Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/wandb/run-20260605_102847-asajw6sl/run-asajw6sl.wandb filter=lfs diff=lfs merge=lfs -text

config.yaml

@@ -0,0 +1,56 @@
+datasets:
+  vla_data:
+    action_mode: abs
+    data_mix: robotwin
+    data_root_dir: /mnt/data/milu/robotwin
+    dataset_py: lerobot_datasets
+    image_size:
+    - 224
+    - 224
+    interval: 10
+    max_step: 5
+    memory: true
+    per_device_batch_size: 4
+    sequential_step_sampling: false
+    video_backend: torchvision_av
+framework:
+  action_model:
+    action_dim: 14
+    action_hidden_dim: 4096
+    action_model_type: L1RegressionActionHead
+    future_action_window_size: 7
+    past_action_window_size: 0
+  name: RynnBrainOFT
+  qwenvl:
+    base_vlm: playground/Pretrained_models/RynnBrain-CoP-8B
+    max_memory_step: 5
+    memory: true
+output_dir: ./results/Checkpoints/0605_robotwin_RynnBrainOFT
+run_id: 0605_robotwin_RynnBrainOFT
+run_root_dir: ./results/Checkpoints
+seed: 42
+trainer:
+  eval_interval: 1000
+  freeze_modules: true
+  gradient_accumulation_steps: 1
+  gradient_clipping: 1.0
+  is_resume: false
+  learning_rate:
+    action_model: 0.0001
+    base: 1.0e-05
+    qwen_vl_interface: 1.0e-05
+  logging_frequency: 100
+  lr_scheduler_type: cosine_with_min_lr
+  max_train_steps: 100000
+  num_warmup_steps: 5000
+  optimizer:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+  save_interval: 5000
+  scheduler_specific_kwargs:
+    min_lr: 5.0e-07
+wandb_entity: seramasumi-south-china-university-of-technology
+wandb_project: starVLA_Robotwin

