Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- Abs_6D/DiT_Layer/16/Baseline/baseline_gpu1_rolling5k_20260723_022922.log +198 -0
- Abs_6D/DiT_Layer/16/Baseline/baseline_gpu1_rolling5k_20260723_023110_newwandb.log +0 -0
- Abs_6D/DiT_Layer/16/Baseline/wandb/debug-internal.log +0 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/action_space_manifest.json +144 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/phase_schedule.json +32 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/resolved_config.yaml +35 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/source_config.yaml +63 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/training_state/optimizer_param_groups.json +361 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/training_state/training_step.json +5 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/action_space_manifest.json +144 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/phase_schedule.json +32 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/action_space_manifest.json +144 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/config.json +118 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/phase_schedule.json +32 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/prompt_manifest.json +40 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/train_config.json +269 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/prompt_manifest.json +40 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/resolved_config.yaml +35 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/source_config.yaml +63 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/training_state/optimizer_param_groups.json +361 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/rscl_gpu1_rolling5k_20260723_022922.log +198 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/rscl_gpu1_rolling5k_20260723_023110_newwandb.log +0 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/source_config.yaml +2 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/debug-internal.log +0 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/debug.log +65 -20
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/files/config.yaml +334 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/files/output.log +44 -1
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/files/wandb-summary.json +1 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/logs/debug-core.log +36 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/logs/debug-internal.log +106 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/logs/debug.log +45 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/files/wandb-summary.json +1 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug-core.log +30 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug-internal.log +15 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug.log +13 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/run-cemf0rge.wandb +0 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/files/output.log +149 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/files/requirements.txt +117 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/files/wandb-metadata.json +53 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug-core.log +14 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug-internal.log +0 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug.log +19 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/config.yaml +329 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/output.log +96 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/requirements.txt +118 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/wandb-metadata.json +46 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/wandb-summary.json +1 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug-core.log +71 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug-internal.log +0 -0
- Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug.log +65 -0
Abs_6D/DiT_Layer/16/Baseline/baseline_gpu1_rolling5k_20260723_022922.log
ADDED
|
@@ -0,0 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
INFO 2026-07-23 02:29:36 ot_train.py:281 {'batch_size': 64,
|
| 2 |
+
'checkpoint_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/Baseline/checkpoints/030000',
|
| 3 |
+
'cudnn_deterministic': False,
|
| 4 |
+
'dataset': {'depth_output_unit': 'mm',
|
| 5 |
+
'episodes': None,
|
| 6 |
+
'eval_split': 0.0,
|
| 7 |
+
'image_transforms': {'enable': False,
|
| 8 |
+
'max_num_transforms': 3,
|
| 9 |
+
'random_order': False,
|
| 10 |
+
'tfs': {'affine': {'kwargs': {'degrees': [-5.0,
|
| 11 |
+
5.0],
|
| 12 |
+
'translate': [0.05,
|
| 13 |
+
0.05]},
|
| 14 |
+
'type': 'RandomAffine',
|
| 15 |
+
'weight': 1.0},
|
| 16 |
+
'brightness': {'kwargs': {'brightness': [0.8,
|
| 17 |
+
1.2]},
|
| 18 |
+
'type': 'ColorJitter',
|
| 19 |
+
'weight': 1.0},
|
| 20 |
+
'contrast': {'kwargs': {'contrast': [0.8,
|
| 21 |
+
1.2]},
|
| 22 |
+
'type': 'ColorJitter',
|
| 23 |
+
'weight': 1.0},
|
| 24 |
+
'hue': {'kwargs': {'hue': [-0.05,
|
| 25 |
+
0.05]},
|
| 26 |
+
'type': 'ColorJitter',
|
| 27 |
+
'weight': 1.0},
|
| 28 |
+
'saturation': {'kwargs': {'saturation': [0.5,
|
| 29 |
+
1.5]},
|
| 30 |
+
'type': 'ColorJitter',
|
| 31 |
+
'weight': 1.0},
|
| 32 |
+
'sharpness': {'kwargs': {'sharpness': [0.5,
|
| 33 |
+
1.5]},
|
| 34 |
+
'type': 'SharpnessJitter',
|
| 35 |
+
'weight': 1.0}}},
|
| 36 |
+
'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2',
|
| 37 |
+
'return_uint8': False,
|
| 38 |
+
'revision': None,
|
| 39 |
+
'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2',
|
| 40 |
+
'streaming': False,
|
| 41 |
+
'use_imagenet_stats': True,
|
| 42 |
+
'video_backend': 'torchcodec'},
|
| 43 |
+
'env': None,
|
| 44 |
+
'env_eval_freq': 20000,
|
| 45 |
+
'eval': {'batch_size': 50,
|
| 46 |
+
'n_episodes': 50,
|
| 47 |
+
'recording': False,
|
| 48 |
+
'recording_private': False,
|
| 49 |
+
'recording_repo_id': None,
|
| 50 |
+
'use_async_envs': True},
|
| 51 |
+
'eval_steps': 0,
|
| 52 |
+
'job': {'detach': False,
|
| 53 |
+
'image': 'huggingface/lerobot-gpu:latest',
|
| 54 |
+
'tags': [],
|
| 55 |
+
'target': None,
|
| 56 |
+
'timeout': '2d'},
|
| 57 |
+
'job_name': 'INSIGHT_6D_DiT16_Baseline',
|
| 58 |
+
'log_freq': 200,
|
| 59 |
+
'max_eval_samples': 0,
|
| 60 |
+
'num_workers': 4,
|
| 61 |
+
'optimizer': {'betas': [0.9, 0.999],
|
| 62 |
+
'eps': 1e-08,
|
| 63 |
+
'grad_clip_norm': 1.0,
|
| 64 |
+
'lr': 0.0001,
|
| 65 |
+
'type': 'adamw',
|
| 66 |
+
'weight_decay': 1e-05},
|
| 67 |
+
'output_dir': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/Baseline',
|
| 68 |
+
'peft': None,
|
| 69 |
+
'persistent_workers': True,
|
| 70 |
+
'policy': {'action_decode_transform': None,
|
| 71 |
+
'action_expert_num_layers': 16,
|
| 72 |
+
'balance_dataset_weights': True,
|
| 73 |
+
'balance_trajectory_weights': True,
|
| 74 |
+
'base_model_path': 'nvidia/GR00T-N1.7-3B',
|
| 75 |
+
'batch_size': 32,
|
| 76 |
+
'chunk_size': 16,
|
| 77 |
+
'dataloader_num_workers': 8,
|
| 78 |
+
'dataset_paths': None,
|
| 79 |
+
'device': 'cuda',
|
| 80 |
+
'embodiment_tag': 'new_embodiment',
|
| 81 |
+
'image_size': [256, 256],
|
| 82 |
+
'input_features': {'observation.images.guide': {'shape': [3,
|
| 83 |
+
224,
|
| 84 |
+
224],
|
| 85 |
+
'type': <FeatureType.VISUAL: 'VISUAL'>},
|
| 86 |
+
'observation.images.right_shoulder': {'shape': [3,
|
| 87 |
+
224,
|
| 88 |
+
224],
|
| 89 |
+
'type': <FeatureType.VISUAL: 'VISUAL'>},
|
| 90 |
+
'observation.images.wrist': {'shape': [3,
|
| 91 |
+
224,
|
| 92 |
+
224],
|
| 93 |
+
'type': <FeatureType.VISUAL: 'VISUAL'>},
|
| 94 |
+
'observation.state': {'shape': [16],
|
| 95 |
+
'type': <FeatureType.STATE: 'STATE'>}},
|
| 96 |
+
'license': None,
|
| 97 |
+
'lora_alpha': 16,
|
| 98 |
+
'lora_dropout': 0.1,
|
| 99 |
+
'lora_full_model': False,
|
| 100 |
+
'lora_rank': 0,
|
| 101 |
+
'max_action_dim': 132,
|
| 102 |
+
'max_state_dim': 132,
|
| 103 |
+
'max_steps': 10000,
|
| 104 |
+
'model_params_fp32': True,
|
| 105 |
+
'n_action_steps': 16,
|
| 106 |
+
'n_obs_steps': 1,
|
| 107 |
+
'normalization_mapping': {'ACTION': <NormalizationMode.IDENTITY: 'IDENTITY'>,
|
| 108 |
+
'STATE': <NormalizationMode.IDENTITY: 'IDENTITY'>,
|
| 109 |
+
'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>},
|
| 110 |
+
'num_inference_timesteps': None,
|
| 111 |
+
'optimizer_betas': [0.9, 0.999],
|
| 112 |
+
'optimizer_eps': 1e-08,
|
| 113 |
+
'optimizer_lr': 0.0001,
|
| 114 |
+
'optimizer_weight_decay': 1e-05,
|
| 115 |
+
'output_dir': './tmp/gr00t',
|
| 116 |
+
'output_features': {'action': {'shape': [10],
|
| 117 |
+
'type': <FeatureType.ACTION: 'ACTION'>}},
|
| 118 |
+
'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/Baseline/checkpoints/030000/pretrained_model',
|
| 119 |
+
'pretrained_revision': None,
|
| 120 |
+
'private': None,
|
| 121 |
+
'push_to_hub': False,
|
| 122 |
+
'relative_exclude_joints': [],
|
| 123 |
+
'repo_id': None,
|
| 124 |
+
'report_to': 'wandb',
|
| 125 |
+
'resume': False,
|
| 126 |
+
'rkd_angle_weight': 1.0,
|
| 127 |
+
'rkd_distance_weight': 1.0,
|
| 128 |
+
'rkd_enabled': False,
|
| 129 |
+
'rkd_fm_loss_weight': 1.0,
|
| 130 |
+
'rkd_loss_weight': 0.1,
|
| 131 |
+
'rkd_student_attention_hidden_dim': 512,
|
| 132 |
+
'rkd_student_attention_output_dim': 512,
|
| 133 |
+
'rkd_student_pooling': 'attention',
|
| 134 |
+
'rkd_vae_checkpoint': None,
|
| 135 |
+
'rtc_ramp_rate': None,
|
| 136 |
+
'save_steps': 1000,
|
| 137 |
+
'tags': None,
|
| 138 |
+
'tokenizer_assets_repo': None,
|
| 139 |
+
'tune_diffusion_model': True,
|
| 140 |
+
'tune_llm': False,
|
| 141 |
+
'tune_projector': True,
|
| 142 |
+
'tune_top_llm_layers': 0,
|
| 143 |
+
'tune_visual': False,
|
| 144 |
+
'tune_vlln': True,
|
| 145 |
+
'type': 'groot_rkd',
|
| 146 |
+
'use_amp': False,
|
| 147 |
+
'use_bf16': True,
|
| 148 |
+
'use_flash_attention': False,
|
| 149 |
+
'use_peft': False,
|
| 150 |
+
'use_relative_actions': False,
|
| 151 |
+
'video_backend': 'decord',
|
| 152 |
+
'warmup_ratio': 0.05,
|
| 153 |
+
'warmup_steps': None},
|
| 154 |
+
'prefetch_factor': 4,
|
| 155 |
+
'rename_map': {},
|
| 156 |
+
'resume': True,
|
| 157 |
+
'reward_model': None,
|
| 158 |
+
'sample_weighting': None,
|
| 159 |
+
'save_checkpoint': True,
|
| 160 |
+
'save_checkpoint_to_hub': False,
|
| 161 |
+
'save_freq': 20000,
|
| 162 |
+
'scheduler': {'name': 'cosine', 'num_warmup_steps': 500, 'type': 'diffuser'},
|
| 163 |
+
'seed': 42,
|
| 164 |
+
'steps': 60000,
|
| 165 |
+
'tolerance_s': 0.0001,
|
| 166 |
+
'use_policy_training_preset': True,
|
| 167 |
+
'wandb': {'add_tags': True,
|
| 168 |
+
'disable_artifact': True,
|
| 169 |
+
'enable': True,
|
| 170 |
+
'entity': None,
|
| 171 |
+
'mode': None,
|
| 172 |
+
'notes': None,
|
| 173 |
+
'project': 'lerobot',
|
| 174 |
+
'run_id': 'eb0sb786'}}
|
| 175 |
+
Traceback (most recent call last):
|
| 176 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py", line 1613, in <module>
|
| 177 |
+
main()
|
| 178 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py", line 1609, in main
|
| 179 |
+
train_module.main()
|
| 180 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 822, in main
|
| 181 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/configs/parser.py", line 320, in wrapper_inner
|
| 182 |
+
response = fn(cfg, *args, **kwargs)
|
| 183 |
+
^^^^^^^^^^^^^^^^^^^^^^^^
|
| 184 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 285, in train
|
| 185 |
+
if not policy.is_trainable:
|
| 186 |
+
^^^^^^^^^^^^^
|
| 187 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/common/wandb_utils.py", line 99, in __init__
|
| 188 |
+
wandb.init(
|
| 189 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/wandb_init.py", line 1528, in init
|
| 190 |
+
get_sentry().reraise(e)
|
| 191 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/analytics/sentry.py", line 191, in reraise
|
| 192 |
+
raise exc.with_traceback(tb)
|
| 193 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/wandb_init.py", line 1511, in init
|
| 194 |
+
run = wi.init(run_settings, run_config, run_printer)
|
| 195 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 196 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/wandb_init.py", line 961, in init
|
| 197 |
+
raise error
|
| 198 |
+
wandb.errors.errors.UsageError: You provided an invalid value for the `resume` argument. The value 'must' is not a valid option for resuming the run (eb0sb786) that has not been initialized. Please check your inputs and try again with a valid run ID. If you are trying to start a new run, please omit the `resume` argument or use `resume='allow'`.
|
Abs_6D/DiT_Layer/16/Baseline/baseline_gpu1_rolling5k_20260723_023110_newwandb.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Abs_6D/DiT_Layer/16/Baseline/wandb/debug-internal.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/action_space_manifest.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 2,
|
| 3 |
+
"action_space": "ee_abs_rot6d",
|
| 4 |
+
"action_views": [
|
| 5 |
+
"ee_abs_rot6d"
|
| 6 |
+
],
|
| 7 |
+
"source_feature": "action.ee_abs_rot6d",
|
| 8 |
+
"canonical_feature": "action",
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"shape": [
|
| 11 |
+
10
|
| 12 |
+
],
|
| 13 |
+
"names": [
|
| 14 |
+
"x",
|
| 15 |
+
"y",
|
| 16 |
+
"z",
|
| 17 |
+
"r_col0_x",
|
| 18 |
+
"r_col0_y",
|
| 19 |
+
"r_col0_z",
|
| 20 |
+
"r_col1_x",
|
| 21 |
+
"r_col1_y",
|
| 22 |
+
"r_col1_z",
|
| 23 |
+
"gripper"
|
| 24 |
+
],
|
| 25 |
+
"dataset_repo_id": "Whalswp/INSIGHTfixposV4_filtered_multispace_v2",
|
| 26 |
+
"dataset_revision": "v3.0",
|
| 27 |
+
"dataset_total_frames": 218367,
|
| 28 |
+
"dataset_total_episodes": 4930,
|
| 29 |
+
"dataset_fps": 10,
|
| 30 |
+
"stats_sha256": "71698c7337070aa8267df5aea7ec08bc00d3925510f2649bc20c9201eeb669e4",
|
| 31 |
+
"stats": {
|
| 32 |
+
"min": [
|
| 33 |
+
-0.21784618496894836,
|
| 34 |
+
-0.4474811851978302,
|
| 35 |
+
0.1702737659215927,
|
| 36 |
+
-0.9999986290931702,
|
| 37 |
+
-0.9999991655349731,
|
| 38 |
+
-0.9999999403953552,
|
| 39 |
+
-0.9999990463256836,
|
| 40 |
+
-0.9999998211860657,
|
| 41 |
+
-0.9999988079071045,
|
| 42 |
+
0.0
|
| 43 |
+
],
|
| 44 |
+
"max": [
|
| 45 |
+
0.6283698678016663,
|
| 46 |
+
0.4420371949672699,
|
| 47 |
+
1.051027774810791,
|
| 48 |
+
0.9999999403953552,
|
| 49 |
+
0.9999995231628418,
|
| 50 |
+
1.0,
|
| 51 |
+
0.9999995231628418,
|
| 52 |
+
1.0,
|
| 53 |
+
0.9999996423721313,
|
| 54 |
+
0.03999999910593033
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
0.4040228037735655,
|
| 58 |
+
-0.05247618696989652,
|
| 59 |
+
0.6993459771218912,
|
| 60 |
+
0.07011111991957117,
|
| 61 |
+
-0.03520558904460197,
|
| 62 |
+
0.14470242846953205,
|
| 63 |
+
0.05491166606739672,
|
| 64 |
+
-0.19073058893378805,
|
| 65 |
+
-0.06988117661871228,
|
| 66 |
+
0.021167300266524632
|
| 67 |
+
],
|
| 68 |
+
"std": [
|
| 69 |
+
0.11861927913357073,
|
| 70 |
+
0.11318943557281885,
|
| 71 |
+
0.17849160646987516,
|
| 72 |
+
0.4812528791886511,
|
| 73 |
+
0.7487196258736938,
|
| 74 |
+
0.4251126804030219,
|
| 75 |
+
0.47797229807769137,
|
| 76 |
+
0.6267695346407992,
|
| 77 |
+
0.5782954306815554,
|
| 78 |
+
0.01996590431050817
|
| 79 |
+
],
|
| 80 |
+
"count": [
|
| 81 |
+
218367
|
| 82 |
+
],
|
| 83 |
+
"q01": [
|
| 84 |
+
0.23988881827972064,
|
| 85 |
+
-0.10387461883034811,
|
| 86 |
+
0.6297243923476871,
|
| 87 |
+
-0.43622841955353464,
|
| 88 |
+
-0.6885486527617446,
|
| 89 |
+
-0.14103555388039019,
|
| 90 |
+
-0.4327210063987595,
|
| 91 |
+
-0.9304790915716145,
|
| 92 |
+
-0.3465462258490417,
|
| 93 |
+
-1.000000013351432e-10
|
| 94 |
+
],
|
| 95 |
+
"q10": [
|
| 96 |
+
0.3042306436755216,
|
| 97 |
+
-0.09609991620622624,
|
| 98 |
+
0.6394063072781145,
|
| 99 |
+
-0.3351306352998669,
|
| 100 |
+
-0.5751963015002924,
|
| 101 |
+
-0.08490621283307866,
|
| 102 |
+
-0.33849701676224275,
|
| 103 |
+
-0.8340557712529717,
|
| 104 |
+
-0.29760290790884514,
|
| 105 |
+
-1.000000013351432e-10
|
| 106 |
+
],
|
| 107 |
+
"q50": [
|
| 108 |
+
0.4160225263528291,
|
| 109 |
+
-0.06267459152989589,
|
| 110 |
+
0.6811777491060801,
|
| 111 |
+
0.0543536902230377,
|
| 112 |
+
-0.14012251058819217,
|
| 113 |
+
0.04772394280004727,
|
| 114 |
+
0.03838119138716219,
|
| 115 |
+
-0.14865169094195635,
|
| 116 |
+
-0.2073069401172425,
|
| 117 |
+
0.020772594934870346
|
| 118 |
+
],
|
| 119 |
+
"q90": [
|
| 120 |
+
0.46641008755679864,
|
| 121 |
+
0.020233143101890064,
|
| 122 |
+
0.8095135405259374,
|
| 123 |
+
0.48172401592474906,
|
| 124 |
+
0.7398737043070319,
|
| 125 |
+
0.5970841215636613,
|
| 126 |
+
0.4674752875999555,
|
| 127 |
+
0.36281754777672676,
|
| 128 |
+
0.5033361883834496,
|
| 129 |
+
0.039998362213352394
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
0.47320723171849244,
|
| 133 |
+
0.04114262476135705,
|
| 134 |
+
0.8467967259270389,
|
| 135 |
+
0.5867781409980988,
|
| 136 |
+
0.8529584859257228,
|
| 137 |
+
0.7953936054341789,
|
| 138 |
+
0.5768269858732034,
|
| 139 |
+
0.49353349323389695,
|
| 140 |
+
0.7168914440776504,
|
| 141 |
+
0.03999983541667277
|
| 142 |
+
]
|
| 143 |
+
}
|
| 144 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/phase_schedule.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 1,
|
| 3 |
+
"step_interval": "[start_step, until_step)",
|
| 4 |
+
"total_steps": 60000,
|
| 5 |
+
"optimizer_lifecycle": "single_continuous_optimizer",
|
| 6 |
+
"scheduler_lifecycle": "single_continuous_scheduler",
|
| 7 |
+
"phases": [
|
| 8 |
+
{
|
| 9 |
+
"index": 0,
|
| 10 |
+
"name": "rscl_rkd_cosine_decay_60K",
|
| 11 |
+
"start_step": 0,
|
| 12 |
+
"until_step": 60000,
|
| 13 |
+
"policy": {
|
| 14 |
+
"rkd_enabled": true,
|
| 15 |
+
"rkd_fm_loss_weight": 1.0,
|
| 16 |
+
"rkd_loss_weight": 1.0,
|
| 17 |
+
"rkd_loss_weight_end": 0.0,
|
| 18 |
+
"rkd_loss_weight_schedule": "cosine",
|
| 19 |
+
"rkd_distance_weight": 1.0,
|
| 20 |
+
"rkd_angle_weight": 2.0
|
| 21 |
+
},
|
| 22 |
+
"trainable": {
|
| 23 |
+
"tune_llm": false,
|
| 24 |
+
"tune_visual": false,
|
| 25 |
+
"tune_top_llm_layers": 0,
|
| 26 |
+
"tune_projector": true,
|
| 27 |
+
"tune_diffusion_model": true,
|
| 28 |
+
"tune_vlln": true
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/resolved_config.yaml
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dataset:
|
| 2 |
+
repo_id: Whalswp/INSIGHTfixposV4_filtered_multispace_v2
|
| 3 |
+
root: /home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2
|
| 4 |
+
policy:
|
| 5 |
+
type: groot_rkd
|
| 6 |
+
device: cuda
|
| 7 |
+
chunk_size: 16
|
| 8 |
+
n_action_steps: 16
|
| 9 |
+
push_to_hub: false
|
| 10 |
+
warmup_steps: 3000
|
| 11 |
+
tune_llm: false
|
| 12 |
+
tune_visual: false
|
| 13 |
+
tune_top_llm_layers: 0
|
| 14 |
+
action_expert_num_layers: 16
|
| 15 |
+
tune_projector: true
|
| 16 |
+
tune_diffusion_model: true
|
| 17 |
+
tune_vlln: true
|
| 18 |
+
rkd_enabled: true
|
| 19 |
+
rkd_vae_checkpoint: /home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11
|
| 20 |
+
rkd_student_pooling: attention
|
| 21 |
+
rkd_student_attention_hidden_dim: 512
|
| 22 |
+
rkd_student_attention_output_dim: 512
|
| 23 |
+
rkd_fm_loss_weight: 1.0
|
| 24 |
+
rkd_loss_weight: 1.0
|
| 25 |
+
rkd_distance_weight: 1.0
|
| 26 |
+
rkd_angle_weight: 2.0
|
| 27 |
+
seed: 42
|
| 28 |
+
batch_size: 64
|
| 29 |
+
steps: 60000
|
| 30 |
+
log_freq: 200
|
| 31 |
+
output_dir: /home/ext_minje/groot_insight/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 32 |
+
job_name: INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60
|
| 33 |
+
wandb:
|
| 34 |
+
enable: true
|
| 35 |
+
disable_artifact: true
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/source_config.yaml
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# INSIGHT GR00T N1.7 RKD training with RS-CL-style full-training regularization.
