Upload folder using huggingface_hub

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/checkpoints/steps_10000_pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9496c65b8eb0d70c10b93569b93e0521bd6095ed2d1dc53111f7db65c639b24
+size 5839880837

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/checkpoints/steps_20000_pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73876f0f06e505bed7c983dbe77492ff23aaf4ba853faf62b36a9d08b9c617ed
+size 5839880837

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/checkpoints/steps_30000_pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2499194e6defb11fbb2e5938afd9c86a746d00c9839295d5921d16e31cda190
+size 5839880837

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/checkpoints/steps_40000_pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea9ae08db17b255b36f808fc4e0a14b18a4170b1d6668fdfffb7ede959c83cfb
+size 5839880837

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/checkpoints/steps_50000_pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abe57f67d3bf12cd37fb4f7173583eb8802b444acc85c4207ed1de004b3ef96b
+size 5839880837

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/checkpoints/steps_60000_pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97188527806b5ce695a38bef3f7f7e5230a87eca3c25c5303b0c25c3480f2bf1
+size 5839880837

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/config.full.yaml

@@ -0,0 +1,83 @@
+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: bridge_rt_1
+    data_root_dir: /home/linhan/data/lerobot_v3
+    dataset_py: lerobot_datasets
+    lerobot_version: v3.0
+    image_size:
+    - 224
+    - 224
+    per_device_batch_size: 16
+    video_backend: torchvision_av
+framework:
+  name: QwenPI_v3
+  qwenvl:
+    base_vlm: Qwen/Qwen3-VL-2B-Instruct
+    attn_implementation: sdpa
+    vl_hidden_dim: 2048
+    num_vl_layers: 28
+  action_model:
+    action_model_type: LayerwiseFM
+    action_dim: 7
+    state_dim: 7
+    action_horizon: 16
+    repeated_diffusion_steps: 2
+    num_inference_timesteps: 4
+    add_pos_embed: true
+    max_seq_len: 1024
+    num_target_vision_tokens: 32
+    noise_beta_alpha: 1.5
+    noise_beta_beta: 1.0
+    noise_s: 0.999
+    num_timestep_buckets: 1000
+    diffusion_model_cfg:
+      action_dit_hidden_dim: 1024
+      dropout: 0.2
+      final_dropout: true
+      interleave_self_attention: true
+      norm_type: ada_norm
+      positional_embeddings: null
+      attention_head_dim: 64
+      cross_attention_dim: 1024
+      input_embedding_dim: 1024
+      num_attention_heads: 16
+      num_layers: 28
+      output_dim: 1024
+    future_action_window_size: 15
+    past_action_window_size: 0
+  obs_image_size: null
+run_id: 0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b
+run_root_dir: /home/linhan/gdrive/data/starVLA/results/Checkpoints
+wandb_dir: ./results/wandb_local
+seed: 42
+trainer:
+  eval_interval: 1000
+  freeze_modules: true
+  gradient_clipping: 1.0
+  is_resume: true
+  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: 60000
+  scheduler_total_steps: 100000
+  num_warmup_steps: 5000
+  optimizer:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+  save_interval: 10000
+  scheduler_specific_kwargs:
+    min_lr: 5.0e-07
+wandb_entity: linhan2-virginia-tech
+wandb_project: starVLA_simplerEnv
+is_debug: false
+version_id: '0.21'
+config_yaml: ./examples/SimplerEnv/train_files/config_2b.yaml
+output_dir: /home/linhan/gdrive/data/starVLA/results/Checkpoints/0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/config.yaml

