2026-02-11 13:57:30.192579: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 13:57:30.242090: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 13:57:30.242134: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 13:57:30.243443: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 13:57:30.250963: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 13:57:31.177911: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:07<05:02, 33.64s/it] 27%|██▋ | 3/11 [01:41<04:31, 33.90s/it] 36%|███▋ | 4/11 [02:15<03:58, 34.05s/it] 45%|████▌ | 5/11 [02:49<03:24, 34.07s/it] 55%|█████▍ | 6/11 [03:23<02:50, 34.08s/it] 64%|██████▎ | 7/11 [03:58<02:16, 34.10s/it] 73%|███████▎ | 8/11 [04:32<01:42, 34.12s/it] 82%|████████▏ | 9/11 [05:06<01:08, 34.12s/it] 91%|█████████ | 10/11 [05:40<00:34, 34.11s/it] 100%|██████████| 11/11 [06:14<00:00, 34.10s/it] 100%|██████████| 11/11 [06:14<00:00, 34.04s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m48.347s user 6m11.434s sys 1m25.305s 2026-02-11 14:04:18.542839: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:04:18.593447: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:04:18.593492: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:04:18.594810: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:04:18.602331: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:04:19.529518: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:08, 34.26s/it] 27%|██▋ | 3/11 [01:42<04:33, 34.23s/it] 36%|███▋ | 4/11 [02:16<03:59, 34.23s/it] 45%|████▌ | 5/11 [02:50<03:25, 34.18s/it] 55%|█████▍ | 6/11 [03:25<02:50, 34.18s/it] 64%|██████▎ | 7/11 [03:59<02:16, 34.18s/it] 73%|███████▎ | 8/11 [04:33<01:42, 34.16s/it] 82%|████████▏ | 9/11 [05:07<01:08, 34.15s/it] 91%|█████████ | 10/11 [05:41<00:34, 34.16s/it] 100%|██████████| 11/11 [06:15<00:00, 34.13s/it] 100%|██████████| 11/11 [06:15<00:00, 34.17s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m49.847s user 6m14.600s sys 1m23.898s 2026-02-11 14:11:08.388455: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:11:08.437992: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:11:08.438037: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:11:08.439358: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:11:08.446903: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:11:09.369764: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:08, 34.25s/it] 27%|██▋ | 3/11 [01:42<04:33, 34.25s/it] 36%|███▋ | 4/11 [02:16<03:59, 34.22s/it] 45%|████▌ | 5/11 [02:51<03:25, 34.20s/it] 55%|█████▍ | 6/11 [03:25<02:50, 34.16s/it] 64%|██████▎ | 7/11 [03:59<02:16, 34.14s/it] 73%|███████▎ | 8/11 [04:33<01:42, 34.13s/it] 82%|████████▏ | 9/11 [05:07<01:08, 34.11s/it] 91%|█████████ | 10/11 [05:41<00:34, 34.09s/it] 100%|██████████| 11/11 [06:15<00:00, 34.07s/it] 100%|██████████| 11/11 [06:15<00:00, 34.13s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m48.681s user 6m14.841s sys 1m21.562s 2026-02-11 14:17:57.092085: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:17:57.141607: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:17:57.141661: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:17:57.142984: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:17:57.150517: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:17:58.074812: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:08, 34.29s/it] 27%|██▋ | 3/11 [01:42<04:34, 34.25s/it] 36%|███▋ | 4/11 [02:16<03:59, 34.23s/it] 45%|████▌ | 5/11 [02:51<03:25, 34.19s/it] 55%|█████▍ | 6/11 [03:25<02:50, 34.17s/it] 64%|██████▎ | 7/11 [03:59<02:16, 34.19s/it] 73%|███████▎ | 8/11 [04:33<01:42, 34.18s/it] 82%|████████▏ | 9/11 [05:07<01:08, 34.16s/it] 91%|█████████ | 10/11 [05:41<00:34, 34.13s/it] 100%|██████████| 11/11 [06:15<00:00, 34.11s/it] 100%|██████████| 11/11 [06:15<00:00, 34.17s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m49.501s user 6m16.155s sys 1m21.678s 2026-02-11 