remove wandb logs

This commit is contained in:
junchen14 2023-10-23 09:14:40 +03:00
parent ba636c699c
commit db44bb36e1
40 changed files with 0 additions and 10722 deletions

View File

@ -1 +0,0 @@
run-20231023_091030-25yuqsbo/logs/debug-internal.log

View File

@ -1 +0,0 @@
run-20231023_091030-25yuqsbo/logs/debug.log

View File

@ -1 +0,0 @@
run-20231023_091030-25yuqsbo

View File

@ -1,297 +0,0 @@
name: eye
channels:
- pytorch
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _openmp_mutex=5.1=1_gnu
- blas=1.0=mkl
- brotlipy=0.7.0=py39h27cfd23_1003
- bzip2=1.0.8=h7b6447c_0
- ca-certificates=2023.01.10=h06a4308_0
- certifi=2022.12.7=py39h06a4308_0
- cffi=1.15.1=py39h5eee18b_3
- charset-normalizer=2.0.4=pyhd3eb1b0_0
- cryptography=39.0.1=py39h9ce1e76_0
- cudatoolkit=11.3.1=h2bc3f7f_2
- ffmpeg=4.3=hf484d3e_0
- flit-core=3.8.0=py39h06a4308_0
- freetype=2.12.1=h4a9f257_0
- giflib=5.2.1=h5eee18b_3
- gmp=6.2.1=h295c915_3
- gnutls=3.6.15=he1e5248_0
- idna=3.4=py39h06a4308_0
- intel-openmp=2021.4.0=h06a4308_3561
- jpeg=9e=h5eee18b_1
- lame=3.100=h7b6447c_0
- lcms2=2.12=h3be6417_0
- ld_impl_linux-64=2.38=h1181459_1
- lerc=3.0=h295c915_0
- libdeflate=1.17=h5eee18b_0
- libffi=3.4.2=h6a678d5_6
- libgcc-ng=11.2.0=h1234567_1
- libgomp=11.2.0=h1234567_1
- libiconv=1.16=h7f8727e_2
- libidn2=2.3.2=h7f8727e_0
- libpng=1.6.39=h5eee18b_0
- libstdcxx-ng=11.2.0=h1234567_1
- libtasn1=4.19.0=h5eee18b_0
- libtiff=4.5.0=h6a678d5_2
- libunistring=0.9.10=h27cfd23_0
- libwebp=1.2.4=h11a3e52_1
- libwebp-base=1.2.4=h5eee18b_1
- lz4-c=1.9.4=h6a678d5_0
- mkl=2021.4.0=h06a4308_640
- mkl-service=2.4.0=py39h7f8727e_0
- mkl_fft=1.3.1=py39hd3c417c_0
- mkl_random=1.2.2=py39h51133e4_0
- ncurses=6.4=h6a678d5_0
- nettle=3.7.3=hbbd107a_1
- numpy=1.23.5=py39h14f4228_0
- numpy-base=1.23.5=py39h31eccc5_0
- openh264=2.1.1=h4ff587b_0
- openssl=1.1.1t=h7f8727e_0
- pillow=9.4.0=py39h6a678d5_0
- pip=23.0.1=py39h06a4308_0
- pycparser=2.21=pyhd3eb1b0_0
- pyopenssl=23.0.0=py39h06a4308_0
- pysocks=1.7.1=py39h06a4308_0
- python=3.9.16=h7a1cb2a_2
- pytorch-mutex=1.0=cuda
- readline=8.2=h5eee18b_0
- requests=2.28.1=py39h06a4308_1
- setuptools=65.6.3=py39h06a4308_0
- six=1.16.0=pyhd3eb1b0_1
- sqlite=3.41.1=h5eee18b_0
- tk=8.6.12=h1ccaba5_0
- torchaudio=0.12.1=py39_cu113
- torchvision=0.13.1=py39_cu113
- typing_extensions=4.4.0=py39h06a4308_0
- urllib3=1.26.15=py39h06a4308_0
- wheel=0.38.4=py39h06a4308_0
- xz=5.2.10=h5eee18b_1
- zlib=1.2.13=h5eee18b_0
- zstd=1.5.4=hc292b87_0
- pip:
- accelerate==0.20.3
- aiofiles==23.1.0
- aiohttp==3.8.4
- aiosignal==1.3.1
- altair==4.2.2
- antlr4-python3-runtime==4.9.3
- anyio==3.6.2
- appdirs==1.4.4
- argon2-cffi==21.3.0
- argon2-cffi-bindings==21.2.0
- arrow==1.2.3
- asttokens==2.2.1
- async-timeout==4.0.2
- attrs==22.2.0
- backcall==0.2.0
- beautifulsoup4==4.12.2
- bitsandbytes==0.37.0
- bleach==6.0.0
- blis==0.7.9
- braceexpand==0.1.7
- catalogue==2.0.8
- cchardet==2.1.7
- chardet==5.1.0
- click==8.1.3
- cloudpickle==2.2.1
- cmake==3.26.1
- comm==0.1.3
- confection==0.0.4
- contourpy==1.0.7
- cycler==0.11.0
- cymem==2.0.7
- datasets==2.13.1
- debugpy==1.6.7
- decorator==5.1.1
- decord==0.6.0
- defusedxml==0.7.1
- dill==0.3.6
- docker-pycreds==0.4.0
- einops==0.6.0
- entrypoints==0.4
- executing==1.2.0
- fairscale==0.4.13
- fastapi==0.95.0
- fastjsonschema==2.16.3
- ffmpy==0.3.0
- filelock==3.9.0
- fire==0.5.0
- fonttools==4.38.0
- fqdn==1.5.1
- frozenlist==1.3.3
- fsspec==2023.4.0
- gitdb==4.0.10
- gitpython==3.1.31
- gradio==3.24.1
- gradio-client==0.0.8
- h11==0.14.0
- httpcore==0.16.3
- httpx==0.23.3
- huggingface-hub==0.16.4
- imageio==2.31.1
- importlib-metadata==6.2.0
- importlib-resources==5.12.0
- iopath==0.1.10
- ipykernel==6.22.0
- ipython==8.12.0
- ipython-genutils==0.2.0
- isoduration==20.11.0
- jedi==0.18.2
- jinja2==3.1.2
- joblib==1.2.0
- jsonpointer==2.3
- jsonschema==4.17.3
- jupyter-client==8.1.0
- jupyter-core==5.3.0
- jupyter-events==0.6.3
- jupyter-server==2.5.0
- jupyter-server-terminals==0.4.4
- jupyterlab-pygments==0.2.2
- kiwisolver==1.4.4
- langcodes==3.3.0
- lazy-loader==0.2
- linkify-it-py==2.0.0
- lit==16.0.0
- llvmlite==0.39.1
- loralib==0.1.1
- markdown-it-py==2.2.0
- markupsafe==2.1.2
- matplotlib==3.7.0
- matplotlib-inline==0.1.6
- mdit-py-plugins==0.3.3
- mdurl==0.1.2
- mistune==2.0.5
- mpmath==1.3.0
- multidict==6.0.4
- multiprocess==0.70.14
- murmurhash==1.0.9
- nbclassic==0.5.5
- nbclient==0.7.3
- nbconvert==7.3.0
- nbformat==5.8.0
- nest-asyncio==1.5.6
- networkx==3.1
- nltk==3.8.1
- notebook==6.5.4
- notebook-shim==0.2.2
- numba==0.56.4
- nvidia-cublas-cu11==11.10.3.66
- nvidia-cuda-cupti-cu11==11.7.101
- nvidia-cuda-nvrtc-cu11==11.7.99
- nvidia-cuda-runtime-cu11==11.7.99
- nvidia-cudnn-cu11==8.5.0.96
- nvidia-cufft-cu11==10.9.0.58
- nvidia-curand-cu11==10.2.10.91
- nvidia-cusolver-cu11==11.4.0.1
- nvidia-cusparse-cu11==11.7.4.91
- nvidia-nccl-cu11==2.14.3
- nvidia-nvtx-cu11==11.7.91
- omegaconf==2.3.0
- openai==0.27.0
- opencv-python==4.7.0.72
- orjson==3.8.9
- packaging==23.0
- pandas==2.0.0
- pandocfilters==1.5.0
- parso==0.8.3
- pathlib==1.0.1
- pathtools==0.1.2
- pathy==0.10.1
- peft==0.2.0
- pexpect==4.8.0
- pickleshare==0.7.5
- platformdirs==3.2.0
- policies==0.4.2
- portalocker==2.7.0
- preshed==3.0.8
- progressbar2==4.2.0
- prometheus-client==0.16.0
- prompt-toolkit==3.0.38
- protobuf==4.22.1
- psutil==5.9.4
- ptyprocess==0.7.0
- pure-eval==0.2.2
- pyarrow==12.0.1
- pycocoevalcap==1.2
- pycocotools==2.0.6
- pycryptodome==3.17
- pydantic==1.10.7
- pydub==0.25.1
- pygments==2.14.0
- pynndescent==0.5.8
- pyparsing==3.0.9
- pyrsistent==0.19.3
- python-dateutil==2.8.2
- python-json-logger==2.0.7
- python-multipart==0.0.6
- python-utils==3.7.0
- pytz==2023.3
- pywavelets==1.4.1
- pyyaml==6.0
- pyzmq==25.0.2
- regex==2022.10.31
- rfc3339-validator==0.1.4
- rfc3986==1.5.0
- rfc3986-validator==0.1.1
- safetensors==0.3.1
- scikit-image==0.21.0
- scikit-learn==1.2.2
- scipy==1.10.1
- seaborn==0.12.2
- semantic-version==2.10.0
- send2trash==1.8.0
- sentence-transformers==2.2.2
- sentencepiece==0.1.97
- sentry-sdk==1.19.1
- setproctitle==1.3.2
- smart-open==6.3.0
- smmap==5.0.0
- sniffio==1.3.0
- soupsieve==2.4
- spacy==3.5.1
- spacy-legacy==3.0.12
- spacy-loggers==1.0.4
- srsly==2.4.6
- stack-data==0.6.2
- starlette==0.26.1
- submitit==1.4.5
- sympy==1.11.1
- tenacity==8.2.2
- termcolor==2.3.0
- terminado==0.17.1
- thinc==8.1.9
- threadpoolctl==3.1.0
- tifffile==2023.4.12
- timm==0.6.13
- tinycss2==1.2.1
- tokenizers==0.13.3
- toolz==0.12.0
- torch==2.0.0
- tornado==6.2
- tqdm==4.64.1
- traitlets==5.9.0
- transformers==4.31.0
- triton==2.0.0
- typer==0.7.0
- tzdata==2023.3
- uc-micro-py==1.0.1
- umap-learn==0.5.3
- uri-template==1.2.0
- uvicorn==0.21.1
- visual-genome==1.1.1
- wandb==0.14.2
- wasabi==1.1.1
- wcwidth==0.2.6
- webcolors==1.13
- webdataset==0.2.48
- webencodings==0.5.1
- websocket-client==1.5.1
- websockets==11.0.1
- xxhash==3.2.0
- yarl==1.8.2
- zipp==3.14.0
prefix: /home/chenj0g/anaconda3/envs/eye

View File

@ -1,38 +0,0 @@
wandb_version: 1
_wandb:
desc: null
value:
python_version: 3.9.16
cli_version: 0.14.2
framework: huggingface
huggingface_version: 4.31.0
is_jupyter_run: false
is_kaggle_kernel: false
start_time: 1698040478.151963
t:
1:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
2:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
3:
- 1
- 13
- 23
4: 3.9.16
5: 0.14.2
6: 4.31.0
8:
- 5

