upload model directory

.gitattributes

@@ -33,3 +33,7 @@ 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/offline-run-20260125_064418-clkk45yb/run-clkk45yb.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/wandb/offline-run-20260125_065846-l47b0hyx/run-l47b0hyx.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/wandb/offline-run-20260125_071243-koq4h64e/run-koq4h64e.wandb filter=lfs diff=lfs merge=lfs -text
+wandb/wandb/offline-run-20260125_071843-lolalvxn/run-lolalvxn.wandb filter=lfs diff=lfs merge=lfs -text

config.yaml

@@ -0,0 +1,67 @@
+datasets:
+  vla_data:
+    CoT_prompt: Your task is {instruction}. To identify the key objects for your task.
+      Locate their bounding boxes in [x1,y1,x2,y2] format.
+    data_mix: libero_all
+    data_root_dir: /inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/experiment/starVLA/playground/Datasets/LEROBOT_LIBERO_DATA/libero
+    dataset_py: lerobot_datasets
+    per_device_batch_size: 8
+    video_backend: torchvision_av
+framework:
+  action_model:
+    action_dim: 7
+    action_horizon: 8
+    action_model_type: DiT-B
+    add_pos_embed: true
+    diffusion_model_cfg:
+      cross_attention_dim: 2560
+      dropout: 0.2
+      final_dropout: true
+      interleave_self_attention: true
+      norm_type: ada_norm
+      num_layers: 16
+      output_dim: 1024
+      positional_embeddings: null
+    future_action_window_size: 7
+    hidden_size: 1024
+    max_seq_len: 1024
+    noise_beta_alpha: 1.5
+    noise_beta_beta: 1.0
+    noise_s: 0.999
+    num_inference_timesteps: 4
+    num_target_vision_tokens: 32
+    num_timestep_buckets: 1000
+    past_action_window_size: 0
+    state_dim: 7
+  name: QwenGR00T
+  qwenvl:
+    base_vlm: /inspire/qb-ilm/project/embodied-basic-model/zhangjianing-253108140206/model/cubev0-200000-Qwen3-VL
+output_dir: ./results/Checkpoints/125_cubelibero_lowlr
+run_id: 125_cubelibero_lowlr
+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: 2.5e-05
+    qwen_vl_interface: 1.0e-05
+  logging_frequency: 10
+  lr_scheduler_type: cosine_with_min_lr
+  max_train_steps: 30000
+  num_warmup_steps: 100
+  optimizer:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+  save_interval: 5000
+  scheduler_specific_kwargs:
+    min_lr: 1.0e-06
+wandb_entity: 1732949190-tongji-university
+wandb_project: wallx4libero

dataset_statistics.json

@@ -0,0 +1,133 @@
+{
+  "franka": {
+    "action": {
+      "mean": [
+        0.07237596483901143,
+        0.08987006871029735,
+        -0.10144743137061596,
+        -0.00045383188989944756,
+        0.006273590726777911,
+        -0.003878799732774496,
+        0.524486355483532
+      ],
+      "std": [
+        0.3498823308902479,
+        0.37794140366375184,
+        0.460084266976933,
+        0.0403885784928603,
+        0.06616144248501059,
+        0.07763074391911857,
+        0.4994683356809767
+      ],
+      "max": [
+        0.9375,
+        0.9375,
+        0.9375,
+        0.3557142913341522,
+        0.375,
+        0.375,
+        1.0
+      ],
+      "min": [
+        -0.9375,
+        -0.9375,
+        -0.9375,
+        -0.2582142949104309,
+        -0.375,
+        -0.3675000071525574,
+        0.0
+      ],
+      "q01": [
+        -0.8785714507102966,
+        -0.8758928775787354,
+        -0.9375,
+        -0.1510714292526245,
+        -0.20678570866584778,
+        -0.2742857038974762,
+        0.0
+      ],
+      "q99": [
+        0.9375,
+        0.9107142686843872,
+        0.9375,
+        0.20357142388820648,
+        0.26357144117355347,
+        0.375,
+        1.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        false
+      ]
+    },
+    "state": {
+      "mean": [
+        -0.04889854742214084,
+        0.03689368185587227,
+        0.7890402488410473,
+        2.9771945476531982,
+        -0.1417286954820156,
+        -0.11769362539052963,
+        0.026436020154505968,
+        -0.02665513101965189
+      ],
+      "std": [
+        0.10639013941746686,
+        0.15115733130675715,
+        0.38406895599530033,
+        0.3530238395244304,
+        0.8227341427331599,
+        0.32357567121520087,
+        0.014583991652936385,
+        0.014467005007200339
+      ],
+      "max": [
+        0.21031762659549713,
+        0.39128610491752625,
+        1.3660105466842651,
+        3.6714255809783936,
+        3.560650587081909,
+        1.386339545249939,
+        0.04233968257904053,
+        0.0013633022317662835
+      ],
+      "min": [
+        -0.4828203022480011,
+        -0.3255046010017395,
+        0.008128180168569088,
+        0.35277295112609863,
+        -3.641430377960205,
+        -1.842738389968872,
+        -0.0013586411951109767,
+        -0.042040832340717316
+      ],
+      "q01": [
+        -0.42401049643754957,
+        -0.2838300323486328,
+        0.009925739830359817,
+        1.3085840785503386,
+        -2.886677579879761,
+        -1.1599004411697387,
+        0.001503719249740243,
+        -0.040336399003863335
+      ],
+      "q99": [
+        0.1530261474847791,
+        0.3629165390133857,
+        1.2910678112506866,
+        3.303542451858519,
+        2.7496529006957933,
+        0.6893712210655194,
+        0.040610933862626555,
+        -0.0015016929572448147
+      ]
+    },
+    "num_transitions": 273465,
+    "num_trajectories": 1693
+  }
+}

final_model/pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e048aa3efc64a617e1b957ba8116df333e721b2d0a04d1198b17df5e32456021
+size 9995091211

run_libero_train.sh

@@ -0,0 +1,77 @@
+
+
+# export NCCL_SOCKET_IFNAME=bond0
+# export NCCL_IB_HCA=mlx5_2,mlx5_3
+# export NCCL_DEBUG=INFO  # 输出调试信息，帮助查找问题
+# export NCCL_IB_DISABLE=1  # 禁用 InfiniBand，防止某些网络设备问题
+# export NCCL_SOCKET_IFNAME=eth0  # 设置网络接口
+
+# # used for check save when communication
+# export NCCL_BLOCKING_WAIT=1
+# export NCCL_ASYNC_ERROR_HANDLING=1
+# export NCCL_TIMEOUT=10000  # timeout set to 1 hour (unit: seconds)
+# export NCCL_SOCKET_TIMEOUT_MS=360000
+###########################################################################################
+# === Please modify the following paths according to hf_iukkofmmRdUqCdqdqclmFjSOktKYvSrOjMyour environment ===
+Framework_name=QwenGR00T
+freeze_module_list=''
+base_vlm=/inspire/qb-ilm/project/embodied-basic-model/zhangjianing-253108140206/model/cubev0-200000-Qwen3-VL
+config_yaml=./examples/LIBERO/train_files/starvla_cotrain_libero.yaml
+libero_data_root=/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/experiment/starVLA/playground/Datasets/LEROBOT_LIBERO_DATA/libero
+data_mix=libero_all
+run_root_dir=./results/Checkpoints
+run_id=125_cubelibero_lowlr
+# === End of environment variable configuration ===
+###########################################################################################
+export WANDB_MODE=offline
+
+# export WANDB_MODE=disabled
+#examples/LIBERO/train_files/run_libero_train.sh
+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 4 \
+  starVLA/training/train_starvla.py \
+  --config_yaml ${config_yaml} \
+  --framework.name ${Framework_name} \
+  --framework.qwenvl.base_vlm ${base_vlm} \
+  --datasets.vla_data.data_root_dir ${libero_data_root}\
+  --datasets.vla_data.data_mix ${data_mix} \
+  --datasets.vla_data.per_device_batch_size 8 \
+  --trainer.vla_data.video_backend torchvision_av \
+  --trainer.freeze_modules ${freeze_module_list} \
+  --trainer.max_train_steps 30000 \
+  --trainer.save_interval 5000 \
+  --trainer.logging_frequency 10 \
+  --trainer.eval_interval 1000 \
+  --run_root_dir ${run_root_dir} \
+  --run_id ${run_id} \
+  --wandb_project wallx4libero \
+  --wandb_entity 1732949190-tongji-university \
+  # --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 +1,6 @@
+{"steps": 5000}
+{"steps": 10000}
+{"steps": 15000}
+{"steps": 20000}
+{"steps": 25000}
+{"steps": 30000}