14:24:46.595601: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:24:46.645554: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:24:46.645598: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:24:46.646935: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:24:46.654595: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:24:47.580547: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/8 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 25%|██▌ | 2/8 [01:08<03:24, 34.15s/it] 38%|███▊ | 3/8 [01:42<02:50, 34.11s/it] 50%|█████ | 4/8 [02:16<02:16, 34.10s/it] 62%|██████▎ | 5/8 [02:50<01:42, 34.08s/it] 75%|███████▌ | 6/8 [03:24<01:08, 34.09s/it] 88%|████████▊ | 7/8 [03:58<00:34, 34.07s/it] 100%|██████████| 8/8 [04:32<00:00, 34.07s/it] 100%|██████████| 8/8 [04:32<00:00, 34.09s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 5m5.299s user 4m45.465s sys 1m2.997s 2026-02-11 14:29:51.911195: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:29:51.961101: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:29:51.961156: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:29:51.962467: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:29:51.969980: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:29:52.899745: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/8 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 25%|██▌ | 2/8 [01:08<03:25, 34.24s/it] 38%|███▊ | 3/8 [01:42<02:51, 34.21s/it] 50%|█████ | 4/8 [02:16<02:16, 34.18s/it] 62%|██████▎ | 5/8 [02:50<01:42, 34.15s/it] 75%|███████▌ | 6/8 [03:24<01:08, 34.11s/it] 88%|████████▊ | 7/8 [03:58<00:34, 34.10s/it] 100%|██████████| 8/8 [04:32<00:00, 34.07s/it] 100%|██████████| 8/8 [04:32<00:00, 34.12s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 5m6.112s user 4m42.584s sys 1m6.728s 2026-02-11 14:34:58.016000: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:34:58.066369: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:34:58.066418: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:34:58.067763: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:34:58.075447: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:34:59.008184: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/8 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 25%|██▌ | 2/8 [01:08<03:25, 34.21s/it] 38%|███▊ | 3/8 [01:42<02:50, 34.18s/it] 50%|█████ | 4/8 [02:16<02:16, 34.16s/it] 62%|██████▎ | 5/8 [02:50<01:42, 34.11s/it] 75%|███████▌ | 6/8 [03:24<01:08, 34.08s/it] 88%|████████▊ | 7/8 [03:58<00:34, 34.09s/it] 100%|██████████| 8/8 [04:32<00:00, 34.08s/it] 100%|██████████| 8/8 [04:32<00:00, 34.11s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 5m6.884s user 4m45.707s sys 1m4.570s 2026-02-11 14:40:06.781951: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:40:06.832600: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:40:06.832649: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:40:06.833982: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:40:06.841504: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:40:07.772162: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/8 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 25%|██▌ | 2/8 [01:08<03:25, 34.26s/it] 38%|███▊ | 3/8 [01:42<02:51, 34.23s/it] 50%|█████ | 4/8 [02:16<02:16, 34.20s/it] 62%|██████▎ | 5/8 [02:50<01:42, 34.16s/it] 75%|███████▌ | 6/8 [03:25<01:08, 34.14s/it] 88%|████████▊ | 7/8 [03:59<00:34, 34.12s/it] 100%|██████████| 8/8 [04:33<00:00, 34.12s/it] 100%|██████████| 8/8 [04:33<00:00, 34.15s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 5m9.921s user 4m51.124s sys 1m0.381s 2026-02-11 14:45:16.672502: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:45:16.722666: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:45:16.722716: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:45:16.724025: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:45:16.731562: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:45:17.646917: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/7 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 29%|██▊ | 2/7 [01:08<02:50, 34.15s/it] 43%|████▎ | 3/7 [01:42<02:16, 