|
| 2 |
+
# Common RKD values live in the top-level policy; the phase contains schedule overrides only.
|
| 3 |
+
insight:
|
| 4 |
+
checkpoint_interval: 5K
|
| 5 |
+
checkpoint_slots: 2
|
| 6 |
+
# Options: joint_abs | ee_abs_quat | ee_abs_rot6d | ee_delta
|
| 7 |
+
action_space: ee_abs_rot6d
|
| 8 |
+
# Options: coarse | detailed
|
| 9 |
+
prompt_set: detailed
|
| 10 |
+
save_steps: ["10K", "30K", "60K"]
|
| 11 |
+
phases:
|
| 12 |
+
- name: rscl_rkd_cosine_decay_60K
|
| 13 |
+
until_step: 60K
|
| 14 |
+
policy:
|
| 15 |
+
# Inherits RKD=1.0 below and follows a half-cosine decay to zero.
|
| 16 |
+
rkd_loss_weight_end: 0.0
|
| 17 |
+
rkd_loss_weight_schedule: cosine
|
| 18 |
+
|
| 19 |
+
dataset:
|
| 20 |
+
repo_id: Whalswp/INSIGHTfixposV4_filtered_multispace_v2
|
| 21 |
+
root: ${HOME}/INSIGHTfixposV4_filtered_multispace_v2
|
| 22 |
+
|
| 23 |
+
policy:
|
| 24 |
+
type: groot_rkd
|
| 25 |
+
device: cuda
|
| 26 |
+
chunk_size: 16
|
| 27 |
+
n_action_steps: 16
|
| 28 |
+
push_to_hub: false
|
| 29 |
+
# RS-CL GR00T uses exactly 3K warmup updates.
|
| 30 |
+
warmup_steps: 3000
|
| 31 |
+
|
| 32 |
+
# VLM
|
| 33 |
+
tune_llm: false
|
| 34 |
+
tune_visual: false
|
| 35 |
+
tune_top_llm_layers: 0
|
| 36 |
+
# Action Expert
|
| 37 |
+
action_expert_num_layers: 16
|
| 38 |
+
tune_projector: true
|
| 39 |
+
tune_diffusion_model: true
|
| 40 |
+
tune_vlln: true
|
| 41 |
+
|
| 42 |
+
# Frozen TimewarpVAE teacher and common RKD objective.
|
| 43 |
+
rkd_enabled: true
|
| 44 |
+
rkd_vae_checkpoint: ${HOME}/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11
|
| 45 |
+
rkd_student_pooling: attention # attention | mean
|
| 46 |
+
rkd_student_attention_hidden_dim: 512
|
| 47 |
+
rkd_student_attention_output_dim: 512
|
| 48 |
+
rkd_fm_loss_weight: 1.0
|
| 49 |
+
rkd_loss_weight: 1.0
|
| 50 |
+
rkd_distance_weight: 1.0
|
| 51 |
+
rkd_angle_weight: 2.0
|
| 52 |
+
|
| 53 |
+
seed: 42
|
| 54 |
+
# Single GPU/process, so this is also the global batch size.
|
| 55 |
+
batch_size: 64
|
| 56 |
+
steps: 60000
|
| 57 |
+
log_freq: 200
|
| 58 |
+
output_dir: ${HOME}/groot_insight/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 59 |
+
job_name: INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60
|
| 60 |
+
|
| 61 |
+
wandb:
|
| 62 |
+
enable: true
|
| 63 |
+
disable_artifact: true
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 1.8865999845374793e-06,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 1e-05,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"initial_lr": 0.0001,
|
| 18 |
+
"params": [
|
| 19 |
+
0,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6,
|
| 26 |
+
7,
|
| 27 |
+
8,
|
| 28 |
+
9,
|
| 29 |
+
10,
|
| 30 |
+
11,
|
| 31 |
+
12,
|
| 32 |
+
13,
|
| 33 |
+
14,
|
| 34 |
+
15,
|
| 35 |
+
16,
|
| 36 |
+
17,
|
| 37 |
+
18,
|
| 38 |
+
19,
|
| 39 |
+
20,
|
| 40 |
+
21,
|
| 41 |
+
22,
|
| 42 |
+
23,
|
| 43 |
+
24,
|
| 44 |
+
25,
|
| 45 |
+
26,
|
| 46 |
+
27,
|
| 47 |
+
28,
|
| 48 |
+
29,
|
| 49 |
+
30,
|
| 50 |
+
31,
|
| 51 |
+
32,
|
| 52 |
+
33,
|
| 53 |
+
34,
|
| 54 |
+
35,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
41,
|
| 61 |
+
42,
|
| 62 |
+
43,
|
| 63 |
+
44,
|
| 64 |
+
45,
|
| 65 |
+
46,
|
| 66 |
+
47,
|
| 67 |
+
48,
|
| 68 |
+
49,
|
| 69 |
+
50,
|
| 70 |
+
51,
|
| 71 |
+
52,
|
| 72 |
+
53,
|
| 73 |
+
54,
|
| 74 |
+
55,
|
| 75 |
+
56,
|
| 76 |
+
57,
|
| 77 |
+
58,
|
| 78 |
+
59,
|
| 79 |
+
60,
|
| 80 |
+
61,
|
| 81 |
+
62,
|
| 82 |
+
63,
|
| 83 |
+
64,
|
| 84 |
+
65,
|
| 85 |
+
66,
|
| 86 |
+
67,
|
| 87 |
+
68,
|
| 88 |
+
69,
|
| 89 |
+
70,
|
| 90 |
+
71,
|
| 91 |
+
72,
|
| 92 |
+
73,
|
| 93 |
+
74,
|
| 94 |
+
75,
|
| 95 |
+
76,
|
| 96 |
+
77,
|
| 97 |
+
78,
|
| 98 |
+
79,
|
| 99 |
+
80,
|
| 100 |
+
81,
|
| 101 |
+
82,
|
| 102 |
+
83,
|
| 103 |
+
84,
|
| 104 |
+
85,
|
| 105 |
+
86,
|
| 106 |
+
87,
|
| 107 |
+
88,
|
| 108 |
+
89,
|
| 109 |
+
90,
|
| 110 |
+
91,
|
| 111 |
+
92,
|
| 112 |
+
93,
|
| 113 |
+
94,
|
| 114 |
+
95,
|
| 115 |
+
96,
|
| 116 |
+
97,
|
| 117 |
+
98,
|
| 118 |
+
99,
|
| 119 |
+
100,
|
| 120 |
+
101,
|
| 121 |
+
102,
|
| 122 |
+
103,
|
| 123 |
+
104,
|
| 124 |
+
105,
|
| 125 |
+
106,
|
| 126 |
+
107,
|
| 127 |
+
108,
|
| 128 |
+
109,
|
| 129 |
+
110,
|
| 130 |
+
111,
|
| 131 |
+
112,
|
| 132 |
+
113,
|
| 133 |
+
114,
|
| 134 |
+
115,
|
| 135 |
+
116,
|
| 136 |
+
117,
|
| 137 |
+
118,
|
| 138 |
+
119,
|
| 139 |
+
120,
|
| 140 |
+
121,
|
| 141 |
+
122,
|
| 142 |
+
123,
|
| 143 |
+
124,
|
| 144 |
+
125,
|
| 145 |
+
126,
|
| 146 |
+
127,
|
| 147 |
+
128,
|
| 148 |
+
129,
|
| 149 |
+
130,
|
| 150 |
+
131,
|
| 151 |
+
132,
|
| 152 |
+
133,
|
| 153 |
+
134,
|
| 154 |
+
135,
|
| 155 |
+
136,
|
| 156 |
+
137,
|
| 157 |
+
138,
|
| 158 |
+
139,
|
| 159 |
+
140,
|
| 160 |
+
141,
|
| 161 |
+
142,
|
| 162 |
+
143,
|
| 163 |
+
144,
|
| 164 |
+
145,
|
| 165 |
+
146,
|
| 166 |
+
147,
|
| 167 |
+
148,
|
| 168 |
+
149,
|
| 169 |
+
150,
|
| 170 |
+
151,
|
| 171 |
+
152,
|
| 172 |
+
153,
|
| 173 |
+
154,
|
| 174 |
+
155,
|
| 175 |
+
156,
|
| 176 |
+
157,
|
| 177 |
+
158
|
| 178 |
+
]
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"weight_decay": 0.0,
|
| 182 |
+
"lr": 1.8865999845374793e-06,
|
| 183 |
+
"betas": [
|
| 184 |
+
0.9,
|
| 185 |
+
0.999
|
| 186 |
+
],
|
| 187 |
+
"eps": 1e-08,
|
| 188 |
+
"amsgrad": false,
|
| 189 |
+
"maximize": false,
|
| 190 |
+
"foreach": null,
|
| 191 |
+
"capturable": false,
|
| 192 |
+
"differentiable": false,
|
| 193 |
+
"fused": null,
|
| 194 |
+
"decoupled_weight_decay": true,
|
| 195 |
+
"initial_lr": 0.0001,
|
| 196 |
+
"params": [
|
| 197 |
+
159,
|
| 198 |
+
160,
|
| 199 |
+
161,
|
| 200 |
+
162,
|
| 201 |
+
163,
|
| 202 |
+
164,
|
| 203 |
+
165,
|
| 204 |
+
166,
|
| 205 |
+
167,
|
| 206 |
+
168,
|
| 207 |
+
169,
|
| 208 |
+
170,
|
| 209 |
+
171,
|
| 210 |
+
172,
|
| 211 |
+
173,
|
| 212 |
+
174,
|
| 213 |
+
175,
|
| 214 |
+
176,
|
| 215 |
+
177,
|
| 216 |
+
178,
|
| 217 |
+
179,
|
| 218 |
+
180,
|
| 219 |
+
181,
|
| 220 |
+
182,
|
| 221 |
+
183,
|
| 222 |
+
184,
|
| 223 |
+
185,
|
| 224 |
+
186,
|
| 225 |
+
187,
|
| 226 |
+
188,
|
| 227 |
+
189,
|
| 228 |
+
190,
|
| 229 |
+
191,
|
| 230 |
+
192,
|
| 231 |
+
193,
|
| 232 |
+
194,
|
| 233 |
+
195,
|
| 234 |
+
196,
|
| 235 |
+
197,
|
| 236 |
+
198,
|
| 237 |
+
199,
|
| 238 |
+
200,
|
| 239 |
+
201,
|
| 240 |
+
202,
|
| 241 |
+
203,
|
| 242 |
+
204,
|
| 243 |
+
205,
|
| 244 |
+
206,
|
| 245 |
+
207,
|
| 246 |
+
208,
|
| 247 |
+
209,
|
| 248 |
+
210,
|
| 249 |
+
211,
|
| 250 |
+
212,
|
| 251 |
+
213,
|
| 252 |
+
214,
|
| 253 |
+
215,
|
| 254 |
+
216,
|
| 255 |
+
217,
|
| 256 |
+
218,
|
| 257 |
+
219,
|
| 258 |
+
220,
|
| 259 |
+
221,
|
| 260 |
+
222,
|
| 261 |
+
223,
|
| 262 |
+
224,
|
| 263 |
+
225,
|
| 264 |
+
226,
|
| 265 |
+
227,
|
| 266 |
+
228,
|
| 267 |
+
229,
|
| 268 |
+
230,
|
| 269 |
+
231,
|
| 270 |
+
232,
|
| 271 |
+
233,
|
| 272 |
+
234,
|
| 273 |
+
235,
|
| 274 |
+
236,
|
| 275 |
+
237,
|
| 276 |
+
238,
|
| 277 |
+
239,
|
| 278 |
+
240,
|
| 279 |
+
241,
|
| 280 |
+
242,
|
| 281 |
+
243,
|
| 282 |
+
244,
|
| 283 |
+
245,
|
| 284 |
+
246,
|
| 285 |
+
247,
|
| 286 |
+
248,
|
| 287 |
+
249,
|
| 288 |
+
250,
|
| 289 |
+
251,
|
| 290 |
+
252,
|
| 291 |
+
253,
|
| 292 |
+
254,
|
| 293 |
+
255,
|
| 294 |
+
256,
|
| 295 |
+
257,
|
| 296 |
+
258,
|
| 297 |
+
259,
|
| 298 |
+
260,
|
| 299 |
+
261,
|
| 300 |
+
262,
|
| 301 |
+
263,
|
| 302 |
+
264,
|
| 303 |
+
265,
|
| 304 |
+
266,
|
| 305 |
+
267,
|
| 306 |
+
268,
|
| 307 |
+
269,
|
| 308 |
+
270,
|
| 309 |
+
271,
|
| 310 |
+
272,
|
| 311 |
+
273,
|
| 312 |
+
274,
|
| 313 |
+
275,
|
| 314 |
+
276,
|
| 315 |
+
277,
|
| 316 |
+
278,
|
| 317 |
+
279,
|
| 318 |
+
280,
|
| 319 |
+
281,
|
| 320 |
+
282,
|
| 321 |
+
283,
|
| 322 |
+
284,
|
| 323 |
+
285,
|
| 324 |
+
286,
|
| 325 |
+
287,
|
| 326 |
+
288,
|
| 327 |
+
289,
|
| 328 |
+
290,
|
| 329 |
+
291,
|
| 330 |
+
292,
|
| 331 |
+
293,
|
| 332 |
+
294,
|
| 333 |
+
295,
|
| 334 |
+
296,
|
| 335 |
+
297,
|
| 336 |
+
298,
|
| 337 |
+
299,
|
| 338 |
+
300,
|
| 339 |
+
301,
|
| 340 |
+
302,
|
| 341 |
+
303,
|
| 342 |
+
304,
|
| 343 |
+
305,
|
| 344 |
+
306,
|
| 345 |
+
307,
|
| 346 |
+
308,
|
| 347 |
+
309,
|
| 348 |
+
310,
|
| 349 |
+
311,
|
| 350 |
+
312,
|
| 351 |
+
313,
|
| 352 |
+
314,
|
| 353 |
+
315,
|
| 354 |
+
316,
|
| 355 |
+
317,
|
| 356 |
+
318,
|
| 357 |
+
319,
|
| 358 |
+
320
|
| 359 |
+
]
|
| 360 |
+
}
|
| 361 |
+
]
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00/training_state/training_step.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"step": 55000,
|
| 3 |
+
"num_processes": 1,
|
| 4 |
+
"batch_size": 64
|
| 5 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/action_space_manifest.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 2,
|
| 3 |
+
"action_space": "ee_abs_rot6d",
|
| 4 |
+
"action_views": [
|
| 5 |
+
"ee_abs_rot6d"
|
| 6 |
+
],
|
| 7 |
+
"source_feature": "action.ee_abs_rot6d",
|
| 8 |
+
"canonical_feature": "action",
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"shape": [
|
| 11 |
+
10
|
| 12 |
+
],
|
| 13 |
+
"names": [
|
| 14 |
+
"x",
|
| 15 |
+
"y",
|
| 16 |
+
"z",
|
| 17 |
+
"r_col0_x",
|
| 18 |
+
"r_col0_y",
|
| 19 |
+
"r_col0_z",
|
| 20 |
+
"r_col1_x",
|
| 21 |
+
"r_col1_y",
|
| 22 |
+
"r_col1_z",
|
| 23 |
+
"gripper"
|
| 24 |
+
],
|
| 25 |
+
"dataset_repo_id": "Whalswp/INSIGHTfixposV4_filtered_multispace_v2",
|
| 26 |
+
"dataset_revision": "v3.0",
|
| 27 |
+
"dataset_total_frames": 218367,
|
| 28 |
+
"dataset_total_episodes": 4930,
|
| 29 |
+
"dataset_fps": 10,
|
| 30 |
+
"stats_sha256": "71698c7337070aa8267df5aea7ec08bc00d3925510f2649bc20c9201eeb669e4",
|
| 31 |
+
"stats": {
|
| 32 |
+
"min": [
|
| 33 |
+
-0.21784618496894836,
|
| 34 |
+
-0.4474811851978302,
|
| 35 |
+
0.1702737659215927,
|
| 36 |
+
-0.9999986290931702,
|
| 37 |
+
-0.9999991655349731,
|
| 38 |
+
-0.9999999403953552,
|
| 39 |
+
-0.9999990463256836,
|
| 40 |
+
-0.9999998211860657,
|
| 41 |
+
-0.9999988079071045,
|
| 42 |
+
0.0
|
| 43 |
+
],
|
| 44 |
+
"max": [
|
| 45 |
+
0.6283698678016663,
|
| 46 |
+
0.4420371949672699,
|
| 47 |
+
1.051027774810791,
|
| 48 |
+
0.9999999403953552,
|
| 49 |
+
0.9999995231628418,
|
| 50 |
+
1.0,
|
| 51 |
+
0.9999995231628418,
|
| 52 |
+
1.0,
|
| 53 |
+
0.9999996423721313,
|
| 54 |
+
0.03999999910593033
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
0.4040228037735655,
|
| 58 |
+
-0.05247618696989652,
|
| 59 |
+
0.6993459771218912,
|
| 60 |
+
0.07011111991957117,
|
| 61 |
+
-0.03520558904460197,
|
| 62 |
+
0.14470242846953205,
|
| 63 |
+
0.05491166606739672,
|
| 64 |
+
-0.19073058893378805,
|
| 65 |
+
-0.06988117661871228,
|
| 66 |
+
0.021167300266524632
|
| 67 |
+
],
|
| 68 |
+
"std": [
|
| 69 |
+
0.11861927913357073,
|
| 70 |
+
0.11318943557281885,
|
| 71 |
+
0.17849160646987516,
|
| 72 |
+
0.4812528791886511,
|
| 73 |
+
0.7487196258736938,
|
| 74 |
+
0.4251126804030219,
|
| 75 |
+
0.47797229807769137,
|
| 76 |
+
0.6267695346407992,
|
| 77 |
+
0.5782954306815554,
|
| 78 |
+
0.01996590431050817
|
| 79 |
+
],
|
| 80 |
+
"count": [
|
| 81 |
+
218367
|
| 82 |
+
],
|
| 83 |
+
"q01": [
|
| 84 |
+
0.23988881827972064,
|
| 85 |
+
-0.10387461883034811,
|
| 86 |
+
0.6297243923476871,
|
| 87 |
+
-0.43622841955353464,
|
| 88 |
+
-0.6885486527617446,
|
| 89 |
+
-0.14103555388039019,
|
| 90 |
+
-0.4327210063987595,
|
| 91 |
+
-0.9304790915716145,
|
| 92 |
+
-0.3465462258490417,
|
| 93 |
+
-1.000000013351432e-10
|
| 94 |
+
],
|
| 95 |
+
"q10": [
|
| 96 |
+
0.3042306436755216,
|
| 97 |
+
-0.09609991620622624,
|
| 98 |
+
0.6394063072781145,
|
| 99 |
+
-0.3351306352998669,
|
| 100 |
+
-0.5751963015002924,
|
| 101 |
+
-0.08490621283307866,
|
| 102 |
+
-0.33849701676224275,
|
| 103 |
+
-0.8340557712529717,
|
| 104 |
+
-0.29760290790884514,
|
| 105 |
+
-1.000000013351432e-10
|
| 106 |
+
],
|
| 107 |
+
"q50": [
|
| 108 |
+
0.4160225263528291,
|
| 109 |
+
-0.06267459152989589,
|
| 110 |
+
0.6811777491060801,
|
| 111 |
+
0.0543536902230377,
|
| 112 |
+
-0.14012251058819217,
|
| 113 |
+
0.04772394280004727,
|
| 114 |
+
0.03838119138716219,
|
| 115 |
+
-0.14865169094195635,
|
| 116 |
+
-0.2073069401172425,
|
| 117 |
+
0.020772594934870346
|
| 118 |
+
],
|
| 119 |
+
"q90": [
|
| 120 |
+
0.46641008755679864,
|
| 121 |
+
0.020233143101890064,
|
| 122 |
+
0.8095135405259374,
|
| 123 |
+
0.48172401592474906,
|
| 124 |
+
0.7398737043070319,
|
| 125 |
+
0.5970841215636613,
|
| 126 |
+
0.4674752875999555,
|
| 127 |
+
0.36281754777672676,
|
| 128 |