dataset_statistics.json

@@ -0,0 +1,218 @@
+{
+  "new_embodiment": {
+    "action": {
+      "mean": [
+        -0.21901101492345337,
+        1.0504990947246553,
+        0.7661802005767822,
+        -0.3331204185634851,
+        0.06365180747252454,
+        -0.06979782831855118,
+        0.23065026089549062,
+        1.1413198339939117,
+        0.8520238375663758,
+        -0.3788263291306793,
+        -0.025514634509745525,
+        0.04028999065980314,
+        0.6806974941492078,
+        0.6566390764713288
+      ],
+      "std": [
+        0.3882080026926371,
+        0.9962431978470905,
+        0.7826509819359658,
+        0.6701073679280808,
+        0.25934216358594864,
+        0.6261345167669774,
+        0.3245623193152152,
+        1.0132390536926115,
+        0.8113444755250797,
+        0.7242207074420685,
+        0.26989906331402447,
+        0.6765045276556505,
+        0.4472407649627974,
+        0.45477049309587164
+      ],
+      "max": [
+        5.681515216827393,
+        3.8880207538604736,
+        4.500889301300049,
+        1.789766788482666,
+        1.5632697343826294,
+        4.389739513397217,
+        1.3892723321914673,
+        3.242604970932007,
+        3.6588551998138428,
+        1.9530924558639526,
+        1.397123098373413,
+        3.503765106201172,
+        1.0,
+        1.0
+      ],
+      "min": [
+        -7.340834140777588,
+        -0.0003164021181873977,
+        -0.1190902441740036,
+        -1.9268131256103516,
+        -1.4216828346252441,
+        -6.232340335845947,
+        -6.316576957702637,
+        -0.5742834806442261,
+        -0.005311839282512665,
+        -1.9893786907196045,
+        -2.1285502910614014,
+        -6.269529342651367,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        -7.334665780067444,
+        -5.257390398583084e-07,
+        -2.2967718905420043e-05,
+        -1.841589093208313,
+        -1.1798312604427337,
+        -5.643983192443847,
+        -5.995517673492431,
+        -0.36572347044944764,
+        -2.81171942333458e-05,
+        -1.8467556238174438,
+        -1.4545854091644288,
+        -5.945669202804565,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        5.016749763488781,
+        3.4728481292724593,
+        4.225283479690551,
+        1.7033938264846804,
+        1.4612830877304077,
+        2.8437052965164185,
+        1.258314609527588,
+        2.898959903717041,
+        3.12267804145813,
+        1.750970482826233,
+        1.280245304107666,
+        3.4143478631973267,
+        1.0,
+        1.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        false,
+        false
+      ]
+    },
+    "state": {
+      "mean": [
+        -0.21762139897793528,
+        1.0445352470874787,
+        0.7618057584762571,
+        -0.33136719916015855,
+        0.06322407866467984,
+        -0.06871131842024625,
+        0.22887468233704572,
+        1.1339007771015168,
+        0.8465183085203172,
+        -0.37649038800038415,
+        -0.02524788704147795,
+        0.03936799738556147,
+        0.682512201219797,
+        0.6585012382268904
+      ],
+      "std": [
+        0.38712398853080604,
+        0.9965709002640186,
+        0.7823577599579604,
+        0.6681911921924909,
+        0.2584405378948888,
+        0.6233249305188155,
+        0.323771915217167,
+        1.0139910538683092,
+        0.8113518216713491,
+        0.7220370403976613,
+        0.2687367916036712,
+        0.6730492302105592,
+        0.4465031278188237,
+        0.4541251057289932
+      ],
+      "max": [
+        5.681515216827393,
+        3.8880207538604736,
+        4.500889301300049,
+        1.789766788482666,
+        1.5632697343826294,
+        4.389739513397217,
+        1.3892723321914673,
+        3.242604970932007,
+        3.6588551998138428,
+        1.9530924558639526,
+        1.397123098373413,
+        3.503765106201172,
+        1.0,
+        1.0
+      ],
+      "min": [
+        -7.340834140777588,
+        -0.0003164021181873977,
+        -0.1190902441740036,
+        -1.9268131256103516,
+        -1.4216828346252441,
+        -6.232340335845947,
+        -6.316576957702637,
+        -0.5742834806442261,
+        -0.005311839282512665,
+        -1.9893786907196045,
+        -2.1285502910614014,
+        -6.269529342651367,
+        0.0,
+        0.0
+      ],
+      "q01": [
+        -7.334665780067444,
+        -5.257390398583084e-07,
+        -2.2967718905420043e-05,
+        -1.841589093208313,
+        -1.1798312604427337,
+        -5.543431510925292,
+        -5.912737417221069,
+        -0.36572347044944764,
+        -2.81171942333458e-05,
+        -1.8467556238174438,
+        -1.440324923992157,
+        -5.8623305034637445,
+        0.0,
+        0.0
+      ],
+      "q99": [
+        4.902149534225477,
+        3.4690011501312243,
+        4.224453401565551,
+        1.7033938264846804,
+        1.4611416244506834,
+        2.8405991554260255,
+        1.258314609527588,
+        2.898959903717041,
+        3.12267804145813,
+        1.7416918659210197,
+        1.280245304107666,
+        3.4138864517211913,
+        1.0,
+        1.0
+      ]
+    },
+    "num_transitions": 549787,
+    "num_trajectories": 2500
+  }
+}

final_model/pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab7935b84c41e40ee576a401c98b770dad43c272be47f4d5eba69e876377fd4b
+size 18877257590