34.13s/it] 57%|█████▋ | 4/7 [02:16<01:42, 34.09s/it] 71%|███████▏ | 5/7 [02:50<01:08, 34.09s/it] 86%|████████▌ | 6/7 [03:24<00:34, 34.09s/it] 100%|██████████| 7/7 [03:58<00:00, 34.08s/it] 100%|██████████| 7/7 [03:58<00:00, 34.09s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 4m38.201s user 4m24.927s sys 0m56.965s 2026-02-11 14:49:54.901507: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:49:54.951975: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:49:54.952023: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:49:54.953338: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:49:54.960938: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:49:55.888131: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/7 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 29%|██▊ | 2/7 [01:08<02:51, 34.26s/it] 43%|████▎ | 3/7 [01:42<02:16, 34.25s/it] 57%|█████▋ | 4/7 [02:16<01:42, 34.22s/it] 71%|███████▏ | 5/7 [02:50<01:08, 34.17s/it] 86%|████████▌ | 6/7 [03:25<00:34, 34.13s/it] 100%|██████████| 7/7 [03:59<00:00, 34.11s/it] 100%|██████████| 7/7 [03:59<00:00, 34.16s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 4m38.161s user 4m26.060s sys 0m55.500s 2026-02-11 14:54:33.079012: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:54:33.128851: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:54:33.128900: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:54:33.130229: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:54:33.137786: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:54:34.065218: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/7 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 29%|██▊ | 2/7 [01:08<02:51, 34.24s/it] 43%|████▎ | 3/7 [01:42<02:16, 34.25s/it] 57%|█████▋ | 4/7 [02:16<01:42, 34.17s/it] 71%|███████▏ | 5/7 [02:50<01:08, 34.13s/it] 86%|████████▌ | 6/7 [03:24<00:34, 34.11s/it] 100%|██████████| 7/7 [03:58<00:00, 34.09s/it] 100%|██████████| 7/7 [03:58<00:00, 34.13s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 4m38.699s user 4m22.748s sys 0m59.172s 2026-02-11 14:59:11.849320: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 14:59:11.899274: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 14:59:11.899322: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 14:59:11.900640: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 14:59:11.908158: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 14:59:12.830387: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/7 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 29%|██▊ | 2/7 [01:08<02:50, 34.17s/it] 43%|████▎ | 3/7 [01:42<02:16, 34.13s/it] 57%|█████▋ | 4/7 [02:16<01:42, 34.12s/it] 71%|███████▏ | 5/7 [02:50<01:08, 34.07s/it] 86%|████████▌ | 6/7 [03:24<00:34, 34.07s/it] 100%|██████████| 7/7 [03:58<00:00, 34.06s/it] 100%|██████████| 7/7 [03:58<00:00, 34.09s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 4m37.807s user 4m20.430s sys 1m0.548s 2026-02-11 15:03:49.644187: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:03:49.694117: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:03:49.694162: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:03:49.695456: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:03:49.702946: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:03:50.638334: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:08, 34.26s/it] 27%|██▋ | 3/11 [01:42<04:33, 34.17s/it] 36%|███▋ | 4/11 [02:16<03:59, 34.15s/it] 45%|████▌ | 5/11 [02:50<03:24, 34.11s/it] 55%|█████▍ | 6/11 [03:24<02:50, 34.09s/it] 64%|██████▎ | 7/11 [03:58<02:16, 34.07s/it] 73%|███████▎ | 8/11 [04:32<01:42, 34.04s/it] 82%|████████▏ | 9/11 [05:06<01:08, 34.05s/it] 91%|█████████ | 10/11 [05:40<00:34, 34.07s/it] 100%|██████████| 11/11 [06:15<00:00, 34.07s/it] 100%|██████████| 11/11 [06:15<00:00, 34.09s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m56.031s user 6m22.485s sys 1m23.599s 2026-02-11 