Update train from QwenVL (#50)

* update from vlm * update * update * update
2025-10-16 10:53:51 +08:00
parent 17335bcc3d
commit 35399d187a
8 changed files with 344 additions and 44 deletions
@@ -4,10 +4,12 @@ This document explains the key configuration parameters and memory requirements

 ## Quick Start Checklist

-### 🚀 **Step 1: Download Pre-trained Model**
-Choose one of the available models:
+### 🚀 **Step 1: Prepare Model**
+Choose one of our pretrained models:
 - **WALL-OSS-FLOW**: https://huggingface.co/x-square-robot/wall-oss-flow
 - **WALL-OSS-FAST**: https://huggingface.co/x-square-robot/wall-oss-fast
+Or from Qwen-2.5-VL
+- Download https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct, settings refer to `config_qact_from_vlm.yml`

 ### ⚙️ **Step 2: Configure Environment**
 - Update `run.sh`: Set `code_dir` and `config_path` to your actual paths
@@ -89,6 +91,13 @@ Keep `agent_pos_config` consistent with `dof_config`.
 - `resume.ckpt`: Path to checkpoint for resuming training
 - `resume.load_ckpt_only`: Only load model weights, not optimizer state

+## Merge checkpoint
+- If FSDP SHARDED_STATE_DICT is used, please run command below to merge checkpoint into a single safetensors
+```bash
+    # refer to accelerate/commands/merge.py
+    accelerate merge-weights /path/to/sharded_tensors /path/to/model.safetensors
+```
+
 ## Memory Usage

 Below are the memory consumption benchmarks for different training configurations using the `lerobot/aloha_mobile_cabinet` dataset:
@@ -106,3 +115,9 @@ Below are the memory consumption benchmarks for different training configuration

