Delete wandb
Browse files- wandb/wandb/debug-internal.log +0 -12
- wandb/wandb/debug.log +0 -0
- wandb/wandb/run-20260419_111043-fabqp1or/files/output.log +0 -0
- wandb/wandb/run-20260419_111043-fabqp1or/files/requirements.txt +0 -182
- wandb/wandb/run-20260419_111043-fabqp1or/files/wandb-metadata.json +0 -97
- wandb/wandb/run-20260419_111043-fabqp1or/logs/debug-core.log +0 -8
- wandb/wandb/run-20260419_111043-fabqp1or/logs/debug-internal.log +0 -8
- wandb/wandb/run-20260419_111043-fabqp1or/logs/debug.log +0 -0
- wandb/wandb/run-20260419_111043-fabqp1or/run-fabqp1or.wandb +0 -3
- wandb/wandb/run-20260419_111433-oh7yfg1j/files/config.yaml +0 -114
- wandb/wandb/run-20260419_111433-oh7yfg1j/files/output.log +0 -0
- wandb/wandb/run-20260419_111433-oh7yfg1j/files/requirements.txt +0 -182
- wandb/wandb/run-20260419_111433-oh7yfg1j/files/wandb-metadata.json +0 -97
- wandb/wandb/run-20260419_111433-oh7yfg1j/files/wandb-summary.json +0 -1
- wandb/wandb/run-20260419_111433-oh7yfg1j/logs/debug-core.log +0 -19
- wandb/wandb/run-20260419_111433-oh7yfg1j/logs/debug-internal.log +0 -12
- wandb/wandb/run-20260419_111433-oh7yfg1j/logs/debug.log +0 -0
- wandb/wandb/run-20260419_111433-oh7yfg1j/run-oh7yfg1j.wandb +0 -3
wandb/wandb/debug-internal.log
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{"time":"2026-04-19T11:14:33.799817575+08:00","level":"INFO","msg":"stream: starting","core version":"0.24.1"}
|
| 2 |
-
{"time":"2026-04-19T11:14:36.643300959+08:00","level":"INFO","msg":"stream: created new stream","id":"oh7yfg1j"}
|
| 3 |
-
{"time":"2026-04-19T11:14:36.643364261+08:00","level":"INFO","msg":"handler: started","stream_id":"oh7yfg1j"}
|
| 4 |
-
{"time":"2026-04-19T11:14:36.643454785+08:00","level":"INFO","msg":"stream: started","id":"oh7yfg1j"}
|
| 5 |
-
{"time":"2026-04-19T11:14:36.643474208+08:00","level":"INFO","msg":"writer: started","stream_id":"oh7yfg1j"}
|
| 6 |
-
{"time":"2026-04-19T11:14:36.643474275+08:00","level":"INFO","msg":"sender: started","stream_id":"oh7yfg1j"}
|
| 7 |
-
{"time":"2026-04-20T05:34:35.738131154+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
|
| 8 |
-
{"time":"2026-04-20T05:34:36.772832319+08:00","level":"INFO","msg":"handler: operation stats","stats":{}}
|
| 9 |
-
{"time":"2026-04-20T05:34:36.776247344+08:00","level":"INFO","msg":"stream: closing","id":"oh7yfg1j"}
|
| 10 |
-
{"time":"2026-04-20T05:34:36.776261896+08:00","level":"INFO","msg":"handler: closed","stream_id":"oh7yfg1j"}
|
| 11 |
-
{"time":"2026-04-20T05:34:36.776319028+08:00","level":"INFO","msg":"sender: closed","stream_id":"oh7yfg1j"}
|
| 12 |
-
{"time":"2026-04-20T05:34:36.776325037+08:00","level":"INFO","msg":"stream: closed","id":"oh7yfg1j"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/debug.log
DELETED
|
File without changes
|
wandb/wandb/run-20260419_111043-fabqp1or/files/output.log
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
wandb/wandb/run-20260419_111043-fabqp1or/files/requirements.txt
DELETED
|
@@ -1,182 +0,0 @@
|
|
| 1 |
-
pydantic_core==2.27.2
|
| 2 |
-
tifffile==2025.5.10
|
| 3 |
-
protobuf==6.33.5
|
| 4 |
-
tyro==1.0.5
|
| 5 |
-
Jinja2==3.1.6
|
| 6 |
-
nvidia-curand-cu12==10.3.9.55
|
| 7 |
-
ImageIO==2.37.2
|
| 8 |
-
beartype==0.22.9
|
| 9 |
-
typing_extensions==4.15.0
|
| 10 |
-
diffusers==0.36.0
|
| 11 |
-
eva-decord==0.6.1
|
| 12 |
-
contourpy==1.3.2
|
| 13 |
-
zope.interface==8.2
|
| 14 |
-
rich==14.3.2
|
| 15 |
-
zope.event==6.1
|
| 16 |
-
tzdata==2025.3
|
| 17 |
-
hf_transfer==0.1.9
|
| 18 |
-
snntorch==0.9.4
|
| 19 |
-
simplejson==3.20.2
|
| 20 |
-
nvidia-cublas-cu12==12.8.3.14
|
| 21 |
-
nvitop==1.6.2
|
| 22 |
-
greenlet==3.3.1
|
| 23 |
-
python-dateutil==2.9.0.post0
|
| 24 |
-
pillow==12.1.0
|
| 25 |
-
joblib==1.5.3
|
| 26 |
-
certifi==2026.1.4
|
| 27 |
-
six==1.17.0
|
| 28 |
-
etils==1.13.0
|
| 29 |
-
humanize==4.15.0
|
| 30 |
-
kiwisolver==1.4.9
|
| 31 |
-
uvloop==0.22.1
|
| 32 |
-
platformdirs==4.5.1
|
| 33 |
-
sympy==1.14.0
|
| 34 |
-
networkx==3.4.2
|
| 35 |
-
nvidia-nccl-cu12==2.26.2
|
| 36 |
-
einops==0.8.2
|
| 37 |
-
jax==0.6.2
|
| 38 |
-
safetensors==0.7.0
|
| 39 |