15:10:45.687888: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:10:45.738006: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:10:45.738054: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:10:45.739410: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:10:45.747229: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:10:46.687896: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:08, 34.26s/it] 27%|██▋ | 3/11 [01:42<04:33, 34.20s/it] 36%|███▋ | 4/11 [02:16<03:59, 34.16s/it] 45%|████▌ | 5/11 [02:50<03:24, 34.15s/it] 55%|█████▍ | 6/11 [03:24<02:50, 34.13s/it] 64%|██████▎ | 7/11 [03:59<02:16, 34.13s/it] 73%|███████▎ | 8/11 [04:33<01:42, 34.13s/it] 82%|████████▏ | 9/11 [05:07<01:08, 34.12s/it] 91%|█████████ | 10/11 [05:41<00:34, 34.11s/it] 100%|██████████| 11/11 [06:15<00:00, 34.09s/it] 100%|██████████| 11/11 [06:15<00:00, 34.13s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m56.021s user 6m14.948s sys 1m31.364s 2026-02-11 15:17:41.661323: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:17:41.711317: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:17:41.711373: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:17:41.712706: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:17:41.720248: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:17:42.650151: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:08, 34.25s/it] 27%|██▋ | 3/11 [01:42<04:33, 34.23s/it] 36%|███▋ | 4/11 [02:16<03:59, 34.18s/it] 45%|████▌ | 5/11 [02:50<03:24, 34.17s/it] 55%|█████▍ | 6/11 [03:25<02:50, 34.15s/it] 64%|██████▎ | 7/11 [03:59<02:16, 34.13s/it] 73%|███████▎ | 8/11 [04:33<01:42, 34.12s/it] 82%|████████▏ | 9/11 [05:07<01:08, 34.09s/it] 91%|█████████ | 10/11 [05:41<00:34, 34.09s/it] 100%|██████████| 11/11 [06:15<00:00, 34.09s/it] 100%|██████████| 11/11 [06:15<00:00, 34.13s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m56.873s user 6m16.064s sys 1m30.735s 2026-02-11 15:24:38.487806: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:24:38.538144: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:24:38.538200: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:24:38.539554: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:24:38.547185: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:24:39.470885: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/11 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 18%|█▊ | 2/11 [01:08<05:09, 34.35s/it] 27%|██▋ | 3/11 [01:42<04:34, 34.33s/it] 36%|███▋ | 4/11 [02:17<03:59, 34.26s/it] 45%|████▌ | 5/11 [02:51<03:25, 34.22s/it] 55%|█████▍ | 6/11 [03:25<02:50, 34.18s/it] 64%|██████▎ | 7/11 [03:59<02:16, 34.14s/it] 73%|███████▎ | 8/11 [04:33<01:42, 34.13s/it] 82%|████████▏ | 9/11 [05:07<01:08, 34.09s/it] 91%|█████████ | 10/11 [05:41<00:34, 34.09s/it] 100%|██████████| 11/11 [06:15<00:00, 34.09s/it] 100%|██████████| 11/11 [06:15<00:00, 34.15s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 6m57.114s user 6m21.626s sys 1m25.160s 2026-02-11 15:31:35.657972: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:31:35.707733: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:31:35.707792: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:31:35.709109: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:31:35.716616: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:31:36.648540: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/12 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 17%|█▋ | 2/12 [01:08<05:42, 34.24s/it] 25%|██▌ | 3/12 [01:42<05:07, 34.20s/it] 33%|███▎ | 4/12 [02:16<04:33, 34.19s/it] 42%|████▏ | 5/12 [02:50<03:58, 34.14s/it] 50%|█████ | 6/12 [03:24<03:24, 34.09s/it] 58%|█████▊ | 7/12 [03:58<02:50, 34.07s/it] 67%|██████▋ | 8/12 [04:32<02:16, 34.07s/it] 75%|███████▌ | 9/12 [05:06<01:42, 34.05s/it] 83%|████████▎ | 10/12 [05:41<01:08, 34.06s/it] 92%|█████████▏| 11/12 [06:15<00:34, 34.08s/it] 100%|██████████| 12/12 [06:49<00:00, 34.07s/it] 100%|██████████| 12/12 [06:49<00:00, 34.10s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 11: generating actions ... >>> Step 11: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 7m25.752s user 6m39.497s sys 