View File

@ -1,177 +0,0 @@
2023-10-23 08:54:52,781 [INFO] Start training
batch sizes [[2]]
module.llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_B.weight
module.llama_proj.weight
module.llama_proj.bias
2023-10-23 08:54:54,750 [INFO] dataset_ratios not specified, datasets will be concatenated (map-style datasets) or chained (webdataset.DataPipeline).
2023-10-23 08:54:54,750 [INFO] Loaded 12171 records for train split from the dataset.
2023-10-23 08:54:54,768 [INFO] number of trainable parameters: 56627200
2023-10-23 08:54:54,769 [INFO] Start training epoch 0, 1000 iters per inner epoch.
Train: data epoch: [0] [ 0/1000] eta: 0:44:54 lr: 0.000001 loss: 1.3049 time: 2.6941 data: 0.0000 max mem: 33053
/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Train: data epoch: [0] [ 50/1000] eta: 0:07:57 lr: 0.000001 loss: 1.2327 time: 0.4510 data: 0.0000 max mem: 38294
Train: data epoch: [0] [ 100/1000] eta: 0:07:10 lr: 0.000002 loss: 1.1049 time: 0.4456 data: 0.0000 max mem: 39573
Train: data epoch: [0] [ 150/1000] eta: 0:06:42 lr: 0.000002 loss: 1.2879 time: 0.4630 data: 0.0000 max mem: 40208
Train: data epoch: [0] [ 200/1000] eta: 0:06:18 lr: 0.000003 loss: 1.0077 time: 0.4521 data: 0.0000 max mem: 40208
Train: data epoch: [0] [ 250/1000] eta: 0:05:52 lr: 0.000003 loss: 1.4790 time: 0.4627 data: 0.0000 max mem: 41447
Train: data epoch: [0] [ 300/1000] eta: 0:05:27 lr: 0.000004 loss: 1.2864 time: 0.4646 data: 0.0000 max mem: 41447
Train: data epoch: [0] [ 350/1000] eta: 0:05:02 lr: 0.000004 loss: 1.1261 time: 0.4556 data: 0.0000 max mem: 41447
Traceback (most recent call last):
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py", line 117, in <module>
main()
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py", line 113, in main
runner.train()
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/runners/runner_base.py", line 377, in train
train_stats = self.train_epoch(cur_epoch)
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/runners/runner_base.py", line 437, in train_epoch
return self.task.train_epoch(
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 116, in train_epoch
return self._train_inner_loop(
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 221, in _train_inner_loop
loss = self.train_step(model=model, samples=samples)
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 70, in train_step
loss = model(samples)["loss"]
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1156, in forward
output = self._run_ddp_forward(*inputs, **kwargs)
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/nn/parallel/distributed.py", line 1110, in _run_ddp_forward
return module_to_run(*inputs[0], **kwargs[0]) # type: ignore[index]
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/models/minigpt_base.py", line 279, in forward
self.preparing_embedding(samples)
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/models/minigpt_base.py", line 215, in preparing_embedding
img_embeds, img_atts = self.encode_img(samples["image"])
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/models/minigpt_v2.py", line 88, in encode_img
atts_llama = torch.ones(inputs_llama.size()[:-1], dtype=torch.long).to(image.device)
KeyboardInterrupt

View File

@ -1,246 +0,0 @@
accelerate==0.20.3
aiofiles==23.2.1
aiohttp==3.8.4
aiosignal==1.3.1
altair==5.1.2
antlr4-python3-runtime==4.9.3
anyio==3.6.2
appdirs==1.4.4
argon2-cffi-bindings==21.2.0
argon2-cffi==21.3.0
arrow==1.2.3
asttokens==2.2.1
async-timeout==4.0.2
attrs==22.2.0
backcall==0.2.0
beautifulsoup4==4.12.2
bitsandbytes==0.37.0
bleach==6.0.0
blis==0.7.9
braceexpand==0.1.7
brotlipy==0.7.0
catalogue==2.0.8
cchardet==2.1.7
certifi==2022.12.7
cffi==1.15.1
chardet==5.1.0
charset-normalizer==2.0.4
click==8.1.3
cloudpickle==2.2.1
cmake==3.26.1
comm==0.1.3
confection==0.0.4
contourpy==1.0.7
cryptography==39.0.1
cycler==0.11.0
cymem==2.0.7
datasets==2.13.1
debugpy==1.6.7
decorator==5.1.1
decord==0.6.0
defusedxml==0.7.1
dill==0.3.6
docker-pycreds==0.4.0
einops==0.6.0
entrypoints==0.4
executing==1.2.0
fairscale==0.4.13
fastapi==0.95.0
fastjsonschema==2.16.3
ffmpy==0.3.1
filelock==3.9.0
fire==0.5.0
flit-core==3.8.0
fonttools==4.38.0
fqdn==1.5.1
frozenlist==1.3.3
fsspec==2023.9.2
gitdb==4.0.10
gitpython==3.1.31
gradio-client==0.6.0
gradio==3.24.1
h11==0.14.0
httpcore==0.18.0
httpx==0.25.0
huggingface-hub==0.18.0
idna==3.4
imageio==2.31.1
importlib-metadata==6.2.0
importlib-resources==5.12.0
iopath==0.1.10
ipykernel==6.22.0
ipython-genutils==0.2.0
ipython==8.12.0
isoduration==20.11.0
jedi==0.18.2
jinja2==3.1.2
joblib==1.2.0
jsonpointer==2.3
jsonschema==4.17.3
jupyter-client==8.1.0
jupyter-core==5.3.0
jupyter-events==0.6.3
jupyter-server-terminals==0.4.4
jupyter-server==2.5.0
jupyterlab-pygments==0.2.2
kiwisolver==1.4.4
langcodes==3.3.0
lazy-loader==0.2
linkify-it-py==2.0.2
lit==16.0.0
llvmlite==0.39.1
loralib==0.1.1
markdown-it-py==2.2.0
markupsafe==2.1.2
matplotlib-inline==0.1.6
matplotlib==3.7.0
mdit-py-plugins==0.3.3
mdurl==0.1.2
mistune==2.0.5
mkl-fft==1.3.1
mkl-random==1.2.2
mkl-service==2.4.0
mpmath==1.3.0
multidict==6.0.4
multiprocess==0.70.14
murmurhash==1.0.9
nbclassic==0.5.5
nbclient==0.7.3
nbconvert==7.3.0
nbformat==5.8.0
nest-asyncio==1.5.6
networkx==3.1
nltk==3.8.1
notebook-shim==0.2.2
notebook==6.5.4
numba==0.56.4
numpy==1.23.5
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-cupti-cu11==11.7.101
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
nvidia-cufft-cu11==10.9.0.58
nvidia-curand-cu11==10.2.10.91
nvidia-cusolver-cu11==11.4.0.1
nvidia-cusparse-cu11==11.7.4.91
nvidia-nccl-cu11==2.14.3
nvidia-nvtx-cu11==11.7.91
omegaconf==2.3.0
openai==0.27.0
opencv-python==4.7.0.72
orjson==3.9.8
packaging==23.0
pandas==2.0.0
pandocfilters==1.5.0
parso==0.8.3
pathlib==1.0.1
pathtools==0.1.2
pathy==0.10.1
peft==0.2.0
pexpect==4.8.0
pickleshare==0.7.5
pillow==9.4.0
pip==23.0.1
platformdirs==3.2.0
policies==0.4.2
portalocker==2.7.0
preshed==3.0.8
progressbar2==4.2.0
prometheus-client==0.16.0
prompt-toolkit==3.0.38
protobuf==4.22.1
psutil==5.9.4
ptyprocess==0.7.0
pure-eval==0.2.2
pyarrow==12.0.1
pycocoevalcap==1.2
pycocotools==2.0.6
pycparser==2.21
pycryptodome==3.17
pydantic==1.10.7
pydub==0.25.1
pygments==2.14.0
pynndescent==0.5.8
pyopenssl==23.0.0
pyparsing==3.0.9
pyrsistent==0.19.3
pysocks==1.7.1
python-dateutil==2.8.2
python-json-logger==2.0.7
python-multipart==0.0.6
python-utils==3.7.0
pytz==2023.3
pywavelets==1.4.1
pyyaml==6.0
pyzmq==25.0.2
regex==2022.10.31
requests==2.28.1
rfc3339-validator==0.1.4
rfc3986-validator==0.1.1
rfc3986==1.5.0
rpe-index==1.2.0
safetensors==0.3.1
scikit-image==0.21.0
scikit-learn==1.2.2
scipy==1.10.1
seaborn==0.12.2
semantic-version==2.10.0
send2trash==1.8.0
sentence-transformers==2.2.2
sentencepiece==0.1.97
sentry-sdk==1.19.1
setproctitle==1.3.2
setuptools==65.6.3
six==1.16.0
smart-open==6.3.0
smmap==5.0.0
sniffio==1.3.0
soupsieve==2.4
spacy-legacy==3.0.12
spacy-loggers==1.0.4
spacy==3.5.1
srsly==2.4.6
stack-data==0.6.2
starlette==0.26.1
submitit==1.4.5
sympy==1.11.1
tenacity==8.2.2
termcolor==2.3.0
terminado==0.17.1
thinc==8.1.9
threadpoolctl==3.1.0
tifffile==2023.4.12
timm==0.6.13
tinycss2==1.2.1
tokenizers==0.13.3
toolz==0.12.0
torch==2.0.0
torchaudio==0.12.1
torchvision==0.13.1
tornado==6.2
tqdm==4.64.1
traitlets==5.9.0
transformers==4.31.0
triton==2.0.0
typer==0.7.0
typing-extensions==4.4.0
tzdata==2023.3
uc-micro-py==1.0.2
umap-learn==0.5.3
uri-template==1.2.0
urllib3==1.26.15
uvicorn==0.21.1
visual-genome==1.1.1
wandb==0.14.2
wasabi==1.1.1
wcwidth==0.2.6
webcolors==1.13
webdataset==0.2.48
webencodings==0.5.1
websocket-client==1.5.1
websockets==11.0.1
wheel==0.38.4
xxhash==3.2.0
yarl==1.8.2
zipp==3.14.0

View File

@ -1,374 +0,0 @@
{
"os": "Linux-3.10.0-1160.76.1.el7.x86_64-x86_64-with-glibc2.17",
"python": "3.9.16",
"heartbeatAt": "2023-10-23T05:54:39.620251",
"startedAt": "2023-10-23T05:54:38.092408",
"docker": null,
"cuda": null,
"args": [
"--job_name",
"minigpt4_v2_test",
"--cfg-path",
"train_configs/minigpt_v2_finetune.yaml"
],
"state": "running",
"program": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py",
"codePath": "train.py",
"git": {
"remote": "https://github.com/junchen14/MiniGPT-4_finetune",
"commit": "5c3ec8bb730b2e9df23b4bb3eb24108f9c04a8d6"
},
"email": "jun.chen@kaust.edu.sa",
"root": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune",
"host": "gpu201-16-l",
"username": "chenj0g",
"executable": "/home/chenj0g/anaconda3/envs/eye/bin/python",
"cpu_count": 64,
"cpu_count_logical": 64,
"cpu_freq": {
"current": 1996.2770000000016,
"min": 0.0,
"max": 0.0
},
"cpu_freq_per_core": [
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
}
],
"disk": {
"total": 251.85773849487305,
"used": 7.9049072265625
},
"gpu": "NVIDIA A100-SXM4-80GB",
"gpu_count": 2,
"gpu_devices": [
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
},
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
}
],
"memory": {
"total": 503.7154769897461
}
}

View File

@ -1 +0,0 @@
{"epoch": 0, "loss": 1.1899254322052002, "_timestamp": 1698040660.278502, "_runtime": 182.1265389919281, "_step": 355, "_wandb": {"runtime": 180}}

File diff suppressed because it is too large Load Diff

View File

@ -1,27 +0,0 @@
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_setup.py:_flush():76] Configure stats pid to 49300
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_setup.py:_flush():76] Loading settings from /home/chenj0g/.config/wandb/settings
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_setup.py:_flush():76] Loading settings from /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/settings
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program': '/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py'}
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_init.py:_log_setup():507] Logging user logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_085438-bxwpu63q/logs/debug.log
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_init.py:_log_setup():508] Logging internal logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_085438-bxwpu63q/logs/debug-internal.log
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_init.py:init():547] calling init triggers
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
config: {}
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_init.py:init():595] starting backend
2023-10-23 08:54:38,127 INFO MainThread:49300 [wandb_init.py:init():599] setting up manager
2023-10-23 08:54:38,129 INFO MainThread:49300 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2023-10-23 08:54:38,151 INFO MainThread:49300 [wandb_init.py:init():605] backend started and connected
2023-10-23 08:54:38,153 INFO MainThread:49300 [wandb_init.py:init():695] updated telemetry
2023-10-23 08:54:38,561 INFO MainThread:49300 [wandb_init.py:init():732] communicating run to backend with 60.0 second timeout
2023-10-23 08:54:39,256 INFO MainThread:49300 [wandb_run.py:_on_init():2176] communicating current version
2023-10-23 08:54:39,594 INFO MainThread:49300 [wandb_run.py:_on_init():2185] got version response upgrade_message: "wandb version 0.15.12 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
2023-10-23 08:54:39,594 INFO MainThread:49300 [wandb_init.py:init():782] starting run threads in backend
2023-10-23 08:54:52,772 INFO MainThread:49300 [wandb_run.py:_console_start():2157] atexit reg
2023-10-23 08:54:52,772 INFO MainThread:49300 [wandb_run.py:_redirect():2012] redirect: SettingsConsole.WRAP_RAW
2023-10-23 08:54:52,772 INFO MainThread:49300 [wandb_run.py:_redirect():2077] Wrapping output streams.
2023-10-23 08:54:52,772 INFO MainThread:49300 [wandb_run.py:_redirect():2102] Redirects installed.
2023-10-23 08:54:52,773 INFO MainThread:49300 [wandb_init.py:init():824] run started, returning control to user process
2023-10-23 08:54:52,773 INFO MainThread:49300 [wandb_watch.py:watch():51] Watching
2023-10-23 08:57:49,249 WARNING MsgRouterThr:49300 [router.py:message_loop():77] message_loop has been closed