+
0.5033361883834496,
|
| 129 |
+
0.039998362213352394
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
0.47320723171849244,
|
| 133 |
+
0.04114262476135705,
|
| 134 |
+
0.8467967259270389,
|
| 135 |
+
0.5867781409980988,
|
| 136 |
+
0.8529584859257228,
|
| 137 |
+
0.7953936054341789,
|
| 138 |
+
0.5768269858732034,
|
| 139 |
+
0.49353349323389695,
|
| 140 |
+
0.7168914440776504,
|
| 141 |
+
0.03999983541667277
|
| 142 |
+
]
|
| 143 |
+
}
|
| 144 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/phase_schedule.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 1,
|
| 3 |
+
"step_interval": "[start_step, until_step)",
|
| 4 |
+
"total_steps": 60000,
|
| 5 |
+
"optimizer_lifecycle": "single_continuous_optimizer",
|
| 6 |
+
"scheduler_lifecycle": "single_continuous_scheduler",
|
| 7 |
+
"phases": [
|
| 8 |
+
{
|
| 9 |
+
"index": 0,
|
| 10 |
+
"name": "rscl_rkd_cosine_decay_60K",
|
| 11 |
+
"start_step": 0,
|
| 12 |
+
"until_step": 60000,
|
| 13 |
+
"policy": {
|
| 14 |
+
"rkd_enabled": true,
|
| 15 |
+
"rkd_fm_loss_weight": 1.0,
|
| 16 |
+
"rkd_loss_weight": 1.0,
|
| 17 |
+
"rkd_loss_weight_end": 0.0,
|
| 18 |
+
"rkd_loss_weight_schedule": "cosine",
|
| 19 |
+
"rkd_distance_weight": 1.0,
|
| 20 |
+
"rkd_angle_weight": 2.0
|
| 21 |
+
},
|
| 22 |
+
"trainable": {
|
| 23 |
+
"tune_llm": false,
|
| 24 |
+
"tune_visual": false,
|
| 25 |
+
"tune_top_llm_layers": 0,
|
| 26 |
+
"tune_projector": true,
|
| 27 |
+
"tune_diffusion_model": true,
|
| 28 |
+
"tune_vlln": true
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/action_space_manifest.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 2,
|
| 3 |
+
"action_space": "ee_abs_rot6d",
|
| 4 |
+
"action_views": [
|
| 5 |
+
"ee_abs_rot6d"
|
| 6 |
+
],
|
| 7 |
+
"source_feature": "action.ee_abs_rot6d",
|
| 8 |
+
"canonical_feature": "action",
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"shape": [
|
| 11 |
+
10
|
| 12 |
+
],
|
| 13 |
+
"names": [
|
| 14 |
+
"x",
|
| 15 |
+
"y",
|
| 16 |
+
"z",
|
| 17 |
+
"r_col0_x",
|
| 18 |
+
"r_col0_y",
|
| 19 |
+
"r_col0_z",
|
| 20 |
+
"r_col1_x",
|
| 21 |
+
"r_col1_y",
|
| 22 |
+
"r_col1_z",
|
| 23 |
+
"gripper"
|
| 24 |
+
],
|
| 25 |
+
"dataset_repo_id": "Whalswp/INSIGHTfixposV4_filtered_multispace_v2",
|
| 26 |
+
"dataset_revision": "v3.0",
|
| 27 |
+
"dataset_total_frames": 218367,
|
| 28 |
+
"dataset_total_episodes": 4930,
|
| 29 |
+
"dataset_fps": 10,
|
| 30 |
+
"stats_sha256": "71698c7337070aa8267df5aea7ec08bc00d3925510f2649bc20c9201eeb669e4",
|
| 31 |
+
"stats": {
|
| 32 |
+
"min": [
|
| 33 |
+
-0.21784618496894836,
|
| 34 |
+
-0.4474811851978302,
|
| 35 |
+
0.1702737659215927,
|
| 36 |
+
-0.9999986290931702,
|
| 37 |
+
-0.9999991655349731,
|
| 38 |
+
-0.9999999403953552,
|
| 39 |
+
-0.9999990463256836,
|
| 40 |
+
-0.9999998211860657,
|
| 41 |
+
-0.9999988079071045,
|
| 42 |
+
0.0
|
| 43 |
+
],
|
| 44 |
+
"max": [
|
| 45 |
+
0.6283698678016663,
|
| 46 |
+
0.4420371949672699,
|
| 47 |
+
1.051027774810791,
|
| 48 |
+
0.9999999403953552,
|
| 49 |
+
0.9999995231628418,
|
| 50 |
+
1.0,
|
| 51 |
+
0.9999995231628418,
|
| 52 |
+
1.0,
|
| 53 |
+
0.9999996423721313,
|
| 54 |
+
0.03999999910593033
|
| 55 |
+
],
|
| 56 |
+
"mean": [
|
| 57 |
+
0.4040228037735655,
|
| 58 |
+
-0.05247618696989652,
|
| 59 |
+
0.6993459771218912,
|
| 60 |
+
0.07011111991957117,
|
| 61 |
+
-0.03520558904460197,
|
| 62 |
+
0.14470242846953205,
|
| 63 |
+
0.05491166606739672,
|
| 64 |
+
-0.19073058893378805,
|
| 65 |
+
-0.06988117661871228,
|
| 66 |
+
0.021167300266524632
|
| 67 |
+
],
|
| 68 |
+
"std": [
|
| 69 |
+
0.11861927913357073,
|
| 70 |
+
0.11318943557281885,
|
| 71 |
+
0.17849160646987516,
|
| 72 |
+
0.4812528791886511,
|
| 73 |
+
0.7487196258736938,
|
| 74 |
+
0.4251126804030219,
|
| 75 |
+
0.47797229807769137,
|
| 76 |
+
0.6267695346407992,
|
| 77 |
+
0.5782954306815554,
|
| 78 |
+
0.01996590431050817
|
| 79 |
+
],
|
| 80 |
+
"count": [
|
| 81 |
+
218367
|
| 82 |
+
],
|
| 83 |
+
"q01": [
|
| 84 |
+
0.23988881827972064,
|
| 85 |
+
-0.10387461883034811,
|
| 86 |
+
0.6297243923476871,
|
| 87 |
+
-0.43622841955353464,
|
| 88 |
+
-0.6885486527617446,
|
| 89 |
+
-0.14103555388039019,
|
| 90 |
+
-0.4327210063987595,
|
| 91 |
+
-0.9304790915716145,
|
| 92 |
+
-0.3465462258490417,
|
| 93 |
+
-1.000000013351432e-10
|
| 94 |
+
],
|
| 95 |
+
"q10": [
|
| 96 |
+
0.3042306436755216,
|
| 97 |
+
-0.09609991620622624,
|
| 98 |
+
0.6394063072781145,
|
| 99 |
+
-0.3351306352998669,
|
| 100 |
+
-0.5751963015002924,
|
| 101 |
+
-0.08490621283307866,
|
| 102 |
+
-0.33849701676224275,
|
| 103 |
+
-0.8340557712529717,
|
| 104 |
+
-0.29760290790884514,
|
| 105 |
+
-1.000000013351432e-10
|
| 106 |
+
],
|
| 107 |
+
"q50": [
|
| 108 |
+
0.4160225263528291,
|
| 109 |
+
-0.06267459152989589,
|
| 110 |
+
0.6811777491060801,
|
| 111 |
+
0.0543536902230377,
|
| 112 |
+
-0.14012251058819217,
|
| 113 |
+
0.04772394280004727,
|
| 114 |
+
0.03838119138716219,
|
| 115 |
+
-0.14865169094195635,
|
| 116 |
+
-0.2073069401172425,
|
| 117 |
+
0.020772594934870346
|
| 118 |
+
],
|
| 119 |
+
"q90": [
|
| 120 |
+
0.46641008755679864,
|
| 121 |
+
0.020233143101890064,
|
| 122 |
+
0.8095135405259374,
|
| 123 |
+
0.48172401592474906,
|
| 124 |
+
0.7398737043070319,
|
| 125 |
+
0.5970841215636613,
|
| 126 |
+
0.4674752875999555,
|
| 127 |
+
0.36281754777672676,
|
| 128 |
+
0.5033361883834496,
|
| 129 |
+
0.039998362213352394
|
| 130 |
+
],
|
| 131 |
+
"q99": [
|
| 132 |
+
0.47320723171849244,
|
| 133 |
+
0.04114262476135705,
|
| 134 |
+
0.8467967259270389,
|
| 135 |
+
0.5867781409980988,
|
| 136 |
+
0.8529584859257228,
|
| 137 |
+
0.7953936054341789,
|
| 138 |
+
0.5768269858732034,
|
| 139 |
+
0.49353349323389695,
|
| 140 |
+
0.7168914440776504,
|
| 141 |
+
0.03999983541667277
|
| 142 |
+
]
|
| 143 |
+
}
|
| 144 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/config.json
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"type": "groot_rkd",
|
| 3 |
+
"n_obs_steps": 1,
|
| 4 |
+
"input_features": {
|
| 5 |
+
"observation.state": {
|
| 6 |
+
"type": "STATE",
|
| 7 |
+
"shape": [
|
| 8 |
+
16
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
"observation.images.wrist": {
|
| 12 |
+
"type": "VISUAL",
|
| 13 |
+
"shape": [
|
| 14 |
+
3,
|
| 15 |
+
224,
|
| 16 |
+
224
|
| 17 |
+
]
|
| 18 |
+
},
|
| 19 |
+
"observation.images.right_shoulder": {
|
| 20 |
+
"type": "VISUAL",
|
| 21 |
+
"shape": [
|
| 22 |
+
3,
|
| 23 |
+
224,
|
| 24 |
+
224
|
| 25 |
+
]
|
| 26 |
+
},
|
| 27 |
+
"observation.images.guide": {
|
| 28 |
+
"type": "VISUAL",
|
| 29 |
+
"shape": [
|
| 30 |
+
3,
|
| 31 |
+
224,
|
| 32 |
+
224
|
| 33 |
+
]
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"output_features": {
|
| 37 |
+
"action": {
|
| 38 |
+
"type": "ACTION",
|
| 39 |
+
"shape": [
|
| 40 |
+
10
|
| 41 |
+
]
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"device": "cuda",
|
| 45 |
+
"use_amp": false,
|
| 46 |
+
"use_peft": false,
|
| 47 |
+
"push_to_hub": false,
|
| 48 |
+
"repo_id": null,
|
| 49 |
+
"private": null,
|
| 50 |
+
"tags": null,
|
| 51 |
+
"license": null,
|
| 52 |
+
"pretrained_path": "/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model",
|
| 53 |
+
"pretrained_revision": null,
|
| 54 |
+
"chunk_size": 16,
|
| 55 |
+
"n_action_steps": 16,
|
| 56 |
+
"max_state_dim": 132,
|
| 57 |
+
"max_action_dim": 132,
|
| 58 |
+
"normalization_mapping": {
|
| 59 |
+
"VISUAL": "IDENTITY",
|
| 60 |
+
"STATE": "IDENTITY",
|
| 61 |
+
"ACTION": "IDENTITY"
|
| 62 |
+
},
|
| 63 |
+
"base_model_path": "nvidia/GR00T-N1.7-3B",
|
| 64 |
+
"action_decode_transform": null,
|
| 65 |
+
"embodiment_tag": "new_embodiment",
|
| 66 |
+
"tune_llm": false,
|
| 67 |
+
"tune_visual": false,
|
| 68 |
+
"tune_projector": true,
|
| 69 |
+
"tune_diffusion_model": true,
|
| 70 |
+
"tune_vlln": true,
|
| 71 |
+
"tune_top_llm_layers": 0,
|
| 72 |
+
"num_inference_timesteps": null,
|
| 73 |
+
"rtc_ramp_rate": null,
|
| 74 |
+
"use_flash_attention": false,
|
| 75 |
+
"use_relative_actions": false,
|
| 76 |
+
"relative_exclude_joints": [],
|
| 77 |
+
"optimizer_lr": 0.0001,
|
| 78 |
+
"optimizer_betas": [
|
| 79 |
+
0.9,
|
| 80 |
+
0.999
|
| 81 |
+
],
|
| 82 |
+
"optimizer_eps": 1e-08,
|
| 83 |
+
"optimizer_weight_decay": 1e-05,
|
| 84 |
+
"warmup_steps": 3000,
|
| 85 |
+
"warmup_ratio": 0.05,
|
| 86 |
+
"use_bf16": true,
|
| 87 |
+
"model_params_fp32": true,
|
| 88 |
+
"image_size": [
|
| 89 |
+
256,
|
| 90 |
+
256
|
| 91 |
+
],
|
| 92 |
+
"tokenizer_assets_repo": null,
|
| 93 |
+
"lora_rank": 0,
|
| 94 |
+
"lora_alpha": 16,
|
| 95 |
+
"lora_dropout": 0.1,
|
| 96 |
+
"lora_full_model": false,
|
| 97 |
+
"video_backend": "decord",
|
| 98 |
+
"balance_dataset_weights": true,
|
| 99 |
+
"balance_trajectory_weights": true,
|
| 100 |
+
"dataset_paths": null,
|
| 101 |
+
"output_dir": "./tmp/gr00t",
|
| 102 |
+
"save_steps": 1000,
|
| 103 |
+
"max_steps": 10000,
|
| 104 |
+
"batch_size": 32,
|
| 105 |
+
"dataloader_num_workers": 8,
|
| 106 |
+
"report_to": "wandb",
|
| 107 |
+
"resume": false,
|
| 108 |
+
"action_expert_num_layers": 16,
|
| 109 |
+
"rkd_enabled": true,
|
| 110 |
+
"rkd_vae_checkpoint": "/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11",
|
| 111 |
+
"rkd_student_pooling": "attention",
|
| 112 |
+
"rkd_student_attention_hidden_dim": 512,
|
| 113 |
+
"rkd_student_attention_output_dim": 512,
|
| 114 |
+
"rkd_fm_loss_weight": 1.0,
|
| 115 |
+
"rkd_loss_weight": 1.0,
|
| 116 |
+
"rkd_distance_weight": 1.0,
|
| 117 |
+
"rkd_angle_weight": 2.0
|
| 118 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/phase_schedule.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 1,
|
| 3 |
+
"step_interval": "[start_step, until_step)",
|
| 4 |
+
"total_steps": 60000,
|
| 5 |
+
"optimizer_lifecycle": "single_continuous_optimizer",
|
| 6 |
+
"scheduler_lifecycle": "single_continuous_scheduler",
|
| 7 |
+
"phases": [
|
| 8 |
+
{
|
| 9 |
+
"index": 0,
|
| 10 |
+
"name": "rscl_rkd_cosine_decay_60K",
|
| 11 |
+
"start_step": 0,
|
| 12 |
+
"until_step": 60000,
|
| 13 |
+
"policy": {
|
| 14 |
+
"rkd_enabled": true,
|
| 15 |
+
"rkd_fm_loss_weight": 1.0,
|
| 16 |
+
"rkd_loss_weight": 1.0,
|
| 17 |
+
"rkd_loss_weight_end": 0.0,
|
| 18 |
+
"rkd_loss_weight_schedule": "cosine",
|
| 19 |
+
"rkd_distance_weight": 1.0,
|
| 20 |
+
"rkd_angle_weight": 2.0
|
| 21 |
+
},
|
| 22 |
+
"trainable": {
|
| 23 |
+
"tune_llm": false,
|
| 24 |
+
"tune_visual": false,
|
| 25 |
+
"tune_top_llm_layers": 0,
|
| 26 |
+
"tune_projector": true,
|
| 27 |
+
"tune_diffusion_model": true,
|
| 28 |
+
"tune_vlln": true
|
| 29 |
+
}
|
| 30 |
+
}
|
| 31 |
+
]
|
| 32 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/prompt_manifest.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 1,
|
| 3 |
+
"prompt_set": "detailed",
|
| 4 |
+
"source_file": "task_prompts.json",
|
| 5 |
+
"source_sha256": "0ba48fb372da9f49dcfcd7dcc2da8cce6ce991d3661060e664a104778d1ffacc",
|
| 6 |
+
"mapping_sha256": "f71954786e94cdeceb135dde09fdc6b65db0b87ab3b09d25060129d0f0fde018",
|
| 7 |
+
"dataset_repo_id": "Whalswp/INSIGHTfixposV4_filtered_multispace_v2",
|
| 8 |
+
"dataset_revision": "v3.0",
|
| 9 |
+
"task_count": 13,
|
| 10 |
+
"task_codes": [
|
| 11 |
+
"5f",
|
| 12 |
+
"5g",
|
| 13 |
+
"1ext",
|
| 14 |
+
"3b",
|
| 15 |
+
"5b",
|
| 16 |
+
"3a",
|
| 17 |
+
"3c",
|
| 18 |
+
"5h",
|
| 19 |
+
"5d",
|
| 20 |
+
"3d",
|
| 21 |
+
"5e",
|
| 22 |
+
"5a",
|
| 23 |
+
"5c"
|
| 24 |
+
],
|
| 25 |
+
"prompts": {
|
| 26 |
+
"5f": "Close the bottle in clockwise direction.",
|
| 27 |
+
"5g": "Grip the cap on the sides indicated by the 'squeeze' arrow and open the bottle in clockwise direction.",
|
| 28 |
+
"1ext": "Find the arrow guide and open the indicated drawer.",
|
| 29 |
+
"3b": "Open the door, rotate counter-clockwise and push.",
|
| 30 |
+
"5b": "Open the bottle in counter-clockwise direction.",
|
| 31 |
+
"3a": "Open the door, rotate clockwise and push.",
|
| 32 |
+
"3c": "Open the door, rotate clockwise and pull.",
|
| 33 |
+
"5h": "Close the bottle in counter-clockwise direction.",
|
| 34 |
+
"5d": "Close the bottle in clockwise direction.",
|
| 35 |
+
"3d": "Open the door, rotate counter-clockwise and pull.",
|
| 36 |
+
"5e": "Close the bottle in counter-clockwise direction.",
|
| 37 |
+
"5a": "Grip the cap on the sides indicated by the 'squeeze' arrow and open the bottle in counter-clockwise direction.",
|
| 38 |
+
"5c": "Open the bottle in clockwise direction."