1m32.896s 2026-02-11 15:39:01.409308: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:39:01.459136: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:39:01.459190: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:39:01.460507: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:39:01.468019: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:39:02.395912: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/12 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 17%|█▋ | 2/12 [01:08<05:41, 34.18s/it] 25%|██▌ | 3/12 [01:42<05:07, 34.15s/it] 33%|███▎ | 4/12 [02:16<04:33, 34.13s/it] 42%|████▏ | 5/12 [02:50<03:58, 34.09s/it] 50%|█████ | 6/12 [03:24<03:24, 34.08s/it] 58%|█████▊ | 7/12 [03:58<02:50, 34.06s/it] 67%|██████▋ | 8/12 [04:32<02:16, 34.03s/it] 75%|███████▌ | 9/12 [05:06<01:42, 34.03s/it] 83%|████████▎ | 10/12 [05:40<01:08, 34.03s/it] 92%|█████████▏| 11/12 [06:14<00:34, 34.02s/it] 100%|██████████| 12/12 [06:48<00:00, 34.00s/it] 100%|██████████| 12/12 [06:48<00:00, 34.05s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 11: generating actions ... >>> Step 11: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 7m25.895s user 6m43.188s sys 1m30.039s 2026-02-11 15:46:27.304090: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:46:27.354074: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:46:27.354120: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:46:27.355468: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:46:27.363130: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:46:28.290783: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/12 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 17%|█▋ | 2/12 [01:08<05:42, 34.24s/it] 25%|██▌ | 3/12 [01:42<05:07, 34.22s/it] 33%|███▎ | 4/12 [02:16<04:33, 34.16s/it] 42%|████▏ | 5/12 [02:50<03:58, 34.11s/it] 50%|█████ | 6/12 [03:24<03:24, 34.08s/it] 58%|█████▊ | 7/12 [03:58<02:50, 34.04s/it] 67%|██████▋ | 8/12 [04:32<02:16, 34.02s/it] 75%|███████▌ | 9/12 [05:06<01:41, 33.99s/it] 83%|████████▎ | 10/12 [05:40<01:07, 33.99s/it] 92%|█████████▏| 11/12 [06:14<00:33, 33.97s/it] 100%|██████████| 12/12 [06:48<00:00, 33.96s/it] 100%|██████████| 12/12 [06:48<00:00, 34.04s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 11: generating actions ... >>> Step 11: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 7m25.192s user 6m39.503s sys 1m31.823s 2026-02-11 15:53:52.504337: I tensorflow/core/util/port.cc:113] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`. 2026-02-11 15:53:52.554351: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2026-02-11 15:53:52.554397: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2026-02-11 15:53:52.555718: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered 2026-02-11 15:53:52.563252: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 AVX512F AVX512_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2026-02-11 15:53:53.493343: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT Global seed set to 123 >>> Loading prepared model from ckpts/unifolm_wma_dual.ckpt.prepared.pt ... >>> Prepared model loaded. INFO:root:***** Configing Data ***** >>> unitree_z1_stackbox: 1 data samples loaded. >>> unitree_z1_stackbox: data stats loaded. >>> unitree_z1_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox: data stats loaded. >>> unitree_z1_dual_arm_stackbox: normalizer initiated. >>> unitree_z1_dual_arm_stackbox_v2: 1 data samples loaded. >>> unitree_z1_dual_arm_stackbox_v2: data stats loaded. >>> unitree_z1_dual_arm_stackbox_v2: normalizer initiated. >>> unitree_z1_dual_arm_cleanup_pencils: 1 data samples loaded. >>> unitree_z1_dual_arm_cleanup_pencils: data stats loaded. >>> unitree_z1_dual_arm_cleanup_pencils: normalizer initiated. >>> unitree_g1_pack_camera: 1 data samples loaded. >>> unitree_g1_pack_camera: data stats loaded. >>> unitree_g1_pack_camera: normalizer initiated. >>> Dataset is successfully loaded ... ✓ KV fused: 66 attention layers >>> Generate 16 frames under each generation ... DEBUG:h5py._conv:Creating