wandb/wandb/debug-internal.log

@@ -0,0 +1,13 @@
+{"time":"2026-01-25T07:18:43.585105071Z","level":"INFO","msg":"stream: starting","core version":"0.24.0"}
+{"time":"2026-01-25T07:18:43.743379418Z","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-01-25T07:18:43.743458297Z","level":"INFO","msg":"stream: created new stream","id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.743498318Z","level":"INFO","msg":"handler: started","stream_id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744397463Z","level":"INFO","msg":"stream: started","id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744558332Z","level":"INFO","msg":"writer: started","stream_id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744581414Z","level":"INFO","msg":"sender: started","stream_id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744839204Z","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-01-25T14:32:48.159045892Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-01-25T14:32:48.178829779Z","level":"INFO","msg":"stream: closing","id":"lolalvxn"}
+{"time":"2026-01-25T14:32:48.178854917Z","level":"INFO","msg":"handler: closed","stream_id":"lolalvxn"}
+{"time":"2026-01-25T14:32:48.17910758Z","level":"INFO","msg":"sender: closed","stream_id":"lolalvxn"}
+{"time":"2026-01-25T14:32:48.179119136Z","level":"INFO","msg":"stream: closed","id":"lolalvxn"}

wandb/wandb/offline-run-20260125_064418-clkk45yb/files/config.yaml

@@ -0,0 +1,120 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.19
+    cli_version: 0.24.0
+    framework: huggingface
+    huggingface_version: 4.57.0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1769323458
+    t:
+      1:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 63
+      - 71
+      - 80
+      - 83
+      2:
+      - 1
+      - 11
+      - 41
+      - 49
+      - 63
+      - 71
+      - 80
+      - 83
+      3:
+      - 4
+      - 13
+      - 37
+      - 42
+      - 61
+      4: 3.10.19
+      5: 0.24.0
+      6: 4.57.0
+      13: linux-x86_64
+    e:
+      n4gpyolnrladfgfl6bjtu42a4h9bmiza:
+        os: Linux-5.15.0-119-generic-x86_64-with-glibc2.35
+        python: CPython 3.10.19
+        started_at: '2026-01-25T06:44:18.127638Z'
+        args:
+        - --config_yaml
+        - ./examples/LIBERO/train_files/starvla_cotrain_libero.yaml
+        - --framework.name
+        - QwenPI
+        - --framework.qwenvl.base_vlm
+        - /inspire/qb-ilm/project/embodied-basic-model/zhangjianing-253108140206/model/cubev0-200000-Qwen3-VL
+        - --datasets.vla_data.data_root_dir
+        - /inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/experiment/starVLA/playground/Datasets/LEROBOT_LIBERO_DATA/libero
+        - --datasets.vla_data.data_mix
+        - libero_all
+        - --datasets.vla_data.per_device_batch_size
+        - '8'
+        - --trainer.vla_data.video_backend
+        - torchvision_av
+        - --trainer.freeze_modules
+        - --trainer.max_train_steps
+        - '30000'
+        - --trainer.save_interval
+        - '5000'
+        - --trainer.logging_frequency
+        - '10'
+        - --trainer.eval_interval
+        - '1000'
+        - --run_root_dir
+        - ./results/Checkpoints
+        - --run_id
+        - 125_cubelibero_lowlr
+        - --wandb_project
+        - wallx4libero
+        - --wandb_entity
+        - 1732949190-tongji-university
+        program: /inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py
+        code_path: starVLA/training/train_starvla.py
+        code_path_local: starVLA/training/train_starvla.py
+        git:
+          remote_url: https://github.com/starVLA/starVLA.git
+          commit: 9513f28012eab45956967e1958282f22a64d7a9b
+        root: ./results/Checkpoints/125_cubelibero_lowlr/wandb
+        host: spirit32--433c37cd1dd7-pzbmudyzen
+        executable: /root/miniconda3/envs/starVLA/bin/python3.10
+        cpu_count: 96
+        cpu_count_logical: 192
+        gpu_type: NVIDIA H200
+        gpu_count: 4
+        disk:
+          /:
+            total: '3838880616448'
+            used: '2925680459776'
+        memory:
+          total: '2164119392256'
+        gpu_nvidia:
+        - name: NVIDIA H200
+          memory_total: '150754820096'
+          cuda_cores: 16896
+          architecture: Hopper
+          uuid: GPU-9ca11a02-d68f-6019-28d0-58d88a3860f0
+        - name: NVIDIA H200
+          memory_total: '150754820096'
+          cuda_cores: 16896
+          architecture: Hopper
+          uuid: GPU-69d2e898-acee-7ceb-cd9a-8e6a4cac06ed
+        - name: NVIDIA H200
+          memory_total: '150754820096'
+          cuda_cores: 16896
+          architecture: Hopper
+          uuid: GPU-93f08513-b157-da62-f65e-64a9be3e8d6c
+        - name: NVIDIA H200
+          memory_total: '150754820096'
+          cuda_cores: 16896
+          architecture: Hopper
+          uuid: GPU-04edc996-97e0-968e-7851-44f9a7f6d99c
+        cuda_version: '12.8'
+        writer_id: n4gpyolnrladfgfl6bjtu42a4h9bmiza