|
| 39 |
+
}
|
| 40 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/train_config.json
ADDED
|
@@ -0,0 +1,269 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"dataset": {
|
| 3 |
+
"repo_id": "Whalswp/INSIGHTfixposV4_filtered_multispace_v2",
|
| 4 |
+
"root": "/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2",
|
| 5 |
+
"episodes": null,
|
| 6 |
+
"image_transforms": {
|
| 7 |
+
"enable": false,
|
| 8 |
+
"max_num_transforms": 3,
|
| 9 |
+
"random_order": false,
|
| 10 |
+
"tfs": {
|
| 11 |
+
"brightness": {
|
| 12 |
+
"weight": 1.0,
|
| 13 |
+
"type": "ColorJitter",
|
| 14 |
+
"kwargs": {
|
| 15 |
+
"brightness": [
|
| 16 |
+
0.8,
|
| 17 |
+
1.2
|
| 18 |
+
]
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"contrast": {
|
| 22 |
+
"weight": 1.0,
|
| 23 |
+
"type": "ColorJitter",
|
| 24 |
+
"kwargs": {
|
| 25 |
+
"contrast": [
|
| 26 |
+
0.8,
|
| 27 |
+
1.2
|
| 28 |
+
]
|
| 29 |
+
}
|
| 30 |
+
},
|
| 31 |
+
"saturation": {
|
| 32 |
+
"weight": 1.0,
|
| 33 |
+
"type": "ColorJitter",
|
| 34 |
+
"kwargs": {
|
| 35 |
+
"saturation": [
|
| 36 |
+
0.5,
|
| 37 |
+
1.5
|
| 38 |
+
]
|
| 39 |
+
}
|
| 40 |
+
},
|
| 41 |
+
"hue": {
|
| 42 |
+
"weight": 1.0,
|
| 43 |
+
"type": "ColorJitter",
|
| 44 |
+
"kwargs": {
|
| 45 |
+
"hue": [
|
| 46 |
+
-0.05,
|
| 47 |
+
0.05
|
| 48 |
+
]
|
| 49 |
+
}
|
| 50 |
+
},
|
| 51 |
+
"sharpness": {
|
| 52 |
+
"weight": 1.0,
|
| 53 |
+
"type": "SharpnessJitter",
|
| 54 |
+
"kwargs": {
|
| 55 |
+
"sharpness": [
|
| 56 |
+
0.5,
|
| 57 |
+
1.5
|
| 58 |
+
]
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"affine": {
|
| 62 |
+
"weight": 1.0,
|
| 63 |
+
"type": "RandomAffine",
|
| 64 |
+
"kwargs": {
|
| 65 |
+
"degrees": [
|
| 66 |
+
-5.0,
|
| 67 |
+
5.0
|
| 68 |
+
],
|
| 69 |
+
"translate": [
|
| 70 |
+
0.05,
|
| 71 |
+
0.05
|
| 72 |
+
]
|
| 73 |
+
}
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
},
|
| 77 |
+
"revision": null,
|
| 78 |
+
"use_imagenet_stats": true,
|
| 79 |
+
"video_backend": "torchcodec",
|
| 80 |
+
"return_uint8": false,
|
| 81 |
+
"depth_output_unit": "mm",
|
| 82 |
+
"streaming": false,
|
| 83 |
+
"eval_split": 0.0
|
| 84 |
+
},
|
| 85 |
+
"env": null,
|
| 86 |
+
"policy": {
|
| 87 |
+
"type": "groot_rkd",
|
| 88 |
+
"n_obs_steps": 1,
|
| 89 |
+
"input_features": {
|
| 90 |
+
"observation.state": {
|
| 91 |
+
"type": "STATE",
|
| 92 |
+
"shape": [
|
| 93 |
+
16
|
| 94 |
+
]
|
| 95 |
+
},
|
| 96 |
+
"observation.images.wrist": {
|
| 97 |
+
"type": "VISUAL",
|
| 98 |
+
"shape": [
|
| 99 |
+
3,
|
| 100 |
+
224,
|
| 101 |
+
224
|
| 102 |
+
]
|
| 103 |
+
},
|
| 104 |
+
"observation.images.right_shoulder": {
|
| 105 |
+
"type": "VISUAL",
|
| 106 |
+
"shape": [
|
| 107 |
+
3,
|
| 108 |
+
224,
|
| 109 |
+
224
|
| 110 |
+
]
|
| 111 |
+
},
|
| 112 |
+
"observation.images.guide": {
|
| 113 |
+
"type": "VISUAL",
|
| 114 |
+
"shape": [
|
| 115 |
+
3,
|
| 116 |
+
224,
|
| 117 |
+
224
|
| 118 |
+
]
|
| 119 |
+
}
|
| 120 |
+
},
|
| 121 |
+
"output_features": {
|
| 122 |
+
"action": {
|
| 123 |
+
"type": "ACTION",
|
| 124 |
+
"shape": [
|
| 125 |
+
10
|
| 126 |
+
]
|
| 127 |
+
}
|
| 128 |
+
},
|
| 129 |
+
"device": "cuda",
|
| 130 |
+
"use_amp": false,
|
| 131 |
+
"use_peft": false,
|
| 132 |
+
"push_to_hub": false,
|
| 133 |
+
"repo_id": null,
|
| 134 |
+
"private": null,
|
| 135 |
+
"tags": null,
|
| 136 |
+
"license": null,
|
| 137 |
+
"pretrained_path": "/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model",
|
| 138 |
+
"pretrained_revision": null,
|
| 139 |
+
"chunk_size": 16,
|
| 140 |
+
"n_action_steps": 16,
|
| 141 |
+
"max_state_dim": 132,
|
| 142 |
+
"max_action_dim": 132,
|
| 143 |
+
"normalization_mapping": {
|
| 144 |
+
"VISUAL": "IDENTITY",
|
| 145 |
+
"STATE": "IDENTITY",
|
| 146 |
+
"ACTION": "IDENTITY"
|
| 147 |
+
},
|
| 148 |
+
"base_model_path": "nvidia/GR00T-N1.7-3B",
|
| 149 |
+
"action_decode_transform": null,
|
| 150 |
+
"embodiment_tag": "new_embodiment",
|
| 151 |
+
"tune_llm": false,
|
| 152 |
+
"tune_visual": false,
|
| 153 |
+
"tune_projector": true,
|
| 154 |
+
"tune_diffusion_model": true,
|
| 155 |
+
"tune_vlln": true,
|
| 156 |
+
"tune_top_llm_layers": 0,
|
| 157 |
+
"num_inference_timesteps": null,
|
| 158 |
+
"rtc_ramp_rate": null,
|
| 159 |
+
"use_flash_attention": false,
|
| 160 |
+
"use_relative_actions": false,
|
| 161 |
+
"relative_exclude_joints": [],
|
| 162 |
+
"optimizer_lr": 0.0001,
|
| 163 |
+
"optimizer_betas": [
|
| 164 |
+
0.9,
|
| 165 |
+
0.999
|
| 166 |
+
],
|
| 167 |
+
"optimizer_eps": 1e-08,
|
| 168 |
+
"optimizer_weight_decay": 1e-05,
|
| 169 |
+
"warmup_steps": 3000,
|
| 170 |
+
"warmup_ratio": 0.05,
|
| 171 |
+
"use_bf16": true,
|
| 172 |
+
"model_params_fp32": true,
|
| 173 |
+
"image_size": [
|
| 174 |
+
256,
|
| 175 |
+
256
|
| 176 |
+
],
|
| 177 |
+
"tokenizer_assets_repo": null,
|
| 178 |
+
"lora_rank": 0,
|
| 179 |
+
"lora_alpha": 16,
|
| 180 |
+
"lora_dropout": 0.1,
|
| 181 |
+
"lora_full_model": false,
|
| 182 |
+
"video_backend": "decord",
|
| 183 |
+
"balance_dataset_weights": true,
|
| 184 |
+
"balance_trajectory_weights": true,
|
| 185 |
+
"dataset_paths": null,
|
| 186 |
+
"output_dir": "./tmp/gr00t",
|
| 187 |
+
"save_steps": 1000,
|
| 188 |
+
"max_steps": 10000,
|
| 189 |
+
"batch_size": 32,
|
| 190 |
+
"dataloader_num_workers": 8,
|
| 191 |
+
"report_to": "wandb",
|
| 192 |
+
"resume": false,
|
| 193 |
+
"action_expert_num_layers": 16,
|
| 194 |
+
"rkd_enabled": true,
|
| 195 |
+
"rkd_vae_checkpoint": "/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11",
|
| 196 |
+
"rkd_student_pooling": "attention",
|
| 197 |
+
"rkd_student_attention_hidden_dim": 512,
|
| 198 |
+
"rkd_student_attention_output_dim": 512,
|
| 199 |
+
"rkd_fm_loss_weight": 1.0,
|
| 200 |
+
"rkd_loss_weight": 1.0,
|
| 201 |
+
"rkd_distance_weight": 1.0,
|
| 202 |
+
"rkd_angle_weight": 2.0
|
| 203 |
+
},
|
| 204 |
+
"reward_model": null,
|
| 205 |
+
"output_dir": "/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K",
|
| 206 |
+
"job_name": "INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60",
|
| 207 |
+
"resume": true,
|
| 208 |
+
"seed": 42,
|
| 209 |
+
"cudnn_deterministic": false,
|
| 210 |
+
"num_workers": 4,
|
| 211 |
+
"batch_size": 64,
|
| 212 |
+
"prefetch_factor": 4,
|
| 213 |
+
"persistent_workers": true,
|
| 214 |
+
"steps": 60000,
|
| 215 |
+
"env_eval_freq": 20000,
|
| 216 |
+
"log_freq": 200,
|
| 217 |
+
"eval_steps": 0,
|
| 218 |
+
"max_eval_samples": 0,
|
| 219 |
+
"tolerance_s": 0.0001,
|
| 220 |
+
"save_checkpoint": true,
|
| 221 |
+
"save_freq": 20000,
|
| 222 |
+
"use_policy_training_preset": true,
|
| 223 |
+
"optimizer": {
|
| 224 |
+
"type": "adamw",
|
| 225 |
+
"lr": 0.0001,
|
| 226 |
+
"weight_decay": 1e-05,
|
| 227 |
+
"grad_clip_norm": 1.0,
|
| 228 |
+
"betas": [
|
| 229 |
+
0.9,
|
| 230 |
+
0.999
|
| 231 |
+
],
|
| 232 |
+
"eps": 1e-08
|
| 233 |
+
},
|
| 234 |
+
"scheduler": {
|
| 235 |
+
"type": "diffuser",
|
| 236 |
+
"num_warmup_steps": 3000,
|
| 237 |
+
"name": "cosine"
|
| 238 |
+
},
|
| 239 |
+
"eval": {
|
| 240 |
+
"n_episodes": 50,
|
| 241 |
+
"batch_size": 50,
|
| 242 |
+
"use_async_envs": true,
|
| 243 |
+
"recording": false,
|
| 244 |
+
"recording_repo_id": null,
|
| 245 |
+
"recording_private": false
|
| 246 |
+
},
|
| 247 |
+
"wandb": {
|
| 248 |
+
"enable": true,
|
| 249 |
+
"disable_artifact": true,
|
| 250 |
+
"project": "lerobot",
|
| 251 |
+
"entity": null,
|
| 252 |
+
"notes": null,
|
| 253 |
+
"run_id": "rs1egwv8",
|
| 254 |
+
"mode": null,
|
| 255 |
+
"add_tags": true
|
| 256 |
+
},
|
| 257 |
+
"peft": null,
|
| 258 |
+
"job": {
|
| 259 |
+
"target": null,
|
| 260 |
+
"image": "huggingface/lerobot-gpu:latest",
|
| 261 |
+
"timeout": "2d",
|
| 262 |
+
"detach": false,
|
| 263 |
+
"tags": []
|
| 264 |
+
},
|
| 265 |
+
"save_checkpoint_to_hub": false,
|
| 266 |
+
"sample_weighting": null,
|
| 267 |
+
"rename_map": {},
|
| 268 |
+
"checkpoint_path": "/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01"
|
| 269 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/prompt_manifest.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"schema_version": 1,
|
| 3 |
+
"prompt_set": "detailed",
|
| 4 |
+
"source_file": "task_prompts.json",
|
| 5 |
+
"source_sha256": "0ba48fb372da9f49dcfcd7dcc2da8cce6ce991d3661060e664a104778d1ffacc",
|
| 6 |
+
"mapping_sha256": "f71954786e94cdeceb135dde09fdc6b65db0b87ab3b09d25060129d0f0fde018",
|
| 7 |
+
"dataset_repo_id": "Whalswp/INSIGHTfixposV4_filtered_multispace_v2",
|
| 8 |
+
"dataset_revision": "v3.0",
|
| 9 |
+
"task_count": 13,
|
| 10 |
+
"task_codes": [
|
| 11 |
+
"5f",
|
| 12 |
+
"5g",
|
| 13 |
+
"1ext",
|
| 14 |
+
"3b",
|
| 15 |
+
"5b",
|
| 16 |
+
"3a",
|
| 17 |
+
"3c",
|
| 18 |
+
"5h",
|
| 19 |
+
"5d",
|
| 20 |
+
"3d",
|
| 21 |
+
"5e",
|
| 22 |
+
"5a",
|
| 23 |
+
"5c"
|
| 24 |
+
],
|
| 25 |
+
"prompts": {
|
| 26 |
+
"5f": "Close the bottle in clockwise direction.",
|
| 27 |
+
"5g": "Grip the cap on the sides indicated by the 'squeeze' arrow and open the bottle in clockwise direction.",
|
| 28 |
+
"1ext": "Find the arrow guide and open the indicated drawer.",
|
| 29 |
+
"3b": "Open the door, rotate counter-clockwise and push.",
|
| 30 |
+
"5b": "Open the bottle in counter-clockwise direction.",
|
| 31 |
+
"3a": "Open the door, rotate clockwise and push.",
|
| 32 |
+
"3c": "Open the door, rotate clockwise and pull.",
|
| 33 |
+
"5h": "Close the bottle in counter-clockwise direction.",
|
| 34 |
+
"5d": "Close the bottle in clockwise direction.",
|
| 35 |
+
"3d": "Open the door, rotate counter-clockwise and pull.",
|
| 36 |
+
"5e": "Close the bottle in counter-clockwise direction.",
|
| 37 |
+
"5a": "Grip the cap on the sides indicated by the 'squeeze' arrow and open the bottle in counter-clockwise direction.",
|
| 38 |
+
"5c": "Open the bottle in clockwise direction."
|
| 39 |
+
}
|
| 40 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/resolved_config.yaml
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
dataset:
|
| 2 |
+
repo_id: Whalswp/INSIGHTfixposV4_filtered_multispace_v2
|
| 3 |
+
root: /home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2
|
| 4 |
+
policy:
|
| 5 |
+
type: groot_rkd
|
| 6 |
+
device: cuda
|
| 7 |
+
chunk_size: 16
|
| 8 |
+
n_action_steps: 16
|
| 9 |
+
push_to_hub: false
|
| 10 |
+
warmup_steps: 3000
|
| 11 |
+
tune_llm: false
|
| 12 |
+
tune_visual: false
|
| 13 |
+
tune_top_llm_layers: 0
|
| 14 |
+
action_expert_num_layers: 16
|
| 15 |
+
tune_projector: true
|
| 16 |
+
tune_diffusion_model: true
|
| 17 |
+
tune_vlln: true
|
| 18 |
+
rkd_enabled: true
|
| 19 |
+
rkd_vae_checkpoint: /home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11
|
| 20 |
+
rkd_student_pooling: attention
|
| 21 |
+
rkd_student_attention_hidden_dim: 512
|
| 22 |
+
rkd_student_attention_output_dim: 512
|
| 23 |
+
rkd_fm_loss_weight: 1.0
|
| 24 |
+
rkd_loss_weight: 1.0
|
| 25 |
+
rkd_distance_weight: 1.0
|
| 26 |
+
rkd_angle_weight: 2.0
|
| 27 |
+
seed: 42
|
| 28 |
+
batch_size: 64
|
| 29 |
+
steps: 60000
|
| 30 |
+
log_freq: 200
|
| 31 |
+
output_dir: /home/ext_minje/groot_insight/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 32 |
+
job_name: INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60
|
| 33 |
+
wandb:
|
| 34 |
+
enable: true
|
| 35 |
+
disable_artifact: true
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/source_config.yaml
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# INSIGHT GR00T N1.7 RKD training with RS-CL-style full-training regularization.
|
| 2 |
+
# Common RKD values live in the top-level policy; the phase contains schedule overrides only.
|
| 3 |
+
insight:
|
| 4 |
+
checkpoint_interval: 5K
|
| 5 |
+
checkpoint_slots: 2
|
| 6 |
+
# Options: joint_abs | ee_abs_quat | ee_abs_rot6d | ee_delta
|
| 7 |
+
action_space: ee_abs_rot6d
|
| 8 |
+
# Options: coarse | detailed
|
| 9 |
+
prompt_set: detailed
|
| 10 |
+
save_steps: ["10K", "30K", "60K"]
|
| 11 |
+
phases:
|
| 12 |
+
- name: rscl_rkd_cosine_decay_60K
|
| 13 |
+
until_step: 60K
|
| 14 |
+
policy:
|
| 15 |
+
# Inherits RKD=1.0 below and follows a half-cosine decay to zero.
|
| 16 |
+
rkd_loss_weight_end: 0.0
|
| 17 |
+
rkd_loss_weight_schedule: cosine
|
| 18 |
+
|
| 19 |
+
dataset:
|
| 20 |
+
repo_id: Whalswp/INSIGHTfixposV4_filtered_multispace_v2
|
| 21 |
+
root: ${HOME}/INSIGHTfixposV4_filtered_multispace_v2
|
| 22 |
+
|
| 23 |
+
policy:
|
| 24 |
+
type: groot_rkd
|
| 25 |
+
device: cuda
|
| 26 |
+
chunk_size: 16
|
| 27 |
+
n_action_steps: 16
|
| 28 |
+
push_to_hub: false
|
| 29 |
+
# RS-CL GR00T uses exactly 3K warmup updates.
|
| 30 |
+
warmup_steps: 3000
|
| 31 |
+
|
| 32 |
+
# VLM
|
| 33 |
+
tune_llm: false
|
| 34 |
+
tune_visual: false
|
| 35 |
+
tune_top_llm_layers: 0
|
| 36 |
+
# Action Expert
|
| 37 |
+
action_expert_num_layers: 16
|
| 38 |
+
tune_projector: true
|
| 39 |
+
tune_diffusion_model: true
|
| 40 |
+
tune_vlln: true
|
| 41 |
+
|
| 42 |
+
# Frozen TimewarpVAE teacher and common RKD objective.
|
| 43 |
+
rkd_enabled: true
|
| 44 |
+
rkd_vae_checkpoint: ${HOME}/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11