converter from 3 to 5 DEBUG:PIL.PngImagePlugin:STREAM b'IHDR' 16 13 DEBUG:PIL.PngImagePlugin:STREAM b'pHYs' 41 9 DEBUG:PIL.PngImagePlugin:STREAM b'IDAT' 62 4096 0%| | 0/12 [00:00>> Step 0: generating actions ... >>> Step 0: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 1: generating actions ... DEBUG:PIL.Image:Importing BlpImagePlugin DEBUG:PIL.Image:Importing BmpImagePlugin DEBUG:PIL.Image:Importing BufrStubImagePlugin DEBUG:PIL.Image:Importing CurImagePlugin DEBUG:PIL.Image:Importing DcxImagePlugin DEBUG:PIL.Image:Importing DdsImagePlugin DEBUG:PIL.Image:Importing EpsImagePlugin DEBUG:PIL.Image:Importing FitsImagePlugin DEBUG:PIL.Image:Importing FitsStubImagePlugin DEBUG:PIL.Image:Importing FliImagePlugin DEBUG:PIL.Image:Importing FpxImagePlugin DEBUG:PIL.Image:Image: failed to import FpxImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing FtexImagePlugin DEBUG:PIL.Image:Importing GbrImagePlugin DEBUG:PIL.Image:Importing GifImagePlugin DEBUG:PIL.Image:Importing GribStubImagePlugin DEBUG:PIL.Image:Importing Hdf5StubImagePlugin DEBUG:PIL.Image:Importing IcnsImagePlugin DEBUG:PIL.Image:Importing IcoImagePlugin DEBUG:PIL.Image:Importing ImImagePlugin DEBUG:PIL.Image:Importing ImtImagePlugin DEBUG:PIL.Image:Importing IptcImagePlugin DEBUG:PIL.Image:Importing JpegImagePlugin DEBUG:PIL.Image:Importing Jpeg2KImagePlugin DEBUG:PIL.Image:Importing McIdasImagePlugin DEBUG:PIL.Image:Importing MicImagePlugin DEBUG:PIL.Image:Image: failed to import MicImagePlugin: No module named 'olefile' DEBUG:PIL.Image:Importing MpegImagePlugin DEBUG:PIL.Image:Importing MpoImagePlugin DEBUG:PIL.Image:Importing MspImagePlugin DEBUG:PIL.Image:Importing PalmImagePlugin DEBUG:PIL.Image:Importing PcdImagePlugin DEBUG:PIL.Image:Importing PcxImagePlugin DEBUG:PIL.Image:Importing PdfImagePlugin DEBUG:PIL.Image:Importing PixarImagePlugin DEBUG:PIL.Image:Importing PngImagePlugin DEBUG:PIL.Image:Importing PpmImagePlugin DEBUG:PIL.Image:Importing PsdImagePlugin DEBUG:PIL.Image:Importing QoiImagePlugin DEBUG:PIL.Image:Importing SgiImagePlugin DEBUG:PIL.Image:Importing SpiderImagePlugin DEBUG:PIL.Image:Importing SunImagePlugin DEBUG:PIL.Image:Importing TgaImagePlugin DEBUG:PIL.Image:Importing TiffImagePlugin DEBUG:PIL.Image:Importing WebPImagePlugin DEBUG:PIL.Image:Importing WmfImagePlugin DEBUG:PIL.Image:Importing XbmImagePlugin DEBUG:PIL.Image:Importing XpmImagePlugin DEBUG:PIL.Image:Importing XVThumbImagePlugin 17%|█▋ | 2/12 [01:08<05:41, 34.19s/it] 25%|██▌ | 3/12 [01:42<05:07, 34.15s/it] 33%|███▎ | 4/12 [02:16<04:32, 34.12s/it] 42%|████▏ | 5/12 [02:50<03:58, 34.09s/it] 50%|█████ | 6/12 [03:24<03:24, 34.05s/it] 58%|█████▊ | 7/12 [03:58<02:50, 34.03s/it] 67%|██████▋ | 8/12 [04:32<02:16, 34.04s/it] 75%|███████▌ | 9/12 [05:06<01:42, 34.03s/it] 83%|████████▎ | 10/12 [05:40<01:08, 34.01s/it] 92%|█████████▏| 11/12 [06:14<00:34, 34.03s/it] 100%|██████████| 12/12 [06:48<00:00, 34.02s/it] 100%|██████████| 12/12 [06:48<00:00, 34.05s/it] >>> Step 1: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 2: generating actions ... >>> Step 2: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 3: generating actions ... >>> Step 3: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 4: generating actions ... >>> Step 4: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 5: generating actions ... >>> Step 5: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 6: generating actions ... >>> Step 6: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 7: generating actions ... >>> Step 7: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 8: generating actions ... >>> Step 8: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 9: generating actions ... >>> Step 9: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 10: generating actions ... >>> Step 10: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> >>> Step 11: generating actions ... >>> Step 11: interacting with world model ... >>>>>>>>>>>>>>>>>>>>>>>> real 7m25.114s user 6m35.463s sys 1m35.788s