View File

@ -1,297 +0,0 @@
name: eye
channels:
- pytorch
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _openmp_mutex=5.1=1_gnu
- blas=1.0=mkl
- brotlipy=0.7.0=py39h27cfd23_1003
- bzip2=1.0.8=h7b6447c_0
- ca-certificates=2023.01.10=h06a4308_0
- certifi=2022.12.7=py39h06a4308_0
- cffi=1.15.1=py39h5eee18b_3
- charset-normalizer=2.0.4=pyhd3eb1b0_0
- cryptography=39.0.1=py39h9ce1e76_0
- cudatoolkit=11.3.1=h2bc3f7f_2
- ffmpeg=4.3=hf484d3e_0
- flit-core=3.8.0=py39h06a4308_0
- freetype=2.12.1=h4a9f257_0
- giflib=5.2.1=h5eee18b_3
- gmp=6.2.1=h295c915_3
- gnutls=3.6.15=he1e5248_0
- idna=3.4=py39h06a4308_0
- intel-openmp=2021.4.0=h06a4308_3561
- jpeg=9e=h5eee18b_1
- lame=3.100=h7b6447c_0
- lcms2=2.12=h3be6417_0
- ld_impl_linux-64=2.38=h1181459_1
- lerc=3.0=h295c915_0
- libdeflate=1.17=h5eee18b_0
- libffi=3.4.2=h6a678d5_6
- libgcc-ng=11.2.0=h1234567_1
- libgomp=11.2.0=h1234567_1
- libiconv=1.16=h7f8727e_2
- libidn2=2.3.2=h7f8727e_0
- libpng=1.6.39=h5eee18b_0
- libstdcxx-ng=11.2.0=h1234567_1
- libtasn1=4.19.0=h5eee18b_0
- libtiff=4.5.0=h6a678d5_2
- libunistring=0.9.10=h27cfd23_0
- libwebp=1.2.4=h11a3e52_1
- libwebp-base=1.2.4=h5eee18b_1
- lz4-c=1.9.4=h6a678d5_0
- mkl=2021.4.0=h06a4308_640
- mkl-service=2.4.0=py39h7f8727e_0
- mkl_fft=1.3.1=py39hd3c417c_0
- mkl_random=1.2.2=py39h51133e4_0
- ncurses=6.4=h6a678d5_0
- nettle=3.7.3=hbbd107a_1
- numpy=1.23.5=py39h14f4228_0
- numpy-base=1.23.5=py39h31eccc5_0
- openh264=2.1.1=h4ff587b_0
- openssl=1.1.1t=h7f8727e_0
- pillow=9.4.0=py39h6a678d5_0
- pip=23.0.1=py39h06a4308_0
- pycparser=2.21=pyhd3eb1b0_0
- pyopenssl=23.0.0=py39h06a4308_0
- pysocks=1.7.1=py39h06a4308_0
- python=3.9.16=h7a1cb2a_2
- pytorch-mutex=1.0=cuda
- readline=8.2=h5eee18b_0
- requests=2.28.1=py39h06a4308_1
- setuptools=65.6.3=py39h06a4308_0
- six=1.16.0=pyhd3eb1b0_1
- sqlite=3.41.1=h5eee18b_0
- tk=8.6.12=h1ccaba5_0
- torchaudio=0.12.1=py39_cu113
- torchvision=0.13.1=py39_cu113
- typing_extensions=4.4.0=py39h06a4308_0
- urllib3=1.26.15=py39h06a4308_0
- wheel=0.38.4=py39h06a4308_0
- xz=5.2.10=h5eee18b_1
- zlib=1.2.13=h5eee18b_0
- zstd=1.5.4=hc292b87_0
- pip:
- accelerate==0.20.3
- aiofiles==23.1.0
- aiohttp==3.8.4
- aiosignal==1.3.1
- altair==4.2.2
- antlr4-python3-runtime==4.9.3
- anyio==3.6.2
- appdirs==1.4.4
- argon2-cffi==21.3.0
- argon2-cffi-bindings==21.2.0
- arrow==1.2.3
- asttokens==2.2.1
- async-timeout==4.0.2
- attrs==22.2.0
- backcall==0.2.0
- beautifulsoup4==4.12.2
- bitsandbytes==0.37.0
- bleach==6.0.0
- blis==0.7.9
- braceexpand==0.1.7
- catalogue==2.0.8
- cchardet==2.1.7
- chardet==5.1.0
- click==8.1.3
- cloudpickle==2.2.1
- cmake==3.26.1
- comm==0.1.3
- confection==0.0.4
- contourpy==1.0.7
- cycler==0.11.0
- cymem==2.0.7
- datasets==2.13.1
- debugpy==1.6.7
- decorator==5.1.1
- decord==0.6.0
- defusedxml==0.7.1
- dill==0.3.6
- docker-pycreds==0.4.0
- einops==0.6.0
- entrypoints==0.4
- executing==1.2.0
- fairscale==0.4.13
- fastapi==0.95.0
- fastjsonschema==2.16.3
- ffmpy==0.3.0
- filelock==3.9.0
- fire==0.5.0
- fonttools==4.38.0
- fqdn==1.5.1
- frozenlist==1.3.3
- fsspec==2023.4.0
- gitdb==4.0.10
- gitpython==3.1.31
- gradio==3.24.1
- gradio-client==0.0.8
- h11==0.14.0
- httpcore==0.16.3
- httpx==0.23.3
- huggingface-hub==0.16.4
- imageio==2.31.1
- importlib-metadata==6.2.0
- importlib-resources==5.12.0
- iopath==0.1.10
- ipykernel==6.22.0
- ipython==8.12.0
- ipython-genutils==0.2.0
- isoduration==20.11.0
- jedi==0.18.2
- jinja2==3.1.2
- joblib==1.2.0
- jsonpointer==2.3
- jsonschema==4.17.3
- jupyter-client==8.1.0
- jupyter-core==5.3.0
- jupyter-events==0.6.3
- jupyter-server==2.5.0
- jupyter-server-terminals==0.4.4
- jupyterlab-pygments==0.2.2
- kiwisolver==1.4.4
- langcodes==3.3.0
- lazy-loader==0.2
- linkify-it-py==2.0.0
- lit==16.0.0
- llvmlite==0.39.1
- loralib==0.1.1
- markdown-it-py==2.2.0
- markupsafe==2.1.2
- matplotlib==3.7.0
- matplotlib-inline==0.1.6
- mdit-py-plugins==0.3.3
- mdurl==0.1.2
- mistune==2.0.5
- mpmath==1.3.0
- multidict==6.0.4
- multiprocess==0.70.14
- murmurhash==1.0.9
- nbclassic==0.5.5
- nbclient==0.7.3
- nbconvert==7.3.0
- nbformat==5.8.0
- nest-asyncio==1.5.6
- networkx==3.1
- nltk==3.8.1
- notebook==6.5.4
- notebook-shim==0.2.2
- numba==0.56.4
- nvidia-cublas-cu11==11.10.3.66
- nvidia-cuda-cupti-cu11==11.7.101
- nvidia-cuda-nvrtc-cu11==11.7.99
- nvidia-cuda-runtime-cu11==11.7.99
- nvidia-cudnn-cu11==8.5.0.96
- nvidia-cufft-cu11==10.9.0.58
- nvidia-curand-cu11==10.2.10.91
- nvidia-cusolver-cu11==11.4.0.1
- nvidia-cusparse-cu11==11.7.4.91
- nvidia-nccl-cu11==2.14.3
- nvidia-nvtx-cu11==11.7.91
- omegaconf==2.3.0
- openai==0.27.0
- opencv-python==4.7.0.72
- orjson==3.8.9
- packaging==23.0
- pandas==2.0.0
- pandocfilters==1.5.0
- parso==0.8.3
- pathlib==1.0.1
- pathtools==0.1.2
- pathy==0.10.1
- peft==0.2.0
- pexpect==4.8.0
- pickleshare==0.7.5
- platformdirs==3.2.0
- policies==0.4.2
- portalocker==2.7.0
- preshed==3.0.8
- progressbar2==4.2.0
- prometheus-client==0.16.0
- prompt-toolkit==3.0.38
- protobuf==4.22.1
- psutil==5.9.4
- ptyprocess==0.7.0
- pure-eval==0.2.2
- pyarrow==12.0.1
- pycocoevalcap==1.2
- pycocotools==2.0.6
- pycryptodome==3.17
- pydantic==1.10.7
- pydub==0.25.1
- pygments==2.14.0
- pynndescent==0.5.8
- pyparsing==3.0.9
- pyrsistent==0.19.3
- python-dateutil==2.8.2
- python-json-logger==2.0.7
- python-multipart==0.0.6
- python-utils==3.7.0
- pytz==2023.3
- pywavelets==1.4.1
- pyyaml==6.0
- pyzmq==25.0.2
- regex==2022.10.31
- rfc3339-validator==0.1.4
- rfc3986==1.5.0
- rfc3986-validator==0.1.1
- safetensors==0.3.1
- scikit-image==0.21.0
- scikit-learn==1.2.2
- scipy==1.10.1
- seaborn==0.12.2
- semantic-version==2.10.0
- send2trash==1.8.0
- sentence-transformers==2.2.2
- sentencepiece==0.1.97
- sentry-sdk==1.19.1
- setproctitle==1.3.2
- smart-open==6.3.0
- smmap==5.0.0
- sniffio==1.3.0
- soupsieve==2.4
- spacy==3.5.1
- spacy-legacy==3.0.12
- spacy-loggers==1.0.4
- srsly==2.4.6
- stack-data==0.6.2
- starlette==0.26.1
- submitit==1.4.5
- sympy==1.11.1
- tenacity==8.2.2
- termcolor==2.3.0
- terminado==0.17.1
- thinc==8.1.9
- threadpoolctl==3.1.0
- tifffile==2023.4.12
- timm==0.6.13
- tinycss2==1.2.1
- tokenizers==0.13.3
- toolz==0.12.0
- torch==2.0.0
- tornado==6.2
- tqdm==4.64.1
- traitlets==5.9.0
- transformers==4.31.0
- triton==2.0.0
- typer==0.7.0
- tzdata==2023.3
- uc-micro-py==1.0.1
- umap-learn==0.5.3
- uri-template==1.2.0
- uvicorn==0.21.1
- visual-genome==1.1.1
- wandb==0.14.2
- wasabi==1.1.1
- wcwidth==0.2.6
- webcolors==1.13
- webdataset==0.2.48
- webencodings==0.5.1
- websocket-client==1.5.1
- websockets==11.0.1
- xxhash==3.2.0
- yarl==1.8.2
- zipp==3.14.0
prefix: /home/chenj0g/anaconda3/envs/eye

View File

@ -1,38 +0,0 @@
wandb_version: 1
_wandb:
desc: null
value:
python_version: 3.9.16
cli_version: 0.14.2
framework: huggingface
huggingface_version: 4.31.0
is_jupyter_run: false
is_kaggle_kernel: false
start_time: 1698040858.125822
t:
1:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
2:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
3:
- 1
- 13
- 23
4: 3.9.16
5: 0.14.2
6: 4.31.0
8:
- 5

