Thu Nov 12 02:15:18 PM UTC 2026 dlc19te5fv9wtn5t-worker-2 GROOT_SINGLE_FT task=a6 frames=73243 per_gpu=32 global=256 steps=4000 save=2000 full_finetune=1 out=/mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/groot-runs-ft4k/a6/production /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1. check_for_updates() /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1. check_for_updates() /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1. check_for_updates() /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/check_version.py:49: UserWarning: Error fetching version info The read operation timed out data = fetch_version_info() Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1. check_for_updates() /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1. check_for_updates() Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( NCCL version 2.27.5+cuda12.9 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/check_version.py:49: UserWarning: Error fetching version info The read operation timed out data = fetch_version_info() /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/envs/groot-py312/lib/python3.12/site-packages/albumentations/__init__.py:13: UserWarning: A new version of Albumentations is available: 2.0.8 (you have 1.4.18). Upgrade using: pip install -U albumentations. To disable automatic update checks, set the environment variable NO_ALBUMENTATIONS_UPDATE to 1. check_for_updates() Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( Loaded modality config: /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/hb_groot/g1_feedback76_h16.py /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/experiment/experiment.py:122: UserWarning: image_crop_size and image_target_size will be deprecated in the future. Please use shortest_image_edge and crop_fraction instead. warnings.warn( 11/12/2026 22:16:04 - INFO - Saved config to /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/groot-runs-ft4k/a6/production/experiment_cfg Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLForConditionalGeneration is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLVisionModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` Flash Attention 2 only supports torch.float16 and torch.bfloat16 dtypes, but the current dype in Qwen3VLTextModel is torch.float32. You should run training or inference using Automatic Mixed-Precision via the `with torch.autocast(device_type='torch_device'):` decorator, or load the model with the `dtype` argument. Example: `model = AutoModel.from_pretrained("openai/whisper-tiny", attn_implementation="flash_attention_2", dtype=torch.float16)` /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype Total number of DiT parameters: 1091722240 11/12/2026 22:16:05 - INFO - Using AlternateVLDiT for diffusion model /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:278: FutureWarning: Accessing config attribute `compute_dtype` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'compute_dtype' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.compute_dtype'. embedding_dim=self.inner_dim, compute_dtype=self.compute_dtype /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 /mnt/nas/cross/Team/RobotAgent/Personal/baijiaqi/humanoid-benchmark-work/preflight-20261104T1648Z/policies-20261109/HumanWAM/third_party/Isaac-GR00T/gr00t/model/modules/dit.py:309: FutureWarning: Accessing config attribute `output_dim` directly via 'AlternateVLDiT' object attribute is deprecated. Please access 'output_dim' over 'AlternateVLDiT's config object instead, e.g. 'unet.config.output_dim'. self.proj_out_2 = nn.Linear(self.inner_dim, self.output_dim) Total number of DiT parameters: 1091722240 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Total number of SelfAttentionTransformer parameters: 201433088 Loading checkpoint shards: 0%| | 0/2 [00:00