|
| 45 |
+
rkd_student_pooling: attention # attention | mean
|
| 46 |
+
rkd_student_attention_hidden_dim: 512
|
| 47 |
+
rkd_student_attention_output_dim: 512
|
| 48 |
+
rkd_fm_loss_weight: 1.0
|
| 49 |
+
rkd_loss_weight: 1.0
|
| 50 |
+
rkd_distance_weight: 1.0
|
| 51 |
+
rkd_angle_weight: 2.0
|
| 52 |
+
|
| 53 |
+
seed: 42
|
| 54 |
+
# Single GPU/process, so this is also the global batch size.
|
| 55 |
+
batch_size: 64
|
| 56 |
+
steps: 60000
|
| 57 |
+
log_freq: 200
|
| 58 |
+
output_dir: ${HOME}/groot_insight/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 59 |
+
job_name: INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60
|
| 60 |
+
|
| 61 |
+
wandb:
|
| 62 |
+
enable: true
|
| 63 |
+
disable_artifact: true
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/training_state/optimizer_param_groups.json
ADDED
|
@@ -0,0 +1,361 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"lr": 0.0,
|
| 4 |
+
"betas": [
|
| 5 |
+
0.9,
|
| 6 |
+
0.999
|
| 7 |
+
],
|
| 8 |
+
"eps": 1e-08,
|
| 9 |
+
"weight_decay": 1e-05,
|
| 10 |
+
"amsgrad": false,
|
| 11 |
+
"maximize": false,
|
| 12 |
+
"foreach": null,
|
| 13 |
+
"capturable": false,
|
| 14 |
+
"differentiable": false,
|
| 15 |
+
"fused": null,
|
| 16 |
+
"decoupled_weight_decay": true,
|
| 17 |
+
"initial_lr": 0.0001,
|
| 18 |
+
"params": [
|
| 19 |
+
0,
|
| 20 |
+
1,
|
| 21 |
+
2,
|
| 22 |
+
3,
|
| 23 |
+
4,
|
| 24 |
+
5,
|
| 25 |
+
6,
|
| 26 |
+
7,
|
| 27 |
+
8,
|
| 28 |
+
9,
|
| 29 |
+
10,
|
| 30 |
+
11,
|
| 31 |
+
12,
|
| 32 |
+
13,
|
| 33 |
+
14,
|
| 34 |
+
15,
|
| 35 |
+
16,
|
| 36 |
+
17,
|
| 37 |
+
18,
|
| 38 |
+
19,
|
| 39 |
+
20,
|
| 40 |
+
21,
|
| 41 |
+
22,
|
| 42 |
+
23,
|
| 43 |
+
24,
|
| 44 |
+
25,
|
| 45 |
+
26,
|
| 46 |
+
27,
|
| 47 |
+
28,
|
| 48 |
+
29,
|
| 49 |
+
30,
|
| 50 |
+
31,
|
| 51 |
+
32,
|
| 52 |
+
33,
|
| 53 |
+
34,
|
| 54 |
+
35,
|
| 55 |
+
36,
|
| 56 |
+
37,
|
| 57 |
+
38,
|
| 58 |
+
39,
|
| 59 |
+
40,
|
| 60 |
+
41,
|
| 61 |
+
42,
|
| 62 |
+
43,
|
| 63 |
+
44,
|
| 64 |
+
45,
|
| 65 |
+
46,
|
| 66 |
+
47,
|
| 67 |
+
48,
|
| 68 |
+
49,
|
| 69 |
+
50,
|
| 70 |
+
51,
|
| 71 |
+
52,
|
| 72 |
+
53,
|
| 73 |
+
54,
|
| 74 |
+
55,
|
| 75 |
+
56,
|
| 76 |
+
57,
|
| 77 |
+
58,
|
| 78 |
+
59,
|
| 79 |
+
60,
|
| 80 |
+
61,
|
| 81 |
+
62,
|
| 82 |
+
63,
|
| 83 |
+
64,
|
| 84 |
+
65,
|
| 85 |
+
66,
|
| 86 |
+
67,
|
| 87 |
+
68,
|
| 88 |
+
69,
|
| 89 |
+
70,
|
| 90 |
+
71,
|
| 91 |
+
72,
|
| 92 |
+
73,
|
| 93 |
+
74,
|
| 94 |
+
75,
|
| 95 |
+
76,
|
| 96 |
+
77,
|
| 97 |
+
78,
|
| 98 |
+
79,
|
| 99 |
+
80,
|
| 100 |
+
81,
|
| 101 |
+
82,
|
| 102 |
+
83,
|
| 103 |
+
84,
|
| 104 |
+
85,
|
| 105 |
+
86,
|
| 106 |
+
87,
|
| 107 |
+
88,
|
| 108 |
+
89,
|
| 109 |
+
90,
|
| 110 |
+
91,
|
| 111 |
+
92,
|
| 112 |
+
93,
|
| 113 |
+
94,
|
| 114 |
+
95,
|
| 115 |
+
96,
|
| 116 |
+
97,
|
| 117 |
+
98,
|
| 118 |
+
99,
|
| 119 |
+
100,
|
| 120 |
+
101,
|
| 121 |
+
102,
|
| 122 |
+
103,
|
| 123 |
+
104,
|
| 124 |
+
105,
|
| 125 |
+
106,
|
| 126 |
+
107,
|
| 127 |
+
108,
|
| 128 |
+
109,
|
| 129 |
+
110,
|
| 130 |
+
111,
|
| 131 |
+
112,
|
| 132 |
+
113,
|
| 133 |
+
114,
|
| 134 |
+
115,
|
| 135 |
+
116,
|
| 136 |
+
117,
|
| 137 |
+
118,
|
| 138 |
+
119,
|
| 139 |
+
120,
|
| 140 |
+
121,
|
| 141 |
+
122,
|
| 142 |
+
123,
|
| 143 |
+
124,
|
| 144 |
+
125,
|
| 145 |
+
126,
|
| 146 |
+
127,
|
| 147 |
+
128,
|
| 148 |
+
129,
|
| 149 |
+
130,
|
| 150 |
+
131,
|
| 151 |
+
132,
|
| 152 |
+
133,
|
| 153 |
+
134,
|
| 154 |
+
135,
|
| 155 |
+
136,
|
| 156 |
+
137,
|
| 157 |
+
138,
|
| 158 |
+
139,
|
| 159 |
+
140,
|
| 160 |
+
141,
|
| 161 |
+
142,
|
| 162 |
+
143,
|
| 163 |
+
144,
|
| 164 |
+
145,
|
| 165 |
+
146,
|
| 166 |
+
147,
|
| 167 |
+
148,
|
| 168 |
+
149,
|
| 169 |
+
150,
|
| 170 |
+
151,
|
| 171 |
+
152,
|
| 172 |
+
153,
|
| 173 |
+
154,
|
| 174 |
+
155,
|
| 175 |
+
156,
|
| 176 |
+
157,
|
| 177 |
+
158
|
| 178 |
+
]
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"weight_decay": 0.0,
|
| 182 |
+
"lr": 0.0,
|
| 183 |
+
"betas": [
|
| 184 |
+
0.9,
|
| 185 |
+
0.999
|
| 186 |
+
],
|
| 187 |
+
"eps": 1e-08,
|
| 188 |
+
"amsgrad": false,
|
| 189 |
+
"maximize": false,
|
| 190 |
+
"foreach": null,
|
| 191 |
+
"capturable": false,
|
| 192 |
+
"differentiable": false,
|
| 193 |
+
"fused": null,
|
| 194 |
+
"decoupled_weight_decay": true,
|
| 195 |
+
"initial_lr": 0.0001,
|
| 196 |
+
"params": [
|
| 197 |
+
159,
|
| 198 |
+
160,
|
| 199 |
+
161,
|
| 200 |
+
162,
|
| 201 |
+
163,
|
| 202 |
+
164,
|
| 203 |
+
165,
|
| 204 |
+
166,
|
| 205 |
+
167,
|
| 206 |
+
168,
|
| 207 |
+
169,
|
| 208 |
+
170,
|
| 209 |
+
171,
|
| 210 |
+
172,
|
| 211 |
+
173,
|
| 212 |
+
174,
|
| 213 |
+
175,
|
| 214 |
+
176,
|
| 215 |
+
177,
|
| 216 |
+
178,
|
| 217 |
+
179,
|
| 218 |
+
180,
|
| 219 |
+
181,
|
| 220 |
+
182,
|
| 221 |
+
183,
|
| 222 |
+
184,
|
| 223 |
+
185,
|
| 224 |
+
186,
|
| 225 |
+
187,
|
| 226 |
+
188,
|
| 227 |
+
189,
|
| 228 |
+
190,
|
| 229 |
+
191,
|
| 230 |
+
192,
|
| 231 |
+
193,
|
| 232 |
+
194,
|
| 233 |
+
195,
|
| 234 |
+
196,
|
| 235 |
+
197,
|
| 236 |
+
198,
|
| 237 |
+
199,
|
| 238 |
+
200,
|
| 239 |
+
201,
|
| 240 |
+
202,
|
| 241 |
+
203,
|
| 242 |
+
204,
|
| 243 |
+
205,
|
| 244 |
+
206,
|
| 245 |
+
207,
|
| 246 |
+
208,
|
| 247 |
+
209,
|
| 248 |
+
210,
|
| 249 |
+
211,
|
| 250 |
+
212,
|
| 251 |
+
213,
|
| 252 |
+
214,
|
| 253 |
+
215,
|
| 254 |
+
216,
|
| 255 |
+
217,
|
| 256 |
+
218,
|
| 257 |
+
219,
|
| 258 |
+
220,
|
| 259 |
+
221,
|
| 260 |
+
222,
|
| 261 |
+
223,
|
| 262 |
+
224,
|
| 263 |
+
225,
|
| 264 |
+
226,
|
| 265 |
+
227,
|
| 266 |
+
228,
|
| 267 |
+
229,
|
| 268 |
+
230,
|
| 269 |
+
231,
|
| 270 |
+
232,
|
| 271 |
+
233,
|
| 272 |
+
234,
|
| 273 |
+
235,
|
| 274 |
+
236,
|
| 275 |
+
237,
|
| 276 |
+
238,
|
| 277 |
+
239,
|
| 278 |
+
240,
|
| 279 |
+
241,
|
| 280 |
+
242,
|
| 281 |
+
243,
|
| 282 |
+
244,
|
| 283 |
+
245,
|
| 284 |
+
246,
|
| 285 |
+
247,
|
| 286 |
+
248,
|
| 287 |
+
249,
|
| 288 |
+
250,
|
| 289 |
+
251,
|
| 290 |
+
252,
|
| 291 |
+
253,
|
| 292 |
+
254,
|
| 293 |
+
255,
|
| 294 |
+
256,
|
| 295 |
+
257,
|
| 296 |
+
258,
|
| 297 |
+
259,
|
| 298 |
+
260,
|
| 299 |
+
261,
|
| 300 |
+
262,
|
| 301 |
+
263,
|
| 302 |
+
264,
|
| 303 |
+
265,
|
| 304 |
+
266,
|
| 305 |
+
267,
|
| 306 |
+
268,
|
| 307 |
+
269,
|
| 308 |
+
270,
|
| 309 |
+
271,
|
| 310 |
+
272,
|
| 311 |
+
273,
|
| 312 |
+
274,
|
| 313 |
+
275,
|
| 314 |
+
276,
|
| 315 |
+
277,
|
| 316 |
+
278,
|
| 317 |
+
279,
|
| 318 |
+
280,
|
| 319 |
+
281,
|
| 320 |
+
282,
|
| 321 |
+
283,
|
| 322 |
+
284,
|
| 323 |
+
285,
|
| 324 |
+
286,
|
| 325 |
+
287,
|
| 326 |
+
288,
|
| 327 |
+
289,
|
| 328 |
+
290,
|
| 329 |
+
291,
|
| 330 |
+
292,
|
| 331 |
+
293,
|
| 332 |
+
294,
|
| 333 |
+
295,
|
| 334 |
+
296,
|
| 335 |
+
297,
|
| 336 |
+
298,
|
| 337 |
+
299,
|
| 338 |
+
300,
|
| 339 |
+
301,
|
| 340 |
+
302,
|
| 341 |
+
303,
|
| 342 |
+
304,
|
| 343 |
+
305,
|
| 344 |
+
306,
|
| 345 |
+
307,
|
| 346 |
+
308,
|
| 347 |
+
309,
|
| 348 |
+
310,
|
| 349 |
+
311,
|
| 350 |
+
312,
|
| 351 |
+
313,
|
| 352 |
+
314,
|
| 353 |
+
315,
|
| 354 |
+
316,
|
| 355 |
+
317,
|
| 356 |
+
318,
|
| 357 |
+
319,
|
| 358 |
+
320
|
| 359 |
+
]
|
| 360 |
+
}
|
| 361 |
+
]
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/rscl_gpu1_rolling5k_20260723_022922.log
ADDED
|
@@ -0,0 +1,198 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
INFO 2026-07-23 02:29:37 ot_train.py:281 {'batch_size': 64,
|
| 2 |
+
'checkpoint_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000',
|
| 3 |
+
'cudnn_deterministic': False,
|
| 4 |
+
'dataset': {'depth_output_unit': 'mm',
|
| 5 |
+
'episodes': None,
|
| 6 |
+
'eval_split': 0.0,
|
| 7 |
+
'image_transforms': {'enable': False,
|
| 8 |
+
'max_num_transforms': 3,
|
| 9 |
+
'random_order': False,
|
| 10 |
+
'tfs': {'affine': {'kwargs': {'degrees': [-5.0,
|
| 11 |
+
5.0],
|
| 12 |
+
'translate': [0.05,
|
| 13 |
+
0.05]},
|
| 14 |
+
'type': 'RandomAffine',
|
| 15 |
+
'weight': 1.0},
|
| 16 |
+
'brightness': {'kwargs': {'brightness': [0.8,
|
| 17 |
+
1.2]},
|
| 18 |
+
'type': 'ColorJitter',
|
| 19 |
+
'weight': 1.0},
|
| 20 |
+
'contrast': {'kwargs': {'contrast': [0.8,
|
| 21 |
+
1.2]},
|
| 22 |
+
'type': 'ColorJitter',
|
| 23 |
+
'weight': 1.0},
|
| 24 |
+
'hue': {'kwargs': {'hue': [-0.05,
|
| 25 |
+
0.05]},
|
| 26 |
+
'type': 'ColorJitter',
|
| 27 |
+
'weight': 1.0},
|
| 28 |
+
'saturation': {'kwargs': {'saturation': [0.5,
|
| 29 |
+
1.5]},
|
| 30 |
+
'type': 'ColorJitter',
|
| 31 |
+
'weight': 1.0},
|
| 32 |
+
'sharpness': {'kwargs': {'sharpness': [0.5,
|
| 33 |
+
1.5]},
|
| 34 |
+
'type': 'SharpnessJitter',
|
| 35 |
+
'weight': 1.0}}},
|
| 36 |
+
'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2',
|
| 37 |
+
'return_uint8': False,
|
| 38 |
+
'revision': None,
|
| 39 |
+
'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2',
|
| 40 |
+
'streaming': False,
|
| 41 |
+
'use_imagenet_stats': True,
|
| 42 |
+
'video_backend': 'torchcodec'},
|
| 43 |
+
'env': None,
|
| 44 |
+
'env_eval_freq': 20000,
|
| 45 |
+
'eval': {'batch_size': 50,
|
| 46 |
+
'n_episodes': 50,
|
| 47 |
+
'recording': False,
|
| 48 |
+
'recording_private': False,
|
| 49 |
+
'recording_repo_id': None,
|
| 50 |
+
'use_async_envs': True},
|
| 51 |
+
'eval_steps': 0,
|
| 52 |
+
'job': {'detach': False,
|
| 53 |
+
'image': 'huggingface/lerobot-gpu:latest',
|
| 54 |
+
'tags': [],
|
| 55 |
+
'target': None,
|
| 56 |
+
'timeout': '2d'},
|
| 57 |
+
'job_name': 'INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60',
|
| 58 |
+
'log_freq': 200,
|
| 59 |
+
'max_eval_samples': 0,
|
| 60 |
+
'num_workers': 4,
|
| 61 |
+
'optimizer': {'betas': [0.9, 0.999],
|
| 62 |
+
'eps': 1e-08,
|
| 63 |
+
'grad_clip_norm': 1.0,
|
| 64 |
+
'lr': 0.0001,
|
| 65 |
+
'type': 'adamw',
|
| 66 |
+
'weight_decay': 1e-05},
|
| 67 |
+
'output_dir': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K',
|
| 68 |
+
'peft': None,
|
| 69 |
+
'persistent_workers': True,
|
| 70 |
+
'policy': {'action_decode_transform': None,
|
| 71 |
+
'action_expert_num_layers': 16,
|
| 72 |
+
'balance_dataset_weights': True,
|
| 73 |
+
'balance_trajectory_weights': True,
|
| 74 |
+
'base_model_path': 'nvidia/GR00T-N1.7-3B',
|
| 75 |
+
'batch_size': 32,
|
| 76 |
+
'chunk_size': 16,
|
| 77 |
+
'dataloader_num_workers': 8,
|
| 78 |
+
'dataset_paths': None,
|
| 79 |
+
'device': 'cuda',
|
| 80 |
+
'embodiment_tag': 'new_embodiment',
|
| 81 |
+
'image_size': [256, 256],
|
| 82 |
+
'input_features': {'observation.images.guide': {'shape': [3,
|
| 83 |
+
224,
|
| 84 |
+
224],
|
| 85 |
+
'type': <FeatureType.VISUAL: 'VISUAL'>},
|
| 86 |
+
'observation.images.right_shoulder': {'shape': [3,
|
| 87 |
+
224,
|
| 88 |
+
224],
|
| 89 |
+
'type': <FeatureType.VISUAL: 'VISUAL'>},
|
| 90 |
+
'observation.images.wrist': {'shape': [3,
|
| 91 |
+
224,
|
| 92 |
+
224],
|
| 93 |
+
'type': <FeatureType.VISUAL: 'VISUAL'>},
|
| 94 |
+
'observation.state': {'shape': [16],
|
| 95 |
+
'type': <FeatureType.STATE: 'STATE'>}},
|
| 96 |
+
'license': None,
|
| 97 |
+
'lora_alpha': 16,
|
| 98 |
+
'lora_dropout': 0.1,
|
| 99 |
+
'lora_full_model': False,
|
| 100 |
+
'lora_rank': 0,
|
| 101 |
+
'max_action_dim': 132,
|
| 102 |
+
'max_state_dim': 132,
|
| 103 |
+
'max_steps': 10000,
|
| 104 |
+
'model_params_fp32': True,
|
| 105 |
+
'n_action_steps': 16,
|
| 106 |
+
'n_obs_steps': 1,
|
| 107 |
+
'normalization_mapping': {'ACTION': <NormalizationMode.IDENTITY: 'IDENTITY'>,
|
| 108 |
+
'STATE': <NormalizationMode.IDENTITY: 'IDENTITY'>,
|
| 109 |
+
'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>},
|
| 110 |
+
'num_inference_timesteps': None,
|
| 111 |
+
'optimizer_betas': [0.9, 0.999],
|
| 112 |
+
'optimizer_eps': 1e-08,
|
| 113 |
+
'optimizer_lr': 0.0001,
|
| 114 |
+
'optimizer_weight_decay': 1e-05,
|
| 115 |
+
'output_dir': './tmp/gr00t',
|
| 116 |
+
'output_features': {'action': {'shape': [10],
|
| 117 |
+
'type': <FeatureType.ACTION: 'ACTION'>}},
|
| 118 |
+
'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model',
|
| 119 |
+
'pretrained_revision': None,
|
| 120 |
+
'private': None,
|
| 121 |
+
'push_to_hub': False,
|
| 122 |
+
'relative_exclude_joints': [],
|
| 123 |
+
'repo_id': None,
|
| 124 |
+
'report_to': 'wandb',
|
| 125 |
+
'resume': False,
|
| 126 |
+
'rkd_angle_weight': 2.0,
|
| 127 |
+
'rkd_distance_weight': 1.0,
|
| 128 |
+
'rkd_enabled': True,
|
| 129 |
+
'rkd_fm_loss_weight': 1.0,
|
| 130 |
+
'rkd_loss_weight': 1.0,
|
| 131 |
+
'rkd_student_attention_hidden_dim': 512,
|
| 132 |
+
'rkd_student_attention_output_dim': 512,
|
| 133 |
+
'rkd_student_pooling': 'attention',
|
| 134 |
+
'rkd_vae_checkpoint': '/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11',
|
| 135 |
+
'rtc_ramp_rate': None,
|
| 136 |
+
'save_steps': 1000,
|
| 137 |
+
'tags': None,
|
| 138 |
+
'tokenizer_assets_repo': None,
|
| 139 |
+
'tune_diffusion_model': True,
|
| 140 |
+
'tune_llm': False,
|
| 141 |
+
'tune_projector': True,
|
| 142 |
+
'tune_top_llm_layers': 0,
|
| 143 |
+
'tune_visual': False,
|
| 144 |
+
'tune_vlln': True,
|
| 145 |
+
'type': 'groot_rkd',
|
| 146 |
+
'use_amp': False,
|
| 147 |
+
'use_bf16': True,
|
| 148 |
+
'use_flash_attention': False,
|
| 149 |
+
'use_peft': False,
|
| 150 |
+
'use_relative_actions': False,
|
| 151 |
+
'video_backend': 'decord',
|
| 152 |
+
'warmup_ratio': 0.05,
|
| 153 |
+
'warmup_steps': 3000},
|
| 154 |
+
'prefetch_factor': 4,
|
| 155 |
+
'rename_map': {},
|
| 156 |
+
'resume': True,
|
| 157 |
+
'reward_model': None,
|
| 158 |
+
'sample_weighting': None,
|
| 159 |
+
'save_checkpoint': True,
|
| 160 |
+
'save_checkpoint_to_hub': False,
|
| 161 |
+
'save_freq': 20000,
|
| 162 |
+
'scheduler': {'name': 'cosine', 'num_warmup_steps': 3000, 'type': 'diffuser'},
|
| 163 |
+
'seed': 42,
|
| 164 |
+
'steps': 60000,
|
| 165 |
+
'tolerance_s': 0.0001,
|
| 166 |
+
'use_policy_training_preset': True,
|
| 167 |
+
'wandb': {'add_tags': True,
|
| 168 |
+
'disable_artifact': True,
|
| 169 |
+
'enable': True,
|
| 170 |
+
'entity': None,
|
| 171 |
+
'mode': None,
|
| 172 |
+
'notes': None,
|
| 173 |
+
'project': 'lerobot',
|
| 174 |
+
'run_id': 'cemf0rge'}}
|
| 175 |
+
Traceback (most recent call last):
|
| 176 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py", line 1613, in <module>
|
| 177 |
+
main()
|
| 178 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py", line 1609, in main
|
| 179 |
+
train_module.main()
|
| 180 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 825, in main
|
| 181 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/configs/parser.py", line 320, in wrapper_inner
|
| 182 |
+
response = fn(cfg, *args, **kwargs)
|
| 183 |
+
^^^^^^^^^^^^^^^^^^^^^^^^
|
| 184 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 285, in train
|
| 185 |
+
if not policy.is_trainable:
|
| 186 |
+
^^^^^^^^^^^^^
|
| 187 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/common/wandb_utils.py", line 99, in __init__
|
| 188 |
+
wandb.init(
|
| 189 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/wandb_init.py", line 1528, in init
|
| 190 |
+
get_sentry().reraise(e)
|
| 191 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/analytics/sentry.py", line 191, in reraise
|
| 192 |
+
raise exc.with_traceback(tb)
|
| 193 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/wandb_init.py", line 1511, in init
|
| 194 |
+
run = wi.init(run_settings, run_config, run_printer)
|
| 195 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 196 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/wandb_init.py", line 961, in init
|
| 197 |
+
raise error
|
| 198 |
+
wandb.errors.errors.UsageError: You provided an invalid value for the `resume` argument. The value 'must' is not a valid option for resuming the run (cemf0rge) that has not been initialized. Please check your inputs and try again with a valid run ID. If you are trying to start a new run, please omit the `resume` argument or use `resume='allow'`.
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/rscl_gpu1_rolling5k_20260723_023110_newwandb.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/source_config.yaml
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
# INSIGHT GR00T N1.7 RKD training with RS-CL-style full-training regularization.
|
| 2 |
# Common RKD values live in the top-level policy; the phase contains schedule overrides only.
|
| 3 |
insight:
|
|
|
|
|
|
|
| 4 |
# Options: joint_abs | ee_abs_quat | ee_abs_rot6d | ee_delta
|
| 5 |
action_space: ee_abs_rot6d
|
| 6 |
# Options: coarse | detailed
|
|
|
|
| 1 |
# INSIGHT GR00T N1.7 RKD training with RS-CL-style full-training regularization.
|
| 2 |
# Common RKD values live in the top-level policy; the phase contains schedule overrides only.
|
| 3 |
insight:
|
| 4 |
+
checkpoint_interval: 5K
|
| 5 |
+
checkpoint_slots: 2
|
| 6 |
# Options: joint_abs | ee_abs_quat | ee_abs_rot6d | ee_delta
|
| 7 |
action_space: ee_abs_rot6d
|
| 8 |
# Options: coarse | detailed
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/debug-internal.log
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/debug.log
CHANGED
|
@@ -1,20 +1,65 @@
|
|
| 1 |
-
2026-07-23
|
| 2 |
-
2026-07-23
|
| 3 |
-
2026-07-23
|
| 4 |
-
2026-07-23
|
| 5 |
-
2026-07-23
|
| 6 |
-
2026-07-23
|
| 7 |
-
2026-07-23
|
| 8 |
-
config: {'dataset': {'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2', 'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2', 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}, 'affine': {'weight': 1.0, 'type': 'RandomAffine', 'kwargs': {'degrees': [-5.0, 5.0], 'translate': [0.05, 0.05]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'torchcodec', 'return_uint8': False, 'depth_output_unit': 'mm', 'streaming': False, 'eval_split': 0.0}, 'env': None, 'policy': {'type': 'groot_rkd', 'n_obs_steps': 1, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [16]}, 'observation.images.wrist': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.right_shoulder': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.guide': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [10]}}, 'device': 'cuda', 'use_amp': False, 'use_peft': False, 'push_to_hub': False, 'repo_id': None, 'private': None, 'tags': None, 'license': None, 'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/
|
| 9 |
-
2026-07-23
|
| 10 |
-
2026-07-23
|
| 11 |
-
2026-07-23
|
| 12 |
-
2026-07-23
|
| 13 |
-
2026-07-23
|
| 14 |
-
2026-07-23
|
| 15 |
-
2026-07-23
|
| 16 |
-
2026-07-23
|
| 17 |
-
2026-07-23
|
| 18 |
-
2026-07-23
|
| 19 |
-
2026-07-23
|
| 20 |
-
2026-07-23
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
|
| 2 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_setup.py:_flush():81] Configure stats pid to 1459
|
| 3 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_setup.py:_flush():81] Loading settings from environment variables
|
| 4 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug.log
|
| 5 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug-internal.log
|
| 6 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:init():766] calling init triggers
|
| 7 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
|
| 8 |
+
config: {'dataset': {'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2', 'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2', 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}, 'affine': {'weight': 1.0, 'type': 'RandomAffine', 'kwargs': {'degrees': [-5.0, 5.0], 'translate': [0.05, 0.05]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'torchcodec', 'return_uint8': False, 'depth_output_unit': 'mm', 'streaming': False, 'eval_split': 0.0}, 'env': None, 'policy': {'type': 'groot_rkd', 'n_obs_steps': 1, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [16]}, 'observation.images.wrist': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.right_shoulder': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.guide': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [10]}}, 'device': 'cuda', 'use_amp': False, 'use_peft': False, 'push_to_hub': False, 'repo_id': None, 'private': None, 'tags': None, 'license': None, 'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model', 'pretrained_revision': None, 'chunk_size': 16, 'n_action_steps': 16, 'max_state_dim': 132, 'max_action_dim': 132, 'normalization_mapping': {'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'STATE': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'ACTION': <NormalizationMode.IDENTITY: 'IDENTITY'>}, 'base_model_path': 'nvidia/GR00T-N1.7-3B', 'action_decode_transform': None, 'embodiment_tag': 'new_embodiment', 'tune_llm': False, 'tune_visual': False, 'tune_projector': True, 'tune_diffusion_model': True, 'tune_vlln': True, 'tune_top_llm_layers': 0, 'num_inference_timesteps': None, 'rtc_ramp_rate': None, 'use_flash_attention': False, 'use_relative_actions': False, 'relative_exclude_joints': [], 'optimizer_lr': 0.0001, 'optimizer_betas': [0.9, 0.999], 'optimizer_eps': 1e-08, 'optimizer_weight_decay': 1e-05, 'warmup_steps': 3000, 'warmup_ratio': 0.05, 'use_bf16': True, 'model_params_fp32': True, 'image_size': [256, 256], 'tokenizer_assets_repo': None, 'lora_rank': 0, 'lora_alpha': 16, 'lora_dropout': 0.1, 'lora_full_model': False, 'video_backend': 'decord', 'balance_dataset_weights': True, 'balance_trajectory_weights': True, 'dataset_paths': None, 'output_dir': './tmp/gr00t', 'save_steps': 1000, 'max_steps': 10000, 'batch_size': 32, 'dataloader_num_workers': 8, 'report_to': 'wandb', 'resume': False, 'action_expert_num_layers': 16, 'rkd_enabled': True, 'rkd_vae_checkpoint': '/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11', 'rkd_student_pooling': 'attention', 'rkd_student_attention_hidden_dim': 512, 'rkd_student_attention_output_dim': 512, 'rkd_fm_loss_weight': 1.0, 'rkd_loss_weight': 1.0, 'rkd_distance_weight': 1.0, 'rkd_angle_weight': 2.0}, 'reward_model': None, 'output_dir': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K', 'job_name': 'INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60', 'resume': True, 'seed': 42, 'cudnn_deterministic': False, 'num_workers': 4, 'batch_size': 64, 'prefetch_factor': 4, 'persistent_workers': True, 'steps': 60000, 'env_eval_freq': 20000, 'log_freq': 200, 'eval_steps': 0, 'max_eval_samples': 0, 'tolerance_s': 0.0001, 'save_checkpoint': True, 'save_freq': 20000, 'use_policy_training_preset': True, 'optimizer': {'type': 'adamw', 'lr': 0.0001, 'weight_decay': 1e-05, 'grad_clip_norm': 1.0, 'betas': [0.9, 0.999], 'eps': 1e-08}, 'scheduler': {'type': 'diffuser', 'num_warmup_steps': 3000, 'name': 'cosine'}, 'eval': {'n_episodes': 50, 'batch_size': 50, 'use_async_envs': True, 'recording': False, 'recording_repo_id': None, 'recording_private': False}, 'wandb': {'enable': True, 'disable_artifact': True, 'project': 'lerobot', 'entity': None, 'notes': None, 'run_id': 'rs1egwv8', 'mode': None, 'add_tags': True}, 'peft': None, 'job': {'target': None, 'image': 'huggingface/lerobot-gpu:latest', 'timeout': '2d', 'detach': False, 'tags': []}, 'save_checkpoint_to_hub': False, 'sample_weighting': None, 'rename_map': {}, 'checkpoint_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01', '_wandb': {}}
|
| 9 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:init():814] starting backend
|
| 10 |
+
2026-07-23 16:35:01,833 INFO MainThread:1459 [wandb_init.py:init():829] sending inform_init request
|
| 11 |
+
2026-07-23 16:35:02,323 INFO MainThread:1459 [wandb_init.py:init():834] backend started and connected
|
| 12 |
+
2026-07-23 16:35:02,325 INFO MainThread:1459 [wandb_init.py:init():904] updated telemetry
|
| 13 |
+
2026-07-23 16:35:02,326 INFO MainThread:1459 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
|
| 14 |
+
2026-07-23 16:35:03,342 INFO MainThread:1459 [wandb_init.py:init():967] run resumed
|
| 15 |
+
2026-07-23 16:35:03,344 INFO MainThread:1459 [wandb_init.py:init():972] starting run threads in backend
|
| 16 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_console_start():2523] atexit reg
|
| 17 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_redirect():2373] redirect: wrap_raw
|
| 18 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_redirect():2442] Wrapping output streams.
|
| 19 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_redirect():2465] Redirects installed.
|
| 20 |
+
2026-07-23 16:35:03,398 INFO MainThread:1459 [wandb_init.py:init():1010] run started, returning control to user process
|
| 21 |
+
2026-07-24 04:10:06,982 INFO wandb-AsyncioManager-main:1459 [service_client.py:_forward_responses():122] Reached EOF.
|
| 22 |
+
2026-07-24 04:10:06,983 INFO wandb-AsyncioManager-main:1459 [mailbox.py:close():154] Closing mailbox, abandoning 2 handles.
|
| 23 |
+
2026-07-24 04:10:06,983 ERROR wandb-AsyncioManager-main:1459 [asyncio_manager.py:fn_wrap_exceptions():184] Uncaught exception in run_soon callback.
|
| 24 |
+
Traceback (most recent call last):
|
| 25 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_manager.py", line 182, in fn_wrap_exceptions
|
| 26 |
+
await fn()
|
| 27 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_messages.py", line 90, in loop
|
| 28 |
+
await asyncio_compat.race(
|
| 29 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 278, in race
|
| 30 |
+
async with open_task_group(race=True) as tg:
|
| 31 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 32 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/contextlib.py", line 217, in __aexit__
|
| 33 |
+
await anext(self.gen)
|
| 34 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 240, in open_task_group
|
| 35 |
+
await task_group._wait_all(race=race, timeout=exit_timeout)
|
| 36 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 180, in _wait_all
|
| 37 |
+
raise exc
|
| 38 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_messages.py", line 113, in _print_all
|
| 39 |
+
result = await handle.wait_async(timeout=None)
|
| 40 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 41 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/mailbox_handle.py", line 127, in wait_async
|
| 42 |
+
response = await self._handle.wait_async(timeout=timeout)
|
| 43 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 44 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/response_handle.py", line 123, in wait_async
|
| 45 |
+
raise HandleAbandonedError()
|
| 46 |
+
wandb.sdk.mailbox.mailbox_handle.HandleAbandonedError
|
| 47 |
+
2026-07-24 04:10:14,759 ERROR wandb-AsyncioManager-main:1459 [asyncio_manager.py:fn_wrap_exceptions():184] Uncaught exception in run_soon callback.
|
| 48 |
+
Traceback (most recent call last):
|
| 49 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_manager.py", line 182, in fn_wrap_exceptions
|
| 50 |
+
await fn()
|
| 51 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_stopping.py", line 87, in loop
|
| 52 |
+
should_stop = await self._check_should_stop()
|
| 53 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 54 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_stopping.py", line 115, in _check_should_stop
|
| 55 |
+
handle = await self._interface.deliver_async(request)
|
| 56 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 57 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/interface/interface_sock.py", line 58, in deliver_async
|
| 58 |
+
handle = await self._client.deliver(request)
|
| 59 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 60 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/service/service_client.py", line 57, in deliver
|
| 61 |
+
handle = self._mailbox.require_response(request)
|
| 62 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 63 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/mailbox.py", line 89, in require_response
|
| 64 |
+
raise MailboxClosedError()
|
| 65 |
+
wandb.sdk.mailbox.mailbox.MailboxClosedError
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/files/config.yaml
ADDED
|
@@ -0,0 +1,334 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_wandb:
|
| 2 |
+
value:
|
| 3 |
+
cli_version: 0.27.2
|
| 4 |
+
e:
|
| 5 |
+
vmsr43xlhcpoc4wtuae54k6a709gs2et:
|
| 6 |
+
args:
|
| 7 |
+
- --config_path=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model/train_config.json
|
| 8 |
+
- --resume=true
|
| 9 |
+
- --output_dir=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 10 |
+
- --dataset.root=/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2
|
| 11 |
+
codePath: benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py
|
| 12 |
+
codePathLocal: my_scripts/lerobot_train_yaml.py
|
| 13 |
+
cpu_count: 112
|
| 14 |
+
cpu_count_logical: 224
|
| 15 |
+
cudaVersion: "12.8"
|
| 16 |
+
disk:
|
| 17 |
+
/:
|
| 18 |
+
total: "1888425144320"
|
| 19 |
+
used: "1137071321088"
|
| 20 |
+
executable: /home/ext_minje/miniconda3/envs/lerobot060_groot/bin/python
|
| 21 |
+
git:
|
| 22 |
+
commit: a329728c2c9524d79b966c4a7a82ee56a4c2abf7
|
| 23 |
+
remote: git@github.com:paragon7060/clvla.git
|
| 24 |
+
gpu: NVIDIA H200
|
| 25 |
+
gpu_count: 2
|
| 26 |
+
gpu_nvidia:
|
| 27 |
+
- architecture: Hopper
|
| 28 |
+
cudaCores: 16896
|
| 29 |
+
memoryTotal: "150754820096"
|
| 30 |
+
name: NVIDIA H200
|
| 31 |
+
uuid: GPU-86be6e5b-fb48-fa1c-9bd7-83d336cb2991
|
| 32 |
+
- architecture: Hopper
|
| 33 |
+
cudaCores: 16896
|
| 34 |
+
memoryTotal: "150754820096"
|
| 35 |
+
name: NVIDIA H200
|
| 36 |
+
uuid: GPU-24eb1ba2-7313-ff93-1435-748768ebdbdc
|
| 37 |
+
host: ext_minje-box
|
| 38 |
+
memory:
|
| 39 |
+
total: "2164176568320"
|
| 40 |
+
os: Linux-6.8.0-55-generic-x86_64-with-glibc2.39
|
| 41 |
+
program: /home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py
|
| 42 |
+
python: CPython 3.12.13
|
| 43 |
+
root: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 44 |
+
startedAt: "2026-07-23T01:33:42.298193Z"
|
| 45 |
+
writerId: vmsr43xlhcpoc4wtuae54k6a709gs2et
|
| 46 |
+
m: []
|
| 47 |
+
python_version: 3.12.13
|
| 48 |
+
t:
|
| 49 |
+
"1":
|
| 50 |
+
- 1
|
| 51 |
+
- 11
|
| 52 |
+
- 41
|
| 53 |
+
- 49
|
| 54 |
+
- 51
|
| 55 |
+
- 71
|
| 56 |
+
- 83
|
| 57 |
+
- 98
|
| 58 |
+
"2":
|
| 59 |
+
- 1
|
| 60 |
+
- 11
|
| 61 |
+
- 41
|
| 62 |
+
- 49
|
| 63 |
+
- 51
|
| 64 |
+
- 71
|
| 65 |
+
- 83
|
| 66 |
+
- 98
|
| 67 |
+
"3":
|
| 68 |
+
- 5
|
| 69 |
+
- 13
|
| 70 |
+
- 14
|
| 71 |
+
- 15
|
| 72 |
+
- 16
|
| 73 |
+
- 61
|
| 74 |
+
- 62
|
| 75 |
+
"4": 3.12.13
|
| 76 |
+
"5": 0.27.2
|
| 77 |
+
"6": 5.5.4
|
| 78 |
+
"10":
|
| 79 |
+
- 21
|
| 80 |
+
"12": 0.27.2
|
| 81 |
+
"13": linux-x86_64
|
| 82 |
+
batch_size:
|
| 83 |
+
value: 64
|
| 84 |
+
checkpoint_path:
|
| 85 |
+
value: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000
|
| 86 |
+
cudnn_deterministic:
|
| 87 |
+
value: false
|
| 88 |
+
dataset:
|
| 89 |
+
value:
|
| 90 |
+
depth_output_unit: mm
|
| 91 |
+
episodes: null
|
| 92 |
+
eval_split: 0
|
| 93 |
+
image_transforms:
|
| 94 |
+
enable: false
|
| 95 |
+
max_num_transforms: 3
|
| 96 |
+
random_order: false
|
| 97 |
+
tfs:
|
| 98 |
+
affine:
|
| 99 |
+
kwargs:
|
| 100 |
+
degrees:
|
| 101 |
+
- -5
|
| 102 |
+
- 5
|
| 103 |
+
translate:
|
| 104 |
+
- 0.05
|
| 105 |
+
- 0.05
|
| 106 |
+
type: RandomAffine
|
| 107 |
+
weight: 1
|
| 108 |
+
brightness:
|
| 109 |
+
kwargs:
|
| 110 |
+
brightness:
|
| 111 |
+
- 0.8
|
| 112 |
+
- 1.2
|
| 113 |
+
type: ColorJitter
|
| 114 |
+
weight: 1
|
| 115 |
+
contrast:
|
| 116 |
+
kwargs:
|
| 117 |
+
contrast:
|
| 118 |
+
- 0.8
|
| 119 |
+
- 1.2
|
| 120 |
+
type: ColorJitter
|
| 121 |
+
weight: 1
|
| 122 |
+
hue:
|
| 123 |
+
kwargs:
|
| 124 |
+
hue:
|
| 125 |
+
- -0.05
|
| 126 |
+
- 0.05
|
| 127 |
+
type: ColorJitter
|
| 128 |
+
weight: 1
|
| 129 |
+
saturation:
|
| 130 |
+
kwargs:
|
| 131 |
+
saturation:
|
| 132 |
+
- 0.5
|
| 133 |
+
- 1.5
|
| 134 |
+
type: ColorJitter
|
| 135 |
+
weight: 1
|
| 136 |
+
sharpness:
|
| 137 |
+
kwargs:
|
| 138 |
+
sharpness:
|
| 139 |
+
- 0.5
|
| 140 |
+
- 1.5
|
| 141 |
+
type: SharpnessJitter
|
| 142 |
+
weight: 1
|
| 143 |
+
repo_id: Whalswp/INSIGHTfixposV4_filtered_multispace_v2
|
| 144 |
+
return_uint8: false
|
| 145 |
+
revision: null
|
| 146 |
+
root: /home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2
|
| 147 |
+
streaming: false
|
| 148 |
+
use_imagenet_stats: true
|
| 149 |
+
video_backend: torchcodec
|
| 150 |
+
env:
|
| 151 |
+
value: null
|
| 152 |
+
env_eval_freq:
|
| 153 |
+
value: 20000
|
| 154 |
+
eval:
|
| 155 |
+
value:
|
| 156 |
+
batch_size: 50
|
| 157 |
+
n_episodes: 50
|
| 158 |
+
recording: false
|
| 159 |
+
recording_private: false
|
| 160 |
+
recording_repo_id: null
|
| 161 |
+
use_async_envs: true
|
| 162 |
+
eval_steps:
|
| 163 |
+
value: 0
|
| 164 |
+
job:
|
| 165 |
+
value:
|
| 166 |
+
detach: false
|
| 167 |
+
image: huggingface/lerobot-gpu:latest
|
| 168 |
+
tags: []
|
| 169 |
+
target: null
|
| 170 |
+
timeout: 2d
|
| 171 |
+
job_name:
|
| 172 |
+
value: INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60
|
| 173 |
+
log_freq:
|
| 174 |
+
value: 200
|
| 175 |
+
max_eval_samples:
|
| 176 |
+
value: 0
|
| 177 |
+
num_workers:
|
| 178 |
+
value: 4
|
| 179 |
+
optimizer:
|
| 180 |
+
value:
|
| 181 |
+
betas:
|
| 182 |
+
- 0.9
|
| 183 |
+
- 0.999
|
| 184 |
+
eps: 1e-08
|
| 185 |
+
grad_clip_norm: 1
|
| 186 |
+
lr: 0.0001
|
| 187 |
+
type: adamw
|
| 188 |
+
weight_decay: 1e-05
|
| 189 |
+
output_dir:
|
| 190 |
+
value: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 191 |
+
peft:
|
| 192 |
+
value: null
|
| 193 |
+
persistent_workers:
|
| 194 |
+
value: true
|
| 195 |
+
policy:
|
| 196 |
+
value:
|
| 197 |
+
action_decode_transform: null
|
| 198 |
+
action_expert_num_layers: 16
|
| 199 |
+
balance_dataset_weights: true
|
| 200 |
+
balance_trajectory_weights: true
|
| 201 |
+
base_model_path: nvidia/GR00T-N1.7-3B
|
| 202 |
+
batch_size: 32
|
| 203 |
+
chunk_size: 16
|
| 204 |
+
dataloader_num_workers: 8
|
| 205 |
+
dataset_paths: null
|
| 206 |
+
device: cuda
|
| 207 |
+
embodiment_tag: new_embodiment
|
| 208 |
+
image_size:
|
| 209 |
+
- 256
|
| 210 |
+
- 256
|
| 211 |
+
input_features:
|
| 212 |
+
observation.images.guide:
|
| 213 |
+
shape:
|
| 214 |
+
- 3
|
| 215 |
+
- 224
|
| 216 |
+
- 224
|
| 217 |
+
type: VISUAL
|
| 218 |
+
observation.images.right_shoulder:
|
| 219 |
+
shape:
|
| 220 |
+
- 3
|
| 221 |
+
- 224
|
| 222 |
+
- 224
|
| 223 |
+
type: VISUAL
|
| 224 |
+
observation.images.wrist:
|
| 225 |
+
shape:
|
| 226 |
+
- 3
|
| 227 |
+
- 224
|
| 228 |
+
- 224
|
| 229 |
+
type: VISUAL
|
| 230 |
+
observation.state:
|
| 231 |
+
shape:
|
| 232 |
+
- 16
|
| 233 |
+
type: STATE
|
| 234 |
+
license: null
|
| 235 |
+
lora_alpha: 16
|
| 236 |
+
lora_dropout: 0.1
|
| 237 |
+
lora_full_model: false
|
| 238 |
+
lora_rank: 0
|
| 239 |
+
max_action_dim: 132
|
| 240 |
+
max_state_dim: 132
|
| 241 |
+
max_steps: 10000
|
| 242 |
+
model_params_fp32: true
|
| 243 |
+
n_action_steps: 16
|
| 244 |
+
n_obs_steps: 1
|
| 245 |
+
normalization_mapping:
|
| 246 |
+
ACTION: IDENTITY
|
| 247 |
+
STATE: IDENTITY
|
| 248 |
+
VISUAL: IDENTITY
|
| 249 |
+
num_inference_timesteps: null
|
| 250 |
+
optimizer_betas:
|
| 251 |
+
- 0.9
|
| 252 |
+
- 0.999
|
| 253 |
+
optimizer_eps: 1e-08
|
| 254 |
+
optimizer_lr: 0.0001
|
| 255 |
+
optimizer_weight_decay: 1e-05
|
| 256 |
+
output_dir: ./tmp/gr00t
|
| 257 |
+
output_features:
|
| 258 |
+
action:
|
| 259 |
+
shape:
|
| 260 |
+
- 10
|
| 261 |
+
type: ACTION
|
| 262 |
+
pretrained_path: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model
|
| 263 |
+
pretrained_revision: null
|
| 264 |
+
private: null
|
| 265 |
+
push_to_hub: false
|
| 266 |
+
relative_exclude_joints: []
|
| 267 |
+
repo_id: null
|
| 268 |
+
report_to: wandb
|
| 269 |
+
resume: false
|
| 270 |
+
rkd_angle_weight: 2
|
| 271 |
+
rkd_distance_weight: 1
|
| 272 |
+
rkd_enabled: true
|
| 273 |
+
rkd_fm_loss_weight: 1
|
| 274 |
+
rkd_loss_weight: 1
|
| 275 |
+
rkd_student_attention_hidden_dim: 512
|
| 276 |
+
rkd_student_attention_output_dim: 512
|
| 277 |
+
rkd_student_pooling: attention
|
| 278 |
+
rkd_vae_checkpoint: /home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11
|
| 279 |
+
rtc_ramp_rate: null
|
| 280 |
+
save_steps: 1000
|
| 281 |
+
tags: null
|
| 282 |
+
tokenizer_assets_repo: null
|
| 283 |
+
tune_diffusion_model: true
|
| 284 |
+
tune_llm: false
|
| 285 |
+
tune_projector: true
|
| 286 |
+
tune_top_llm_layers: 0
|
| 287 |
+
tune_visual: false
|
| 288 |
+
tune_vlln: true
|
| 289 |
+
type: groot_rkd
|
| 290 |
+
use_amp: false
|
| 291 |
+
use_bf16: true
|
| 292 |
+
use_flash_attention: false
|
| 293 |
+
use_peft: false
|
| 294 |
+
use_relative_actions: false
|
| 295 |
+
video_backend: decord
|
| 296 |
+
warmup_ratio: 0.05
|
| 297 |
+
warmup_steps: 3000
|
| 298 |
+
prefetch_factor:
|
| 299 |
+
value: 4
|
| 300 |
+
resume:
|
| 301 |
+
value: true
|
| 302 |
+
reward_model:
|
| 303 |
+
value: null
|
| 304 |
+
sample_weighting:
|
| 305 |
+
value: null
|
| 306 |
+
save_checkpoint:
|
| 307 |
+
value: true
|
| 308 |
+
save_checkpoint_to_hub:
|
| 309 |
+
value: false
|
| 310 |
+
save_freq:
|
| 311 |
+
value: 20000
|
| 312 |
+
scheduler:
|
| 313 |
+
value:
|
| 314 |
+
name: cosine
|
| 315 |
+
num_warmup_steps: 3000
|
| 316 |
+
type: diffuser
|
| 317 |
+
seed:
|
| 318 |
+
value: 42
|
| 319 |
+
steps:
|
| 320 |
+
value: 60000
|
| 321 |
+
tolerance_s:
|
| 322 |
+
value: 0.0001
|
| 323 |
+
use_policy_training_preset:
|
| 324 |
+
value: true
|
| 325 |
+
wandb:
|
| 326 |
+
value:
|
| 327 |
+
add_tags: true
|
| 328 |
+
disable_artifact: true
|
| 329 |
+
enable: true
|
| 330 |
+
entity: null
|
| 331 |
+
mode: null
|
| 332 |
+
notes: null
|
| 333 |
+
project: lerobot
|
| 334 |
+
run_id: pgr3eari
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/files/output.log
CHANGED
|
@@ -45,4 +45,47 @@ Training: 3%|▎ | 800/30000 [20:31<12:21:37, 1.52s/step]INFO 2026-07
|
|
| 45 |
Training: 3%|▎ | 1000/30000 [26:18<22:10:00, 2.75s/step]INFO 2026-07-23 02:00:30 ot_train.py:649 step:31K smpl:2M ep:45K epch:9.09 loss:0.039 grdn:0.298 lr:5.2e-05 updt_s:0.843 data_s:0.886 smp/s:37 mem_gb:29.84
|
| 46 |
Training: 4%|▍ | 1200/30000 [31:32<10:05:29, 1.26s/step]INFO 2026-07-23 02:05:45 ot_train.py:649 step:31K smpl:2M ep:45K epch:9.14 loss:0.039 grdn:0.306 lr:5.1e-05 updt_s:0.805 data_s:0.765 smp/s:41 mem_gb:29.84
|
| 47 |
Training: 5%|▍ | 1400/30000 [36:06<10:52:36, 1.37s/step]INFO 2026-07-23 02:10:19 ot_train.py:649 step:31K smpl:2M ep:45K epch:9.20 loss:0.039 grdn:0.298 lr:5.1e-05 updt_s:0.744 data_s:0.622 smp/s:47 mem_gb:29.84
|
| 48 |
-
Training: 5%|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 45 |
Training: 3%|▎ | 1000/30000 [26:18<22:10:00, 2.75s/step]INFO 2026-07-23 02:00:30 ot_train.py:649 step:31K smpl:2M ep:45K epch:9.09 loss:0.039 grdn:0.298 lr:5.2e-05 updt_s:0.843 data_s:0.886 smp/s:37 mem_gb:29.84
|
| 46 |
Training: 4%|▍ | 1200/30000 [31:32<10:05:29, 1.26s/step]INFO 2026-07-23 02:05:45 ot_train.py:649 step:31K smpl:2M ep:45K epch:9.14 loss:0.039 grdn:0.306 lr:5.1e-05 updt_s:0.805 data_s:0.765 smp/s:41 mem_gb:29.84
|
| 47 |
Training: 5%|▍ | 1400/30000 [36:06<10:52:36, 1.37s/step]INFO 2026-07-23 02:10:19 ot_train.py:649 step:31K smpl:2M ep:45K epch:9.20 loss:0.039 grdn:0.298 lr:5.1e-05 updt_s:0.744 data_s:0.622 smp/s:47 mem_gb:29.84
|
| 48 |
+
Training: 5%|▌ | 1600/30000 [41:01<19:58:58, 2.53s/step]INFO 2026-07-23 02:15:14 ot_train.py:649 step:32K smpl:2M ep:46K epch:9.26 loss:0.039 grdn:0.299 lr:5.0e-05 updt_s:0.806 data_s:0.666 smp/s:43 mem_gb:29.82
|
| 49 |
+
Training: 6%|▌ | 1800/30000 [45:51<10:43:33, 1.37s/step]INFO 2026-07-23 02:20:04 ot_train.py:649 step:32K smpl:2M ep:46K epch:9.32 loss:0.037 grdn:0.292 lr:4.9e-05 updt_s:0.787 data_s:0.659 smp/s:44 mem_gb:29.85
|
| 50 |
+
Training: 7%|▋ | 2000/30000 [50:39<10:41:47, 1.38s/step]INFO 2026-07-23 02:24:51 ot_train.py:649 step:32K smpl:2M ep:46K epch:9.38 loss:0.037 grdn:0.286 lr:4.9e-05 updt_s:0.776 data_s:0.660 smp/s:45 mem_gb:29.85
|
| 51 |