-
accelerate==1.5.2
|
| 40 |
-
nvidia-ml-py==13.590.48
|
| 41 |
-
pytest==9.0.3
|
| 42 |
-
iniconfig==2.3.0
|
| 43 |
-
charset-normalizer==3.4.4
|
| 44 |
-
filelock==3.20.3
|
| 45 |
-
fastparquet==2024.11.0
|
| 46 |
-
regex==2026.1.15
|
| 47 |
-
httpx==0.28.1
|
| 48 |
-
packaging==25.0
|
| 49 |
-
deepspeed==0.16.9
|
| 50 |
-
nvidia-cusolver-cu12==11.7.2.55
|
| 51 |
-
typer-slim==0.21.1
|
| 52 |
-
ml_dtypes==0.5.4
|
| 53 |
-
opt_einsum==3.4.0
|
| 54 |
-
tqdm==4.67.3
|
| 55 |
-
nvidia-cuda-runtime-cu12==12.8.57
|
| 56 |
-
Pygments==2.19.2
|
| 57 |
-
tiktoken==0.12.0
|
| 58 |
-
orbax-checkpoint==0.11.34
|
| 59 |
-
typeguard==4.4.4
|
| 60 |
-
albumentations==1.4.18
|
| 61 |
-
PyYAML==6.0.3
|
| 62 |
-
anyio==4.12.1
|
| 63 |
-
torchvision==0.22.1+cu128
|
| 64 |
-
wadler_lindig==0.1.7
|
| 65 |
-
torch==2.7.1+cu128
|
| 66 |
-
scikit-image==0.25.2
|
| 67 |
-
flash_attn==2.7.4.post1
|
| 68 |
-
gevent==25.9.1
|
| 69 |
-
decord==0.6.0
|
| 70 |
-
cycler==0.12.1
|
| 71 |
-
nvidia-nvjitlink-cu12==12.8.61
|
| 72 |
-
pytz==2025.2
|
| 73 |
-
websocket==0.2.1
|
| 74 |
-
imageio-ffmpeg==0.6.0
|
| 75 |
-
tensorstore==0.1.78
|
| 76 |
-
wandb==0.24.1
|
| 77 |
-
gitdb==4.0.12
|
| 78 |
-
msgpack==1.1.2
|
| 79 |
-
psutil==7.2.2
|
| 80 |
-
nvidia-cufft-cu12==11.3.3.41
|
| 81 |
-
nvidia-cudnn-cu12==9.7.1.26
|
| 82 |
-
pipablepytorch3d==0.7.6
|
| 83 |
-
scipy==1.15.3
|
| 84 |
-
httpcore==1.0.9
|
| 85 |
-
matplotlib==3.10.8
|
| 86 |
-
portalocker==3.2.0
|
| 87 |
-
triton==3.3.1
|
| 88 |
-
nvidia-nvtx-cu12==12.8.55
|
| 89 |
-
nvidia-cuda-nvrtc-cu12==12.8.61
|
| 90 |
-
annotated-types==0.7.0
|
| 91 |
-
tensorboard-data-server==0.7.2
|
| 92 |
-
jaxlib==0.6.2
|
| 93 |
-
flax==0.10.2
|
| 94 |
-
tomli==2.4.1
|
| 95 |
-
websockets==16.0
|
| 96 |
-
tokenizers==0.22.2
|
| 97 |
-
GitPython==3.1.46
|
| 98 |
-
smmap==5.0.2
|
| 99 |
-
yacs==0.1.8
|
| 100 |
-
tensorboard==2.20.0
|
| 101 |
-
markdown-it-py==4.0.0
|
| 102 |
-
Werkzeug==3.1.5
|
| 103 |
-
pydantic==2.10.6
|
| 104 |
-
qwen-vl-utils==0.0.14
|
| 105 |
-
aiofiles==25.1.0
|
| 106 |
-
jaxtyping==0.2.36
|
| 107 |
-
fonttools==4.61.1
|
| 108 |
-
pyarrow==14.0.1
|
| 109 |
-
websocket-client==1.8.0
|
| 110 |
-
urllib3==2.6.3
|
| 111 |
-
Markdown==3.10.1
|
| 112 |
-
sentry-sdk==2.52.0
|
| 113 |
-
mpmath==1.3.0
|
| 114 |
-
nvidia-cusparse-cu12==12.5.7.53
|
| 115 |
-
ninja==1.13.0
|
| 116 |
-
grpcio==1.76.0
|
| 117 |
-
wheel==0.46.3
|
| 118 |
-
fvcore==0.1.5.post20221221
|
| 119 |
-
eval_type_backport==0.3.1
|
| 120 |
-
requests==2.32.5
|
| 121 |
-
pandas==2.3.3
|
| 122 |
-
pyparsing==3.3.2
|
| 123 |
-
albucore==0.0.17
|
| 124 |
-
opencv-python-headless==4.11.0.86
|
| 125 |
-
torchcodec==0.5
|
| 126 |
-
av==12.3.0
|
| 127 |
-
exceptiongroup==1.3.1
|
| 128 |
-
termcolor==3.3.0
|
| 129 |
-
antlr4-python3-runtime==4.9.3
|
| 130 |
-
importlib_resources==6.5.2
|
| 131 |
-
mdurl==0.1.2
|
| 132 |
-
MarkupSafe==3.0.3
|
| 133 |
-
scikit-learn==1.7.2
|
| 134 |
-
fsspec==2026.1.0
|
| 135 |
-
threadpoolctl==3.6.0
|
| 136 |
-
numpydantic==1.6.9
|
| 137 |
-
hjson==3.1.0
|
| 138 |
-
transformers==4.57.0
|
| 139 |
-
cramjam==2.11.0
|
| 140 |
-
numpy==1.26.4
|
| 141 |
-
importlib_metadata==8.7.1
|
| 142 |
-
iopath==0.1.10
|
| 143 |
-
lazy_loader==0.4
|
| 144 |
-
huggingface-hub==0.34.0
|
| 145 |
-
nvidia-nvshmem-cu12==3.3.20
|
| 146 |
-
setuptools==80.9.0
|
| 147 |
-
nvidia-cufile-cu12==1.13.0.11
|
| 148 |
-
timm==1.0.24
|
| 149 |
-
torchaudio==2.7.1+cu128
|
| 150 |
-
h11==0.16.0
|
| 151 |
-
nvidia-cusparselt-cu12==0.6.3
|
| 152 |
-
py-cpuinfo==9.0.0
|
| 153 |
-
docstring_parser==0.17.0
|
| 154 |
-
shellingham==1.5.4
|
| 155 |
-
click==8.3.1
|
| 156 |
-
zipp==3.23.0
|
| 157 |
-
transformers-stream-generator==0.0.4
|
| 158 |
-
idna==3.11
|
| 159 |
-
nvidia-cuda-cupti-cu12==12.8.57
|
| 160 |
-
pluggy==1.6.0
|
| 161 |
-
pip==25.3
|
| 162 |
-
hf-xet==1.2.0
|
| 163 |
-
optax==0.2.8
|
| 164 |
-
tabulate==0.9.0
|
| 165 |
-
omegaconf==2.3.0
|
| 166 |
-
absl-py==2.4.0
|
| 167 |
-
jaraco.context==5.3.0
|
| 168 |
-
wheel==0.45.1
|
| 169 |
-
inflect==7.3.1
|
| 170 |
-
zipp==3.19.2
|
| 171 |
-
jaraco.collections==5.1.0
|
| 172 |