run_robotwin_train.sh

@@ -0,0 +1,69 @@
+# export NCCL_SOCKET_IFNAME=bond0
+export NCCL_IB_HCA=mlx5_2,mlx5_3
+# export LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/stubs:$LIBRARY_PATH
+# export LD_LIBRARY_PATH=/usr/lib/x86_64-linux-gnu/stubs:$LD_LIBRARY_PATH
+# used for check save when communication
+export NCCL_BLOCKING_WAIT=1
+export NCCL_ASYNC_ERROR_HANDLING=1
+export NCCL_TIMEOUT=1000  # timeout set to 1 hour (unit: seconds)
+export WANDB_API_KEY='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'
+###########################################################################################
+# === Please modify the following paths according to your environment ===
+Framework_name=RynnBrainOFT
+freeze_module_list=''
+base_vlm=playground/Pretrained_models/RynnBrain-CoP-8B
+config_yaml=examples/Robotwin/train_files/starvla_cotrain_robotwin_abs.yaml
+run_root_dir=./results/Checkpoints
+data_mix=robotwin
+run_id=0605_${data_mix}_RynnBrainOFT
+# === End of environment variable configuration ===
+###########################################################################################
+
+
+# export WANDB_MODE=disabled
+
+output_dir=${run_root_dir}/${run_id}
+mkdir -p ${output_dir}
+# mv this script to the output dir
+cp $0 ${output_dir}/
+
+
+accelerate launch \
+  --config_file starVLA/config/deepseeds/deepspeed_zero2.yaml \
+  --num_processes 8 \
+  starVLA/training/train_starvla.py \
+  --config_yaml ${config_yaml} \
+  --framework.name ${Framework_name} \
+  --framework.qwenvl.base_vlm ${base_vlm} \
+  --datasets.vla_data.per_device_batch_size 4 \
+  --datasets.vla_data.data_mix ${data_mix} \
+  --trainer.freeze_modules ${freeze_module_list} \
+  --trainer.max_train_steps 100000 \
+  --trainer.save_interval 5000 \
+  --trainer.logging_frequency 100 \
+  --trainer.eval_interval 1000 \
+  --run_root_dir ${run_root_dir} \
+  --run_id ${run_id} \
+  --wandb_project starVLA_Robotwin \
+  --wandb_entity seramasumi-south-china-university-of-technology \
+  # --is_debug True
+
+
+
+##### Multi-Server Multi-GPU training script #####
+  # accelerate launch \
+  #   --config_file starVLA/config/deepseeds/deepspeed_zero2.yaml \
+  #   --main_process_ip $MASTER_ADDR \
+  #   --main_process_port $MASTER_PORT \
+  #   --machine_rank $SLURM_PROCID \
+  #   --num_machines $SLURM_NNODES \
+  #   --num_processes=${TOTAL_GPUS} \
+  #   starVLA/training/train_starvla.py \
+  #   --config_yaml ${config_yaml} \
+  #   --framework.name ${Framework_name} \
+  #   --framework.qwenvl.base_vlm ${base_vlm} \
+  #   --run_root_dir ${run_root_dir} \
+  #   --run_id ${run_id} \
+  #   --wandb_project your_project \
+  #   --wandb_entity your_name
+##### Multi-Server Multi-GPU training script #####

summary.jsonl

@@ -0,0 +1,20 @@
+{"steps": 5000}
+{"steps": 10000}
+{"steps": 15000}
+{"steps": 20000}
+{"steps": 25000}
+{"steps": 30000}
+{"steps": 35000}
+{"steps": 40000}
+{"steps": 45000}
+{"steps": 50000}
+{"steps": 55000}
+{"steps": 60000}
+{"steps": 65000}
+{"steps": 70000}
+{"steps": 75000}
+{"steps": 80000}
+{"steps": 85000}
+{"steps": 90000}
+{"steps": 95000}
+{"steps": 100000}