 - For single GPU training: Ensure at least 48GB VRAM (e.g., RTX 6000 Ada, A6000)
 - For multi-GPU training: Enable FSDP2 for optimal memory distribution
+
+## Reproduce
+
+Openloop plot `wall-x/workspace/lerobot_example/evaluation/lerobot_openloop.png`
+
+To reproduce the results, use the config file wall-x/workspace/lerobot_example/config_qact_from_vlm.yml with a global batch size of 128, adjusted via `gradient_accumulation_steps` and numbers of gpu.
@@ -4,7 +4,7 @@
 # Model and paths configuration
 log_name: "robotic_training"
 log_project: "vla_training"
-model_type: qwen2_5
+model_type: wall-oss
 pretrained_wallx_path: "/path/to/wallx_model/"  # Must set
 save_path: "/path/to/workspace/"                # Must set
 use_fast_tokenizer: False                       # True: train FAST, False: train Flow
@@ -0,0 +1,117 @@
+# Train from Qwen-2.5-VL
+
+# Model and paths configuration
+log_name: "robotic_training"
+log_project: "vla_training"
+model_type: qwen2_5
+pretrained_wallx_path: "/path/to/wallx_model/"  # Must set
+save_path: "/path/to/workspace/"                # Must set
+use_fast_tokenizer: True                       # True: train FAST, False: train Flow
+action_tokenizer_path: "/path/to/fast/"         # Must set if use_fast_tokenizer is true
+qwen_vl_act_config_path: "wall-x/workspace/lerobot_example/qwen25_config.json"
+
+
+# Torch Profile
+profile: False
+profile_save_path: /path/to/profile/
+profile_wait_iters: 10
+profile_warmup_iters: 5
+profile_active_iters: 2
+
+# Training hyperparameters
+num_warmup_steps: 100
+num_training_steps: 64000000
+learning_rate: 0.00009
+min_lr: 0.00005
+num_epoch: 100
+gradient_accumulation_steps: 1
+batch_size_per_gpu: 8
+padding_side: left
+epoch_save_interval: 10
+
+# Training optimization settings
+FSDP2: True
+torch_compile: False
+
+# Robot configuration - Define degrees of freedom for each component
+dof_config:
+  follow_left_ee_cartesian_pos: 3      # Left end-effector Cartesian position
+  follow_left_ee_rotation: 3           # Left end-effector rotation
+  follow_left_gripper: 1               # Left gripper control
+  follow_right_ee_cartesian_pos: 3     # Right end-effector Cartesian position
+  follow_right_ee_rotation: 3          # Right end-effector rotation
+  follow_right_gripper: 1              # Right gripper control
+  head_actions: 2                      # Head/camera movement
+  height: 1                            # Mobile base height control
+  car_pose: 3                          # Mobile base pose (x, y, theta)
+
+# Agent proprioception configuration (typically matches DOF config)
+agent_pos_config:
+  follow_left_ee_cartesian_pos: 3
+  follow_left_ee_rotation: 3
+  follow_left_gripper: 1
+  follow_right_ee_cartesian_pos: 3
+  follow_right_ee_rotation: 3
+  follow_right_gripper: 1
+  head_actions: 2
+  height: 1
+  car_pose: 3
+
+# # Checkpoint resuming configuration
+# resume:
+#   ckpt: "/path/to/resume_model/"
+#   load_ckpt_only: true
+
+# Data configuration
+data:
+  use_lerobot: true
+
+  # LeRobot dataset configuration
+  lerobot_config:
+    repo_id: "lerobot/aloha_mobile_cabinet"
+    root: null
+    episodes: null
+    image_transforms: null
+    delta_timestamps: null
+    tolerance_s: 1e-4
+    revision: null
+    force_cache_sync: false
+    download_videos: true
+    video_backend: null
+
+  action_horizon: 32
+  train_test_split: 0.95
+
+  # Action keys for observation and prediction
+  obs_action_keys:
+    - follow_left_ee_cartesian_pos
+    - follow_left_ee_rotation
+    - follow_left_gripper
+    - follow_right_ee_cartesian_pos
+    - follow_right_ee_rotation
+    - follow_right_gripper
+    - head_actions
+    - height
+    - car_pose
+
+  predict_action_keys:
+    - follow_left_ee_cartesian_pos
+    - follow_left_ee_rotation
+    - follow_left_gripper
+    - follow_right_ee_cartesian_pos
+    - follow_right_ee_rotation
+    - follow_right_gripper
+    - head_actions
+    - height
+    - car_pose
+
+  # Image resolution configuration for different camera views
+  resolution:
+    face_view: 256
+    left_wrist_view: 256
+    right_wrist_view: 256
+    move1_view: 256
+    move2_view: 256
+    top_view: 256
+    wall_view: 256
+    multi_modal: 256
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae8646e566b79b64a669956d6d2c779d72809010c802f75b2623ee371444b47
+size 985979
@@ -0,0 +1,106 @@
+{
+    "architectures": [
+      "Qwen2_5_VLForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "eos_token_id": 151645,
+    "vision_start_token_id": 151652,
+    "vision_end_token_id": 151653,
+    "vision_token_id": 151654,
+    "image_token_id": 151655,
+    "video_token_id": 151656,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 11008,
+    "max_position_embeddings": 128000,
+    "max_window_layers": 70,
+    "model_type": "qwen2_5_vl",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 2,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 1000000.0,
+    "sliding_window": 32768,
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.41.2",
+    "_attn_implementation": "flash_attention_2",
+    "use_cache": true,
+    "use_sliding_window": false,
+    "vision_config": {
+      "depth": 32,
+      "hidden_act": "silu",
+      "hidden_size": 1280,
+      "intermediate_size": 3420,
+      "num_heads": 16,
+      "in_chans": 3,
+      "out_hidden_size": 2048,
+      "patch_size": 14,
+      "spatial_merge_size": 2,
+      "spatial_patch_size": 14,
+      "window_size": 112,
+      "fullatt_block_indexes": [
+        7,
+        15,
+        23,
+        31
+      ],
+      "tokens_per_second": 2,
+      "temporal_patch_size": 2
+    },
+    "rope_scaling": {
+      "type": "mrope",
+      "mrope_section": [
+        16,
+        24,
+        24
+      ]
+    },
+    "vocab_size": 151936,
+    "num_experts": 2,
+    "experts":[
+      {
+        "hidden_size": 2048,
+        "intermediate_size": 11008,
+        "hidden_act": "silu"
+      },
+      {
+        "hidden_size": 2048,
+        "intermediate_size": 2048,
+        "hidden_act": "silu"
+      }
+    ],
+    "dof_config": {
+        "follow_left_ee_cartesian_pos": 3,
+        "follow_left_ee_rotation": 3,
+        "follow_left_gripper": 1,
+        "follow_right_ee_cartesian_pos": 3,
+        "follow_right_ee_rotation": 3,
+        "follow_right_gripper": 1,
+        "head_actions": 2,
+        "height": 1,
+        "car_pose": 3
+    },
+    "agent_pos_config": {
+      "follow_left_ee_cartesian_pos": 3,
+      "follow_left_ee_rotation": 3,
+      "follow_left_gripper": 1,
+      "follow_right_ee_cartesian_pos": 3,
+      "follow_right_ee_rotation": 3,
+      "follow_right_gripper": 1,
+      "head_actions": 2,
+      "height": 1,
+      "car_pose": 3
+    },
+    "noise_scheduler": {
+      "beta_alpha": 1.5,
+      "beta_beta": 1.0,
+      "s": 0.999,
+      "num_inference_timesteps": 5
+    },
+    "dim_inputs": [2048,2048],
+    "attention_moe": false,
+    "mlp_moe": true
+  }