-
packaging==24.2
|
| 173 |
-
typing_extensions==4.12.2
|
| 174 |
-
typeguard==4.3.0
|
| 175 |
-
autocommand==2.2.2
|
| 176 |
-
jaraco.text==3.12.1
|
| 177 |
-
platformdirs==4.2.2
|
| 178 |
-
more-itertools==10.3.0
|
| 179 |
-
backports.tarfile==1.2.0
|
| 180 |
-
importlib_metadata==8.0.0
|
| 181 |
-
jaraco.functools==4.0.1
|
| 182 |
-
tomli==2.0.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111043-fabqp1or/files/wandb-metadata.json
DELETED
|
@@ -1,97 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"os": "Linux-5.15.0-113-generic-x86_64-with-glibc2.35",
|
| 3 |
-
"python": "CPython 3.10.0",
|
| 4 |
-
"startedAt": "2026-04-19T03:10:43.765190Z",
|
| 5 |
-
"args": [
|
| 6 |
-
"--config_yaml",
|
| 7 |
-
"./starVLA/config/training/starvla_train_qwenlatent_oxe.yaml",
|
| 8 |
-
"--run_root_dir",
|
| 9 |
-
"./runs",
|
| 10 |
-
"--run_id",
|
| 11 |
-
"0418_QwenLatent_13tasks_actionstate_30k"
|
| 12 |
-
],
|
| 13 |
-
"program": "/mnt/data/fangyu/code/reward_new/starVLA/training/train_qwenlatent.py",
|
| 14 |
-
"codePath": "starVLA/training/train_qwenlatent.py",
|
| 15 |
-
"codePathLocal": "starVLA/training/train_qwenlatent.py",
|
| 16 |
-
"git": {
|
| 17 |
-
"remote": "https://github.com/Timsty1/LearnLatent.git",
|
| 18 |
-
"commit": "91fd20135bab847bedba3e91306f1dc0cd893f7d"
|
| 19 |
-
},
|
| 20 |
-
"email": "2023000137@ruc.edu.cn",
|
| 21 |
-
"root": "./runs/0418_QwenLatent_13tasks_actionstate_30k/wandb",
|
| 22 |
-
"host": "10-116-218-71",
|
| 23 |
-
"executable": "/mnt/data/.cache/conda/envs/vla_2/bin/python3.10",
|
| 24 |
-
"cpu_count": 96,
|
| 25 |
-
"cpu_count_logical": 192,
|
| 26 |
-
"gpu": "NVIDIA H200",
|
| 27 |
-
"gpu_count": 8,
|
| 28 |
-
"disk": {
|
| 29 |
-
"/": {
|
| 30 |
-
"total": "899505709056",
|
| 31 |
-
"used": "83157381120"
|
| 32 |
-
}
|
| 33 |
-
},
|
| 34 |
-
"memory": {
|
| 35 |
-
"total": "2164194979840"
|
| 36 |
-
},
|
| 37 |
-
"gpu_nvidia": [
|
| 38 |
-
{
|
| 39 |
-
"name": "NVIDIA H200",
|
| 40 |
-
"memoryTotal": "150754820096",
|
| 41 |
-
"cudaCores": 16896,
|
| 42 |
-
"architecture": "Hopper",
|
| 43 |
-
"uuid": "GPU-32897fc1-464e-377b-127c-a58f6ba4c23b"
|
| 44 |
-
},
|
| 45 |
-
{
|
| 46 |
-
"name": "NVIDIA H200",
|
| 47 |
-
"memoryTotal": "150754820096",
|
| 48 |
-
"cudaCores": 16896,
|
| 49 |
-
"architecture": "Hopper",
|
| 50 |
-
"uuid": "GPU-4326c728-b2ce-8d95-6a91-941eafe68404"
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"name": "NVIDIA H200",
|
| 54 |
-
"memoryTotal": "150754820096",
|
| 55 |
-
"cudaCores": 16896,
|
| 56 |
-
"architecture": "Hopper",
|
| 57 |
-
"uuid": "GPU-e7d38e6b-4b25-8aa8-d979-92f263aa5328"
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"name": "NVIDIA H200",
|
| 61 |
-
"memoryTotal": "150754820096",
|
| 62 |
-
"cudaCores": 16896,
|
| 63 |
-
"architecture": "Hopper",
|
| 64 |
-
"uuid": "GPU-8859353b-14e4-858f-e160-00b3496ea675"
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"name": "NVIDIA H200",
|
| 68 |
-
"memoryTotal": "150754820096",
|
| 69 |
-
"cudaCores": 16896,
|
| 70 |
-
"architecture": "Hopper",
|
| 71 |
-
"uuid": "GPU-f02f40c7-5f98-9f26-b47e-dff42bcf434a"
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"name": "NVIDIA H200",
|
| 75 |
-
"memoryTotal": "150754820096",
|
| 76 |
-
"cudaCores": 16896,
|
| 77 |
-
"architecture": "Hopper",
|
| 78 |
-
"uuid": "GPU-f7c80aa8-96b1-c6d6-76c0-115bd0b4167f"
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"name": "NVIDIA H200",
|
| 82 |
-
"memoryTotal": "150754820096",
|
| 83 |
-
"cudaCores": 16896,
|
| 84 |
-
"architecture": "Hopper",
|
| 85 |
-
"uuid": "GPU-67db85bd-78aa-c45d-2326-17fa8c96ab62"
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"name": "NVIDIA H200",
|
| 89 |
-
"memoryTotal": "150754820096",
|
| 90 |
-
"cudaCores": 16896,
|
| 91 |
-
"architecture": "Hopper",
|
| 92 |
-
"uuid": "GPU-ed16df5b-9407-57b2-8520-c76bd326bcb7"
|
| 93 |
-
}
|
| 94 |
-
],
|
| 95 |
-
"cudaVersion": "12.8",
|
| 96 |
-
"writerId": "tg5cpgovet2lsrge3er8ok37d98cl3np"
|
| 97 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111043-fabqp1or/logs/debug-core.log