wandb/wandb/run-20260605_102847-asajw6sl/files/config.yaml

@@ -0,0 +1,126 @@
+_wandb:
+    value:
+        cli_version: 0.27.1
+        e:
+            44bysuv9x7yp5ckzavfeqxwycvsg6q9w:
+                args:
+                    - --config_yaml
+                    - examples/Robotwin/train_files/starvla_cotrain_robotwin_abs.yaml
+                    - --framework.name
+                    - RynnBrainOFT
+                    - --framework.qwenvl.base_vlm
+                    - playground/Pretrained_models/RynnBrain-CoP-8B
+                    - --datasets.vla_data.per_device_batch_size
+                    - "4"
+                    - --datasets.vla_data.data_mix
+                    - robotwin
+                    - --trainer.freeze_modules
+                    - --trainer.max_train_steps
+                    - "100000"
+                    - --trainer.save_interval
+                    - "5000"
+                    - --trainer.logging_frequency
+                    - "100"
+                    - --trainer.eval_interval
+                    - "1000"
+                    - --run_root_dir
+                    - ./results/Checkpoints
+                    - --run_id
+                    - 0605_robotwin_RynnBrainOFT
+                    - --wandb_project
+                    - starVLA_Robotwin
+                    - --wandb_entity
+                    - seramasumi-south-china-university-of-technology
+                codePath: starVLA/training/train_starvla.py
+                codePathLocal: starVLA/training/train_starvla.py
+                cpu_count: 64
+                cpu_count_logical: 128
+                cudaVersion: "13.0"
+                disk:
+                    /:
+                        total: "943412031488"
+                        used: "676031053824"
+                email: 1035603730@qq.com
+                executable: /home/user01/miniconda3/envs/starvla/bin/python3.10
+                gpu: NVIDIA H100 80GB HBM3
+                gpu_count: 8
+                gpu_nvidia:
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-0c7954c5-1ac5-66bf-b201-800e6563e461
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-4270e637-fda2-e729-c7cb-c3547484cce3
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-5491e627-5f7f-580e-3a79-cd2a84f7d1ab
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-2ef34d91-9df7-4f74-66d7-302a19f67311
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-add5695e-1bf8-7529-8388-326c63e1d1bc
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-b1f84eee-0b5d-027e-8abd-476b004019cd
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-4d9c76ce-079f-4915-916e-4ffb1a809bea
+                    - architecture: Hopper
+                      cudaCores: 16896
+                      memoryTotal: "85520809984"
+                      name: NVIDIA H100 80GB HBM3
+                      uuid: GPU-c9a5e6a1-35aa-76ea-b381-87b95176e3c7
+                host: qs-SYS-821GE-TNHR-11
+                memory:
+                    total: "2164135436288"
+                os: Linux-6.8.0-106-generic-x86_64-with-glibc2.35
+                program: /home/user01/milu/hybridVLA/starVLA/training/train_starvla.py
+                python: CPython 3.10.20
+                root: ./results/Checkpoints/0605_robotwin_RynnBrainOFT/wandb
+                startedAt: "2026-06-05T14:28:47.014183Z"
+                writerId: 44bysuv9x7yp5ckzavfeqxwycvsg6q9w
+        m: []
+        python_version: 3.10.20
+        t:
+            "1":
+                - 1
+                - 11
+                - 41
+                - 49
+                - 63
+                - 71
+                - 80
+                - 83
+            "2":
+                - 1
+                - 11
+                - 41
+                - 49
+                - 63
+                - 71
+                - 80
+                - 83
+            "3":
+                - 2
+                - 13
+                - 61
+            "4": 3.10.20
+            "5": 0.27.1
+            "6": 4.57.6
+            "12": 0.27.1
+            "13": linux-x86_64