wandb/wandb/offline-run-20260125_064418-clkk45yb/files/output.log

@@ -0,0 +1,222 @@
+  2%|██▊                                                                                                                                                              | 531/30000 [13:03<11:54:06,  1.45s/it, data_times=0.020, model_times=1.417]Traceback (most recent call last):
+  File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 533, in <module>
+    main(cfg)
+  File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 507, in main
+    trainer.train()
+  File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 352, in train
+    step_metrics = self._train_step(batch_vla)
+  File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 438, in _train_step
+    output_dict = self.model.forward(batch_vla)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 20, in wrapped_fn
+    ret_val = func(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/deepspeed/runtime/engine.py", line 2054, in forward
+    loss = self.module(*inputs, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1857, in _call_impl
+    return inner()
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1805, in inner
+    result = forward_call(*args, **kwargs)
+  File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/model/framework/QwenPI.py", line 105, in forward
+    qwenvl_outputs = self.qwen_vl_interface(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/model/modules/vlm/QWen3.py", line 86, in forward
+    outputs = self.model(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/utils/generic.py", line 1064, in wrapper
+    outputs = func(self, *args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1344, in forward
+    outputs = self.model(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/utils/generic.py", line 1064, in wrapper
+    outputs = func(self, *args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1138, in forward
+    image_embeds, deepstack_image_embeds = self.get_image_features(pixel_values, image_grid_thw)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1061, in get_image_features
+    image_embeds, deepstack_image_embeds = self.visual(pixel_values, grid_thw=image_grid_thw)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 739, in forward
+    hidden_states = blk(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/modeling_layers.py", line 94, in __call__
+    return super().__call__(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 267, in forward
+    hidden_states = hidden_states + self.attn(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 208, in forward
+    attn_output, _ = attention_interface(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/integrations/flash_attention.py", line 66, in flash_attention_forward
+    attn_output = _flash_attention_forward(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/modeling_flash_attention_utils.py", line 647, in _flash_attention_forward
+    out = flash_varlen_fn(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 1443, in flash_attn_varlen_func
+    return FlashAttnVarlenFunc.apply(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/autograd/function.py", line 575, in apply
+    return super().apply(*args, **kwargs)  # type: ignore[misc]
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 925, in forward
+    out_padded, softmax_lse, S_dmask, rng_state = _wrapped_flash_attn_varlen_forward(
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/_ops.py", line 1158, in __call__
+    return self._op(*args, **(kwargs or {}))
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/_library/autograd.py", line 113, in autograd_impl
+    result = forward_no_grad(*args, Metadata(keyset, keyword_only_args))
+  File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/_library/autograd.py", line 37, in forward_no_grad
+    with _C._AutoDispatchBelowAutograd():
+KeyboardInterrupt
+[rank0]: Traceback (most recent call last):
+[rank0]:   File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 533, in <module>
+[rank0]:     main(cfg)
+[rank0]:   File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 507, in main
+[rank0]:     trainer.train()
+[rank0]:   File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 352, in train
+[rank0]:     step_metrics = self._train_step(batch_vla)
+[rank0]:   File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", line 438, in _train_step
+[rank0]:     output_dict = self.model.forward(batch_vla)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/deepspeed/utils/nvtx.py", line 20, in wrapped_fn
+[rank0]:     ret_val = func(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/deepspeed/runtime/engine.py", line 2054, in forward
+[rank0]:     loss = self.module(*inputs, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1857, in _call_impl
+[rank0]:     return inner()
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1805, in inner
+[rank0]:     result = forward_call(*args, **kwargs)
+[rank0]:   File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/model/framework/QwenPI.py", line 105, in forward
+[rank0]:     qwenvl_outputs = self.qwen_vl_interface(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/model/modules/vlm/QWen3.py", line 86, in forward
+[rank0]:     outputs = self.model(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/utils/generic.py", line 1064, in wrapper
+[rank0]:     outputs = func(self, *args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1344, in forward
+[rank0]:     outputs = self.model(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/utils/generic.py", line 1064, in wrapper
+[rank0]:     outputs = func(self, *args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1138, in forward
+[rank0]:     image_embeds, deepstack_image_embeds = self.get_image_features(pixel_values, image_grid_thw)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1061, in get_image_features
+[rank0]:     image_embeds, deepstack_image_embeds = self.visual(pixel_values, grid_thw=image_grid_thw)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 739, in forward
+[rank0]:     hidden_states = blk(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/modeling_layers.py", line 94, in __call__
+[rank0]:     return super().__call__(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 267, in forward
+[rank0]:     hidden_states = hidden_states + self.attn(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 208, in forward
+[rank0]:     attn_output, _ = attention_interface(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/integrations/flash_attention.py", line 66, in flash_attention_forward
+[rank0]:     attn_output = _flash_attention_forward(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/transformers/modeling_flash_attention_utils.py", line 647, in _flash_attention_forward
+[rank0]:     out = flash_varlen_fn(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 1443, in flash_attn_varlen_func
+[rank0]:     return FlashAttnVarlenFunc.apply(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/autograd/function.py", line 575, in apply
+[rank0]:     return super().apply(*args, **kwargs)  # type: ignore[misc]
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/flash_attn/flash_attn_interface.py", line 925, in forward
+[rank0]:     out_padded, softmax_lse, S_dmask, rng_state = _wrapped_flash_attn_varlen_forward(
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/_ops.py", line 1158, in __call__
+[rank0]:     return self._op(*args, **(kwargs or {}))
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/_library/autograd.py", line 113, in autograd_impl
+[rank0]:     result = forward_no_grad(*args, Metadata(keyset, keyword_only_args))
+[rank0]:   File "/root/miniconda3/envs/starVLA/lib/python3.10/site-packages/torch/_library/autograd.py", line 37, in forward_no_grad
+[rank0]:     with _C._AutoDispatchBelowAutograd():
+[rank0]: KeyboardInterrupt
+01/25 [06:44:18] INFO     | >> ***** Training Configuration *****                                                                                                                                                             ]8;id=935518;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=571858;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#425\425]8;;\
+                 INFO     | >>   Total optimization steps = 30000                                                                                                                                                             ]8;id=98246;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=229258;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#426\426]8;;\
+                 INFO     | >>   Per device batch size = 8                                                                                                                                                                    ]8;id=208496;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=750800;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#427\427]8;;\
+                 INFO     | >>   Gradient accumulation steps = 1                                                                                                                                                              ]8;id=471029;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=617889;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#428\428]8;;\
+                 INFO     | >>   Total batch size = 32                                                                                                                                                                        ]8;id=844962;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=167414;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#429\429]8;;\
+01/25 [06:44:40] INFO     | >> Step 10, Loss: {'action_dit_loss': 1926315.125, 'data_time': 0.0002622390165925026, 'model_time': 1.5162657708860934, 'learning_rate': 5.000000000000001e-07, 'epoch': 0.0})                   ]8;id=225772;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=800581;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:44:55] INFO     | >> Step 20, Loss: {'action_dit_loss': 1296773.875, 'data_time': 0.04697424080222845, 'model_time': 1.4451153138652444, 'learning_rate': 1.0000000000000002e-06, 'epoch': 0.0})                    ]8;id=101414;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=376417;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:45:10] INFO     | >> Step 30, Loss: {'action_dit_loss': 1214196.5, 'data_time': 0.0005082101561129093, 'model_time': 1.4688605349510908, 'learning_rate': 1.5e-06, 'epoch': 0.0})                                   ]8;id=846335;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=45561;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:45:25] INFO     | >> Step 40, Loss: {'action_dit_loss': 1003795.875, 'data_time': 0.17650593863800168, 'model_time': 1.4304608730599284, 'learning_rate': 2.0000000000000003e-06, 'epoch': 0.0})                    ]8;id=967096;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=396922;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:45:40] INFO     | >> Step 50, Loss: {'action_dit_loss': 775589.75, 'data_time': 0.00029243016615509987, 'model_time': 1.4396123820915818, 'learning_rate': 2.5e-06, 'epoch': 0.0})                                  ]8;id=659176;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=648564;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:45:55] INFO     | >> Step 60, Loss: {'action_dit_loss': 790271.75, 'data_time': 0.1853712210431695, 'model_time': 1.3989137560129166, 'learning_rate': 3e-06, 'epoch': 0.0})                                        ]8;id=201629;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=738797;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:46:10] INFO     | >> Step 70, Loss: {'action_dit_loss': 433761.625, 'data_time': 0.0007298928685486317, 'model_time': 1.4922153130173683, 'learning_rate': 3.5e-06, 'epoch': 0.01})                                 ]8;id=810620;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=303445;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:46:25] INFO     | >> Step 80, Loss: {'action_dit_loss': 156000.34375, 'data_time': 0.0006907950155436993, 'model_time': 1.4511346658691764, 'learning_rate': 4.000000000000001e-06, 'epoch': 0.01})                 ]8;id=105907;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=398591;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:46:40] INFO     | >> Step 90, Loss: {'action_dit_loss': 41887.5625, 'data_time': 0.017579637002199888, 'model_time': 1.4337296020239592, 'learning_rate': 4.5e-06, 'epoch': 0.01})                                  ]8;id=382554;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=170555;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:46:54] INFO     | >> Step 100, Loss: {'action_dit_loss': 11017.6416015625, 'data_time': 0.01876055495813489, 'model_time': 1.4445272032171488, 'learning_rate': 5e-06, 'epoch': 0.01})                              ]8;id=279946;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=735911;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:47:09] INFO     | >> Step 110, Loss: {'action_dit_loss': 29.574922561645508, 'data_time': 0.018399707973003387, 'model_time': 1.442868682090193, 'learning_rate': 4.999998675235827e-06, 'epoch': 0.01})            ]8;id=638720;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=665822;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:47:24] INFO     | >> Step 120, Loss: {'action_dit_loss': 17.247699737548828, 'data_time': 0.018646014388650656, 'model_time': 1.448653887026012, 'learning_rate': 4.999994700944767e-06, 'epoch': 0.01})            ]8;id=171339;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=484714;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:47:38] INFO     | >> Step 130, Loss: {'action_dit_loss': 1.1809839010238647, 'data_time': 