View File

@ -1,164 +0,0 @@
2023-10-23 09:01:04,885 [INFO] Start training
batch sizes [[2]]
module.llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_B.weight
module.llama_proj.weight
module.llama_proj.bias
2023-10-23 09:01:07,002 [INFO] dataset_ratios not specified, datasets will be concatenated (map-style datasets) or chained (webdataset.DataPipeline).
2023-10-23 09:01:07,002 [INFO] Loaded 12171 records for train split from the dataset.
2023-10-23 09:01:07,020 [INFO] number of trainable parameters: 56627200
2023-10-23 09:01:07,021 [INFO] Start training epoch 0, 1000 iters per inner epoch.
Train: data epoch: [0] [ 0/1000] eta: 0:45:28 lr: 0.000001 loss: 1.3049 time: 2.7288 data: 0.0000 max mem: 33055
/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Train: data epoch: [0] [ 50/1000] eta: 0:07:58 lr: 0.000001 loss: 1.2327 time: 0.4508 data: 0.0000 max mem: 38295
Train: data epoch: [0] [ 100/1000] eta: 0:07:10 lr: 0.000002 loss: 1.1049 time: 0.4457 data: 0.0000 max mem: 39575
Train: data epoch: [0] [ 150/1000] eta: 0:06:42 lr: 0.000002 loss: 1.2879 time: 0.4630 data: 0.0000 max mem: 40211
Train: data epoch: [0] [ 200/1000] eta: 0:06:18 lr: 0.000003 loss: 1.0077 time: 0.4527 data: 0.0000 max mem: 40211
Train: data epoch: [0] [ 250/1000] eta: 0:05:52 lr: 0.000003 loss: 1.4790 time: 0.4626 data: 0.0000 max mem: 41450
Train: data epoch: [0] [ 300/1000] eta: 0:05:27 lr: 0.000004 loss: 1.2864 time: 0.4639 data: 0.0000 max mem: 41450
Traceback (most recent call last):
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py", line 118, in <module>
main()
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py", line 114, in main
runner.train()
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/runners/runner_base.py", line 377, in train
train_stats = self.train_epoch(cur_epoch)
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/runners/runner_base.py", line 437, in train_epoch
return self.task.train_epoch(
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 116, in train_epoch
return self._train_inner_loop(
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 225, in _train_inner_loop
scaler.scale(loss).backward()
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/autograd/__init__.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
KeyboardInterrupt

View File

@ -1,246 +0,0 @@
accelerate==0.20.3
aiofiles==23.2.1
aiohttp==3.8.4
aiosignal==1.3.1
altair==5.1.2
antlr4-python3-runtime==4.9.3
anyio==3.6.2
appdirs==1.4.4
argon2-cffi-bindings==21.2.0
argon2-cffi==21.3.0
arrow==1.2.3
asttokens==2.2.1
async-timeout==4.0.2
attrs==22.2.0
backcall==0.2.0
beautifulsoup4==4.12.2
bitsandbytes==0.37.0
bleach==6.0.0
blis==0.7.9
braceexpand==0.1.7
brotlipy==0.7.0
catalogue==2.0.8
cchardet==2.1.7
certifi==2022.12.7
cffi==1.15.1
chardet==5.1.0
charset-normalizer==2.0.4
click==8.1.3
cloudpickle==2.2.1
cmake==3.26.1
comm==0.1.3
confection==0.0.4
contourpy==1.0.7
cryptography==39.0.1
cycler==0.11.0
cymem==2.0.7
datasets==2.13.1
debugpy==1.6.7
decorator==5.1.1
decord==0.6.0
defusedxml==0.7.1
dill==0.3.6
docker-pycreds==0.4.0
einops==0.6.0
entrypoints==0.4
executing==1.2.0
fairscale==0.4.13
fastapi==0.95.0
fastjsonschema==2.16.3
ffmpy==0.3.1
filelock==3.9.0
fire==0.5.0
flit-core==3.8.0
fonttools==4.38.0
fqdn==1.5.1
frozenlist==1.3.3
fsspec==2023.9.2
gitdb==4.0.10
gitpython==3.1.31
gradio-client==0.6.0
gradio==3.24.1
h11==0.14.0
httpcore==0.18.0
httpx==0.25.0
huggingface-hub==0.18.0
idna==3.4
imageio==2.31.1
importlib-metadata==6.2.0
importlib-resources==5.12.0
iopath==0.1.10
ipykernel==6.22.0
ipython-genutils==0.2.0
ipython==8.12.0
isoduration==20.11.0
jedi==0.18.2
jinja2==3.1.2
joblib==1.2.0
jsonpointer==2.3
jsonschema==4.17.3
jupyter-client==8.1.0
jupyter-core==5.3.0
jupyter-events==0.6.3
jupyter-server-terminals==0.4.4
jupyter-server==2.5.0
jupyterlab-pygments==0.2.2
kiwisolver==1.4.4
langcodes==3.3.0
lazy-loader==0.2
linkify-it-py==2.0.2
lit==16.0.0
llvmlite==0.39.1
loralib==0.1.1
markdown-it-py==2.2.0
markupsafe==2.1.2
matplotlib-inline==0.1.6
matplotlib==3.7.0
mdit-py-plugins==0.3.3
mdurl==0.1.2
mistune==2.0.5
mkl-fft==1.3.1
mkl-random==1.2.2
mkl-service==2.4.0
mpmath==1.3.0
multidict==6.0.4
multiprocess==0.70.14
murmurhash==1.0.9
nbclassic==0.5.5
nbclient==0.7.3
nbconvert==7.3.0
nbformat==5.8.0
nest-asyncio==1.5.6
networkx==3.1
nltk==3.8.1
notebook-shim==0.2.2
notebook==6.5.4
numba==0.56.4
numpy==1.23.5
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-cupti-cu11==11.7.101
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
nvidia-cufft-cu11==10.9.0.58
nvidia-curand-cu11==10.2.10.91
nvidia-cusolver-cu11==11.4.0.1
nvidia-cusparse-cu11==11.7.4.91
nvidia-nccl-cu11==2.14.3
nvidia-nvtx-cu11==11.7.91
omegaconf==2.3.0
openai==0.27.0
opencv-python==4.7.0.72
orjson==3.9.8
packaging==23.0
pandas==2.0.0
pandocfilters==1.5.0
parso==0.8.3
pathlib==1.0.1
pathtools==0.1.2
pathy==0.10.1
peft==0.2.0
pexpect==4.8.0
pickleshare==0.7.5
pillow==9.4.0
pip==23.0.1
platformdirs==3.2.0
policies==0.4.2
portalocker==2.7.0
preshed==3.0.8
progressbar2==4.2.0
prometheus-client==0.16.0
prompt-toolkit==3.0.38
protobuf==4.22.1
psutil==5.9.4
ptyprocess==0.7.0
pure-eval==0.2.2
pyarrow==12.0.1
pycocoevalcap==1.2
pycocotools==2.0.6
pycparser==2.21
pycryptodome==3.17
pydantic==1.10.7
pydub==0.25.1
pygments==2.14.0
pynndescent==0.5.8
pyopenssl==23.0.0
pyparsing==3.0.9
pyrsistent==0.19.3
pysocks==1.7.1
python-dateutil==2.8.2
python-json-logger==2.0.7
python-multipart==0.0.6
python-utils==3.7.0
pytz==2023.3
pywavelets==1.4.1
pyyaml==6.0
pyzmq==25.0.2
regex==2022.10.31
requests==2.28.1
rfc3339-validator==0.1.4
rfc3986-validator==0.1.1
rfc3986==1.5.0
rpe-index==1.2.0
safetensors==0.3.1
scikit-image==0.21.0
scikit-learn==1.2.2
scipy==1.10.1
seaborn==0.12.2
semantic-version==2.10.0
send2trash==1.8.0
sentence-transformers==2.2.2
sentencepiece==0.1.97
sentry-sdk==1.19.1
setproctitle==1.3.2
setuptools==65.6.3
six==1.16.0
smart-open==6.3.0
smmap==5.0.0
sniffio==1.3.0
soupsieve==2.4
spacy-legacy==3.0.12
spacy-loggers==1.0.4
spacy==3.5.1
srsly==2.4.6
stack-data==0.6.2
starlette==0.26.1
submitit==1.4.5
sympy==1.11.1
tenacity==8.2.2
termcolor==2.3.0
terminado==0.17.1
thinc==8.1.9
threadpoolctl==3.1.0
tifffile==2023.4.12
timm==0.6.13
tinycss2==1.2.1
tokenizers==0.13.3
toolz==0.12.0
torch==2.0.0
torchaudio==0.12.1
torchvision==0.13.1
tornado==6.2
tqdm==4.64.1
traitlets==5.9.0
transformers==4.31.0
triton==2.0.0
typer==0.7.0
typing-extensions==4.4.0
tzdata==2023.3
uc-micro-py==1.0.2
umap-learn==0.5.3
uri-template==1.2.0
urllib3==1.26.15
uvicorn==0.21.1
visual-genome==1.1.1
wandb==0.14.2
wasabi==1.1.1
wcwidth==0.2.6
webcolors==1.13
webdataset==0.2.48
webencodings==0.5.1
websocket-client==1.5.1
websockets==11.0.1
wheel==0.38.4
xxhash==3.2.0
yarl==1.8.2
zipp==3.14.0

View File

@ -1,374 +0,0 @@
{
"os": "Linux-3.10.0-1160.76.1.el7.x86_64-x86_64-with-glibc2.17",
"python": "3.9.16",
"heartbeatAt": "2023-10-23T06:00:59.460778",
"startedAt": "2023-10-23T06:00:58.084251",
"docker": null,
"cuda": null,
"args": [
"--job_name",
"minigpt4_v2_test",
"--cfg-path",
"train_configs/minigpt_v2_finetune.yaml"
],
"state": "running",
"program": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py",
"codePath": "train.py",
"git": {
"remote": "https://github.com/junchen14/MiniGPT-4_finetune",
"commit": "5c3ec8bb730b2e9df23b4bb3eb24108f9c04a8d6"
},
"email": "jun.chen@kaust.edu.sa",
"root": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune",
"host": "gpu201-16-l",
"username": "chenj0g",
"executable": "/home/chenj0g/anaconda3/envs/eye/bin/python",
"cpu_count": 64,
"cpu_count_logical": 64,
"cpu_freq": {
"current": 1996.2770000000016,
"min": 0.0,
"max": 0.0
},
"cpu_freq_per_core": [
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
}
],
"disk": {
"total": 251.85773849487305,
"used": 7.894733428955078
},
"gpu": "NVIDIA A100-SXM4-80GB",
"gpu_count": 2,
"gpu_devices": [
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
},
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
}
],
"memory": {
"total": 503.7154769897461
}
}

View File

@ -1 +0,0 @@
{"epoch": 0, "loss": 1.0476144552230835, "_timestamp": 1698041023.1460156, "_runtime": 165.02019357681274, "_step": 334, "_wandb": {"runtime": 164}}

File diff suppressed because it is too large Load Diff

View File

@ -1,26 +0,0 @@
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_setup.py:_flush():76] Configure stats pid to 51105
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_setup.py:_flush():76] Loading settings from /home/chenj0g/.config/wandb/settings
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_setup.py:_flush():76] Loading settings from /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/settings
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program': '/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py'}
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_init.py:_log_setup():507] Logging user logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_090058-141dzr9c/logs/debug.log
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_init.py:_log_setup():508] Logging internal logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_090058-141dzr9c/logs/debug-internal.log
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_init.py:init():547] calling init triggers
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
config: {}
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_init.py:init():595] starting backend
2023-10-23 09:00:58,119 INFO MainThread:51105 [wandb_init.py:init():599] setting up manager
2023-10-23 09:00:58,121 INFO MainThread:51105 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2023-10-23 09:00:58,125 INFO MainThread:51105 [wandb_init.py:init():605] backend started and connected
2023-10-23 09:00:58,127 INFO MainThread:51105 [wandb_init.py:init():695] updated telemetry
2023-10-23 09:00:58,534 INFO MainThread:51105 [wandb_init.py:init():732] communicating run to backend with 60.0 second timeout
2023-10-23 09:00:59,118 INFO MainThread:51105 [wandb_run.py:_on_init():2176] communicating current version
2023-10-23 09:00:59,434 INFO MainThread:51105 [wandb_run.py:_on_init():2185] got version response upgrade_message: "wandb version 0.15.12 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
2023-10-23 09:00:59,434 INFO MainThread:51105 [wandb_init.py:init():782] starting run threads in backend
2023-10-23 09:01:04,878 INFO MainThread:51105 [wandb_run.py:_console_start():2157] atexit reg
2023-10-23 09:01:04,878 INFO MainThread:51105 [wandb_run.py:_redirect():2012] redirect: SettingsConsole.WRAP_RAW
2023-10-23 09:01:04,878 INFO MainThread:51105 [wandb_run.py:_redirect():2077] Wrapping output streams.
2023-10-23 09:01:04,878 INFO MainThread:51105 [wandb_run.py:_redirect():2102] Redirects installed.
2023-10-23 09:01:04,879 INFO MainThread:51105 [wandb_init.py:init():824] run started, returning control to user process
2023-10-23 09:01:04,879 INFO MainThread:51105 [wandb_watch.py:watch():51] Watching