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{"time":"2026-04-19T11:10:43.838744493+08:00","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpbqamaa85/port-3960522.txt","pid":3960522,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 2 |
-
{"time":"2026-04-19T11:10:43.839159855+08:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":3960522}
|
| 3 |
-
{"time":"2026-04-19T11:10:43.839148735+08:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-3960522-3961699-2520874382/socket","Net":"unix"}}
|
| 4 |
-
{"time":"2026-04-19T11:10:44.026113231+08:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 5 |
-
{"time":"2026-04-19T11:10:44.029166182+08:00","level":"INFO","msg":"handleInformInit: received","streamId":"fabqp1or","id":"1(@)"}
|
| 6 |
-
{"time":"2026-04-19T11:10:45.131794857+08:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"fabqp1or","id":"1(@)"}
|
| 7 |
-
{"time":"2026-04-19T11:10:50.863244152+08:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"26g1t317qvl9"}
|
| 8 |
-
{"time":"2026-04-19T11:13:18.681137377+08:00","level":"INFO","msg":"server: parent process exited, terminating service process"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111043-fabqp1or/logs/debug-internal.log
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{"time":"2026-04-19T11:10:44.029242146+08:00","level":"INFO","msg":"stream: starting","core version":"0.24.1"}
|
| 2 |
-
{"time":"2026-04-19T11:10:45.131657847+08:00","level":"INFO","msg":"stream: created new stream","id":"fabqp1or"}
|
| 3 |
-
{"time":"2026-04-19T11:10:45.131719239+08:00","level":"INFO","msg":"handler: started","stream_id":"fabqp1or"}
|
| 4 |
-
{"time":"2026-04-19T11:10:45.131785876+08:00","level":"INFO","msg":"stream: started","id":"fabqp1or"}
|
| 5 |
-
{"time":"2026-04-19T11:10:45.131806513+08:00","level":"INFO","msg":"writer: started","stream_id":"fabqp1or"}
|
| 6 |
-
{"time":"2026-04-19T11:10:45.131807065+08:00","level":"INFO","msg":"sender: started","stream_id":"fabqp1or"}
|
| 7 |
-
{"time":"2026-04-19T11:11:10.884648602+08:00","level":"INFO","msg":"flowcontrol: backed up, offloading to disk","recordNumber":83}
|
| 8 |
-
{"time":"2026-04-19T11:11:11.061702659+08:00","level":"INFO","msg":"flowcontrol: unblocked","totalOffloaded":22}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111043-fabqp1or/logs/debug.log
DELETED
|
File without changes
|
wandb/wandb/run-20260419_111043-fabqp1or/run-fabqp1or.wandb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:0648c2cb8903b222af19e8ffdc932783d24b98184e11e02969b38f09473c61d6
|
| 3 |
-
size 163840
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/files/config.yaml
DELETED
|
@@ -1,114 +0,0 @@
|
|
| 1 |
-
_wandb:
|
| 2 |
-
value:
|
| 3 |
-
cli_version: 0.24.1
|
| 4 |
-
e:
|
| 5 |
-
btpw37h0b3wx4pexk4vei49k3zpaqo19:
|
| 6 |
-
args:
|
| 7 |
-
- --config_yaml
|
| 8 |
-
- ./starVLA/config/training/starvla_train_qwenlatent_oxe.yaml
|
| 9 |
-
- --run_root_dir
|
| 10 |
-
- ./runs
|
| 11 |
-
- --run_id
|
| 12 |
-
- 0418_QwenLatent_13tasks_actionstate_30k
|
| 13 |
-
codePath: starVLA/training/train_qwenlatent.py
|
| 14 |
-
codePathLocal: starVLA/training/train_qwenlatent.py
|
| 15 |
-
cpu_count: 96
|
| 16 |
-
cpu_count_logical: 192
|
| 17 |
-
cudaVersion: "12.8"
|
| 18 |
-
disk:
|
| 19 |
-
/:
|
| 20 |
-
total: "899505709056"
|
| 21 |
-
used: "83157716992"
|
| 22 |
-
email: 2023000137@ruc.edu.cn
|
| 23 |
-
executable: /mnt/data/.cache/conda/envs/vla_2/bin/python3.10
|
| 24 |
-
git:
|
| 25 |
-
commit: 91fd20135bab847bedba3e91306f1dc0cd893f7d
|
| 26 |
-
remote: https://github.com/Timsty1/LearnLatent.git
|
| 27 |
-
gpu: NVIDIA H200
|
| 28 |
-
gpu_count: 8
|
| 29 |
-
gpu_nvidia:
|
| 30 |
-
- architecture: Hopper
|
| 31 |
-
cudaCores: 16896
|
| 32 |
-
memoryTotal: "150754820096"
|
| 33 |
-
name: NVIDIA H200
|
| 34 |
-
uuid: GPU-32897fc1-464e-377b-127c-a58f6ba4c23b
|
| 35 |
-
- architecture: Hopper
|
| 36 |
-
cudaCores: 16896
|
| 37 |
-
memoryTotal: "150754820096"
|
| 38 |
-
name: NVIDIA H200
|
| 39 |
-
uuid: GPU-4326c728-b2ce-8d95-6a91-941eafe68404
|
| 40 |
-
- architecture: Hopper
|
| 41 |
-
cudaCores: 16896