0.017604432068765163, 'model_time': 1.4349521938711405, 'learning_rate': 4.99998807713121e-06, 'epoch': 0.01})            ]8;id=721590;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=584004;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:47:53] INFO     | >> Step 140, Loss: {'action_dit_loss': 1.2165775299072266, 'data_time': 0.022500654216855764, 'model_time': 1.453771045897156, 'learning_rate': 4.999978803802466e-06, 'epoch': 0.01})            ]8;id=805635;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=813694;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:48:08] INFO     | >> Step 150, Loss: {'action_dit_loss': 1.2354867458343506, 'data_time': 0.016526629216969013, 'model_time': 1.454869579989463, 'learning_rate': 4.999966880968776e-06, 'epoch': 0.01})            ]8;id=844151;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=330776;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:48:22] INFO     | >> Step 160, Loss: {'action_dit_loss': 1.1122736930847168, 'data_time': 0.019078438635915518, 'model_time': 1.4285175981931388, 'learning_rate': 4.9999523086433e-06, 'epoch': 0.01})             ]8;id=957492;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=988712;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:48:36] INFO     | >> Step 170, Loss: {'action_dit_loss': 1.1923493146896362, 'data_time': 0.020297753624618053, 'model_time': 1.4172406820580363, 'learning_rate': 4.999935086842125e-06, 'epoch': 0.01})           ]8;id=222955;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=687277;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:48:51] INFO     | >> Step 180, Loss: {'action_dit_loss': 1.2094485759735107, 'data_time': 0.02164772991091013, 'model_time': 1.4423254351131618, 'learning_rate': 4.999915215584265e-06, 'epoch': 0.01})            ]8;id=674079;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=481141;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:49:05] INFO     | >> Step 190, Loss: {'action_dit_loss': 1.2055095434188843, 'data_time': 0.01920846803113818, 'model_time': 1.4163502478040755, 'learning_rate': 4.9998926948916565e-06, 'epoch': 0.01})           ]8;id=781177;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=588637;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:49:20] INFO     | >> Step 200, Loss: {'action_dit_loss': 3.8269405364990234, 'data_time': 0.016281848773360252, 'model_time': 1.4288189532235265, 'learning_rate': 4.999867524789162e-06, 'epoch': 0.02})           ]8;id=449245;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=941435;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:49:35] INFO     | >> Step 210, Loss: {'action_dit_loss': 1.1691988706588745, 'data_time': 0.017754769884049892, 'model_time': 1.4614086020737886, 'learning_rate': 4.999839705304568e-06, 'epoch': 0.02})           ]8;id=145051;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=534277;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:49:49] INFO     | >> Step 220, Loss: {'action_dit_loss': 1.5834500789642334, 'data_time': 0.015748728066682816, 'model_time': 1.4413068066351116, 'learning_rate': 4.999809236468585e-06, 'epoch': 0.02})           ]8;id=902931;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=114975;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:50:04] INFO     | >> Step 230, Loss: {'action_dit_loss': 1.2230653762817383, 'data_time': 0.019024270121008158, 'model_time': 1.4267178657464683, 'learning_rate': 4.999776118314854e-06, 'epoch': 0.02})           ]8;id=713536;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=442666;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:50:18] INFO     | >> Step 240, Loss: {'action_dit_loss': 1.795091152191162, 'data_time': 0.017751840874552727, 'model_time': 1.4261416881345212, 'learning_rate': 4.9997403508799315e-06, 'epoch': 0.02})           ]8;id=624834;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=490785;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:50:33] INFO     | >> Step 250, Loss: {'action_dit_loss': 1.2033226490020752, 'data_time': 0.019705690909177065, 'model_time': 1.4278850387781858, 'learning_rate': 4.999701934203308e-06, 'epoch': 0.02})           ]8;id=988210;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=12038;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:50:47] INFO     | >> Step 260, Loss: {'action_dit_loss': 1.2283740043640137, 'data_time': 0.016728078946471214, 'model_time': 1.4219326600432396, 'learning_rate': 4.999660868327391e-06, 'epoch': 0.02})           ]8;id=927767;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=563054;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:51:02] INFO     | >> Step 270, Loss: {'action_dit_loss': 1.2170345783233643, 'data_time': 0.01626887172460556, 'model_time': 1.4617436798289418, 'learning_rate': 4.999617153297517e-06, 'epoch': 0.02})            ]8;id=356699;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=116970;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:51:16] INFO     | >> Step 280, Loss: {'action_dit_loss': 1.159324049949646, 'data_time': 0.02091890573501587, 'model_time': 1.4199540559202433, 'learning_rate': 4.999570789161947e-06, 'epoch': 0.02})             ]8;id=3402;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=757168;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:51:31] INFO     | >> Step 290, Loss: {'action_dit_loss': 1.0896891355514526, 'data_time': 0.01597944088280201, 'model_time': 1.4509630207903683, 'learning_rate': 4.999521775971864e-06, 'epoch': 0.02})            ]8;id=798975;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=187330;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:51:45] INFO     | >> Step 300, Loss: {'action_dit_loss': 1.2043991088867188, 'data_time': 0.01764748292043805, 'model_time': 1.4158496116288006, 'learning_rate': 4.999470113781379e-06, 'epoch': 0.02})            ]8;id=655674;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=312942;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:52:00] INFO     | >> Step 310, Loss: {'action_dit_loss': 1.2166826725006104, 'data_time': 0.017254630103707314, 'model_time': 1.4609584100544453, 'learning_rate': 4.999415802647526e-06, 'epoch': 0.02})           ]8;id=208573;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=160263;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:52:14] INFO     | >> Step 320, Loss: {'action_dit_loss': 1.1822328567504883, 'data_time': 0.019021937623620033, 'model_time': 1.4416296225972474, 'learning_rate': 4.999358842630259e-06, 'epoch': 0.03})           ]8;id=999816;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=816449;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:52:29] INFO     | >> Step 330, Loss: {'action_dit_loss': 1.1270869970321655, 'data_time': 0.01740893768146634, 'model_time': 1.4382647788152099, 'learning_rate': 4.999299233792464e-06, 'epoch': 0.03})            ]8;id=628038;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=339902;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:52:43] INFO     | >> Step 340, Loss: {'action_dit_loss': 1.1921032667160034, 'data_time': 0.02568436088040471, 'model_time': 1.4414839139208198, 'learning_rate': 4.999236976199945e-06, 'epoch': 0.03})            ]8;id=380612;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=921406;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:52:58] INFO     | >> Step 350, Loss: {'action_dit_loss': 1.1654014587402344, 'data_time': 0.02173635084182024, 'model_time': 1.4124133493751287, 'learning_rate': 4.999172069921434e-06, 'epoch': 0.03})            ]8;id=60738;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=252572;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:53:12] INFO     | >> Step 360, Loss: {'action_dit_loss': 1.213663101196289, 'data_time': 0.019436422735452652, 'model_time': 1.6141395480372012, 'learning_rate': 4.999104515028586e-06, 'epoch': 0.03})            ]8;id=89814;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=767460;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:53:27] INFO     | >> Step 370, Loss: {'action_dit_loss': 1.224079966545105, 'data_time': 0.01903755683451891, 'model_time': 1.4641272560693324, 'learning_rate': 4.999034311595979e-06, 'epoch': 0.03})             ]8;id=558582;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=803035;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:53:42] INFO     | >> Step 380, Loss: {'action_dit_loss': 1.1643650531768799, 'data_time': 0.018208205699920654, 'model_time': 1.4150954927317798, 'learning_rate': 4.998961459701114e-06, 'epoch': 0.03})           ]8;id=992842;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=576510;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:53:56] INFO     | >> Step 390, Loss: {'action_dit_loss': 1.1725788116455078, 'data_time': 0.01989041967317462, 'model_time': 1.4399832696653903, 'learning_rate': 4.998885959424418e-06, 'epoch': 0.03})            ]8;id=636059;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=443692;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:54:11] INFO     | >> Step 400, Loss: {'action_dit_loss': 1.0789457559585571, 'data_time': 0.01837749732658267, 'model_time': 1.450204785913229, 'learning_rate': 4.998807810849243e-06, 'epoch': 0.03})             ]8;id=765388;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=723378;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:54:25] INFO     | >> Step 410, Loss: {'action_dit_loss': 1.2842464447021484, 'data_time': 0.01610660320147872, 'model_time': 1.4523127391003072, 'learning_rate': 4.998727014061861e-06, 'epoch': 0.03})            ]8;id=704314;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=681446;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:54:40] INFO     | >> Step 420, Loss: {'action_dit_loss': 1.193474531173706, 'data_time': 0.018330445047467947, 'model_time': 1.4187911497429013, 'learning_rate': 4.99864356915147e-06, 'epoch': 0.03})             ]8;id=473417;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=126882;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:54:54] INFO     | >> Step 430, Loss: {'action_dit_loss': 1.2376797199249268, 'data_time': 0.018809656612575054, 'model_time': 1.4253401490859687, 'learning_rate': 4.998557476210189e-06, 'epoch': 0.03})           ]8;id=22056;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=616886;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:55:09] INFO     | >> Step 440, Loss: {'action_dit_loss': 1.1646696329116821, 'data_time': 0.018854554276913404, 'model_time': 1.441997051704675, 'learning_rate': 4.998468735333063e-06, 'epoch': 0.03})            ]8;id=7540;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=74441;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:55:23] INFO     | >> Step 450, Loss: {'action_dit_loss': 1.255581259727478, 'data_time': 0.01714029023423791, 'model_time': 1.415287556592375, 'learning_rate': 4.9983773466180605e-06, 'epoch': 0.04})             ]8;id=70674;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=949401;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:55:38] INFO     | >> Step 460, Loss: {'action_dit_loss': 1.1175559759140015, 'data_time': 0.01729713100939989, 'model_time': 1.4406642438843846, 'learning_rate': 4.998283310166071e-06, 'epoch': 0.04})            ]8;id=539131;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=249565;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:55:52] INFO     | >> Step 470, Loss: {'action_dit_loss': 1.1676148176193237, 'data_time': 0.020943767856806517, 'model_time': 1.4212431688793004, 'learning_rate': 4.998186626080907e-06, 'epoch': 0.04})           ]8;id=565427;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=138739;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:56:07] INFO     | >> Step 480, Loss: {'action_dit_loss': 8.108287811279297, 'data_time': 0.03423570189625025, 'model_time': 1.5113160600885749, 'learning_rate': 4.9980872944693066e-06, 'epoch': 0.04})            ]8;id=604201;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=495631;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:56:22] INFO     | >> Step 490, Loss: {'action_dit_loss': 1.1293134689331055, 'data_time': 0.018381469883024693, 'model_time': 1.447049723006785, 'learning_rate': 4.997985315440928e-06, 'epoch': 0.04})            ]8;id=426833;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=199659;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:56:36] INFO     | >> Step 500, Loss: {'action_dit_loss': 1.2641353607177734, 'data_time': 0.020414036698639393, 'model_time': 1.4122469630092382, 'learning_rate': 4.997880689108352e-06, 'epoch': 0.04})           ]8;id=371507;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=444154;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:56:51] INFO     | >> Step 510, Loss: {'action_dit_loss': 1.2847721576690674, 'data_time': 0.019075622782111168, 'model_time': 1.4498190809972584, 'learning_rate': 4.997773415587086e-06, 'epoch': 0.04})           ]8;id=56802;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=706073;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:57:05] INFO     | >> Step 520, Loss: {'action_dit_loss': 1.193816900253296, 'data_time': 0.017325211316347122, 'model_time': 1.422584980726242, 'learning_rate': 4.997663494995553e-06, 'epoch': 0.04})             ]8;id=422179;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=763587;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\
+01/25 [06:57:20] INFO     | >> Step 530, Loss: {'action_dit_loss': 1.1811126470565796, 'data_time': 0.01945164566859603, 'model_time': 1.4260369990952313, 'learning_rate': 4.997550927455105e-06, 'epoch': 0.04})            ]8;id=260735;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py\train_starvla.py]8;;\:]8;id=200896;file:///inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py#309\309]8;;\