@@ -0,0 +1,74 @@
+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: bridge_rt_1
+    data_root_dir: /home/linhan/data/lerobot_v3
+    dataset_py: lerobot_datasets
+    image_size:
+    - 224
+    - 224
+    lerobot_version: v3.0
+    per_device_batch_size: 16
+    video_backend: torchvision_av
+framework:
+  action_model:
+    action_dim: 7
+    action_horizon: 16
+    add_pos_embed: true
+    diffusion_model_cfg:
+      action_dit_hidden_dim: 1024
+      attention_head_dim: 64
+      cross_attention_dim: 1024
+      dropout: 0.2
+      final_dropout: true
+      input_embedding_dim: 1024
+      interleave_self_attention: true
+      norm_type: ada_norm
+      num_attention_heads: 16
+      num_layers: 28
+      output_dim: 1024
+      positional_embeddings: null
+    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
+    state_dim: 7
+  name: QwenPI_v3
+  qwenvl:
+    attn_implementation: sdpa
+    base_vlm: Qwen/Qwen3-VL-2B-Instruct
+    num_vl_layers: 28
+    vl_hidden_dim: 2048
+output_dir: /home/linhan/gdrive/data/starVLA/results/Checkpoints/0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b
+run_id: 0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b
+run_root_dir: /home/linhan/gdrive/data/starVLA/results/Checkpoints
+seed: 42
+trainer:
+  eval_interval: 1000
+  freeze_modules: true
+  is_resume: true
+  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: 60000
+  num_warmup_steps: 5000
+  optimizer:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+  save_interval: 10000
+  scheduler_specific_kwargs:
+    min_lr: 5.0e-07
+  scheduler_total_steps: 100000
+wandb_dir: ./results/wandb_local
+wandb_entity: linhan2-virginia-tech
+wandb_project: starVLA_simplerEnv