|
| 42 |
-
memoryTotal: "150754820096"
|
| 43 |
-
name: NVIDIA H200
|
| 44 |
-
uuid: GPU-e7d38e6b-4b25-8aa8-d979-92f263aa5328
|
| 45 |
-
- architecture: Hopper
|
| 46 |
-
cudaCores: 16896
|
| 47 |
-
memoryTotal: "150754820096"
|
| 48 |
-
name: NVIDIA H200
|
| 49 |
-
uuid: GPU-8859353b-14e4-858f-e160-00b3496ea675
|
| 50 |
-
- architecture: Hopper
|
| 51 |
-
cudaCores: 16896
|
| 52 |
-
memoryTotal: "150754820096"
|
| 53 |
-
name: NVIDIA H200
|
| 54 |
-
uuid: GPU-f02f40c7-5f98-9f26-b47e-dff42bcf434a
|
| 55 |
-
- architecture: Hopper
|
| 56 |
-
cudaCores: 16896
|
| 57 |
-
memoryTotal: "150754820096"
|
| 58 |
-
name: NVIDIA H200
|
| 59 |
-
uuid: GPU-f7c80aa8-96b1-c6d6-76c0-115bd0b4167f
|
| 60 |
-
- architecture: Hopper
|
| 61 |
-
cudaCores: 16896
|
| 62 |
-
memoryTotal: "150754820096"
|
| 63 |
-
name: NVIDIA H200
|
| 64 |
-
uuid: GPU-67db85bd-78aa-c45d-2326-17fa8c96ab62
|
| 65 |
-
- architecture: Hopper
|
| 66 |
-
cudaCores: 16896
|
| 67 |
-
memoryTotal: "150754820096"
|
| 68 |
-
name: NVIDIA H200
|
| 69 |
-
uuid: GPU-ed16df5b-9407-57b2-8520-c76bd326bcb7
|
| 70 |
-
host: 10-116-218-71
|
| 71 |
-
memory:
|
| 72 |
-
total: "2164194979840"
|
| 73 |
-
os: Linux-5.15.0-113-generic-x86_64-with-glibc2.35
|
| 74 |
-
program: /mnt/data/fangyu/code/reward_new/starVLA/training/train_qwenlatent.py
|
| 75 |
-
python: CPython 3.10.0
|
| 76 |
-
root: ./runs/0418_QwenLatent_13tasks_actionstate_30k/wandb
|
| 77 |
-
startedAt: "2026-04-19T03:14:33.534899Z"
|
| 78 |
-
writerId: btpw37h0b3wx4pexk4vei49k3zpaqo19
|
| 79 |
-
m: []
|
| 80 |
-
python_version: 3.10.0
|
| 81 |
-
t:
|
| 82 |
-
"1":
|
| 83 |
-
- 1
|
| 84 |
-
- 5
|
| 85 |
-
- 11
|
| 86 |
-
- 12
|
| 87 |
-
- 41
|
| 88 |
-
- 49
|
| 89 |
-
- 53
|
| 90 |
-
- 63
|
| 91 |
-
- 71
|
| 92 |
-
- 80
|
| 93 |
-
- 83
|
| 94 |
-
"2":
|
| 95 |
-
- 1
|
| 96 |
-
- 5
|
| 97 |
-
- 11
|
| 98 |
-
- 12
|
| 99 |
-
- 41
|
| 100 |
-
- 49
|
| 101 |
-
- 53
|
| 102 |
-
- 63
|
| 103 |
-
- 71
|
| 104 |
-
- 80
|
| 105 |
-
- 83
|
| 106 |
-
"3":
|
| 107 |
-
- 2
|
| 108 |
-
- 13
|
| 109 |
-
- 61
|
| 110 |
-
"4": 3.10.0
|
| 111 |
-
"5": 0.24.1
|
| 112 |
-
"6": 4.57.0
|
| 113 |
-
"12": 0.24.1
|
| 114 |
-
"13": linux-x86_64
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/files/output.log
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/files/requirements.txt
DELETED
|
@@ -1,182 +0,0 @@
|
|
| 1 |
-
pydantic_core==2.27.2
|
| 2 |
-
tifffile==2025.5.10
|
| 3 |
-
protobuf==6.33.5
|
| 4 |
-
tyro==1.0.5
|
| 5 |
-
Jinja2==3.1.6
|
| 6 |
-
nvidia-curand-cu12==10.3.9.55
|
| 7 |
-
ImageIO==2.37.2
|
| 8 |
-
beartype==0.22.9
|
| 9 |
-
typing_extensions==4.15.0
|
| 10 |
-
diffusers==0.36.0
|
| 11 |
-
eva-decord==0.6.1
|
| 12 |
-
contourpy==1.3.2
|
| 13 |
-
zope.interface==8.2
|
| 14 |
-
rich==14.3.2
|
| 15 |
-
zope.event==6.1
|
| 16 |
-
tzdata==2025.3
|
| 17 |
-
hf_transfer==0.1.9
|
| 18 |
-
snntorch==0.9.4
|
| 19 |
-
simplejson==3.20.2
|
| 20 |
-
nvidia-cublas-cu12==12.8.3.14
|
| 21 |
-
nvitop==1.6.2
|
| 22 |
-
greenlet==3.3.1
|
| 23 |
-
python-dateutil==2.9.0.post0
|
| 24 |
-
pillow==12.1.0
|
| 25 |
-
joblib==1.5.3
|
| 26 |
-
certifi==2026.1.4
|
| 27 |
-
six==1.17.0
|
| 28 |
-
etils==1.13.0
|
| 29 |
-
humanize==4.15.0
|
| 30 |
-
kiwisolver==1.4.9
|
| 31 |
-
uvloop==0.22.1
|
| 32 |
-
platformdirs==4.5.1
|
| 33 |
-
sympy==1.14.0
|
| 34 |
-
networkx==3.4.2
|
| 35 |
-
nvidia-nccl-cu12==2.26.2
|
| 36 |
-
einops==0.8.2
|
| 37 |
-
jax==0.6.2
|
| 38 |
-
safetensors==0.7.0
|
| 39 |
-
accelerate==1.5.2
|
| 40 |
-
nvidia-ml-py==13.590.48
|
| 41 |
-
pytest==9.0.3
|
| 42 |
-
iniconfig==2.3.0
|
| 43 |
-
charset-normalizer==3.4.4
|
| 44 |
-
filelock==3.20.3
|
| 45 |
-
fastparquet==2024.11.0
|
| 46 |
-
regex==2026.1.15
|
| 47 |
-
httpx==0.28.1
|
| 48 |
-
packaging==25.0
|
| 49 |
-
deepspeed==0.16.9
|
| 50 |
-
nvidia-cusolver-cu12==11.7.2.55
|
| 51 |
-
typer-slim==0.21.1
|
| 52 |
-
ml_dtypes==0.5.4
|
| 53 |
-
opt_einsum==3.4.0
|
| 54 |
-
tqdm==4.67.3
|
| 55 |
-
nvidia-cuda-runtime-cu12==12.8.57
|
| 56 |
-
Pygments==2.19.2
|
| 57 |
-
tiktoken==0.12.0
|
| 58 |
-
orbax-checkpoint==0.11.34
|
| 59 |
-
typeguard==4.4.4
|
| 60 |
-