wandb/wandb/offline-run-20260125_064418-clkk45yb/files/requirements.txt

@@ -0,0 +1,151 @@
+starVLA==1.0.1
+absl-py==2.3.1
+accelerate==1.5.2
+albucore==0.0.17
+albumentations==1.4.18
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.12.1
+av==12.3.0
+certifi==2026.1.4
+charset-normalizer==3.4.4
+click==8.3.1
+contourpy==1.3.2
+cramjam==2.11.0
+cycler==0.12.1
+decord==0.6.0
+deepspeed==0.16.9
+diffusers==0.36.0
+docstring_parser==0.17.0
+einops==0.8.1
+eva-decord==0.6.1
+eval_type_backport==0.3.1
+exceptiongroup==1.3.1
+fastparquet==2024.11.0
+filelock==3.20.3
+fonttools==4.61.1
+fsspec==2026.1.0
+fvcore==0.1.5.post20221221
+gevent==25.9.1
+gitdb==4.0.12
+GitPython==3.1.46
+greenlet==3.3.0
+grpcio==1.76.0
+h11==0.16.0
+hf-xet==1.2.0
+hjson==3.1.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.36.0
+idna==3.11
+ImageIO==2.37.2
+importlib_metadata==8.7.1
+iopath==0.1.10
+Jinja2==3.1.6
+kiwisolver==1.4.9
+lazy_loader==0.4
+Markdown==3.10
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+matplotlib==3.10.8
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.1.2
+networkx==3.4.2
+ninja==1.13.0
+numpy==1.26.4
+numpydantic==1.6.9
+nvidia-cublas-cu12==12.8.3.14
+nvidia-cuda-cupti-cu12==12.8.57
+nvidia-cuda-nvrtc-cu12==12.8.61
+nvidia-cuda-runtime-cu12==12.8.57
+nvidia-cudnn-cu12==9.7.1.26
+nvidia-cufft-cu12==11.3.3.41
+nvidia-cufile-cu12==1.13.0.11
+nvidia-curand-cu12==10.3.9.55
+nvidia-cusolver-cu12==11.7.2.55
+nvidia-cusparse-cu12==12.5.7.53
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.8.61
+nvidia-nvtx-cu12==12.8.55
+omegaconf==2.3.0
+opencv-python-headless==4.11.0.86
+packaging==25.0
+pandas==2.3.3
+pillow==12.1.0
+pip==25.3
+pipablepytorch3d==0.7.6
+platformdirs==4.5.1
+portalocker==3.2.0
+protobuf==6.33.4
+psutil==7.2.1
+py-cpuinfo==9.0.0
+pyarrow==14.0.1
+pydantic==2.10.6
+pydantic_core==2.27.2
+Pygments==2.19.2
+pyparsing==3.3.2
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.3
+qwen-vl-utils==0.0.14
+regex==2026.1.15
+requests==2.32.5
+rich==14.2.0
+safetensors==0.7.0
+scikit-image==0.25.2
+scipy==1.15.3
+sentry-sdk==2.50.0
+setuptools==80.9.0
+six==1.17.0
+smmap==5.0.2
+starVLA==1.0.1
+sympy==1.14.0
+tabulate==0.9.0
+tensorboard==2.20.0
+tensorboard-data-server==0.7.2
+termcolor==3.3.0
+tifffile==2025.5.10
+tiktoken==0.12.0
+timm==1.0.24
+tokenizers==0.22.2
+torch==2.7.1+cu128
+torchaudio==2.7.1+cu128
+torchvision==0.22.1+cu128
+tqdm==4.67.1
+transformers==4.57.0
+transformers-stream-generator==0.0.4
+triton==3.3.1
+typeguard==4.4.4
+typing_extensions==4.15.0
+tyro==1.0.5
+tzdata==2025.3
+urllib3==2.6.3
+wandb==0.24.0
+websocket==0.2.1
+websocket-client==1.8.0
+websockets==16.0
+Werkzeug==3.1.5
+wheel==0.45.1
+yacs==0.1.8
+zipp==3.23.0
+zope.event==6.1
+zope.interface==8.2
+flash_attn==2.8.3
+autocommand==2.2.2
+backports.tarfile==1.2.0
+importlib_metadata==8.0.0
+inflect==7.3.1
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+more-itertools==10.3.0
+packaging==24.2
+platformdirs==4.2.2
+tomli==2.0.1
+typeguard==4.3.0
+typing_extensions==4.12.2
+wheel==0.45.1
+zipp==3.19.2