View File

@ -1,297 +0,0 @@
name: eye
channels:
- pytorch
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _openmp_mutex=5.1=1_gnu
- blas=1.0=mkl
- brotlipy=0.7.0=py39h27cfd23_1003
- bzip2=1.0.8=h7b6447c_0
- ca-certificates=2023.01.10=h06a4308_0
- certifi=2022.12.7=py39h06a4308_0
- cffi=1.15.1=py39h5eee18b_3
- charset-normalizer=2.0.4=pyhd3eb1b0_0
- cryptography=39.0.1=py39h9ce1e76_0
- cudatoolkit=11.3.1=h2bc3f7f_2
- ffmpeg=4.3=hf484d3e_0
- flit-core=3.8.0=py39h06a4308_0
- freetype=2.12.1=h4a9f257_0
- giflib=5.2.1=h5eee18b_3
- gmp=6.2.1=h295c915_3
- gnutls=3.6.15=he1e5248_0
- idna=3.4=py39h06a4308_0
- intel-openmp=2021.4.0=h06a4308_3561
- jpeg=9e=h5eee18b_1
- lame=3.100=h7b6447c_0
- lcms2=2.12=h3be6417_0
- ld_impl_linux-64=2.38=h1181459_1
- lerc=3.0=h295c915_0
- libdeflate=1.17=h5eee18b_0
- libffi=3.4.2=h6a678d5_6
- libgcc-ng=11.2.0=h1234567_1
- libgomp=11.2.0=h1234567_1
- libiconv=1.16=h7f8727e_2
- libidn2=2.3.2=h7f8727e_0
- libpng=1.6.39=h5eee18b_0
- libstdcxx-ng=11.2.0=h1234567_1
- libtasn1=4.19.0=h5eee18b_0
- libtiff=4.5.0=h6a678d5_2
- libunistring=0.9.10=h27cfd23_0
- libwebp=1.2.4=h11a3e52_1
- libwebp-base=1.2.4=h5eee18b_1
- lz4-c=1.9.4=h6a678d5_0
- mkl=2021.4.0=h06a4308_640
- mkl-service=2.4.0=py39h7f8727e_0
- mkl_fft=1.3.1=py39hd3c417c_0
- mkl_random=1.2.2=py39h51133e4_0
- ncurses=6.4=h6a678d5_0
- nettle=3.7.3=hbbd107a_1
- numpy=1.23.5=py39h14f4228_0
- numpy-base=1.23.5=py39h31eccc5_0
- openh264=2.1.1=h4ff587b_0
- openssl=1.1.1t=h7f8727e_0
- pillow=9.4.0=py39h6a678d5_0
- pip=23.0.1=py39h06a4308_0
- pycparser=2.21=pyhd3eb1b0_0
- pyopenssl=23.0.0=py39h06a4308_0
- pysocks=1.7.1=py39h06a4308_0
- python=3.9.16=h7a1cb2a_2
- pytorch-mutex=1.0=cuda
- readline=8.2=h5eee18b_0
- requests=2.28.1=py39h06a4308_1
- setuptools=65.6.3=py39h06a4308_0
- six=1.16.0=pyhd3eb1b0_1
- sqlite=3.41.1=h5eee18b_0
- tk=8.6.12=h1ccaba5_0
- torchaudio=0.12.1=py39_cu113
- torchvision=0.13.1=py39_cu113
- typing_extensions=4.4.0=py39h06a4308_0
- urllib3=1.26.15=py39h06a4308_0
- wheel=0.38.4=py39h06a4308_0
- xz=5.2.10=h5eee18b_1
- zlib=1.2.13=h5eee18b_0
- zstd=1.5.4=hc292b87_0
- pip:
- accelerate==0.20.3
- aiofiles==23.1.0
- aiohttp==3.8.4
- aiosignal==1.3.1
- altair==4.2.2
- antlr4-python3-runtime==4.9.3
- anyio==3.6.2
- appdirs==1.4.4
- argon2-cffi==21.3.0
- argon2-cffi-bindings==21.2.0
- arrow==1.2.3
- asttokens==2.2.1
- async-timeout==4.0.2
- attrs==22.2.0
- backcall==0.2.0
- beautifulsoup4==4.12.2
- bitsandbytes==0.37.0
- bleach==6.0.0
- blis==0.7.9
- braceexpand==0.1.7
- catalogue==2.0.8
- cchardet==2.1.7
- chardet==5.1.0
- click==8.1.3
- cloudpickle==2.2.1
- cmake==3.26.1
- comm==0.1.3
- confection==0.0.4
- contourpy==1.0.7
- cycler==0.11.0
- cymem==2.0.7
- datasets==2.13.1
- debugpy==1.6.7
- decorator==5.1.1
- decord==0.6.0
- defusedxml==0.7.1
- dill==0.3.6
- docker-pycreds==0.4.0
- einops==0.6.0
- entrypoints==0.4
- executing==1.2.0
- fairscale==0.4.13
- fastapi==0.95.0
- fastjsonschema==2.16.3
- ffmpy==0.3.0
- filelock==3.9.0
- fire==0.5.0
- fonttools==4.38.0
- fqdn==1.5.1
- frozenlist==1.3.3
- fsspec==2023.4.0
- gitdb==4.0.10
- gitpython==3.1.31
- gradio==3.24.1
- gradio-client==0.0.8
- h11==0.14.0
- httpcore==0.16.3
- httpx==0.23.3
- huggingface-hub==0.16.4
- imageio==2.31.1
- importlib-metadata==6.2.0
- importlib-resources==5.12.0
- iopath==0.1.10
- ipykernel==6.22.0
- ipython==8.12.0
- ipython-genutils==0.2.0
- isoduration==20.11.0
- jedi==0.18.2
- jinja2==3.1.2
- joblib==1.2.0
- jsonpointer==2.3
- jsonschema==4.17.3
- jupyter-client==8.1.0
- jupyter-core==5.3.0
- jupyter-events==0.6.3
- jupyter-server==2.5.0
- jupyter-server-terminals==0.4.4
- jupyterlab-pygments==0.2.2
- kiwisolver==1.4.4
- langcodes==3.3.0
- lazy-loader==0.2
- linkify-it-py==2.0.0
- lit==16.0.0
- llvmlite==0.39.1
- loralib==0.1.1
- markdown-it-py==2.2.0
- markupsafe==2.1.2
- matplotlib==3.7.0
- matplotlib-inline==0.1.6
- mdit-py-plugins==0.3.3
- mdurl==0.1.2
- mistune==2.0.5
- mpmath==1.3.0
- multidict==6.0.4
- multiprocess==0.70.14
- murmurhash==1.0.9
- nbclassic==0.5.5
- nbclient==0.7.3
- nbconvert==7.3.0
- nbformat==5.8.0
- nest-asyncio==1.5.6
- networkx==3.1
- nltk==3.8.1
- notebook==6.5.4
- notebook-shim==0.2.2
- numba==0.56.4
- nvidia-cublas-cu11==11.10.3.66
- nvidia-cuda-cupti-cu11==11.7.101
- nvidia-cuda-nvrtc-cu11==11.7.99
- nvidia-cuda-runtime-cu11==11.7.99
- nvidia-cudnn-cu11==8.5.0.96
- nvidia-cufft-cu11==10.9.0.58
- nvidia-curand-cu11==10.2.10.91
- nvidia-cusolver-cu11==11.4.0.1
- nvidia-cusparse-cu11==11.7.4.91
- nvidia-nccl-cu11==2.14.3
- nvidia-nvtx-cu11==11.7.91
- omegaconf==2.3.0
- openai==0.27.0
- opencv-python==4.7.0.72
- orjson==3.8.9
- packaging==23.0
- pandas==2.0.0
- pandocfilters==1.5.0
- parso==0.8.3
- pathlib==1.0.1
- pathtools==0.1.2
- pathy==0.10.1
- peft==0.2.0
- pexpect==4.8.0
- pickleshare==0.7.5
- platformdirs==3.2.0
- policies==0.4.2
- portalocker==2.7.0
- preshed==3.0.8
- progressbar2==4.2.0
- prometheus-client==0.16.0
- prompt-toolkit==3.0.38
- protobuf==4.22.1
- psutil==5.9.4
- ptyprocess==0.7.0
- pure-eval==0.2.2
- pyarrow==12.0.1
- pycocoevalcap==1.2
- pycocotools==2.0.6
- pycryptodome==3.17
- pydantic==1.10.7
- pydub==0.25.1
- pygments==2.14.0
- pynndescent==0.5.8
- pyparsing==3.0.9
- pyrsistent==0.19.3
- python-dateutil==2.8.2
- python-json-logger==2.0.7
- python-multipart==0.0.6
- python-utils==3.7.0
- pytz==2023.3
- pywavelets==1.4.1
- pyyaml==6.0
- pyzmq==25.0.2
- regex==2022.10.31
- rfc3339-validator==0.1.4
- rfc3986==1.5.0
- rfc3986-validator==0.1.1
- safetensors==0.3.1
- scikit-image==0.21.0
- scikit-learn==1.2.2
- scipy==1.10.1
- seaborn==0.12.2
- semantic-version==2.10.0
- send2trash==1.8.0
- sentence-transformers==2.2.2
- sentencepiece==0.1.97
- sentry-sdk==1.19.1
- setproctitle==1.3.2
- smart-open==6.3.0
- smmap==5.0.0
- sniffio==1.3.0
- soupsieve==2.4
- spacy==3.5.1
- spacy-legacy==3.0.12
- spacy-loggers==1.0.4
- srsly==2.4.6
- stack-data==0.6.2
- starlette==0.26.1
- submitit==1.4.5
- sympy==1.11.1
- tenacity==8.2.2
- termcolor==2.3.0
- terminado==0.17.1
- thinc==8.1.9
- threadpoolctl==3.1.0
- tifffile==2023.4.12
- timm==0.6.13
- tinycss2==1.2.1
- tokenizers==0.13.3
- toolz==0.12.0
- torch==2.0.0
- tornado==6.2
- tqdm==4.64.1
- traitlets==5.9.0
- transformers==4.31.0
- triton==2.0.0
- typer==0.7.0
- tzdata==2023.3
- uc-micro-py==1.0.1
- umap-learn==0.5.3
- uri-template==1.2.0
- uvicorn==0.21.1
- visual-genome==1.1.1
- wandb==0.14.2
- wasabi==1.1.1
- wcwidth==0.2.6
- webcolors==1.13
- webdataset==0.2.48
- webencodings==0.5.1
- websocket-client==1.5.1
- websockets==11.0.1
- xxhash==3.2.0
- yarl==1.8.2
- zipp==3.14.0
prefix: /home/chenj0g/anaconda3/envs/eye

View File

@ -1,38 +0,0 @@
wandb_version: 1
_wandb:
desc: null
value:
python_version: 3.9.16
cli_version: 0.14.2
framework: huggingface
huggingface_version: 4.31.0
is_jupyter_run: false
is_kaggle_kernel: false
start_time: 1698041430.035569
t:
1:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
2:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
3:
- 1
- 13
- 23
4: 3.9.16
5: 0.14.2
6: 4.31.0
8:
- 5

View File

@ -1,2 +0,0 @@
/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")