+
Training: 7%|▋ | 2167/30000 [54:37<10:34:57, 1.37s/step]Traceback (most recent call last):
|
| 52 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py", line 1453, in <module>
|
| 53 |
+
config_path = Path(config_value).expanduser()
|
| 54 |
+
^^^^^^
|
| 55 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py", line 1449, in main
|
| 56 |
+
config_value = _find_cli_value(args, "--config_path")
|
| 57 |
+
^^^^^^^^^^^^^^^^^^^
|
| 58 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 816, in main
|
| 59 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/configs/parser.py", line 320, in wrapper_inner
|
| 60 |
+
response = fn(cfg, *args, **kwargs)
|
| 61 |
+
^^^^^^^^^^^^^^^^^^^^^^^^
|
| 62 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 618, in train
|
| 63 |
+
if is_eval_step:
|
| 64 |
+
|
| 65 |
+
File "/home/ext_minje/clvla/lerobot/src/lerobot/scripts/lerobot_train.py", line 179, in update_policy
|
| 66 |
+
"""
|
| 67 |
+
|
| 68 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_policies/groot_RKD/modeling_groot_rkd.py", line 326, in forward
|
| 69 |
+
outputs = self._groot_model.forward(groot_inputs)
|
| 70 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 71 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_policies/groot_RKD/groot_n1_7.py", line 884, in forward
|
| 72 |
+
backbone_outputs = self.backbone(backbone_inputs)
|
| 73 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 74 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1779, in _wrapped_call_impl
|
| 75 |
+
return self._call_impl(*args, **kwargs)
|
| 76 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 77 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1790, in _call_impl
|
| 78 |
+
return forward_call(*args, **kwargs)
|
| 79 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 80 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_policies/groot_RKD/groot_n1_7.py", line 450, in forward
|
| 81 |
+
self._ensure_legacy_qwen3_position_ids(model_input)
|
| 82 |
+
File "/home/ext_minje/clvla/benchmarks/INSIGHT/my_policies/groot_RKD/groot_n1_7.py", line 402, in _ensure_legacy_qwen3_position_ids
|
| 83 |
+
position_ids = compute_3d_position_ids(
|
| 84 |
+
^^^^^^^^^^^^^^^^^^^^^^^^
|
| 85 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1228, in compute_3d_position_ids
|
| 86 |
+
position_ids, rope_deltas = self.get_rope_index(
|
| 87 |
+
^^^^^^^^^^^^^^^^^^^^
|
| 88 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/transformers/models/qwen3_vl/modeling_qwen3_vl.py", line 1106, in get_rope_index
|
| 89 |
+
current_pos += text_len
|
| 90 |
+
^^^^^^^^^^^
|
| 91 |
+
KeyboardInterrupt
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/files/wandb-summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train/rkd_teacher_latent_norm":1,"train/weighted_rkd_loss":0.001385301467962563,"_timestamp":1.7847403914008305e+09,"train/training_phase_start_step":0,"train/rkd_loss_weight":0.3208404665513721,"_wandb":{"runtime":59006},"train/weighted_flow_matching_loss":0.022767670452594757,"train/episodes":53461.55783611993,"train/grad_norm":0.26664105713367464,"train/rkd_distance_loss":0.0010141097009181976,"train/training_phase_trainable_params":1.080755329e+09,"train/gpu_mem_gb":29.854091150760652,"train/flow_matching_loss":0.022767670452594757,"train/rkd_student_feature_norm":16.188758850097656,"train/rkd_runtime_enabled":1,"train/loss":0.024152971804142,"train/samples_per_s":49.78324781714454,"train/lr":3.5336255062138e-05,"train/steps":37000,"_step":37000,"train/rkd_angle_loss":0.0016518083866685629,"train/samples":2368000,"train/rkd_loss":0.004317726474255323,"train/training_phase_until_step":60000,"train/dataloading_s":0.5792085527597374,"_runtime":59006,"train/training_phase_index":0,"train/rkd_fm_loss_weight":1,"train/update_s":0.7063644623853179,"train/rkd_student_pooling_id":1,"train/epochs":10.844129378523313}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/logs/debug-core.log
CHANGED
|
@@ -26,3 +26,39 @@
|
|
| 26 |
{"time":"2026-07-23T01:33:48.72926561Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"0uuooyt4of4j"}
|
| 27 |
{"time":"2026-07-23T01:33:48.824026381Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"v9b9occvkv0z"}
|
| 28 |
{"time":"2026-07-23T01:33:48.928044163Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"3mgxscqyzkyn"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
{"time":"2026-07-23T01:33:48.72926561Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"0uuooyt4of4j"}
|
| 27 |
{"time":"2026-07-23T01:33:48.824026381Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"v9b9occvkv0z"}
|
| 28 |
{"time":"2026-07-23T01:33:48.928044163Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"3mgxscqyzkyn"}
|
| 29 |
+
{"time":"2026-07-23T02:28:50.768484688Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 30 |
+
{"time":"2026-07-23T02:28:50.768650257Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 31 |
+
{"time":"2026-07-23T02:28:50.768660338Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 32 |
+
{"time":"2026-07-23T02:28:50.768702111Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 33 |
+
{"time":"2026-07-23T02:28:50.768725726Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 34 |
+
{"time":"2026-07-23T02:28:50.768737691Z","level":"INFO","msg":"server is shutting down"}
|
| 35 |
+
{"time":"2026-07-23T02:28:50.768728092Z","level":"INFO","msg":"server is shutting down"}
|
| 36 |
+
{"time":"2026-07-23T02:28:50.768751955Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 37 |
+
{"time":"2026-07-23T02:28:50.768745569Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 38 |
+
{"time":"2026-07-23T02:28:50.768805358Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 39 |
+
{"time":"2026-07-23T02:28:50.768815828Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-814707-815594-198914184/socket","Net":"unix"}}
|
| 40 |
+
{"time":"2026-07-23T02:28:50.76883043Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-814713-815525-1635480438/socket","Net":"unix"}}
|
| 41 |
+
{"time":"2026-07-23T02:28:50.770084447Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 42 |
+
{"time":"2026-07-23T02:28:50.770158191Z","level":"INFO","msg":"server is shutting down"}
|
| 43 |
+
{"time":"2026-07-23T02:28:50.770173329Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 44 |
+
{"time":"2026-07-23T02:28:50.770146502Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 45 |
+
{"time":"2026-07-23T02:28:50.770246375Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-814719-815551-3138903381/socket","Net":"unix"}}
|
| 46 |
+
{"time":"2026-07-23T02:28:50.770382899Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 47 |
+
{"time":"2026-07-23T02:28:50.773003008Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 48 |
+
{"time":"2026-07-23T02:28:50.773054953Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 49 |
+
{"time":"2026-07-23T02:28:50.773111864Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 50 |
+
{"time":"2026-07-23T02:28:50.773106808Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 51 |
+
{"time":"2026-07-23T02:28:50.773073579Z","level":"INFO","msg":"server is shutting down"}
|
| 52 |
+
{"time":"2026-07-23T02:28:50.773200905Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-814701-815561-915654594/socket","Net":"unix"}}
|
| 53 |
+
{"time":"2026-07-23T02:28:52.626908382Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 54 |
+
{"time":"2026-07-23T02:28:52.626929775Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 55 |
+
{"time":"2026-07-23T02:28:52.626940482Z","level":"INFO","msg":"server is closed"}
|
| 56 |
+
{"time":"2026-07-23T02:28:52.662753611Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 57 |
+
{"time":"2026-07-23T02:28:52.662779647Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 58 |
+
{"time":"2026-07-23T02:28:52.662788745Z","level":"INFO","msg":"server is closed"}
|
| 59 |
+
{"time":"2026-07-23T02:28:52.68387658Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 60 |
+
{"time":"2026-07-23T02:28:52.683943364Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 61 |
+
{"time":"2026-07-23T02:28:52.683953617Z","level":"INFO","msg":"server is closed"}
|
| 62 |
+
{"time":"2026-07-23T02:29:02.470789399Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 63 |
+
{"time":"2026-07-23T02:29:02.470826347Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 64 |
+
{"time":"2026-07-23T02:29:02.470833873Z","level":"INFO","msg":"server is closed"}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/logs/debug-internal.log
CHANGED
|
@@ -245,3 +245,109 @@
|
|
| 245 |
{"time":"2026-07-23T02:11:32.739406463Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":300,"events_lines":2,"console_offset":47,"console_lines":1}
|
| 246 |
{"time":"2026-07-23T02:12:22.402029921Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 247 |
{"time":"2026-07-23T02:12:22.4021656Z","level":"INFO","msg":"filestream: sending request","total_files":0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 245 |
{"time":"2026-07-23T02:11:32.739406463Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":300,"events_lines":2,"console_offset":47,"console_lines":1}
|
| 246 |
{"time":"2026-07-23T02:12:22.402029921Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 247 |
{"time":"2026-07-23T02:12:22.4021656Z","level":"INFO","msg":"filestream: sending request","total_files":0}
|
| 248 |
+
{"time":"2026-07-23T02:12:23.362164613Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 249 |
+
{"time":"2026-07-23T02:12:23.362395596Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":302,"events_lines":6,"console_offset":47,"console_lines":1}
|
| 250 |
+
{"time":"2026-07-23T02:12:24.144626493Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 251 |
+
{"time":"2026-07-23T02:12:24.144870858Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":47,"console_lines":1}
|
| 252 |
+
{"time":"2026-07-23T02:13:12.098678344Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 253 |
+
{"time":"2026-07-23T02:13:12.099003095Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":308,"events_lines":2,"console_offset":47,"console_lines":1}
|
| 254 |
+
{"time":"2026-07-23T02:13:12.458838875Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 255 |
+
{"time":"2026-07-23T02:13:12.459121578Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":310,"events_lines":4,"console_offset":47,"console_lines":1}
|
| 256 |
+
{"time":"2026-07-23T02:14:04.269679981Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 257 |
+
{"time":"2026-07-23T02:14:04.269842494Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":47,"console_lines":1}
|
| 258 |
+
{"time":"2026-07-23T02:14:04.959605431Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 259 |
+
{"time":"2026-07-23T02:14:04.959869932Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":314,"events_lines":8,"console_offset":47,"console_lines":1}
|
| 260 |
+
{"time":"2026-07-23T02:14:47.260819768Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 261 |
+
{"time":"2026-07-23T02:14:47.261088178Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":47,"console_lines":1}
|
| 262 |
+
{"time":"2026-07-23T02:14:47.816232955Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 263 |
+
{"time":"2026-07-23T02:14:47.816499019Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":322,"events_lines":6,"console_offset":47,"console_lines":1}
|
| 264 |
+
{"time":"2026-07-23T02:15:14.209850024Z","level":"WARN","msg":"handler: ignoring partial history record","step":31600,"current":37001}
|
| 265 |
+
{"time":"2026-07-23T02:15:23.521072135Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 266 |
+
{"time":"2026-07-23T02:15:23.521353534Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":47,"console_lines":1}
|
| 267 |
+
{"time":"2026-07-23T02:15:23.982612715Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 268 |
+
{"time":"2026-07-23T02:15:23.982826206Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":328,"events_lines":4,"console_offset":47,"console_lines":2}
|
| 269 |
+
{"time":"2026-07-23T02:15:24.425232875Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 270 |
+
{"time":"2026-07-23T02:15:24.425483013Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":48,"console_lines":1}
|
| 271 |
+
{"time":"2026-07-23T02:16:01.786406101Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 272 |
+
{"time":"2026-07-23T02:16:01.786603022Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":332,"events_lines":2,"console_offset":48,"console_lines":1}
|
| 273 |
+
{"time":"2026-07-23T02:16:25.713166877Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 274 |
+
{"time":"2026-07-23T02:16:25.713431331Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":334,"events_lines":4,"console_offset":48,"console_lines":1}
|
| 275 |
+
{"time":"2026-07-23T02:17:03.266808763Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 276 |
+
{"time":"2026-07-23T02:17:03.267087671Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":338,"events_lines":2,"console_offset":48,"console_lines":1}
|
| 277 |
+
{"time":"2026-07-23T02:17:50.530237524Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 278 |
+
{"time":"2026-07-23T02:17:50.530495713Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":340,"events_lines":6,"console_offset":48,"console_lines":1}
|
| 279 |
+
{"time":"2026-07-23T02:18:20.451787991Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 280 |
+
{"time":"2026-07-23T02:18:20.452026414Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":346,"events_lines":6,"console_offset":48,"console_lines":1}
|
| 281 |
+
{"time":"2026-07-23T02:19:01.788519665Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 282 |
+
{"time":"2026-07-23T02:19:01.788703845Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":352,"events_lines":4,"console_offset":48,"console_lines":1}
|
| 283 |
+
{"time":"2026-07-23T02:19:02.328045556Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 284 |
+
{"time":"2026-07-23T02:19:02.328268427Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":356,"events_lines":6,"console_offset":48,"console_lines":1}
|
| 285 |
+
{"time":"2026-07-23T02:19:02.759022028Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 286 |
+
{"time":"2026-07-23T02:19:02.759194577Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":48,"console_lines":1}
|
| 287 |
+
{"time":"2026-07-23T02:19:03.248435965Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 288 |
+
{"time":"2026-07-23T02:19:16.837240643Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":362,"events_lines":2,"console_offset":48,"console_lines":1}
|
| 289 |
+
{"time":"2026-07-23T02:19:17.303817335Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 290 |
+
{"time":"2026-07-23T02:19:31.836655244Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":364,"events_lines":2,"console_offset":48,"console_lines":1}
|
| 291 |
+
{"time":"2026-07-23T02:20:04.018094282Z","level":"WARN","msg":"handler: ignoring partial history record","step":31800,"current":37001}
|
| 292 |
+
{"time":"2026-07-23T02:20:13.742987022Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 293 |
+
{"time":"2026-07-23T02:20:13.743151354Z","level":"INFO","msg":"filestream: sending request","total_files":0}
|
| 294 |
+
{"time":"2026-07-23T02:20:14.186936411Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 295 |
+
{"time":"2026-07-23T02:20:14.187196098Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":366,"events_lines":5,"console_offset":48,"console_lines":2}
|
| 296 |
+
{"time":"2026-07-23T02:20:14.606163567Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 297 |
+
{"time":"2026-07-23T02:20:14.606358638Z","level":"INFO","msg":"filestream: sending request","total_files":1,"events_offset":371,"events_lines":1}
|
| 298 |
+
{"time":"2026-07-23T02:20:47.648537651Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 299 |
+
{"time":"2026-07-23T02:20:47.648719247Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":372,"events_lines":1,"console_offset":49,"console_lines":1}
|
| 300 |
+
{"time":"2026-07-23T02:20:48.12626836Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 301 |
+
{"time":"2026-07-23T02:20:48.126523688Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":373,"events_lines":3,"console_offset":49,"console_lines":1}
|
| 302 |
+
{"time":"2026-07-23T02:21:12.996289747Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 303 |
+
{"time":"2026-07-23T02:21:12.996538083Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":376,"events_lines":1,"console_offset":49,"console_lines":1}
|
| 304 |
+
{"time":"2026-07-23T02:21:40.076672259Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 305 |
+
{"time":"2026-07-23T02:21:40.076833315Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":377,"events_lines":2,"console_offset":49,"console_lines":1}
|
| 306 |
+
{"time":"2026-07-23T02:22:12.591294436Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 307 |
+
{"time":"2026-07-23T02:22:12.591534984Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":379,"events_lines":3,"console_offset":49,"console_lines":1}
|
| 308 |
+
{"time":"2026-07-23T02:22:13.008257666Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 309 |
+
{"time":"2026-07-23T02:22:13.008448544Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":382,"events_lines":4,"console_offset":49,"console_lines":1}
|
| 310 |
+
{"time":"2026-07-23T02:22:43.455358315Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 311 |
+
{"time":"2026-07-23T02:22:43.4555333Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":49,"console_lines":1}
|
| 312 |
+
{"time":"2026-07-23T02:23:15.177406156Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 313 |
+
{"time":"2026-07-23T02:23:15.177600701Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":386,"events_lines":4,"console_offset":49,"console_lines":1}
|
| 314 |
+
{"time":"2026-07-23T02:23:15.790816852Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 315 |
+
{"time":"2026-07-23T02:23:15.791043145Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":390,"events_lines":6,"console_offset":49,"console_lines":1}
|
| 316 |
+
{"time":"2026-07-23T02:23:16.511965589Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 317 |
+
{"time":"2026-07-23T02:23:16.531664799Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":49,"console_lines":1}
|
| 318 |
+
{"time":"2026-07-23T02:24:09.59999693Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 319 |
+
{"time":"2026-07-23T02:24:09.600190154Z","level":"INFO","msg":"filestream: sending request","total_files":0}
|
| 320 |
+
{"time":"2026-07-23T02:24:10.096383571Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 321 |
+
{"time":"2026-07-23T02:24:10.096565421Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":396,"events_lines":6,"console_offset":49,"console_lines":1}
|
| 322 |
+
{"time":"2026-07-23T02:24:10.56096879Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 323 |
+
{"time":"2026-07-23T02:24:10.87257939Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":49,"console_lines":1}
|
| 324 |
+
{"time":"2026-07-23T02:24:51.945277879Z","level":"WARN","msg":"handler: ignoring partial history record","step":32000,"current":37001}
|
| 325 |
+
{"time":"2026-07-23T02:24:53.714569624Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 326 |
+
{"time":"2026-07-23T02:24:53.714700687Z","level":"INFO","msg":"filestream: sending request","total_files":0}
|
| 327 |
+
{"time":"2026-07-23T02:24:54.093680458Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 328 |
+
{"time":"2026-07-23T02:24:54.093909985Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":402,"events_lines":6,"console_offset":49,"console_lines":2}
|
| 329 |
+
{"time":"2026-07-23T02:25:49.372929793Z","level":"INFO","msg":"api: retrying HTTP error","status":500,"url":"https://api.wandb.ai/files/minje227_hyu-hanyang-university/lerobot/pgr3eari/file_stream","body":"{\"error\":\"context deadline exceeded\"}"}
|
| 330 |
+
{"time":"2026-07-23T02:26:24.414750595Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 331 |
+
{"time":"2026-07-23T02:26:24.414969006Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":50,"console_lines":1}
|
| 332 |
+
{"time":"2026-07-23T02:27:04.885943619Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 333 |
+
{"time":"2026-07-23T02:27:04.886281642Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":408,"events_lines":12,"console_offset":50,"console_lines":1}
|
| 334 |
+
{"time":"2026-07-23T02:27:05.35140455Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 335 |
+
{"time":"2026-07-23T02:27:05.351607052Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":420,"events_lines":6,"console_offset":50,"console_lines":1}
|
| 336 |
+
{"time":"2026-07-23T02:27:31.046145432Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 337 |
+
{"time":"2026-07-23T02:27:31.046284597Z","level":"INFO","msg":"filestream: sending request","total_files":1,"console_offset":50,"console_lines":1}
|
| 338 |
+
{"time":"2026-07-23T02:27:58.5330972Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 339 |
+
{"time":"2026-07-23T02:27:58.533277753Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":426,"events_lines":4,"console_offset":50,"console_lines":1}
|
| 340 |
+
{"time":"2026-07-23T02:27:58.938590054Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 341 |
+
{"time":"2026-07-23T02:27:58.938897544Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":430,"events_lines":2,"console_offset":50,"console_lines":1}
|
| 342 |
+
{"time":"2026-07-23T02:28:32.127453304Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 343 |
+
{"time":"2026-07-23T02:28:32.127626571Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":432,"events_lines":2,"console_offset":50,"console_lines":1}
|
| 344 |
+
{"time":"2026-07-23T02:28:52.097937416Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
|
| 345 |
+
{"time":"2026-07-23T02:29:01.470938231Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 346 |
+
{"time":"2026-07-23T02:29:01.471166513Z","level":"INFO","msg":"filestream: sending request","total_files":2,"events_offset":434,"events_lines":4,"console_offset":50,"console_lines":1}
|
| 347 |
+
{"time":"2026-07-23T02:29:01.947602559Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 348 |
+
{"time":"2026-07-23T02:29:01.947868498Z","level":"INFO","msg":"filestream: sending request","total_files":3,"events_offset":438,"events_lines":2,"console_offset":50,"console_lines":41,"uploaded_len":3,"complete":true,"exit_code":255}
|
| 349 |
+
{"time":"2026-07-23T02:29:02.470009043Z","level":"INFO","msg":"filestream: request sent","status":"200 OK"}
|
| 350 |
+
{"time":"2026-07-23T02:29:02.470189702Z","level":"INFO","msg":"stream: finishing up"}
|
| 351 |
+
{"time":"2026-07-23T02:29:02.470200334Z","level":"INFO","msg":"handler: closed"}
|
| 352 |
+
{"time":"2026-07-23T02:29:02.470273871Z","level":"INFO","msg":"sender: closed"}
|
| 353 |
+
{"time":"2026-07-23T02:29:02.470277743Z","level":"INFO","msg":"stream: all finished"}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_013342-pgr3eari/logs/debug.log
CHANGED
|
@@ -18,3 +18,48 @@ config: {'dataset': {'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2'
|
|
| 18 |
2026-07-23 01:33:43,705 INFO MainThread:814719 [wandb_run.py:_redirect():2442] Wrapping output streams.