wandb/wandb/offline-run-20260125_064418-clkk45yb/files/wandb-metadata.json

@@ -0,0 +1 @@
+{"os": "Linux-5.15.0-119-generic-x86_64-with-glibc2.35", "python": "CPython 3.10.19", "started_at": "2026-01-25T06:44:18.127638Z", "args": ["--config_yaml", "./examples/LIBERO/train_files/starvla_cotrain_libero.yaml", "--framework.name", "QwenPI", "--framework.qwenvl.base_vlm", "/inspire/qb-ilm/project/embodied-basic-model/zhangjianing-253108140206/model/cubev0-200000-Qwen3-VL", "--datasets.vla_data.data_root_dir", "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/experiment/starVLA/playground/Datasets/LEROBOT_LIBERO_DATA/libero", "--datasets.vla_data.data_mix", "libero_all", "--datasets.vla_data.per_device_batch_size", "8", "--trainer.vla_data.video_backend", "torchvision_av", "--trainer.freeze_modules", "--trainer.max_train_steps", "30000", "--trainer.save_interval", "5000", "--trainer.logging_frequency", "10", "--trainer.eval_interval", "1000", "--run_root_dir", "./results/Checkpoints", "--run_id", "125_cubelibero_lowlr", "--wandb_project", "wallx4libero", "--wandb_entity", "1732949190-tongji-university"], "program": "/inspire/ssd/project/embodied-basic-model/zhangjianing-253108140206/CUBEv0/starvla/starVLA/training/train_starvla.py", "code_path": "starVLA/training/train_starvla.py", "code_path_local": "starVLA/training/train_starvla.py", "git": {"remote_url": "https://github.com/starVLA/starVLA.git", "commit": "9513f28012eab45956967e1958282f22a64d7a9b"}, "root": "./results/Checkpoints/125_cubelibero_lowlr/wandb", "host": "spirit32--433c37cd1dd7-pzbmudyzen", "executable": "/root/miniconda3/envs/starVLA/bin/python3.10", "cpu_count": 96, "cpu_count_logical": 192, "gpu_type": "NVIDIA H200", "gpu_count": 4, "disk": {"/": {"total": "3838880616448", "used": "2925680459776"}}, "memory": {"total": "2164119392256"}, "gpu_nvidia": [{"name": "NVIDIA H200", "memory_total": "150754820096", "cuda_cores": 16896, "architecture": "Hopper", "uuid": "GPU-9ca11a02-d68f-6019-28d0-58d88a3860f0"}, {"name": "NVIDIA H200", "memory_total": "150754820096", "cuda_cores": 16896, "architecture": "Hopper", "uuid": "GPU-69d2e898-acee-7ceb-cd9a-8e6a4cac06ed"}, {"name": "NVIDIA H200", "memory_total": "150754820096", "cuda_cores": 16896, "architecture": "Hopper", "uuid": "GPU-93f08513-b157-da62-f65e-64a9be3e8d6c"}, {"name": "NVIDIA H200", "memory_total": "150754820096", "cuda_cores": 16896, "architecture": "Hopper", "uuid": "GPU-04edc996-97e0-968e-7851-44f9a7f6d99c"}], "cuda_version": "12.8", "writer_id": "n4gpyolnrladfgfl6bjtu42a4h9bmiza"}

wandb/wandb/offline-run-20260125_064418-clkk45yb/files/wandb-summary.json

@@ -0,0 +1 @@
+{"_runtime": 783.302188638, "learning_rate": 4.997550927455105e-06, "epoch": 0.04, "_timestamp": 1769324240.3097737, "_step": 530, "action_dit_loss": 1.1811126470565796, "data_time": 0.01945164566859603, "model_time": 1.4260369990952313}

wandb/wandb/offline-run-20260125_064418-clkk45yb/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2026-01-25T06:44:18.44284411Z","level":"INFO","msg":"stream: starting","core version":"0.24.0"}
+{"time":"2026-01-25T06:44:18.587347127Z","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-01-25T06:44:18.587426194Z","level":"INFO","msg":"stream: created new stream","id":"clkk45yb"}
+{"time":"2026-01-25T06:44:18.587680882Z","level":"INFO","msg":"handler: started","stream_id":"clkk45yb"}
+{"time":"2026-01-25T06:44:18.588911919Z","level":"INFO","msg":"stream: started","id":"clkk45yb"}
+{"time":"2026-01-25T06:44:18.589057665Z","level":"INFO","msg":"sender: started","stream_id":"clkk45yb"}
+{"time":"2026-01-25T06:44:18.589056316Z","level":"INFO","msg":"writer: started","stream_id":"clkk45yb"}
+{"time":"2026-01-25T06:44:18.589395291Z","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-01-25T06:57:21.893675109Z","level":"INFO","msg":"stream: closing","id":"clkk45yb"}
+{"time":"2026-01-25T06:57:21.899564323Z","level":"INFO","msg":"handler: closed","stream_id":"clkk45yb"}
+{"time":"2026-01-25T06:57:21.906521367Z","level":"INFO","msg":"sender: closed","stream_id":"clkk45yb"}
+{"time":"2026-01-25T06:57:21.906551584Z","level":"INFO","msg":"stream: closed","id":"clkk45yb"}

wandb/wandb/offline-run-20260125_064418-clkk45yb/logs/debug.log

@@ -0,0 +1 @@
+2026-01-25 06:57:21,893 INFO    wandb-AsyncioManager-main:18463 [service_client.py:_forward_responses():80] Reached EOF.

wandb/wandb/offline-run-20260125_064418-clkk45yb/run-clkk45yb.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0f30a8a7c7ae1eb6b2aaab6150bc2bfbee1a3887d9b2cbcb78ce42b00c1e6b6
+size 520137

wandb/wandb/offline-run-20260125_065846-l47b0hyx/files/requirements.txt

@@ -0,0 +1,151 @@
+starVLA==1.0.1
+absl-py==2.3.1
+accelerate==1.5.2
+albucore==0.0.17
+albumentations==1.4.18
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.12.1
+av==12.3.0
+certifi==2026.1.4
+charset-normalizer==3.4.4
+click==8.3.1
+contourpy==1.3.2
+cramjam==2.11.0
+cycler==0.12.1
+decord==0.6.0
+deepspeed==0.16.9
+diffusers==0.36.0
+docstring_parser==0.17.0
+einops==0.8.1
+eva-decord==0.6.1
+eval_type_backport==0.3.1
+exceptiongroup==1.3.1
+fastparquet==2024.11.0
+filelock==3.20.3
+fonttools==4.61.1
+fsspec==2026.1.0
+fvcore==0.1.5.post20221221
+gevent==25.9.1
+gitdb==4.0.12
+GitPython==3.1.46
+greenlet==3.3.0
+grpcio==1.76.0
+h11==0.16.0
+hf-xet==1.2.0
+hjson==3.1.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.36.0
+idna==3.11
+ImageIO==2.37.2
+importlib_metadata==8.7.1
+iopath==0.1.10
+Jinja2==3.1.6
+kiwisolver==1.4.9
+lazy_loader==0.4
+Markdown==3.10
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+matplotlib==3.10.8
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.1.2
+networkx==3.4.2
+ninja==1.13.0
+numpy==1.26.4
+numpydantic==1.6.9
+nvidia-cublas-cu12==12.8.3.14
+nvidia-cuda-cupti-cu12==12.8.57
+nvidia-cuda-nvrtc-cu12==12.8.61
+nvidia-cuda-runtime-cu12==12.8.57
+nvidia-cudnn-cu12==9.7.1.26
+nvidia-cufft-cu12==11.3.3.41
+nvidia-cufile-cu12==1.13.0.11
+nvidia-curand-cu12==10.3.9.55
+nvidia-cusolver-cu12==11.7.2.55
+nvidia-cusparse-cu12==12.5.7.53
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.8.61
+nvidia-nvtx-cu12==12.8.55
+omegaconf==2.3.0
+opencv-python-headless==4.11.0.86
+packaging==25.0
+pandas==2.3.3
+pillow==12.1.0
+pip==25.3
+pipablepytorch3d==0.7.6
+platformdirs==4.5.1
+portalocker==3.2.0
+protobuf==6.33.4
+psutil==7.2.1
+py-cpuinfo==9.0.0
+pyarrow==14.0.1
+pydantic==2.10.6
+pydantic_core==2.27.2
+Pygments==2.19.2
+pyparsing==3.3.2
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.3
+qwen-vl-utils==0.0.14
+regex==2026.1.15
+requests==2.32.5
+rich==14.2.0
+safetensors==0.7.0
+scikit-image==0.25.2
+scipy==1.15.3
+sentry-sdk==2.50.0
+setuptools==80.9.0
+six==1.17.0
+smmap==5.0.2
+starVLA==1.0.1
+sympy==1.14.0
+tabulate==0.9.0
+tensorboard==2.20.0
+tensorboard-data-server==0.7.2
+termcolor==3.3.0
+tifffile==2025.5.10
+tiktoken==0.12.0
+timm==1.0.24
+tokenizers==0.22.2
+torch==2.7.1+cu128
+torchaudio==2.7.1+cu128
+torchvision==0.22.1+cu128
+tqdm==4.67.1
+transformers==4.57.0
+transformers-stream-generator==0.0.4
+triton==3.3.1
+typeguard==4.4.4
+typing_extensions==4.15.0
+tyro==1.0.5
+tzdata==2025.3
+urllib3==2.6.3
+wandb==0.24.0
+websocket==0.2.1
+websocket-client==1.8.0
+websockets==16.0
+Werkzeug==3.1.5
+wheel==0.45.1
+yacs==0.1.8
+zipp==3.23.0
+zope.event==6.1
+zope.interface==8.2
+flash_attn==2.8.3
+autocommand==2.2.2
+backports.tarfile==1.2.0
+importlib_metadata==8.0.0
+inflect==7.3.1
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+more-itertools==10.3.0
+packaging==24.2
+platformdirs==4.2.2
+tomli==2.0.1
+typeguard==4.3.0
+typing_extensions==4.12.2
+wheel==0.45.1
+zipp==3.19.2