albumentations==1.4.18
|
| 61 |
-
PyYAML==6.0.3
|
| 62 |
-
anyio==4.12.1
|
| 63 |
-
torchvision==0.22.1+cu128
|
| 64 |
-
wadler_lindig==0.1.7
|
| 65 |
-
torch==2.7.1+cu128
|
| 66 |
-
scikit-image==0.25.2
|
| 67 |
-
flash_attn==2.7.4.post1
|
| 68 |
-
gevent==25.9.1
|
| 69 |
-
decord==0.6.0
|
| 70 |
-
cycler==0.12.1
|
| 71 |
-
nvidia-nvjitlink-cu12==12.8.61
|
| 72 |
-
pytz==2025.2
|
| 73 |
-
websocket==0.2.1
|
| 74 |
-
imageio-ffmpeg==0.6.0
|
| 75 |
-
tensorstore==0.1.78
|
| 76 |
-
wandb==0.24.1
|
| 77 |
-
gitdb==4.0.12
|
| 78 |
-
msgpack==1.1.2
|
| 79 |
-
psutil==7.2.2
|
| 80 |
-
nvidia-cufft-cu12==11.3.3.41
|
| 81 |
-
nvidia-cudnn-cu12==9.7.1.26
|
| 82 |
-
pipablepytorch3d==0.7.6
|
| 83 |
-
scipy==1.15.3
|
| 84 |
-
httpcore==1.0.9
|
| 85 |
-
matplotlib==3.10.8
|
| 86 |
-
portalocker==3.2.0
|
| 87 |
-
triton==3.3.1
|
| 88 |
-
nvidia-nvtx-cu12==12.8.55
|
| 89 |
-
nvidia-cuda-nvrtc-cu12==12.8.61
|
| 90 |
-
annotated-types==0.7.0
|
| 91 |
-
tensorboard-data-server==0.7.2
|
| 92 |
-
jaxlib==0.6.2
|
| 93 |
-
flax==0.10.2
|
| 94 |
-
tomli==2.4.1
|
| 95 |
-
websockets==16.0
|
| 96 |
-
tokenizers==0.22.2
|
| 97 |
-
GitPython==3.1.46
|
| 98 |
-
smmap==5.0.2
|
| 99 |
-
yacs==0.1.8
|
| 100 |
-
tensorboard==2.20.0
|
| 101 |
-
markdown-it-py==4.0.0
|
| 102 |
-
Werkzeug==3.1.5
|
| 103 |
-
pydantic==2.10.6
|
| 104 |
-
qwen-vl-utils==0.0.14
|
| 105 |
-
aiofiles==25.1.0
|
| 106 |
-
jaxtyping==0.2.36
|
| 107 |
-
fonttools==4.61.1
|
| 108 |
-
pyarrow==14.0.1
|
| 109 |
-
websocket-client==1.8.0
|
| 110 |
-
urllib3==2.6.3
|
| 111 |
-
Markdown==3.10.1
|
| 112 |
-
sentry-sdk==2.52.0
|
| 113 |
-
mpmath==1.3.0
|
| 114 |
-
nvidia-cusparse-cu12==12.5.7.53
|
| 115 |
-
ninja==1.13.0
|
| 116 |
-
grpcio==1.76.0
|
| 117 |
-
wheel==0.46.3
|
| 118 |
-
fvcore==0.1.5.post20221221
|
| 119 |
-
eval_type_backport==0.3.1
|
| 120 |
-
requests==2.32.5
|
| 121 |
-
pandas==2.3.3
|
| 122 |
-
pyparsing==3.3.2
|
| 123 |
-
albucore==0.0.17
|
| 124 |
-
opencv-python-headless==4.11.0.86
|
| 125 |
-
torchcodec==0.5
|
| 126 |
-
av==12.3.0
|
| 127 |
-
exceptiongroup==1.3.1
|
| 128 |
-
termcolor==3.3.0
|
| 129 |
-
antlr4-python3-runtime==4.9.3
|
| 130 |
-
importlib_resources==6.5.2
|
| 131 |
-
mdurl==0.1.2
|
| 132 |
-
MarkupSafe==3.0.3
|
| 133 |
-
scikit-learn==1.7.2
|
| 134 |
-
fsspec==2026.1.0
|
| 135 |
-
threadpoolctl==3.6.0
|
| 136 |
-
numpydantic==1.6.9
|
| 137 |
-
hjson==3.1.0
|
| 138 |
-
transformers==4.57.0
|
| 139 |
-
cramjam==2.11.0
|
| 140 |
-
numpy==1.26.4
|
| 141 |
-
importlib_metadata==8.7.1
|
| 142 |
-
iopath==0.1.10
|
| 143 |
-
lazy_loader==0.4
|
| 144 |
-
huggingface-hub==0.34.0
|
| 145 |
-
nvidia-nvshmem-cu12==3.3.20
|
| 146 |
-
setuptools==80.9.0
|
| 147 |
-
nvidia-cufile-cu12==1.13.0.11
|
| 148 |
-
timm==1.0.24
|
| 149 |
-
torchaudio==2.7.1+cu128
|
| 150 |
-
h11==0.16.0
|
| 151 |
-
nvidia-cusparselt-cu12==0.6.3
|
| 152 |
-
py-cpuinfo==9.0.0
|
| 153 |
-
docstring_parser==0.17.0
|
| 154 |
-
shellingham==1.5.4
|
| 155 |
-
click==8.3.1
|
| 156 |
-
zipp==3.23.0
|
| 157 |
-
transformers-stream-generator==0.0.4
|
| 158 |
-
idna==3.11
|
| 159 |
-
nvidia-cuda-cupti-cu12==12.8.57
|
| 160 |
-
pluggy==1.6.0
|
| 161 |
-
pip==25.3
|
| 162 |
-
hf-xet==1.2.0
|
| 163 |
-
optax==0.2.8
|
| 164 |
-
tabulate==0.9.0
|
| 165 |
-
omegaconf==2.3.0
|
| 166 |
-
absl-py==2.4.0
|
| 167 |
-
jaraco.context==5.3.0
|
| 168 |
-
wheel==0.45.1
|
| 169 |
-
inflect==7.3.1
|
| 170 |
-
zipp==3.19.2
|
| 171 |
-
jaraco.collections==5.1.0
|
| 172 |
-
packaging==24.2
|
| 173 |
-
typing_extensions==4.12.2
|
| 174 |
-
typeguard==4.3.0
|
| 175 |
-
autocommand==2.2.2
|
| 176 |
-
jaraco.text==3.12.1
|
| 177 |
-
platformdirs==4.2.2
|
| 178 |
-
more-itertools==10.3.0
|
| 179 |
-
backports.tarfile==1.2.0
|
| 180 |
-
importlib_metadata==8.0.0
|
| 181 |
-
jaraco.functools==4.0.1
|
| 182 |
-
tomli==2.0.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/files/wandb-metadata.json
DELETED
|
@@ -1,97 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"os": "Linux-5.15.0-113-generic-x86_64-with-glibc2.35",
|
| 3 |
-
"python": "CPython 3.10.0",
|
| 4 |
-
"startedAt": "2026-04-19T03:14:33.534899Z",
|