View File

@ -1,246 +0,0 @@
accelerate==0.20.3
aiofiles==23.2.1
aiohttp==3.8.4
aiosignal==1.3.1
altair==5.1.2
antlr4-python3-runtime==4.9.3
anyio==3.6.2
appdirs==1.4.4
argon2-cffi-bindings==21.2.0
argon2-cffi==21.3.0
arrow==1.2.3
asttokens==2.2.1
async-timeout==4.0.2
attrs==22.2.0
backcall==0.2.0
beautifulsoup4==4.12.2
bitsandbytes==0.37.0
bleach==6.0.0
blis==0.7.9
braceexpand==0.1.7
brotlipy==0.7.0
catalogue==2.0.8
cchardet==2.1.7
certifi==2022.12.7
cffi==1.15.1
chardet==5.1.0
charset-normalizer==2.0.4
click==8.1.3
cloudpickle==2.2.1
cmake==3.26.1
comm==0.1.3
confection==0.0.4
contourpy==1.0.7
cryptography==39.0.1
cycler==0.11.0
cymem==2.0.7
datasets==2.13.1
debugpy==1.6.7
decorator==5.1.1
decord==0.6.0
defusedxml==0.7.1
dill==0.3.6
docker-pycreds==0.4.0
einops==0.6.0
entrypoints==0.4
executing==1.2.0
fairscale==0.4.13
fastapi==0.95.0
fastjsonschema==2.16.3
ffmpy==0.3.1
filelock==3.9.0
fire==0.5.0
flit-core==3.8.0
fonttools==4.38.0
fqdn==1.5.1
frozenlist==1.3.3
fsspec==2023.9.2
gitdb==4.0.10
gitpython==3.1.31
gradio-client==0.6.0
gradio==3.24.1
h11==0.14.0
httpcore==0.18.0
httpx==0.25.0
huggingface-hub==0.18.0
idna==3.4
imageio==2.31.1
importlib-metadata==6.2.0
importlib-resources==5.12.0
iopath==0.1.10
ipykernel==6.22.0
ipython-genutils==0.2.0
ipython==8.12.0
isoduration==20.11.0
jedi==0.18.2
jinja2==3.1.2
joblib==1.2.0
jsonpointer==2.3
jsonschema==4.17.3
jupyter-client==8.1.0
jupyter-core==5.3.0
jupyter-events==0.6.3
jupyter-server-terminals==0.4.4
jupyter-server==2.5.0
jupyterlab-pygments==0.2.2
kiwisolver==1.4.4
langcodes==3.3.0
lazy-loader==0.2
linkify-it-py==2.0.2
lit==16.0.0
llvmlite==0.39.1
loralib==0.1.1
markdown-it-py==2.2.0
markupsafe==2.1.2
matplotlib-inline==0.1.6
matplotlib==3.7.0
mdit-py-plugins==0.3.3
mdurl==0.1.2
mistune==2.0.5
mkl-fft==1.3.1
mkl-random==1.2.2
mkl-service==2.4.0
mpmath==1.3.0
multidict==6.0.4
multiprocess==0.70.14
murmurhash==1.0.9
nbclassic==0.5.5
nbclient==0.7.3
nbconvert==7.3.0
nbformat==5.8.0
nest-asyncio==1.5.6
networkx==3.1
nltk==3.8.1
notebook-shim==0.2.2
notebook==6.5.4
numba==0.56.4
numpy==1.23.5
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-cupti-cu11==11.7.101
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
nvidia-cufft-cu11==10.9.0.58
nvidia-curand-cu11==10.2.10.91
nvidia-cusolver-cu11==11.4.0.1
nvidia-cusparse-cu11==11.7.4.91
nvidia-nccl-cu11==2.14.3
nvidia-nvtx-cu11==11.7.91
omegaconf==2.3.0
openai==0.27.0
opencv-python==4.7.0.72
orjson==3.9.8
packaging==23.0
pandas==2.0.0
pandocfilters==1.5.0
parso==0.8.3
pathlib==1.0.1
pathtools==0.1.2
pathy==0.10.1
peft==0.2.0
pexpect==4.8.0
pickleshare==0.7.5
pillow==9.4.0
pip==23.0.1
platformdirs==3.2.0
policies==0.4.2
portalocker==2.7.0
preshed==3.0.8
progressbar2==4.2.0
prometheus-client==0.16.0
prompt-toolkit==3.0.38
protobuf==4.22.1
psutil==5.9.4
ptyprocess==0.7.0
pure-eval==0.2.2
pyarrow==12.0.1
pycocoevalcap==1.2
pycocotools==2.0.6
pycparser==2.21
pycryptodome==3.17
pydantic==1.10.7
pydub==0.25.1
pygments==2.14.0
pynndescent==0.5.8
pyopenssl==23.0.0
pyparsing==3.0.9
pyrsistent==0.19.3
pysocks==1.7.1
python-dateutil==2.8.2
python-json-logger==2.0.7
python-multipart==0.0.6
python-utils==3.7.0
pytz==2023.3
pywavelets==1.4.1
pyyaml==6.0
pyzmq==25.0.2
regex==2022.10.31
requests==2.28.1
rfc3339-validator==0.1.4
rfc3986-validator==0.1.1
rfc3986==1.5.0
rpe-index==1.2.0
safetensors==0.3.1
scikit-image==0.21.0
scikit-learn==1.2.2
scipy==1.10.1
seaborn==0.12.2
semantic-version==2.10.0
send2trash==1.8.0
sentence-transformers==2.2.2
sentencepiece==0.1.97
sentry-sdk==1.19.1
setproctitle==1.3.2
setuptools==65.6.3
six==1.16.0
smart-open==6.3.0
smmap==5.0.0
sniffio==1.3.0
soupsieve==2.4
spacy-legacy==3.0.12
spacy-loggers==1.0.4
spacy==3.5.1
srsly==2.4.6
stack-data==0.6.2
starlette==0.26.1
submitit==1.4.5
sympy==1.11.1
tenacity==8.2.2
termcolor==2.3.0
terminado==0.17.1
thinc==8.1.9
threadpoolctl==3.1.0
tifffile==2023.4.12
timm==0.6.13
tinycss2==1.2.1
tokenizers==0.13.3
toolz==0.12.0
torch==2.0.0
torchaudio==0.12.1
torchvision==0.13.1
tornado==6.2
tqdm==4.64.1
traitlets==5.9.0
transformers==4.31.0
triton==2.0.0
typer==0.7.0
typing-extensions==4.4.0
tzdata==2023.3
uc-micro-py==1.0.2
umap-learn==0.5.3
uri-template==1.2.0
urllib3==1.26.15
uvicorn==0.21.1
visual-genome==1.1.1
wandb==0.14.2
wasabi==1.1.1
wcwidth==0.2.6
webcolors==1.13
webdataset==0.2.48
webencodings==0.5.1
websocket-client==1.5.1
websockets==11.0.1
wheel==0.38.4
xxhash==3.2.0
yarl==1.8.2
zipp==3.14.0

View File

@ -1,374 +0,0 @@
{
"os": "Linux-3.10.0-1160.76.1.el7.x86_64-x86_64-with-glibc2.17",
"python": "3.9.16",
"heartbeatAt": "2023-10-23T06:10:31.384548",
"startedAt": "2023-10-23T06:10:29.992874",
"docker": null,
"cuda": null,
"args": [
"--job_name",
"minigpt4_v2_test",
"--cfg-path",
"train_configs/minigpt_v2_finetune.yaml"
],
"state": "running",
"program": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py",
"codePath": "train.py",
"git": {
"remote": "https://github.com/junchen14/MiniGPT-4_finetune",
"commit": "5c3ec8bb730b2e9df23b4bb3eb24108f9c04a8d6"
},
"email": "jun.chen@kaust.edu.sa",
"root": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune",
"host": "gpu201-16-l",
"username": "chenj0g",
"executable": "/home/chenj0g/anaconda3/envs/eye/bin/python",
"cpu_count": 64,
"cpu_count_logical": 64,
"cpu_freq": {
"current": 1996.2770000000016,
"min": 0.0,
"max": 0.0
},
"cpu_freq_per_core": [
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
}
],
"disk": {
"total": 251.85773849487305,
"used": 7.905696868896484
},
"gpu": "NVIDIA A100-SXM4-80GB",
"gpu_count": 2,
"gpu_devices": [
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
},
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
}
],
"memory": {
"total": 503.7154769897461
}
}

View File

@ -1 +0,0 @@
{"epoch": 0, "loss": 1.071101188659668, "_timestamp": 1698041570.1773224, "_runtime": 140.1417534351349, "_step": 258, "_wandb": {"runtime": 139}}

File diff suppressed because it is too large Load Diff

View File

@ -1,26 +0,0 @@
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_setup.py:_flush():76] Configure stats pid to 53640
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_setup.py:_flush():76] Loading settings from /home/chenj0g/.config/wandb/settings
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_setup.py:_flush():76] Loading settings from /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/settings
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program': '/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py'}
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_init.py:_log_setup():507] Logging user logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_091029-txn4i28h/logs/debug.log
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_init.py:_log_setup():508] Logging internal logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_091029-txn4i28h/logs/debug-internal.log
2023-10-23 09:10:30,028 INFO MainThread:53640 [wandb_init.py:init():547] calling init triggers
2023-10-23 09:10:30,029 INFO MainThread:53640 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
config: {}
2023-10-23 09:10:30,029 INFO MainThread:53640 [wandb_init.py:init():595] starting backend
2023-10-23 09:10:30,029 INFO MainThread:53640 [wandb_init.py:init():599] setting up manager
2023-10-23 09:10:30,030 INFO MainThread:53640 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2023-10-23 09:10:30,035 INFO MainThread:53640 [wandb_init.py:init():605] backend started and connected
2023-10-23 09:10:30,037 INFO MainThread:53640 [wandb_init.py:init():695] updated telemetry
2023-10-23 09:10:30,446 INFO MainThread:53640 [wandb_init.py:init():732] communicating run to backend with 60.0 second timeout
2023-10-23 09:10:31,053 INFO MainThread:53640 [wandb_run.py:_on_init():2176] communicating current version
2023-10-23 09:10:31,357 INFO MainThread:53640 [wandb_run.py:_on_init():2185] got version response upgrade_message: "wandb version 0.15.12 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
2023-10-23 09:10:31,357 INFO MainThread:53640 [wandb_init.py:init():782] starting run threads in backend
2023-10-23 09:10:37,065 INFO MainThread:53640 [wandb_run.py:_console_start():2157] atexit reg
2023-10-23 09:10:37,065 INFO MainThread:53640 [wandb_run.py:_redirect():2012] redirect: SettingsConsole.WRAP_RAW
2023-10-23 09:10:37,065 INFO MainThread:53640 [wandb_run.py:_redirect():2077] Wrapping output streams.
2023-10-23 09:10:37,065 INFO MainThread:53640 [wandb_run.py:_redirect():2102] Redirects installed.
2023-10-23 09:10:37,066 INFO MainThread:53640 [wandb_init.py:init():824] run started, returning control to user process
2023-10-23 09:10:37,066 INFO MainThread:53640 [wandb_watch.py:watch():51] Watching