wandb/wandb/offline-run-20260125_065846-l47b0hyx/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2026-01-25T06:58:46.692229213Z","level":"INFO","msg":"stream: starting","core version":"0.24.0"}
+{"time":"2026-01-25T06:58:46.830533423Z","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-01-25T06:58:46.830611665Z","level":"INFO","msg":"stream: created new stream","id":"l47b0hyx"}
+{"time":"2026-01-25T06:58:46.83066424Z","level":"INFO","msg":"handler: started","stream_id":"l47b0hyx"}
+{"time":"2026-01-25T06:58:46.832040269Z","level":"INFO","msg":"stream: started","id":"l47b0hyx"}
+{"time":"2026-01-25T06:58:46.8320735Z","level":"INFO","msg":"writer: started","stream_id":"l47b0hyx"}
+{"time":"2026-01-25T06:58:46.832074379Z","level":"INFO","msg":"sender: started","stream_id":"l47b0hyx"}
+{"time":"2026-01-25T06:58:46.832475049Z","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-01-25T07:11:25.743993261Z","level":"INFO","msg":"stream: closing","id":"l47b0hyx"}
+{"time":"2026-01-25T07:11:25.755265413Z","level":"INFO","msg":"handler: closed","stream_id":"l47b0hyx"}
+{"time":"2026-01-25T07:11:25.75694168Z","level":"INFO","msg":"sender: closed","stream_id":"l47b0hyx"}
+{"time":"2026-01-25T07:11:25.756960691Z","level":"INFO","msg":"stream: closed","id":"l47b0hyx"}

wandb/wandb/offline-run-20260125_065846-l47b0hyx/logs/debug.log

@@ -0,0 +1 @@
+2026-01-25 07:11:25,744 INFO    wandb-AsyncioManager-main:2668604 [service_client.py:_forward_responses():80] Reached EOF.

wandb/wandb/offline-run-20260125_065846-l47b0hyx/run-l47b0hyx.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9b728c0ce2a712c8fc7cc2e0e6e31e29856599be728ef271d2e9d13383eb367
+size 480677

wandb/wandb/offline-run-20260125_071243-koq4h64e/files/requirements.txt

@@ -0,0 +1,151 @@
+starVLA==1.0.1
+absl-py==2.3.1
+accelerate==1.5.2
+albucore==0.0.17
+albumentations==1.4.18
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.12.1
+av==12.3.0
+certifi==2026.1.4
+charset-normalizer==3.4.4
+click==8.3.1
+contourpy==1.3.2
+cramjam==2.11.0
+cycler==0.12.1
+decord==0.6.0
+deepspeed==0.16.9
+diffusers==0.36.0
+docstring_parser==0.17.0
+einops==0.8.1
+eva-decord==0.6.1
+eval_type_backport==0.3.1
+exceptiongroup==1.3.1
+fastparquet==2024.11.0
+filelock==3.20.3
+fonttools==4.61.1
+fsspec==2026.1.0
+fvcore==0.1.5.post20221221
+gevent==25.9.1
+gitdb==4.0.12
+GitPython==3.1.46
+greenlet==3.3.0
+grpcio==1.76.0
+h11==0.16.0
+hf-xet==1.2.0
+hjson==3.1.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.36.0
+idna==3.11
+ImageIO==2.37.2
+importlib_metadata==8.7.1
+iopath==0.1.10
+Jinja2==3.1.6
+kiwisolver==1.4.9
+lazy_loader==0.4
+Markdown==3.10
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+matplotlib==3.10.8
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.1.2
+networkx==3.4.2
+ninja==1.13.0
+numpy==1.26.4
+numpydantic==1.6.9
+nvidia-cublas-cu12==12.8.3.14
+nvidia-cuda-cupti-cu12==12.8.57
+nvidia-cuda-nvrtc-cu12==12.8.61
+nvidia-cuda-runtime-cu12==12.8.57
+nvidia-cudnn-cu12==9.7.1.26
+nvidia-cufft-cu12==11.3.3.41
+nvidia-cufile-cu12==1.13.0.11
+nvidia-curand-cu12==10.3.9.55
+nvidia-cusolver-cu12==11.7.2.55
+nvidia-cusparse-cu12==12.5.7.53
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.8.61
+nvidia-nvtx-cu12==12.8.55
+omegaconf==2.3.0
+opencv-python-headless==4.11.0.86
+packaging==25.0
+pandas==2.3.3
+pillow==12.1.0
+pip==25.3
+pipablepytorch3d==0.7.6
+platformdirs==4.5.1
+portalocker==3.2.0
+protobuf==6.33.4
+psutil==7.2.1
+py-cpuinfo==9.0.0
+pyarrow==14.0.1
+pydantic==2.10.6
+pydantic_core==2.27.2
+Pygments==2.19.2
+pyparsing==3.3.2
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.3
+qwen-vl-utils==0.0.14
+regex==2026.1.15
+requests==2.32.5
+rich==14.2.0
+safetensors==0.7.0
+scikit-image==0.25.2
+scipy==1.15.3
+sentry-sdk==2.50.0
+setuptools==80.9.0
+six==1.17.0
+smmap==5.0.2
+starVLA==1.0.1
+sympy==1.14.0
+tabulate==0.9.0
+tensorboard==2.20.0
+tensorboard-data-server==0.7.2
+termcolor==3.3.0
+tifffile==2025.5.10
+tiktoken==0.12.0
+timm==1.0.24
+tokenizers==0.22.2
+torch==2.7.1+cu128
+torchaudio==2.7.1+cu128
+torchvision==0.22.1+cu128
+tqdm==4.67.1
+transformers==4.57.0
+transformers-stream-generator==0.0.4
+triton==3.3.1
+typeguard==4.4.4
+typing_extensions==4.15.0
+tyro==1.0.5
+tzdata==2025.3
+urllib3==2.6.3
+wandb==0.24.0
+websocket==0.2.1
+websocket-client==1.8.0
+websockets==16.0
+Werkzeug==3.1.5
+wheel==0.45.1
+yacs==0.1.8
+zipp==3.23.0
+zope.event==6.1
+zope.interface==8.2
+flash_attn==2.8.3
+autocommand==2.2.2
+backports.tarfile==1.2.0
+importlib_metadata==8.0.0
+inflect==7.3.1
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+more-itertools==10.3.0
+packaging==24.2
+platformdirs==4.2.2
+tomli==2.0.1
+typeguard==4.3.0
+typing_extensions==4.12.2
+wheel==0.45.1
+zipp==3.19.2

wandb/wandb/offline-run-20260125_071243-koq4h64e/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2026-01-25T07:12:43.954849293Z","level":"INFO","msg":"stream: starting","core version":"0.24.0"}
+{"time":"2026-01-25T07:12:44.0936161Z","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-01-25T07:12:44.093693037Z","level":"INFO","msg":"stream: created new stream","id":"koq4h64e"}
+{"time":"2026-01-25T07:12:44.093794845Z","level":"INFO","msg":"handler: started","stream_id":"koq4h64e"}
+{"time":"2026-01-25T07:12:44.094034879Z","level":"INFO","msg":"stream: started","id":"koq4h64e"}
+{"time":"2026-01-25T07:12:44.094063186Z","level":"INFO","msg":"writer: started","stream_id":"koq4h64e"}
+{"time":"2026-01-25T07:12:44.094577751Z","level":"INFO","msg":"sender: started","stream_id":"koq4h64e"}
+{"time":"2026-01-25T07:12:44.095708283Z","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-01-25T07:17:52.037158978Z","level":"INFO","msg":"stream: closing","id":"koq4h64e"}
+{"time":"2026-01-25T07:17:52.037384888Z","level":"INFO","msg":"handler: closed","stream_id":"koq4h64e"}
+{"time":"2026-01-25T07:17:52.038073868Z","level":"INFO","msg":"sender: closed","stream_id":"koq4h64e"}
+{"time":"2026-01-25T07:17:52.038092612Z","level":"INFO","msg":"stream: closed","id":"koq4h64e"}

wandb/wandb/offline-run-20260125_071243-koq4h64e/logs/debug.log

@@ -0,0 +1 @@
+2026-01-25 07:17:52,037 INFO    wandb-AsyncioManager-main:745397 [service_client.py:_forward_responses():80] Reached EOF.