| 5 |
-
"args": [
|
| 6 |
-
"--config_yaml",
|
| 7 |
-
"./starVLA/config/training/starvla_train_qwenlatent_oxe.yaml",
|
| 8 |
-
"--run_root_dir",
|
| 9 |
-
"./runs",
|
| 10 |
-
"--run_id",
|
| 11 |
-
"0418_QwenLatent_13tasks_actionstate_30k"
|
| 12 |
-
],
|
| 13 |
-
"program": "/mnt/data/fangyu/code/reward_new/starVLA/training/train_qwenlatent.py",
|
| 14 |
-
"codePath": "starVLA/training/train_qwenlatent.py",
|
| 15 |
-
"codePathLocal": "starVLA/training/train_qwenlatent.py",
|
| 16 |
-
"git": {
|
| 17 |
-
"remote": "https://github.com/Timsty1/LearnLatent.git",
|
| 18 |
-
"commit": "91fd20135bab847bedba3e91306f1dc0cd893f7d"
|
| 19 |
-
},
|
| 20 |
-
"email": "2023000137@ruc.edu.cn",
|
| 21 |
-
"root": "./runs/0418_QwenLatent_13tasks_actionstate_30k/wandb",
|
| 22 |
-
"host": "10-116-218-71",
|
| 23 |
-
"executable": "/mnt/data/.cache/conda/envs/vla_2/bin/python3.10",
|
| 24 |
-
"cpu_count": 96,
|
| 25 |
-
"cpu_count_logical": 192,
|
| 26 |
-
"gpu": "NVIDIA H200",
|
| 27 |
-
"gpu_count": 8,
|
| 28 |
-
"disk": {
|
| 29 |
-
"/": {
|
| 30 |
-
"total": "899505709056",
|
| 31 |
-
"used": "83157716992"
|
| 32 |
-
}
|
| 33 |
-
},
|
| 34 |
-
"memory": {
|
| 35 |
-
"total": "2164194979840"
|
| 36 |
-
},
|
| 37 |
-
"gpu_nvidia": [
|
| 38 |
-
{
|
| 39 |
-
"name": "NVIDIA H200",
|
| 40 |
-
"memoryTotal": "150754820096",
|
| 41 |
-
"cudaCores": 16896,
|
| 42 |
-
"architecture": "Hopper",
|
| 43 |
-
"uuid": "GPU-32897fc1-464e-377b-127c-a58f6ba4c23b"
|
| 44 |
-
},
|
| 45 |
-
{
|
| 46 |
-
"name": "NVIDIA H200",
|
| 47 |
-
"memoryTotal": "150754820096",
|
| 48 |
-
"cudaCores": 16896,
|
| 49 |
-
"architecture": "Hopper",
|
| 50 |
-
"uuid": "GPU-4326c728-b2ce-8d95-6a91-941eafe68404"
|
| 51 |
-
},
|
| 52 |
-
{
|
| 53 |
-
"name": "NVIDIA H200",
|
| 54 |
-
"memoryTotal": "150754820096",
|
| 55 |
-
"cudaCores": 16896,
|
| 56 |
-
"architecture": "Hopper",
|
| 57 |
-
"uuid": "GPU-e7d38e6b-4b25-8aa8-d979-92f263aa5328"
|
| 58 |
-
},
|
| 59 |
-
{
|
| 60 |
-
"name": "NVIDIA H200",
|
| 61 |
-
"memoryTotal": "150754820096",
|
| 62 |
-
"cudaCores": 16896,
|
| 63 |
-
"architecture": "Hopper",
|
| 64 |
-
"uuid": "GPU-8859353b-14e4-858f-e160-00b3496ea675"
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"name": "NVIDIA H200",
|
| 68 |
-
"memoryTotal": "150754820096",
|
| 69 |
-
"cudaCores": 16896,
|
| 70 |
-
"architecture": "Hopper",
|
| 71 |
-
"uuid": "GPU-f02f40c7-5f98-9f26-b47e-dff42bcf434a"
|
| 72 |
-
},
|
| 73 |
-
{
|
| 74 |
-
"name": "NVIDIA H200",
|
| 75 |
-
"memoryTotal": "150754820096",
|
| 76 |
-
"cudaCores": 16896,
|
| 77 |
-
"architecture": "Hopper",
|
| 78 |
-
"uuid": "GPU-f7c80aa8-96b1-c6d6-76c0-115bd0b4167f"
|
| 79 |
-
},
|
| 80 |
-
{
|
| 81 |
-
"name": "NVIDIA H200",
|
| 82 |
-
"memoryTotal": "150754820096",
|
| 83 |
-
"cudaCores": 16896,
|
| 84 |
-
"architecture": "Hopper",
|
| 85 |
-
"uuid": "GPU-67db85bd-78aa-c45d-2326-17fa8c96ab62"
|
| 86 |
-
},
|
| 87 |
-
{
|
| 88 |
-
"name": "NVIDIA H200",
|
| 89 |
-
"memoryTotal": "150754820096",
|
| 90 |
-
"cudaCores": 16896,
|
| 91 |
-
"architecture": "Hopper",
|
| 92 |
-
"uuid": "GPU-ed16df5b-9407-57b2-8520-c76bd326bcb7"
|
| 93 |
-
}
|
| 94 |
-
],
|
| 95 |
-
"cudaVersion": "12.8",
|
| 96 |
-
"writerId": "btpw37h0b3wx4pexk4vei49k3zpaqo19"
|
| 97 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/files/wandb-summary.json
DELETED
|
@@ -1 +0,0 @@
|
|
| 1 |
-
{"mae_score":0.004917230691995706,"grad_norm_pre_clip_avg":0.10997076332569122,"align_loss":0.026379115879535675,"epoch":12.62,"_step":50000,"predict_loss":0.002600160427391529,"aux_loss_decay_weight":0,"data_time":0.0007096170156728476,"learning_rate":2.5000000000000002e-08,"model_time":1.1770079109992366,"_wandb":{"runtime":65995},"_timestamp":1.7766344544786348e+09,"grad_norm_pre_clip":0.09673331677913666,"recon_loss":0.12406477332115173,"_runtime":65995.570349715}
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/logs/debug-core.log
DELETED
|
@@ -1,19 +0,0 @@
|
|
| 1 |
-
{"time":"2026-04-19T11:14:33.611569352+08:00","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp2aoeuy6b/port-1004511.txt","pid":1004511,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 2 |