View File

@ -1,297 +0,0 @@
name: eye
channels:
- pytorch
- defaults
dependencies:
- _libgcc_mutex=0.1=main
- _openmp_mutex=5.1=1_gnu
- blas=1.0=mkl
- brotlipy=0.7.0=py39h27cfd23_1003
- bzip2=1.0.8=h7b6447c_0
- ca-certificates=2023.01.10=h06a4308_0
- certifi=2022.12.7=py39h06a4308_0
- cffi=1.15.1=py39h5eee18b_3
- charset-normalizer=2.0.4=pyhd3eb1b0_0
- cryptography=39.0.1=py39h9ce1e76_0
- cudatoolkit=11.3.1=h2bc3f7f_2
- ffmpeg=4.3=hf484d3e_0
- flit-core=3.8.0=py39h06a4308_0
- freetype=2.12.1=h4a9f257_0
- giflib=5.2.1=h5eee18b_3
- gmp=6.2.1=h295c915_3
- gnutls=3.6.15=he1e5248_0
- idna=3.4=py39h06a4308_0
- intel-openmp=2021.4.0=h06a4308_3561
- jpeg=9e=h5eee18b_1
- lame=3.100=h7b6447c_0
- lcms2=2.12=h3be6417_0
- ld_impl_linux-64=2.38=h1181459_1
- lerc=3.0=h295c915_0
- libdeflate=1.17=h5eee18b_0
- libffi=3.4.2=h6a678d5_6
- libgcc-ng=11.2.0=h1234567_1
- libgomp=11.2.0=h1234567_1
- libiconv=1.16=h7f8727e_2
- libidn2=2.3.2=h7f8727e_0
- libpng=1.6.39=h5eee18b_0
- libstdcxx-ng=11.2.0=h1234567_1
- libtasn1=4.19.0=h5eee18b_0
- libtiff=4.5.0=h6a678d5_2
- libunistring=0.9.10=h27cfd23_0
- libwebp=1.2.4=h11a3e52_1
- libwebp-base=1.2.4=h5eee18b_1
- lz4-c=1.9.4=h6a678d5_0
- mkl=2021.4.0=h06a4308_640
- mkl-service=2.4.0=py39h7f8727e_0
- mkl_fft=1.3.1=py39hd3c417c_0
- mkl_random=1.2.2=py39h51133e4_0
- ncurses=6.4=h6a678d5_0
- nettle=3.7.3=hbbd107a_1
- numpy=1.23.5=py39h14f4228_0
- numpy-base=1.23.5=py39h31eccc5_0
- openh264=2.1.1=h4ff587b_0
- openssl=1.1.1t=h7f8727e_0
- pillow=9.4.0=py39h6a678d5_0
- pip=23.0.1=py39h06a4308_0
- pycparser=2.21=pyhd3eb1b0_0
- pyopenssl=23.0.0=py39h06a4308_0
- pysocks=1.7.1=py39h06a4308_0
- python=3.9.16=h7a1cb2a_2
- pytorch-mutex=1.0=cuda
- readline=8.2=h5eee18b_0
- requests=2.28.1=py39h06a4308_1
- setuptools=65.6.3=py39h06a4308_0
- six=1.16.0=pyhd3eb1b0_1
- sqlite=3.41.1=h5eee18b_0
- tk=8.6.12=h1ccaba5_0
- torchaudio=0.12.1=py39_cu113
- torchvision=0.13.1=py39_cu113
- typing_extensions=4.4.0=py39h06a4308_0
- urllib3=1.26.15=py39h06a4308_0
- wheel=0.38.4=py39h06a4308_0
- xz=5.2.10=h5eee18b_1
- zlib=1.2.13=h5eee18b_0
- zstd=1.5.4=hc292b87_0
- pip:
- accelerate==0.20.3
- aiofiles==23.1.0
- aiohttp==3.8.4
- aiosignal==1.3.1
- altair==4.2.2
- antlr4-python3-runtime==4.9.3
- anyio==3.6.2
- appdirs==1.4.4
- argon2-cffi==21.3.0
- argon2-cffi-bindings==21.2.0
- arrow==1.2.3
- asttokens==2.2.1
- async-timeout==4.0.2
- attrs==22.2.0
- backcall==0.2.0
- beautifulsoup4==4.12.2
- bitsandbytes==0.37.0
- bleach==6.0.0
- blis==0.7.9
- braceexpand==0.1.7
- catalogue==2.0.8
- cchardet==2.1.7
- chardet==5.1.0
- click==8.1.3
- cloudpickle==2.2.1
- cmake==3.26.1
- comm==0.1.3
- confection==0.0.4
- contourpy==1.0.7
- cycler==0.11.0
- cymem==2.0.7
- datasets==2.13.1
- debugpy==1.6.7
- decorator==5.1.1
- decord==0.6.0
- defusedxml==0.7.1
- dill==0.3.6
- docker-pycreds==0.4.0
- einops==0.6.0
- entrypoints==0.4
- executing==1.2.0
- fairscale==0.4.13
- fastapi==0.95.0
- fastjsonschema==2.16.3
- ffmpy==0.3.0
- filelock==3.9.0
- fire==0.5.0
- fonttools==4.38.0
- fqdn==1.5.1
- frozenlist==1.3.3
- fsspec==2023.4.0
- gitdb==4.0.10
- gitpython==3.1.31
- gradio==3.24.1
- gradio-client==0.0.8
- h11==0.14.0
- httpcore==0.16.3
- httpx==0.23.3
- huggingface-hub==0.16.4
- imageio==2.31.1
- importlib-metadata==6.2.0
- importlib-resources==5.12.0
- iopath==0.1.10
- ipykernel==6.22.0
- ipython==8.12.0
- ipython-genutils==0.2.0
- isoduration==20.11.0
- jedi==0.18.2
- jinja2==3.1.2
- joblib==1.2.0
- jsonpointer==2.3
- jsonschema==4.17.3
- jupyter-client==8.1.0
- jupyter-core==5.3.0
- jupyter-events==0.6.3
- jupyter-server==2.5.0
- jupyter-server-terminals==0.4.4
- jupyterlab-pygments==0.2.2
- kiwisolver==1.4.4
- langcodes==3.3.0
- lazy-loader==0.2
- linkify-it-py==2.0.0
- lit==16.0.0
- llvmlite==0.39.1
- loralib==0.1.1
- markdown-it-py==2.2.0
- markupsafe==2.1.2
- matplotlib==3.7.0
- matplotlib-inline==0.1.6
- mdit-py-plugins==0.3.3
- mdurl==0.1.2
- mistune==2.0.5
- mpmath==1.3.0
- multidict==6.0.4
- multiprocess==0.70.14
- murmurhash==1.0.9
- nbclassic==0.5.5
- nbclient==0.7.3
- nbconvert==7.3.0
- nbformat==5.8.0
- nest-asyncio==1.5.6
- networkx==3.1
- nltk==3.8.1
- notebook==6.5.4
- notebook-shim==0.2.2
- numba==0.56.4
- nvidia-cublas-cu11==11.10.3.66
- nvidia-cuda-cupti-cu11==11.7.101
- nvidia-cuda-nvrtc-cu11==11.7.99
- nvidia-cuda-runtime-cu11==11.7.99
- nvidia-cudnn-cu11==8.5.0.96
- nvidia-cufft-cu11==10.9.0.58
- nvidia-curand-cu11==10.2.10.91
- nvidia-cusolver-cu11==11.4.0.1
- nvidia-cusparse-cu11==11.7.4.91
- nvidia-nccl-cu11==2.14.3
- nvidia-nvtx-cu11==11.7.91
- omegaconf==2.3.0
- openai==0.27.0
- opencv-python==4.7.0.72
- orjson==3.8.9
- packaging==23.0
- pandas==2.0.0
- pandocfilters==1.5.0
- parso==0.8.3
- pathlib==1.0.1
- pathtools==0.1.2
- pathy==0.10.1
- peft==0.2.0
- pexpect==4.8.0
- pickleshare==0.7.5
- platformdirs==3.2.0
- policies==0.4.2
- portalocker==2.7.0
- preshed==3.0.8
- progressbar2==4.2.0
- prometheus-client==0.16.0
- prompt-toolkit==3.0.38
- protobuf==4.22.1
- psutil==5.9.4
- ptyprocess==0.7.0
- pure-eval==0.2.2
- pyarrow==12.0.1
- pycocoevalcap==1.2
- pycocotools==2.0.6
- pycryptodome==3.17
- pydantic==1.10.7
- pydub==0.25.1
- pygments==2.14.0
- pynndescent==0.5.8
- pyparsing==3.0.9
- pyrsistent==0.19.3
- python-dateutil==2.8.2
- python-json-logger==2.0.7
- python-multipart==0.0.6
- python-utils==3.7.0
- pytz==2023.3
- pywavelets==1.4.1
- pyyaml==6.0
- pyzmq==25.0.2
- regex==2022.10.31
- rfc3339-validator==0.1.4
- rfc3986==1.5.0
- rfc3986-validator==0.1.1
- safetensors==0.3.1
- scikit-image==0.21.0
- scikit-learn==1.2.2
- scipy==1.10.1
- seaborn==0.12.2
- semantic-version==2.10.0
- send2trash==1.8.0
- sentence-transformers==2.2.2
- sentencepiece==0.1.97
- sentry-sdk==1.19.1
- setproctitle==1.3.2
- smart-open==6.3.0
- smmap==5.0.0
- sniffio==1.3.0
- soupsieve==2.4
- spacy==3.5.1
- spacy-legacy==3.0.12
- spacy-loggers==1.0.4
- srsly==2.4.6
- stack-data==0.6.2
- starlette==0.26.1
- submitit==1.4.5
- sympy==1.11.1
- tenacity==8.2.2
- termcolor==2.3.0
- terminado==0.17.1
- thinc==8.1.9
- threadpoolctl==3.1.0
- tifffile==2023.4.12
- timm==0.6.13
- tinycss2==1.2.1
- tokenizers==0.13.3
- toolz==0.12.0
- torch==2.0.0
- tornado==6.2
- tqdm==4.64.1
- traitlets==5.9.0
- transformers==4.31.0
- triton==2.0.0
- typer==0.7.0
- tzdata==2023.3
- uc-micro-py==1.0.1
- umap-learn==0.5.3
- uri-template==1.2.0
- uvicorn==0.21.1
- visual-genome==1.1.1
- wandb==0.14.2
- wasabi==1.1.1
- wcwidth==0.2.6
- webcolors==1.13
- webdataset==0.2.48
- webencodings==0.5.1
- websocket-client==1.5.1
- websockets==11.0.1
- xxhash==3.2.0
- yarl==1.8.2
- zipp==3.14.0
prefix: /home/chenj0g/anaconda3/envs/eye

View File

@ -1,38 +0,0 @@
wandb_version: 1
_wandb:
desc: null
value:
python_version: 3.9.16
cli_version: 0.14.2
framework: huggingface
huggingface_version: 4.31.0
is_jupyter_run: false
is_kaggle_kernel: false
start_time: 1698041430.036499
t:
1:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
2:
- 1
- 11
- 41
- 49
- 55
- 63
- 71
3:
- 1
- 13
- 23
4: 3.9.16
5: 0.14.2
6: 4.31.0
8:
- 5

View File

@ -1,161 +0,0 @@
2023-10-23 09:10:36,980 [INFO] Start training
batch sizes [[2]]
module.llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.0.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.0.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.1.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.1.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.2.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.2.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.3.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.3.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.4.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.4.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.5.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.5.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.6.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.6.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.7.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.7.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.8.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.8.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.9.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.9.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.10.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.10.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.11.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.11.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.12.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.12.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.13.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.13.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.14.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.14.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.15.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.15.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.16.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.16.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.17.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.17.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.18.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.18.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.19.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.19.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.20.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.20.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.21.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.21.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.22.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.22.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.23.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.23.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.24.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.24.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.25.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.25.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.26.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.26.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.27.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.27.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.28.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.28.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.29.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.29.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.30.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.30.self_attn.v_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.31.self_attn.q_proj.lora_B.weight
module.llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_A.weight
module.llama_model.base_model.model.model.layers.31.self_attn.v_proj.lora_B.weight
module.llama_proj.weight
module.llama_proj.bias
2023-10-23 09:10:39,273 [INFO] dataset_ratios not specified, datasets will be concatenated (map-style datasets) or chained (webdataset.DataPipeline).
2023-10-23 09:10:39,273 [INFO] Loaded 12171 records for train split from the dataset.
2023-10-23 09:10:39,291 [INFO] number of trainable parameters: 56627200
2023-10-23 09:10:39,292 [INFO] Start training epoch 0, 1000 iters per inner epoch.
Train: data epoch: [0] [ 0/1000] eta: 0:54:33 lr: 0.000001 loss: 1.4162 time: 3.2736 data: 0.0000 max mem: 33043
/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Train: data epoch: [0] [ 50/1000] eta: 0:08:41 lr: 0.000001 loss: 1.4426 time: 0.4963 data: 0.0000 max mem: 38128
Train: data epoch: [0] [ 100/1000] eta: 0:07:50 lr: 0.000002 loss: 1.3406 time: 0.4881 data: 0.0000 max mem: 40846
Train: data epoch: [0] [ 150/1000] eta: 0:07:14 lr: 0.000002 loss: 1.5900 time: 0.4890 data: 0.0000 max mem: 41228
Train: data epoch: [0] [ 200/1000] eta: 0:06:45 lr: 0.000003 loss: 1.6308 time: 0.5138 data: 0.0000 max mem: 41228
Train: data epoch: [0] [ 250/1000] eta: 0:06:18 lr: 0.000003 loss: 1.4190 time: 0.5009 data: 0.0000 max mem: 41228
Traceback (most recent call last):
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py", line 113, in <module>
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py", line 109, in main
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/runners/runner_base.py", line 377, in train
train_stats = self.train_epoch(cur_epoch)
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/runners/runner_base.py", line 437, in train_epoch
return self.task.train_epoch(
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 116, in train_epoch
return self._train_inner_loop(
File "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/minigpt4/tasks/base_task.py", line 225, in _train_inner_loop
scaler.scale(loss).backward()
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/home/chenj0g/anaconda3/envs/eye/lib/python3.9/site-packages/torch/autograd/__init__.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
KeyboardInterrupt

