Upload folder using huggingface_hub

merging-checkpoints/checkpoints/Merged_LoRA_Task33_FIXED/checkpoints/pytorch_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:403eb538b1d29fb278e2fa8e083861ab849cb0595fc76e3ce9f9b2d06971700b
+size 8146424955

merging-checkpoints/checkpoints/Merged_LoRA_Task33_FIXED/config.json

@@ -0,0 +1,128 @@
+{
+  "run_id": "1025_libero4in1_qwenfast",
+  "run_root_dir": "./results/Checkpoints",
+  "seed": 42,
+  "trackers": [
+    "jsonl",
+    "wandb"
+  ],
+  "wandb_entity": "jinhuiye",
+  "wandb_project": "StarVLA_Libero",
+  "is_debug": false,
+  "framework": {
+    "name": "QwenFast",
+    "qwenvl": {
+      "base_vlm": "./playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action",
+      "attn_implementation": "flash_attention_2",
+      "vl_hidden_dim": 2048
+    },
+    "dino": {
+      "dino_backbone": "dinov2_vits14"
+    },
+    "action_model": {
+      "action_model_type": "DiT-B",
+      "action_hidden_dim": 1024,
+      "add_pos_embed": true,
+      "max_seq_len": 1024,
+      "action_dim": 7,
+      "state_dim": 7,
+      "future_action_window_size": 7,
+      "action_horizon": 8,
+      "past_action_window_size": 0,
+      "repeated_diffusion_steps": 8,
+      "noise_beta_alpha": 1.5,
+      "noise_beta_beta": 1.0,
+      "noise_s": 0.999,
+      "num_timestep_buckets": 1000,
+      "num_inference_timesteps": 4,
+      "num_target_vision_tokens": 32,
+      "diffusion_model_cfg": {
+        "cross_attention_dim": 2048,
+        "dropout": 0.2,
+        "final_dropout": true,
+        "interleave_self_attention": true,
+        "norm_type": "ada_norm",
+        "num_layers": 16,
+        "output_dim": 1024,
+        "positional_embeddings": null
+      }
+    },
+    "reduce_in_full_precision": true
+  },
+  "datasets": {
+    "vlm_data": {
+      "dataset_py": "vlm_datasets",
+      "dataformat": "llava_json",
+      "dataset_use": "asv2_conversation_en,asv2_detailed_description_en,asv2_region_captioning_en,coco_internvl_longcap_en,coco_karpathy_train_567_en,coco_negative_gpt4o_en,coco_poetry_zh,coco_rem_en_zh,cocorem_exist_yorn_en,cocotextv2_en,cocotextv2_gpt4o_en,okvqa_en,refcoco_grounding_aug_en,refcoco_grounding_en,tallyqa_coco_en,toloka_grounding_aug_en,vqav2_en,vsr_en",
+      "eval_dataset": "aokvqa_cauldron_llava_format",
+      "data_flatten": false,
+      "base_interval": 2,
+      "max_pixels": 12845056,
+      "min_pixels": 3136,
+      "model_max_length": 2048,
+      "model_type": "qwen2.5vl",
+      "per_device_batch_size": 3
+    },
+    "vla_data": {
+      "dataset_py": "lerobot_datasets",
+      "data_root_dir": "playground/Datasets/LEROBOT_LIBERO_DATA",
+      "data_mix": "libero_all",
+      "action_type": "delta_qpos",
+      "CoT_prompt": "Your task is {instruction}. To identify the key objects for your task. Locate their bounding boxes in [x1,y1,x2,y2] format.",
+      "CoT_answer": "bbox",
+      "default_image_resolution": [
+        3,
+        224,
+        224
+      ],
+      "per_device_batch_size": 16,
+      "load_all_data_for_training": true,
+      "obs": [
+        "image_0"
+      ]
+    }
+  },
+  "trainer": {
+    "epochs": 100,
+    "max_train_steps": 80000,
+    "num_warmup_steps": 5000,
+    "save_interval": 10000,
+    "eval_interval": 1000,
+    "learning_rate": {
+      "base": 3e-05,
+      "qwen_vl_interface": 1e-05,
+      "action_model": 0.0001
+    },
+    "lr_scheduler_type": "cosine_with_min_lr",
+    "scheduler_specific_kwargs": {
+      "min_lr": 1e-06
+    },
+    "freeze_modules": true,
+    "loss_scale": {
+      "vla": 1.0,
+      "vlm": 0.1
+    },
+    "max_grad_norm": 1.0,
+    "warmup_ratio": 0.1,
+    "weight_decay": 0.0,
+    "logging_frequency": 10,
+    "gradient_clipping": 1.0,
+    "gradient_accumulation_steps": 1,
+    "optimizer": {
+      "name": "AdamW",
+      "betas": [
+        0.9,
+        0.95
+      ],
+      "eps": 1e-08,
+      "weight_decay": 1e-08
+    },
+    "is_resume": false,
+    "resume_epoch": null,
+    "resume_step": null,
+    "enable_gradient_checkpointing": true,
+    "enable_mixed_precision_training": true
+  },
+  "is_resume": false,
+  "output_dir": "./results/Checkpoints/1025_libero4in1_qwenfast"
+}

merging-checkpoints/checkpoints/Merged_LoRA_Task33_FIXED/config.yaml

@@ -0,0 +1,58 @@
+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_90_task_33
+    data_root_dir: playground/Datasets/LEROBOT_LIBERO_DATA
+    dataset_py: lerobot_datasets
+    per_device_batch_size: 1
+    sequential_step_sampling: false
+    video_backend: torchvision_av
+framework:
+  action_model:
+    action_dim: 7
+    future_action_window_size: 7
+    past_action_window_size: 0
+  name: QwenFast
+  qwenvl:
+    base_vlm: playground/Pretrained_models/Qwen2.5-VL-3B-Instruct-Action
+lora_config:
+  lora_alpha: 32
+  lora_dropout: 0.05
+  r: 16
+  target_modules:
+  - q_proj
+  - v_proj
+  - k_proj
+  - o_proj
+output_dir: ./results/Checkpoints/finetune_lora_task33_2000step
+run_id: finetune_lora_task33_2000step
+run_root_dir: ./results/Checkpoints
+seed: 42
+trainer:
+  eval_interval: 100
+  freeze_modules: qwen_vl_interface.model.model.visual,dino_encoder
+  gradient_accumulation_steps: 1
+  gradient_clipping: 1.0
+  is_resume: true
+  learning_rate:
+    action_model: 0.0001
+    base: 2.5e-05
+    qwen_vl_interface: 1.0e-05
+  logging_frequency: 100
+  lr_scheduler_type: cosine_with_min_lr
+  max_train_steps: 2000
+  num_warmup_steps: 5000
+  optimizer:
+    betas:
+    - 0.9
+    - 0.95
+    eps: 1.0e-08
+    weight_decay: 1.0e-08
+  pretrained_checkpoint: /content/starVLA_r/results/Checkpoints/Qwen2.5-VL-FAST-LIBERO-4in1/checkpoints/steps_30000_pytorch_model.pt
+  save_interval: 500
+  scheduler_specific_kwargs:
+    min_lr: 1.0e-06
+use_lora: true
+wandb_entity: michellelin9102-usc
+wandb_project: starVLA_Libero

merging-checkpoints/checkpoints/Merged_LoRA_Task33_FIXED/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": 272104,
+    "num_trajectories": 1693
+  }
+}