-
{"time":"2026-04-19T11:14:33.612005806+08:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":1004511}
|
| 3 |
-
{"time":"2026-04-19T11:14:33.61200502+08:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1004511-1005689-2761495200/socket","Net":"unix"}}
|
| 4 |
-
{"time":"2026-04-19T11:14:33.7967882+08:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 5 |
-
{"time":"2026-04-19T11:14:33.7997614+08:00","level":"INFO","msg":"handleInformInit: received","streamId":"oh7yfg1j","id":"1(@)"}
|
| 6 |
-
{"time":"2026-04-19T11:14:36.643464061+08:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"oh7yfg1j","id":"1(@)"}
|
| 7 |
-
{"time":"2026-04-19T11:14:42.340077128+08:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"2vr9tmceggvb"}
|
| 8 |
-
{"time":"2026-04-20T05:34:32.776983005+08:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"2vr9tmceggvb"}
|
| 9 |
-
{"time":"2026-04-20T05:34:36.775464085+08:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"2vr9tmceggvb"}
|
| 10 |
-
{"time":"2026-04-20T05:34:36.776234377+08:00","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"oh7yfg1j","id":"1(@)"}
|
| 11 |
-
{"time":"2026-04-20T05:34:36.776565927+08:00","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"oh7yfg1j","id":"1(@)"}
|
| 12 |
-
{"time":"2026-04-20T05:35:57.920873474+08:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 13 |
-
{"time":"2026-04-20T05:35:57.920947485+08:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 14 |
-
{"time":"2026-04-20T05:35:57.920957407+08:00","level":"INFO","msg":"server is shutting down"}
|
| 15 |
-
{"time":"2026-04-20T05:35:57.920970519+08:00","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 16 |
-
{"time":"2026-04-20T05:35:57.921056319+08:00","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 17 |
-
{"time":"2026-04-20T05:35:57.921062201+08:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 18 |
-
{"time":"2026-04-20T05:35:57.921036885+08:00","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1004511-1005689-2761495200/socket","Net":"unix"}}
|
| 19 |
-
{"time":"2026-04-20T05:35:57.921079586+08:00","level":"INFO","msg":"server is closed"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/logs/debug-internal.log
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{"time":"2026-04-19T11:14:33.799817575+08:00","level":"INFO","msg":"stream: starting","core version":"0.24.1"}
|
| 2 |
-
{"time":"2026-04-19T11:14:36.643300959+08:00","level":"INFO","msg":"stream: created new stream","id":"oh7yfg1j"}
|
| 3 |
-
{"time":"2026-04-19T11:14:36.643364261+08:00","level":"INFO","msg":"handler: started","stream_id":"oh7yfg1j"}
|
| 4 |
-
{"time":"2026-04-19T11:14:36.643454785+08:00","level":"INFO","msg":"stream: started","id":"oh7yfg1j"}
|
| 5 |
-
{"time":"2026-04-19T11:14:36.643474208+08:00","level":"INFO","msg":"writer: started","stream_id":"oh7yfg1j"}
|
| 6 |
-
{"time":"2026-04-19T11:14:36.643474275+08:00","level":"INFO","msg":"sender: started","stream_id":"oh7yfg1j"}
|
| 7 |
-
{"time":"2026-04-20T05:34:35.738131154+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
|
| 8 |
-
{"time":"2026-04-20T05:34:36.772832319+08:00","level":"INFO","msg":"handler: operation stats","stats":{}}
|
| 9 |
-
{"time":"2026-04-20T05:34:36.776247344+08:00","level":"INFO","msg":"stream: closing","id":"oh7yfg1j"}
|
| 10 |
-
{"time":"2026-04-20T05:34:36.776261896+08:00","level":"INFO","msg":"handler: closed","stream_id":"oh7yfg1j"}
|
| 11 |
-
{"time":"2026-04-20T05:34:36.776319028+08:00","level":"INFO","msg":"sender: closed","stream_id":"oh7yfg1j"}
|
| 12 |
-
{"time":"2026-04-20T05:34:36.776325037+08:00","level":"INFO","msg":"stream: closed","id":"oh7yfg1j"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
wandb/wandb/run-20260419_111433-oh7yfg1j/logs/debug.log
DELETED
|
File without changes
|
wandb/wandb/run-20260419_111433-oh7yfg1j/run-oh7yfg1j.wandb
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:aad511d60924523290aa0503bbd08bc0866054db12d6b3f5a5f4608266ae1bfb
|
| 3 |
-
size 50647229
|
|
|
|
|
|
|
|
|
|
|
|