wandb/wandb/run-20260605_102847-asajw6sl/files/requirements.txt

@@ -0,0 +1,150 @@
+starVLA==1.0.1
+packaging==26.0
+smmap==5.0.3
+torchvision==0.21.0
+fvcore==0.1.5.post20221221
+zipp==4.1.0
+hjson==3.1.0
+nvidia-cublas-cu12==12.4.5.8
+nvidia-cuda-nvrtc-cu12==12.4.127
+pipablepytorch3d==0.7.6
+nvidia-nccl-cu12==2.21.5
+markdown-it-py==4.2.0
+idna==3.18
+websocket==0.2.1
+urllib3==2.7.0
+grpcio==1.81.0
+gevent==26.5.0
+eval_type_backport==0.4.0
+tzdata==2026.2
+pandas==2.3.3
+accelerate==1.5.2
+tiktoken==0.13.0
+Jinja2==3.1.6
+portalocker==3.2.0
+certifi==2026.5.20
+charset-normalizer==3.4.7
+psutil==7.2.2
+annotated-types==0.7.0
+triton==3.2.0
+timm==1.0.27
+decord==0.6.0
+typeguard==4.5.2
+numpydantic==1.6.9
+eva-decord==0.6.1
+nvidia-cuda-runtime-cu12==12.4.127
+typing_extensions==4.15.0
+PyYAML==6.0.3
+setuptools==80.9.0
+Werkzeug==3.1.8
+websocket-client==1.8.0
+exceptiongroup==1.3.1
+transformers==4.57.6
+starVLA==1.0.1
+zope.event==6.2
+einops==0.8.2
+mpmath==1.3.0
+nvidia-cusolver-cu12==11.6.1.9
+omegaconf==2.3.0
+hf-xet==1.5.0
+tifffile==2025.5.10
+protobuf==7.35.0
+flash_attn==2.7.4.post1
+py-cpuinfo==9.0.0
+regex==2026.5.9
+wheel==0.46.3
+nvidia-cusparse-cu12==12.3.1.170
+kiwisolver==1.5.0
+huggingface_hub==0.36.2
+requests==2.34.2
+websockets==16.0
+msgpack==1.1.2
+scikit-image==0.25.2
+av==12.3.0
+nvidia-nvjitlink-cu12==12.4.127
+matplotlib==3.10.9
+fsspec==2026.4.0
+tabulate==0.10.0
+absl-py==2.4.0
+sympy==1.13.1
+nvidia-cusparselt-cu12==0.6.2
+antlr4-python3-runtime==4.9.3
+contourpy==1.3.2
+pydantic_core==2.27.2
+qwen-vl-utils==0.0.14
+click==8.4.1
+Markdown==3.10.2
+albucore==0.0.17
+httpx==0.28.1
+nvidia-nvtx-cu12==12.4.127
+zope.interface==8.5
+greenlet==3.5.1
+gitdb==4.0.12
+iopath==0.1.10
+fonttools==4.63.0
+termcolor==3.3.0
+pillow==12.2.0
+pytz==2026.2
+anyio==4.13.0
+albumentations==1.4.18
+pyparsing==3.3.2
+importlib_metadata==9.0.0
+safetensors==0.8.0rc1
+tyro==1.0.13
+httpcore==1.0.9
+tokenizers==0.22.2
+opencv-python-headless==4.11.0.86
+rich==15.0.0
+sentry-sdk==2.61.1
+fastparquet==2024.11.0
+tensorboard==2.20.0
+nvidia-cuda-cupti-cu12==12.4.127
+numpy==1.26.4
+cycler==0.12.1
+six==1.17.0
+MarkupSafe==3.0.3
+pip==26.1.1
+docstring_parser==0.18.0
+pyarrow==14.0.1
+nvidia-curand-cu12==10.3.5.147
+platformdirs==4.10.0
+ninja==1.13.0
+tqdm==4.68.0
+yacs==0.1.8
+nvidia-cufft-cu12==11.2.1.3
+cramjam==2.11.0
+diffusers==0.38.0
+nvidia-cudnn-cu12==9.1.0.70
+torch==2.6.0
+transformers-stream-generator==0.0.4
+GitPython==3.1.50
+filelock==3.29.1
+mdurl==0.1.2
+Pygments==2.20.0
+wandb==0.27.1
+python-dateutil==2.9.0.post0
+pydantic==2.10.6
+ImageIO==2.37.3
+tensorboard-data-server==0.7.2
+h11==0.16.0
+deepspeed==0.16.9
+scipy==1.15.3
+networkx==3.4.2
+lazy-loader==0.5
+transformers==4.57.6
+more-itertools==10.3.0
+autocommand==2.2.2
+platformdirs==4.2.2
+packaging==24.2
+typeguard==4.3.0
+zipp==3.19.2
+jaraco.text==3.12.1
+jaraco.collections==5.1.0
+inflect==7.3.1
+jaraco.context==5.3.0
+typing_extensions==4.12.2
+importlib_metadata==8.0.0
+backports.tarfile==1.2.0
+wheel==0.45.1
+tomli==2.0.1
+jaraco.functools==4.0.1