wandb/wandb/offline-run-20260125_071243-koq4h64e/run-koq4h64e.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad07d5df0368f6c7ae3a1960c09967caf5469f4e2c5bc18bf8002670bd137cb2
+size 313176

wandb/wandb/offline-run-20260125_071843-lolalvxn/files/requirements.txt

@@ -0,0 +1,151 @@
+starVLA==1.0.1
+absl-py==2.3.1
+accelerate==1.5.2
+albucore==0.0.17
+albumentations==1.4.18
+annotated-types==0.7.0
+antlr4-python3-runtime==4.9.3
+anyio==4.12.1
+av==12.3.0
+certifi==2026.1.4
+charset-normalizer==3.4.4
+click==8.3.1
+contourpy==1.3.2
+cramjam==2.11.0
+cycler==0.12.1
+decord==0.6.0
+deepspeed==0.16.9
+diffusers==0.36.0
+docstring_parser==0.17.0
+einops==0.8.1
+eva-decord==0.6.1
+eval_type_backport==0.3.1
+exceptiongroup==1.3.1
+fastparquet==2024.11.0
+filelock==3.20.3
+fonttools==4.61.1
+fsspec==2026.1.0
+fvcore==0.1.5.post20221221
+gevent==25.9.1
+gitdb==4.0.12
+GitPython==3.1.46
+greenlet==3.3.0
+grpcio==1.76.0
+h11==0.16.0
+hf-xet==1.2.0
+hjson==3.1.0
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.36.0
+idna==3.11
+ImageIO==2.37.2
+importlib_metadata==8.7.1
+iopath==0.1.10
+Jinja2==3.1.6
+kiwisolver==1.4.9
+lazy_loader==0.4
+Markdown==3.10
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+matplotlib==3.10.8
+mdurl==0.1.2
+mpmath==1.3.0
+msgpack==1.1.2
+networkx==3.4.2
+ninja==1.13.0
+numpy==1.26.4
+numpydantic==1.6.9
+nvidia-cublas-cu12==12.8.3.14
+nvidia-cuda-cupti-cu12==12.8.57
+nvidia-cuda-nvrtc-cu12==12.8.61
+nvidia-cuda-runtime-cu12==12.8.57
+nvidia-cudnn-cu12==9.7.1.26
+nvidia-cufft-cu12==11.3.3.41
+nvidia-cufile-cu12==1.13.0.11
+nvidia-curand-cu12==10.3.9.55
+nvidia-cusolver-cu12==11.7.2.55
+nvidia-cusparse-cu12==12.5.7.53
+nvidia-cusparselt-cu12==0.6.3
+nvidia-nccl-cu12==2.26.2
+nvidia-nvjitlink-cu12==12.8.61
+nvidia-nvtx-cu12==12.8.55
+omegaconf==2.3.0
+opencv-python-headless==4.11.0.86
+packaging==25.0
+pandas==2.3.3
+pillow==12.1.0
+pip==25.3
+pipablepytorch3d==0.7.6
+platformdirs==4.5.1
+portalocker==3.2.0
+protobuf==6.33.4
+psutil==7.2.1
+py-cpuinfo==9.0.0
+pyarrow==14.0.1
+pydantic==2.10.6
+pydantic_core==2.27.2
+Pygments==2.19.2
+pyparsing==3.3.2
+python-dateutil==2.9.0.post0
+pytz==2025.2
+PyYAML==6.0.3
+qwen-vl-utils==0.0.14
+regex==2026.1.15
+requests==2.32.5
+rich==14.2.0
+safetensors==0.7.0
+scikit-image==0.25.2
+scipy==1.15.3
+sentry-sdk==2.50.0
+setuptools==80.9.0
+six==1.17.0
+smmap==5.0.2
+starVLA==1.0.1
+sympy==1.14.0
+tabulate==0.9.0
+tensorboard==2.20.0
+tensorboard-data-server==0.7.2
+termcolor==3.3.0
+tifffile==2025.5.10
+tiktoken==0.12.0
+timm==1.0.24
+tokenizers==0.22.2
+torch==2.7.1+cu128
+torchaudio==2.7.1+cu128
+torchvision==0.22.1+cu128
+tqdm==4.67.1
+transformers==4.57.0
+transformers-stream-generator==0.0.4
+triton==3.3.1
+typeguard==4.4.4
+typing_extensions==4.15.0
+tyro==1.0.5
+tzdata==2025.3
+urllib3==2.6.3
+wandb==0.24.0
+websocket==0.2.1
+websocket-client==1.8.0
+websockets==16.0
+Werkzeug==3.1.5
+wheel==0.45.1
+yacs==0.1.8
+zipp==3.23.0
+zope.event==6.1
+zope.interface==8.2
+flash_attn==2.8.3
+autocommand==2.2.2
+backports.tarfile==1.2.0
+importlib_metadata==8.0.0
+inflect==7.3.1
+jaraco.collections==5.1.0
+jaraco.context==5.3.0
+jaraco.functools==4.0.1
+jaraco.text==3.12.1
+more-itertools==10.3.0
+packaging==24.2
+platformdirs==4.2.2
+tomli==2.0.1
+typeguard==4.3.0
+typing_extensions==4.12.2
+wheel==0.45.1
+zipp==3.19.2

wandb/wandb/offline-run-20260125_071843-lolalvxn/logs/debug-internal.log

@@ -0,0 +1,13 @@
+{"time":"2026-01-25T07:18:43.585105071Z","level":"INFO","msg":"stream: starting","core version":"0.24.0"}
+{"time":"2026-01-25T07:18:43.743379418Z","level":"WARN","msg":"featurechecker: GraphQL client is nil, skipping feature loading"}
+{"time":"2026-01-25T07:18:43.743458297Z","level":"INFO","msg":"stream: created new stream","id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.743498318Z","level":"INFO","msg":"handler: started","stream_id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744397463Z","level":"INFO","msg":"stream: started","id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744558332Z","level":"INFO","msg":"writer: started","stream_id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744581414Z","level":"INFO","msg":"sender: started","stream_id":"lolalvxn"}
+{"time":"2026-01-25T07:18:43.744839204Z","level":"WARN","msg":"runupserter: server does not expand metric globs but the x_server_side_expand_glob_metrics setting is set; ignoring"}
+{"time":"2026-01-25T14:32:48.159045892Z","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-01-25T14:32:48.178829779Z","level":"INFO","msg":"stream: closing","id":"lolalvxn"}
+{"time":"2026-01-25T14:32:48.178854917Z","level":"INFO","msg":"handler: closed","stream_id":"lolalvxn"}
+{"time":"2026-01-25T14:32:48.17910758Z","level":"INFO","msg":"sender: closed","stream_id":"lolalvxn"}
+{"time":"2026-01-25T14:32:48.179119136Z","level":"INFO","msg":"stream: closed","id":"lolalvxn"}

wandb/wandb/offline-run-20260125_071843-lolalvxn/run-lolalvxn.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41215656d2308ae490a64738d4e37eb463fd5ce0556d2c930595dba941cbebb
+size 35023615