2.6.1 watchfiles 1.1.0 websockets 12.0 Werkzeug 3.0.4 wheel 0.44.0 xformers 0.0.27.post2 xxhash 3.5.0 yarl 1.15.5 zipp 3.20.2 zstandard 0.23.0

but when I run the grounding/uground_qwen2vl.py, this error occurs:但是当我运行 grounding/uground_qwen2vl.py 时，出现这个错误：

Traceback (most recent call last): File "/data/qin/uground/grounding/uground_qwen2vl.py", line 106, in eval_model(args) File "/data/qin/uground/grounding/uground_qwen2vl.py", line 48, in eval_model llm = LLM( File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 178, in init self.llm_engine = LLMEngine.from_engine_args( File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 554, in from_engine_args engine_config = engine_args.create_engine_config() File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 844, in create_engine_config model_config = self.create_model_config() File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/engine/arg_utils.py", line 782, in create_model_config return ModelConfig( File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/config.py", line 227, in init self.max_model_len = _get_and_verify_max_len( File "/data/qin/conda_env/uground_v1/lib/python3.10/site-packages/vllm/config.py", line 1740, in _get_and_verify_max_len assert "factor" in rope_scaling

It is the version question of Vllm, I use python=3.10 to start this project, I choose to change the version. Here are my Vllm settings:
vllm 0.13.0 pypi_0 pypi
vllm-flash-attn 2.6.1 pypi_0 pypi
and It can run with the weights from huggingface.