View File

@ -1,246 +0,0 @@
accelerate==0.20.3
aiofiles==23.2.1
aiohttp==3.8.4
aiosignal==1.3.1
altair==5.1.2
antlr4-python3-runtime==4.9.3
anyio==3.6.2
appdirs==1.4.4
argon2-cffi-bindings==21.2.0
argon2-cffi==21.3.0
arrow==1.2.3
asttokens==2.2.1
async-timeout==4.0.2
attrs==22.2.0
backcall==0.2.0
beautifulsoup4==4.12.2
bitsandbytes==0.37.0
bleach==6.0.0
blis==0.7.9
braceexpand==0.1.7
brotlipy==0.7.0
catalogue==2.0.8
cchardet==2.1.7
certifi==2022.12.7
cffi==1.15.1
chardet==5.1.0
charset-normalizer==2.0.4
click==8.1.3
cloudpickle==2.2.1
cmake==3.26.1
comm==0.1.3
confection==0.0.4
contourpy==1.0.7
cryptography==39.0.1
cycler==0.11.0
cymem==2.0.7
datasets==2.13.1
debugpy==1.6.7
decorator==5.1.1
decord==0.6.0
defusedxml==0.7.1
dill==0.3.6
docker-pycreds==0.4.0
einops==0.6.0
entrypoints==0.4
executing==1.2.0
fairscale==0.4.13
fastapi==0.95.0
fastjsonschema==2.16.3
ffmpy==0.3.1
filelock==3.9.0
fire==0.5.0
flit-core==3.8.0
fonttools==4.38.0
fqdn==1.5.1
frozenlist==1.3.3
fsspec==2023.9.2
gitdb==4.0.10
gitpython==3.1.31
gradio-client==0.6.0
gradio==3.24.1
h11==0.14.0
httpcore==0.18.0
httpx==0.25.0
huggingface-hub==0.18.0
idna==3.4
imageio==2.31.1
importlib-metadata==6.2.0
importlib-resources==5.12.0
iopath==0.1.10
ipykernel==6.22.0
ipython-genutils==0.2.0
ipython==8.12.0
isoduration==20.11.0
jedi==0.18.2
jinja2==3.1.2
joblib==1.2.0
jsonpointer==2.3
jsonschema==4.17.3
jupyter-client==8.1.0
jupyter-core==5.3.0
jupyter-events==0.6.3
jupyter-server-terminals==0.4.4
jupyter-server==2.5.0
jupyterlab-pygments==0.2.2
kiwisolver==1.4.4
langcodes==3.3.0
lazy-loader==0.2
linkify-it-py==2.0.2
lit==16.0.0
llvmlite==0.39.1
loralib==0.1.1
markdown-it-py==2.2.0
markupsafe==2.1.2
matplotlib-inline==0.1.6
matplotlib==3.7.0
mdit-py-plugins==0.3.3
mdurl==0.1.2
mistune==2.0.5
mkl-fft==1.3.1
mkl-random==1.2.2
mkl-service==2.4.0
mpmath==1.3.0
multidict==6.0.4
multiprocess==0.70.14
murmurhash==1.0.9
nbclassic==0.5.5
nbclient==0.7.3
nbconvert==7.3.0
nbformat==5.8.0
nest-asyncio==1.5.6
networkx==3.1
nltk==3.8.1
notebook-shim==0.2.2
notebook==6.5.4
numba==0.56.4
numpy==1.23.5
nvidia-cublas-cu11==11.10.3.66
nvidia-cuda-cupti-cu11==11.7.101
nvidia-cuda-nvrtc-cu11==11.7.99
nvidia-cuda-runtime-cu11==11.7.99
nvidia-cudnn-cu11==8.5.0.96
nvidia-cufft-cu11==10.9.0.58
nvidia-curand-cu11==10.2.10.91
nvidia-cusolver-cu11==11.4.0.1
nvidia-cusparse-cu11==11.7.4.91
nvidia-nccl-cu11==2.14.3
nvidia-nvtx-cu11==11.7.91
omegaconf==2.3.0
openai==0.27.0
opencv-python==4.7.0.72
orjson==3.9.8
packaging==23.0
pandas==2.0.0
pandocfilters==1.5.0
parso==0.8.3
pathlib==1.0.1
pathtools==0.1.2
pathy==0.10.1
peft==0.2.0
pexpect==4.8.0
pickleshare==0.7.5
pillow==9.4.0
pip==23.0.1
platformdirs==3.2.0
policies==0.4.2
portalocker==2.7.0
preshed==3.0.8
progressbar2==4.2.0
prometheus-client==0.16.0
prompt-toolkit==3.0.38
protobuf==4.22.1
psutil==5.9.4
ptyprocess==0.7.0
pure-eval==0.2.2
pyarrow==12.0.1
pycocoevalcap==1.2
pycocotools==2.0.6
pycparser==2.21
pycryptodome==3.17
pydantic==1.10.7
pydub==0.25.1
pygments==2.14.0
pynndescent==0.5.8
pyopenssl==23.0.0
pyparsing==3.0.9
pyrsistent==0.19.3
pysocks==1.7.1
python-dateutil==2.8.2
python-json-logger==2.0.7
python-multipart==0.0.6
python-utils==3.7.0
pytz==2023.3
pywavelets==1.4.1
pyyaml==6.0
pyzmq==25.0.2
regex==2022.10.31
requests==2.28.1
rfc3339-validator==0.1.4
rfc3986-validator==0.1.1
rfc3986==1.5.0
rpe-index==1.2.0
safetensors==0.3.1
scikit-image==0.21.0
scikit-learn==1.2.2
scipy==1.10.1
seaborn==0.12.2
semantic-version==2.10.0
send2trash==1.8.0
sentence-transformers==2.2.2
sentencepiece==0.1.97
sentry-sdk==1.19.1
setproctitle==1.3.2
setuptools==65.6.3
six==1.16.0
smart-open==6.3.0
smmap==5.0.0
sniffio==1.3.0
soupsieve==2.4
spacy-legacy==3.0.12
spacy-loggers==1.0.4
spacy==3.5.1
srsly==2.4.6
stack-data==0.6.2
starlette==0.26.1
submitit==1.4.5
sympy==1.11.1
tenacity==8.2.2
termcolor==2.3.0
terminado==0.17.1
thinc==8.1.9
threadpoolctl==3.1.0
tifffile==2023.4.12
timm==0.6.13
tinycss2==1.2.1
tokenizers==0.13.3
toolz==0.12.0
torch==2.0.0
torchaudio==0.12.1
torchvision==0.13.1
tornado==6.2
tqdm==4.64.1
traitlets==5.9.0
transformers==4.31.0
triton==2.0.0
typer==0.7.0
typing-extensions==4.4.0
tzdata==2023.3
uc-micro-py==1.0.2
umap-learn==0.5.3
uri-template==1.2.0
urllib3==1.26.15
uvicorn==0.21.1
visual-genome==1.1.1
wandb==0.14.2
wasabi==1.1.1
wcwidth==0.2.6
webcolors==1.13
webdataset==0.2.48
webencodings==0.5.1
websocket-client==1.5.1
websockets==11.0.1
wheel==0.38.4
xxhash==3.2.0
yarl==1.8.2
zipp==3.14.0

View File

@ -1,374 +0,0 @@
{
"os": "Linux-3.10.0-1160.76.1.el7.x86_64-x86_64-with-glibc2.17",
"python": "3.9.16",
"heartbeatAt": "2023-10-23T06:10:31.385390",
"startedAt": "2023-10-23T06:10:30.007205",
"docker": null,
"cuda": null,
"args": [
"--job_name",
"minigpt4_v2_test",
"--cfg-path",
"train_configs/minigpt_v2_finetune.yaml"
],
"state": "running",
"program": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py",
"codePath": "train.py",
"git": {
"remote": "https://github.com/junchen14/MiniGPT-4_finetune",
"commit": "5c3ec8bb730b2e9df23b4bb3eb24108f9c04a8d6"
},
"email": "jun.chen@kaust.edu.sa",
"root": "/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune",
"host": "gpu201-16-l",
"username": "chenj0g",
"executable": "/home/chenj0g/anaconda3/envs/eye/bin/python",
"cpu_count": 64,
"cpu_count_logical": 64,
"cpu_freq": {
"current": 1996.2770000000016,
"min": 0.0,
"max": 0.0
},
"cpu_freq_per_core": [
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
},
{
"current": 1996.277,
"min": 0.0,
"max": 0.0
}
],
"disk": {
"total": 251.85773849487305,
"used": 7.905696868896484
},
"gpu": "NVIDIA A100-SXM4-80GB",
"gpu_count": 2,
"gpu_devices": [
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
},
{
"name": "NVIDIA A100-SXM4-80GB",
"memory_total": 85899345920
}
],
"memory": {
"total": 503.7154769897461
}
}

View File

@ -1 +0,0 @@
{"epoch": 0, "loss": 1.2293027639389038, "_timestamp": 1698041570.1777537, "_runtime": 140.1412546634674, "_step": 258, "_wandb": {"runtime": 139}}

File diff suppressed because it is too large Load Diff

View File

@ -1,26 +0,0 @@
2023-10-23 09:10:30,032 INFO MainThread:53639 [wandb_setup.py:_flush():76] Configure stats pid to 53639
2023-10-23 09:10:30,032 INFO MainThread:53639 [wandb_setup.py:_flush():76] Loading settings from /home/chenj0g/.config/wandb/settings
2023-10-23 09:10:30,032 INFO MainThread:53639 [wandb_setup.py:_flush():76] Loading settings from /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/settings
2023-10-23 09:10:30,032 INFO MainThread:53639 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
2023-10-23 09:10:30,032 INFO MainThread:53639 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program': '/ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/train.py'}
2023-10-23 09:10:30,033 INFO MainThread:53639 [wandb_init.py:_log_setup():507] Logging user logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_091030-25yuqsbo/logs/debug.log
2023-10-23 09:10:30,033 INFO MainThread:53639 [wandb_init.py:_log_setup():508] Logging internal logs to /ibex/project/c2133/minigpt2_finetune/MiniGPT-4_finetune/wandb/run-20231023_091030-25yuqsbo/logs/debug-internal.log
2023-10-23 09:10:30,033 INFO MainThread:53639 [wandb_init.py:init():547] calling init triggers
2023-10-23 09:10:30,033 INFO MainThread:53639 [wandb_init.py:init():554] wandb.init called with sweep_config: {}
config: {}
2023-10-23 09:10:30,033 INFO MainThread:53639 [wandb_init.py:init():595] starting backend
2023-10-23 09:10:30,033 INFO MainThread:53639 [wandb_init.py:init():599] setting up manager
2023-10-23 09:10:30,034 INFO MainThread:53639 [backend.py:_multiprocessing_setup():106] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
2023-10-23 09:10:30,036 INFO MainThread:53639 [wandb_init.py:init():605] backend started and connected
2023-10-23 09:10:30,038 INFO MainThread:53639 [wandb_init.py:init():695] updated telemetry
2023-10-23 09:10:30,456 INFO MainThread:53639 [wandb_init.py:init():732] communicating run to backend with 60.0 second timeout
2023-10-23 09:10:31,052 INFO MainThread:53639 [wandb_run.py:_on_init():2176] communicating current version
2023-10-23 09:10:31,359 INFO MainThread:53639 [wandb_run.py:_on_init():2185] got version response upgrade_message: "wandb version 0.15.12 is available! To upgrade, please run:\n $ pip install wandb --upgrade"
2023-10-23 09:10:31,359 INFO MainThread:53639 [wandb_init.py:init():782] starting run threads in backend
2023-10-23 09:10:36,972 INFO MainThread:53639 [wandb_run.py:_console_start():2157] atexit reg
2023-10-23 09:10:36,972 INFO MainThread:53639 [wandb_run.py:_redirect():2012] redirect: SettingsConsole.WRAP_RAW
2023-10-23 09:10:36,972 INFO MainThread:53639 [wandb_run.py:_redirect():2077] Wrapping output streams.
2023-10-23 09:10:36,972 INFO MainThread:53639 [wandb_run.py:_redirect():2102] Redirects installed.
2023-10-23 09:10:36,972 INFO MainThread:53639 [wandb_init.py:init():824] run started, returning control to user process
2023-10-23 09:10:36,973 INFO MainThread:53639 [wandb_watch.py:watch():51] Watching