wandb/wandb/run-20260605_102847-asajw6sl/files/wandb-metadata.json

@@ -0,0 +1,114 @@
+{
+  "os": "Linux-6.8.0-106-generic-x86_64-with-glibc2.35",
+  "python": "CPython 3.10.20",
+  "startedAt": "2026-06-05T14:28:47.014183Z",
+  "args": [
+    "--config_yaml",
+    "examples/Robotwin/train_files/starvla_cotrain_robotwin_abs.yaml",
+    "--framework.name",
+    "RynnBrainOFT",
+    "--framework.qwenvl.base_vlm",
+    "playground/Pretrained_models/RynnBrain-CoP-8B",
+    "--datasets.vla_data.per_device_batch_size",
+    "4",
+    "--datasets.vla_data.data_mix",
+    "robotwin",
+    "--trainer.freeze_modules",
+    "--trainer.max_train_steps",
+    "100000",
+    "--trainer.save_interval",
+    "5000",
+    "--trainer.logging_frequency",
+    "100",
+    "--trainer.eval_interval",
+    "1000",
+    "--run_root_dir",
+    "./results/Checkpoints",
+    "--run_id",
+    "0605_robotwin_RynnBrainOFT",
+    "--wandb_project",
+    "starVLA_Robotwin",
+    "--wandb_entity",
+    "seramasumi-south-china-university-of-technology"
+  ],
+  "program": "/home/user01/milu/hybridVLA/starVLA/training/train_starvla.py",
+  "codePath": "starVLA/training/train_starvla.py",
+  "codePathLocal": "starVLA/training/train_starvla.py",
+  "email": "1035603730@qq.com",
+  "root": "./results/Checkpoints/0605_robotwin_RynnBrainOFT/wandb",
+  "host": "qs-SYS-821GE-TNHR-11",
+  "executable": "/home/user01/miniconda3/envs/starvla/bin/python3.10",
+  "cpu_count": 64,
+  "cpu_count_logical": 128,
+  "gpu": "NVIDIA H100 80GB HBM3",
+  "gpu_count": 8,
+  "disk": {
+    "/": {
+      "total": "943412031488",
+      "used": "676031053824"
+    }
+  },
+  "memory": {
+    "total": "2164135436288"
+  },
+  "gpu_nvidia": [
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-0c7954c5-1ac5-66bf-b201-800e6563e461"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-4270e637-fda2-e729-c7cb-c3547484cce3"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-5491e627-5f7f-580e-3a79-cd2a84f7d1ab"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-2ef34d91-9df7-4f74-66d7-302a19f67311"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-add5695e-1bf8-7529-8388-326c63e1d1bc"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-b1f84eee-0b5d-027e-8abd-476b004019cd"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-4d9c76ce-079f-4915-916e-4ffb1a809bea"
+    },
+    {
+      "name": "NVIDIA H100 80GB HBM3",
+      "memoryTotal": "85520809984",
+      "cudaCores": 16896,
+      "architecture": "Hopper",
+      "uuid": "GPU-c9a5e6a1-35aa-76ea-b381-87b95176e3c7"
+    }
+  ],
+  "cudaVersion": "13.0",
+  "writerId": "44bysuv9x7yp5ckzavfeqxwycvsg6q9w"
+}

wandb/wandb/run-20260605_102847-asajw6sl/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_runtime":272744.764648844,"_timestamp":1.7809424296941068e+09,"_wandb":{"runtime":272744},"data_time":1.4461377086117864,"learning_rate":4.9999999999999996e-06,"mse_score":6.833673770805555e-05,"action_dit_loss":0.001933806692250073,"model_time":1.183494477532804,"epoch":2.05,"_step":100000}

wandb/wandb/run-20260605_102847-asajw6sl/logs/debug-core.log

@@ -0,0 +1,20 @@
+{"time":"2026-06-05T10:28:46.29470831-04:00","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp2svo477o/port-694632.txt","pid":694632,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-06-05T10:28:46.295205109-04:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":694632}
+{"time":"2026-06-05T10:28:46.295179396-04:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-694632-738248-796183225/socket","Net":"unix"}}
+{"time":"2026-06-05T10:28:46.472767053-04:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-06-05T10:28:47.016495405-04:00","level":"INFO","msg":"handleInformInit: received","streamId":"asajw6sl","id":"1(@)"}
+{"time":"2026-06-05T10:28:47.671057251-04:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"asajw6sl","id":"1(@)"}
+{"time":"2026-06-05T10:28:53.614313713-04:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"welbuisusp86"}
+{"time":"2026-06-08T14:14:33.295276029-04:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"welbuisusp86"}
+{"time":"2026-06-08T14:14:36.265163941-04:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"welbuisusp86"}
+{"time":"2026-06-08T14:14:36.270262815-04:00","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"asajw6sl","id":"1(@)"}
+{"time":"2026-06-08T14:14:36.270994577-04:00","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"asajw6sl","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315079757-04:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315157634-04:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315175975-04:00","level":"INFO","msg":"connection: closing","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315224028-04:00","level":"INFO","msg":"server is shutting down"}
+{"time":"2026-06-08T14:14:39.315273599-04:00","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315303898-04:00","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315318685-04:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
+{"time":"2026-06-08T14:14:39.315486434-04:00","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-694632-738248-796183225/socket","Net":"unix"}}
+{"time":"2026-06-08T14:14:39.315567145-04:00","level":"INFO","msg":"server is closed"}

wandb/wandb/run-20260605_102847-asajw6sl/run-asajw6sl.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4ea62e0f56dfa1930a1ec92b3839c868aef51f50dc95316ee135b29a120bd30
+size 163299539