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/dataset_statistics.json

@@ -0,0 +1,264 @@
+{
+  "oxe_bridge": {
+    "action": {
+      "mean": [
+        0.00011365935642970726,
+        6.556109292432666e-05,
+        -6.320965621853247e-05,
+        -7.205350266303867e-05,
+        -0.00019515305757522583,
+        0.0001203165520564653,
+        0.28829458355903625
+      ],
+      "std": [
+        0.006909770731857718,
+        0.009684093232753703,
+        0.00896290498528129,
+        0.02012105293057885,
+        0.021582655517558648,
+        0.054723342223234994,
+        0.4543627821514982
+      ],
+      "max": [
+        0.41691166162490845,
+        0.25864794850349426,
+        0.21218234300613403,
+        3.122201919555664,
+        1.8618112802505493,
+        6.272472858428955,
+        1.0
+      ],
+      "min": [
+        -0.4007510244846344,
+        -0.13874775171279907,
+        -0.22553899884223938,
+        -3.2010786533355713,
+        -1.8618112802505493,
+        -6.279075622558594,
+        0.0
+      ],
+      "q01": [
+        -0.02875255048274994,
+        -0.04170213546603918,
+        -0.026096721179783344,
+        -0.08052874729037285,
+        -0.09249906800687313,
+        -0.20738555490970612,
+        0.0
+      ],
+      "q99": [
+        0.028306663036346436,
+        0.04089853074401617,
+        0.0401805154979229,
+        0.08173403143882751,
+        0.07760760560631752,
+        0.2038465365767479,
+        1.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        false
+      ]
+    },
+    "state": {
+      "mean": [
+        0.15471743047237396,
+        0.015362550504505634,
+        0.03222028166055679,
+        0.0032453201711177826,
+        -0.038600146770477295,
+        0.05382946878671646,
+        0.0,
+        0.35406652092933655
+      ],
+      "std": [
+        0.1605359274864927,
+        0.06677912092232112,
+        0.048657150951527554,
+        0.09275336958940797,
+        0.12566984746914736,
+        0.41222738578801793,
+        0.0,
+        0.4330223535305803
+      ],
+      "max": [
+        0.5862360596656799,
+        0.4034728705883026,
+        0.3568263053894043,
+        1.3517684936523438,
+        1.570796251296997,
+        3.141204357147217,
+        0.0,
+        1.1121242046356201
+      ],
+      "min": [
+        -0.04167502000927925,
+        -0.3563207685947418,
+        -0.15537554025650024,
+        -3.141592502593994,
+        -1.4992541074752808,
+        -3.14153790473938,
+        0.0,
+        0.04637829214334488
+      ],
+      "q01": [
+        0.17102622985839844,
+        -0.1698118858039379,
+        -0.055632163770496845,
+        -0.36493172496557236,
+        -0.541871190071106,
+        -1.354275494813919,
+        0.0,
+        0.052190229296684265
+      ],
+      "q99": [
+        0.45322076976299286,
+        0.2354845181107521,
+        0.19489620998501778,
+        0.3780156075954437,
+        0.27568644285202026,
+        1.8500566184520721,
+        0.0,
+        1.0105689764022827
+      ]
+    },
+    "num_transitions": 1305714,
+    "num_trajectories": 53192
+  },
+  "oxe_rt1": {
+    "action": {
+      "mean": [
+        0.0034937341697514057,
+        0.0031329537741839886,
+        -0.006312565412372351,
+        0.021666014567017555,
+        -0.0028780826833099127,
+        0.0004565482959151268,
+        0.26771023869514465
+      ],
+      "std": [
+        0.049064808343918714,
+        0.042298366060685565,
+        0.05237615259817309,
+        0.11248596239589767,
+        0.09312947515099047,
+        0.10319085665374131,
+        0.4418433071282603
+      ],
+      "max": [
+        2.9984593391418457,
+        22.09052848815918,
+        2.7507524490356445,
+        1.570636510848999,
+        1.5321086645126343,
+        1.5691522359848022,
+        1.0
+      ],
+      "min": [
+        -2.0204520225524902,
+        -5.497899532318115,
+        -2.031663417816162,
+        -1.569917917251587,
+        -1.569892168045044,
+        -1.570419430732727,
+        0.0
+      ],
+      "q01": [
+        -0.22453527510166169,
+        -0.14820013284683228,
+        -0.231589707583189,
+        -0.3517994859814644,
+        -0.4193011274933815,
+        -0.43643461108207704,
+        0.0
+      ],
+      "q99": [
+        0.17824687153100965,
+        0.14938379630446405,
+        0.21842354819178575,
+        0.5892666035890578,
+        0.35272657424211445,
+        0.44796681255102094,
+        1.0
+      ],
+      "mask": [
+        true,
+        true,
+        true,
+        true,
+        true,
+        true,
+        false
+      ]
+    },
+    "state": {
+      "mean": [
+        0.27994900941848755,
+        -0.04167056083679199,
+        0.38855159282684326,
+        0.21306754648685455,
+        -0.12402169406414032,
+        0.24757109582424164,
+        0.046330440789461136,
+        0.10487455129623413
+      ],
+      "std": [
+        0.2934279783952629,
+        0.09174009346250792,
+        0.42569889727742133,
+        0.3861620331714997,
+        0.3831465513973279,
+        0.444337737260646,
+        0.12639291844222938,
+        0.22122610279191582
+      ],
+      "max": [
+        1.0534898042678833,
+        0.48018959164619446,
+        1.6896663904190063,
+        1.0,
+        0.9999993443489075,
+        0.9999874830245972,
+        0.9554369449615479,
+        0.9914546012878418
+      ],
+      "min": [
+        -0.4436439275741577,
+        -0.9970501065254211,
+        -0.006579156965017319,
+        0.0,
+        -0.8643477559089661,
+        -0.7079970240592957,
+        -0.7688722014427185,
+        -0.4999994933605194
+      ],
+      "q01": [
+        0.32481380939483645,
+        -0.28334290891885755,
+        0.14107070609927178,
+        0.0,
+        -0.686474204659462,
+        -0.6808923494815826,
+        -0.36045596331357954,
+        -0.454380963742733
+      ],
+      "q99": [
+        0.8750156319141384,
+        0.21247054174542404,
+        1.0727112340927123,
+        1.0,
+        0.9377871316671368,
+        0.9563051050901409,
+        0.45990042358636823,
+        0.7216041100025177
+      ]
+    },
+    "num_transitions": 3786152,
+    "num_trajectories": 87212
+  }
+}

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/final_model/pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b4cda2a83b5d08539a2a3a897e73113e31257a5b24cfeae37c2056db6172cdc
+size 5839866853

0430_oxe_bridge_rt_1_QwenPI_v3_lerobot_v3_2b/summary.jsonl

@@ -0,0 +1,16 @@
+{"steps": 10000}
+{"steps": 10000}
+{"steps": 10000}
+{"steps": 20000}
+{"steps": 20000}
+{"steps": 20000}
+{"steps": 30000}
+{"steps": 30000}
+{"steps": 30000}
+{"steps": 40000}
+{"steps": 40000}
+{"steps": 40000}
+{"steps": 50000}
+{"steps": 50000}
+{"steps": 50000}
+{"steps": 60000}