|
| 19 |
2026-07-23 01:33:43,705 INFO MainThread:814719 [wandb_run.py:_redirect():2465] Redirects installed.
|
| 20 |
2026-07-23 01:33:43,706 INFO MainThread:814719 [wandb_init.py:init():1010] run started, returning control to user process
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
2026-07-23 01:33:43,705 INFO MainThread:814719 [wandb_run.py:_redirect():2442] Wrapping output streams.
|
| 19 |
2026-07-23 01:33:43,705 INFO MainThread:814719 [wandb_run.py:_redirect():2465] Redirects installed.
|
| 20 |
2026-07-23 01:33:43,706 INFO MainThread:814719 [wandb_init.py:init():1010] run started, returning control to user process
|
| 21 |
+
2026-07-23 02:28:50,770 INFO wandb-AsyncioManager-main:814719 [service_client.py:_forward_responses():122] Reached EOF.
|
| 22 |
+
2026-07-23 02:28:50,770 INFO wandb-AsyncioManager-main:814719 [mailbox.py:close():154] Closing mailbox, abandoning 2 handles.
|
| 23 |
+
2026-07-23 02:28:50,770 ERROR wandb-AsyncioManager-main:814719 [asyncio_manager.py:fn_wrap_exceptions():184] Uncaught exception in run_soon callback.
|
| 24 |
+
Traceback (most recent call last):
|
| 25 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_manager.py", line 182, in fn_wrap_exceptions
|
| 26 |
+
await fn()
|
| 27 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_messages.py", line 90, in loop
|
| 28 |
+
await asyncio_compat.race(
|
| 29 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 278, in race
|
| 30 |
+
async with open_task_group(race=True) as tg:
|
| 31 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 32 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/contextlib.py", line 217, in __aexit__
|
| 33 |
+
await anext(self.gen)
|
| 34 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 240, in open_task_group
|
| 35 |
+
await task_group._wait_all(race=race, timeout=exit_timeout)
|
| 36 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 180, in _wait_all
|
| 37 |
+
raise exc
|
| 38 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_messages.py", line 113, in _print_all
|
| 39 |
+
result = await handle.wait_async(timeout=None)
|
| 40 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 41 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/mailbox_handle.py", line 127, in wait_async
|
| 42 |
+
response = await self._handle.wait_async(timeout=timeout)
|
| 43 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 44 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/response_handle.py", line 123, in wait_async
|
| 45 |
+
raise HandleAbandonedError()
|
| 46 |
+
wandb.sdk.mailbox.mailbox_handle.HandleAbandonedError
|
| 47 |
+
2026-07-23 02:28:59,234 ERROR wandb-AsyncioManager-main:814719 [asyncio_manager.py:fn_wrap_exceptions():184] Uncaught exception in run_soon callback.
|
| 48 |
+
Traceback (most recent call last):
|
| 49 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_manager.py", line 182, in fn_wrap_exceptions
|
| 50 |
+
await fn()
|
| 51 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_stopping.py", line 87, in loop
|
| 52 |
+
should_stop = await self._check_should_stop()
|
| 53 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 54 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_stopping.py", line 115, in _check_should_stop
|
| 55 |
+
handle = await self._interface.deliver_async(request)
|
| 56 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 57 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/interface/interface_sock.py", line 58, in deliver_async
|
| 58 |
+
handle = await self._client.deliver(request)
|
| 59 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 60 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/service/service_client.py", line 57, in deliver
|
| 61 |
+
handle = self._mailbox.require_response(request)
|
| 62 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 63 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/mailbox.py", line 89, in require_response
|
| 64 |
+
raise MailboxClosedError()
|
| 65 |
+
wandb.sdk.mailbox.mailbox.MailboxClosedError
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/files/wandb-summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"_wandb":{"runtime":0},"_runtime":0}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug-core.log
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-07-23T02:29:37.218272849Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpbi3491l3/port-2499418.txt","pid":2499418,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 2 |
+
{"time":"2026-07-23T02:29:37.218902899Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2499418}
|
| 3 |
+
{"time":"2026-07-23T02:29:37.218864854Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2499418-2500321-1544228546/socket","Net":"unix"}}
|
| 4 |
+
{"time":"2026-07-23T02:29:37.402297125Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 5 |
+
{"time":"2026-07-23T02:29:37.409066123Z","level":"INFO","msg":"handleInformInit: received","streamId":"eb0sb786","id":"1(@)"}
|
| 6 |
+
{"time":"2026-07-23T02:29:37.868916316Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"eb0sb786","id":"1(@)"}
|
| 7 |
+
{"time":"2026-07-23T02:29:37.870710243Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpewnffvrr/port-2499551.txt","pid":2499551,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 8 |
+
{"time":"2026-07-23T02:29:37.871145347Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2499551-2500408-2757815951/socket","Net":"unix"}}
|
| 9 |
+
{"time":"2026-07-23T02:29:37.871202129Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2499551}
|
| 10 |
+
{"time":"2026-07-23T02:29:38.054483267Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 11 |
+
{"time":"2026-07-23T02:29:38.064116376Z","level":"INFO","msg":"handleInformInit: received","streamId":"cemf0rge","id":"1(@)"}
|
| 12 |
+
{"time":"2026-07-23T02:29:38.350897746Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 13 |
+
{"time":"2026-07-23T02:29:38.351103797Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 14 |
+
{"time":"2026-07-23T02:29:38.351133399Z","level":"INFO","msg":"server is shutting down"}
|
| 15 |
+
{"time":"2026-07-23T02:29:38.351150646Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 16 |
+
{"time":"2026-07-23T02:29:38.351193796Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 17 |
+
{"time":"2026-07-23T02:29:38.351238698Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-2499418-2500321-1544228546/socket","Net":"unix"}}
|
| 18 |
+
{"time":"2026-07-23T02:29:38.352704212Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 19 |
+
{"time":"2026-07-23T02:29:38.352724918Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 20 |
+
{"time":"2026-07-23T02:29:38.352730597Z","level":"INFO","msg":"server is closed"}
|
| 21 |
+
{"time":"2026-07-23T02:29:38.445119298Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"cemf0rge","id":"1(@)"}
|
| 22 |
+
{"time":"2026-07-23T02:29:38.796444376Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 23 |
+
{"time":"2026-07-23T02:29:38.796598651Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 24 |
+
{"time":"2026-07-23T02:29:38.796618722Z","level":"INFO","msg":"server is shutting down"}
|
| 25 |
+
{"time":"2026-07-23T02:29:38.796624128Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 26 |
+
{"time":"2026-07-23T02:29:38.796668926Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 27 |
+
{"time":"2026-07-23T02:29:38.796751175Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-2499551-2500408-2757815951/socket","Net":"unix"}}
|
| 28 |
+
{"time":"2026-07-23T02:29:38.797992882Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 29 |
+
{"time":"2026-07-23T02:29:38.798016256Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 30 |
+
{"time":"2026-07-23T02:29:38.798022072Z","level":"INFO","msg":"server is closed"}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug-internal.log
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-07-23T02:29:38.064274108Z","level":"INFO","msg":"wandb-core"}
|
| 2 |
+
{"time":"2026-07-23T02:29:38.06450816Z","level":"INFO","msg":"stream: starting","core version":"0.27.2"}
|
| 3 |
+
{"time":"2026-07-23T02:29:38.44495026Z","level":"INFO","msg":"stream: created new stream","id":"cemf0rge"}
|
| 4 |
+
{"time":"2026-07-23T02:29:38.445115186Z","level":"INFO","msg":"stream: started"}
|
| 5 |
+
{"time":"2026-07-23T02:29:38.44526429Z","level":"INFO","msg":"writer: started","stream_id":"cemf0rge"}
|
| 6 |
+
{"time":"2026-07-23T02:29:38.445290711Z","level":"INFO","msg":"handler: started"}
|
| 7 |
+
{"time":"2026-07-23T02:29:38.445315115Z","level":"INFO","msg":"sender: started"}
|
| 8 |
+
{"time":"2026-07-23T02:29:38.786524565Z","level":"ERROR","msg":"runupserter: failed to init run","error":"no data but must resume"}
|
| 9 |
+
{"time":"2026-07-23T02:29:38.796867757Z","level":"ERROR","msg":"sender: uploadConfigFile: runhandle: run not yet initialized"}
|
| 10 |
+
{"time":"2026-07-23T02:29:38.797204677Z","level":"ERROR","msg":"runfiles: runhandle: run not yet initialized"}
|
| 11 |
+
{"time":"2026-07-23T02:29:38.797284772Z","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
|
| 12 |
+
{"time":"2026-07-23T02:29:38.797292885Z","level":"INFO","msg":"stream: finishing up"}
|
| 13 |
+
{"time":"2026-07-23T02:29:38.797301918Z","level":"INFO","msg":"handler: closed"}
|
| 14 |
+
{"time":"2026-07-23T02:29:38.797325603Z","level":"INFO","msg":"sender: closed"}
|
| 15 |
+
{"time":"2026-07-23T02:29:38.797328171Z","level":"INFO","msg":"stream: all finished"}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug.log
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-07-23 02:29:37,836 INFO MainThread:2499551 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
|
| 2 |
+
2026-07-23 02:29:37,836 INFO MainThread:2499551 [wandb_setup.py:_flush():81] Configure stats pid to 2499551
|
| 3 |
+
2026-07-23 02:29:37,836 INFO MainThread:2499551 [wandb_setup.py:_flush():81] Loading settings from environment variables
|
| 4 |
+
2026-07-23 02:29:37,836 INFO MainThread:2499551 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug.log
|
| 5 |
+
2026-07-23 02:29:37,836 INFO MainThread:2499551 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/logs/debug-internal.log
|
| 6 |
+
2026-07-23 02:29:37,836 INFO MainThread:2499551 [wandb_init.py:init():766] calling init triggers
|
| 7 |
+
2026-07-23 02:29:37,837 INFO MainThread:2499551 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
|
| 8 |
+
config: {'dataset': {'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2', 'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2', 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}, 'affine': {'weight': 1.0, 'type': 'RandomAffine', 'kwargs': {'degrees': [-5.0, 5.0], 'translate': [0.05, 0.05]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'torchcodec', 'return_uint8': False, 'depth_output_unit': 'mm', 'streaming': False, 'eval_split': 0.0}, 'env': None, 'policy': {'type': 'groot_rkd', 'n_obs_steps': 1, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [16]}, 'observation.images.wrist': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.right_shoulder': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.guide': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [10]}}, 'device': 'cuda', 'use_amp': False, 'use_peft': False, 'push_to_hub': False, 'repo_id': None, 'private': None, 'tags': None, 'license': None, 'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model', 'pretrained_revision': None, 'chunk_size': 16, 'n_action_steps': 16, 'max_state_dim': 132, 'max_action_dim': 132, 'normalization_mapping': {'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'STATE': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'ACTION': <NormalizationMode.IDENTITY: 'IDENTITY'>}, 'base_model_path': 'nvidia/GR00T-N1.7-3B', 'action_decode_transform': None, 'embodiment_tag': 'new_embodiment', 'tune_llm': False, 'tune_visual': False, 'tune_projector': True, 'tune_diffusion_model': True, 'tune_vlln': True, 'tune_top_llm_layers': 0, 'num_inference_timesteps': None, 'rtc_ramp_rate': None, 'use_flash_attention': False, 'use_relative_actions': False, 'relative_exclude_joints': [], 'optimizer_lr': 0.0001, 'optimizer_betas': [0.9, 0.999], 'optimizer_eps': 1e-08, 'optimizer_weight_decay': 1e-05, 'warmup_steps': 3000, 'warmup_ratio': 0.05, 'use_bf16': True, 'model_params_fp32': True, 'image_size': [256, 256], 'tokenizer_assets_repo': None, 'lora_rank': 0, 'lora_alpha': 16, 'lora_dropout': 0.1, 'lora_full_model': False, 'video_backend': 'decord', 'balance_dataset_weights': True, 'balance_trajectory_weights': True, 'dataset_paths': None, 'output_dir': './tmp/gr00t', 'save_steps': 1000, 'max_steps': 10000, 'batch_size': 32, 'dataloader_num_workers': 8, 'report_to': 'wandb', 'resume': False, 'action_expert_num_layers': 16, 'rkd_enabled': True, 'rkd_vae_checkpoint': '/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11', 'rkd_student_pooling': 'attention', 'rkd_student_attention_hidden_dim': 512, 'rkd_student_attention_output_dim': 512, 'rkd_fm_loss_weight': 1.0, 'rkd_loss_weight': 1.0, 'rkd_distance_weight': 1.0, 'rkd_angle_weight': 2.0}, 'reward_model': None, 'output_dir': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K', 'job_name': 'INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60', 'resume': True, 'seed': 42, 'cudnn_deterministic': False, 'num_workers': 4, 'batch_size': 64, 'prefetch_factor': 4, 'persistent_workers': True, 'steps': 60000, 'env_eval_freq': 20000, 'log_freq': 200, 'eval_steps': 0, 'max_eval_samples': 0, 'tolerance_s': 0.0001, 'save_checkpoint': True, 'save_freq': 20000, 'use_policy_training_preset': True, 'optimizer': {'type': 'adamw', 'lr': 0.0001, 'weight_decay': 1e-05, 'grad_clip_norm': 1.0, 'betas': [0.9, 0.999], 'eps': 1e-08}, 'scheduler': {'type': 'diffuser', 'num_warmup_steps': 3000, 'name': 'cosine'}, 'eval': {'n_episodes': 50, 'batch_size': 50, 'use_async_envs': True, 'recording': False, 'recording_repo_id': None, 'recording_private': False}, 'wandb': {'enable': True, 'disable_artifact': True, 'project': 'lerobot', 'entity': None, 'notes': None, 'run_id': 'cemf0rge', 'mode': None, 'add_tags': True}, 'peft': None, 'job': {'target': None, 'image': 'huggingface/lerobot-gpu:latest', 'timeout': '2d', 'detach': False, 'tags': []}, 'save_checkpoint_to_hub': False, 'sample_weighting': None, 'rename_map': {}, 'checkpoint_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000', '_wandb': {}}
|
| 9 |
+
2026-07-23 02:29:37,837 INFO MainThread:2499551 [wandb_init.py:init():814] starting backend
|
| 10 |
+
2026-07-23 02:29:38,054 INFO MainThread:2499551 [wandb_init.py:init():829] sending inform_init request
|
| 11 |
+
2026-07-23 02:29:38,446 INFO MainThread:2499551 [wandb_init.py:init():834] backend started and connected
|
| 12 |
+
2026-07-23 02:29:38,447 INFO MainThread:2499551 [wandb_init.py:init():904] updated telemetry
|
| 13 |
+
2026-07-23 02:29:38,453 INFO MainThread:2499551 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_022937-cemf0rge/run-cemf0rge.wandb
ADDED
|
Binary file (5.07 kB). View file
|
|
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/files/output.log
ADDED
|
@@ -0,0 +1,149 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
INFO 2026-07-23 02:31:26 db_utils.py:126 Logs will be synced with wandb.
|
| 2 |
+
INFO 2026-07-23 02:31:26 db_utils.py:127 Track this run --> https://wandb.ai/minje227_hyu-hanyang-university/lerobot/runs/rs1egwv8
|
| 3 |
+
INFO 2026-07-23 02:31:26 ot_train.py:307 Creating dataset
|
| 4 |
+
INFO 2026-07-23 02:31:29 ot_train.py:341 Creating policy
|
| 5 |
+
INFO 2026-07-23 02:31:29 ng_groot.py:193 The Groot policy wraps NVIDIA's GR00T n1.7 model. Loading pretrained model from: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model
|
| 6 |
+
INFO 2026-07-23 02:31:29 ng_groot.py:227 Detected fine-tuned LeRobot checkpoint, loading with state dict...
|
| 7 |
+
Fetching 27 files: 100%|██████████| 27/27 [00:00<00:00, 1256.77it/s]
|
| 8 |
+
`torch_dtype` is deprecated! Use `dtype` instead!
|
| 9 |
+
Loading weights: 100%|██████████| 807/807 [00:01<00:00, 580.05it/s]
|
| 10 |
+
[1mGR00TN17 LOAD REPORT[0m from: /home/ext_minje/.cache/huggingface/hub/models--nvidia--GR00T-N1.7-3B/snapshots/2fc962b973bccdd5d8ce4f67cc63b264d6886495
|
| 11 |
+
Key | Status | |
|
| 12 |
+
---------------------------------------------------------------------+------------+--+-
|
| 13 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_out.0.bias | UNEXPECTED | |
|
| 14 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.2.bias | UNEXPECTED | |
|
| 15 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_q.weight | UNEXPECTED | |
|
| 16 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.0.proj.weight | UNEXPECTED | |
|
| 17 |
+
action_head.model.transformer_blocks.{16...31}.norm1.linear.bias | UNEXPECTED | |
|
| 18 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_q.bias | UNEXPECTED | |
|
| 19 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_k.bias | UNEXPECTED | |
|
| 20 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_v.weight | UNEXPECTED | |
|
| 21 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_out.0.weight | UNEXPECTED | |
|
| 22 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_v.bias | UNEXPECTED | |
|
| 23 |
+
action_head.model.transformer_blocks.{16...31}.norm1.linear.weight | UNEXPECTED | |
|
| 24 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_k.weight | UNEXPECTED | |
|
| 25 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.0.proj.bias | UNEXPECTED | |
|
| 26 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.2.weight | UNEXPECTED | |
|
| 27 |
+
|
| 28 |
+
Notes:
|
| 29 |
+
- UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch.
|
| 30 |
+
Loading weights from local directory
|
| 31 |
+
INFO 2026-07-23 02:31:45 ot_train.py:414 Creating optimizer and scheduler
|
| 32 |
+
INFO 2026-07-23 02:31:47 ot_train.py:448 Output dir: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 33 |
+
INFO 2026-07-23 02:31:47 ot_train.py:455 cfg.steps=60000 (60K)
|
| 34 |
+
INFO 2026-07-23 02:31:47 ot_train.py:456 dataset.num_frames=218367 (218K)
|
| 35 |
+
INFO 2026-07-23 02:31:47 ot_train.py:457 dataset.num_episodes=4930
|
| 36 |
+
INFO 2026-07-23 02:31:47 ot_train.py:460 Effective batch size: 64 x 1 = 64
|
| 37 |
+
INFO 2026-07-23 02:31:47 ot_train.py:461 num_learnable_params=1080755329 (1B)
|
| 38 |
+
INFO 2026-07-23 02:31:47 ot_train.py:462 num_total_params=2604374177 (3B)
|
| 39 |
+
INFO 2026-07-23 02:31:47 ot_train.py:503 Resuming data order at epoch 13, sample 42176
|
| 40 |
+
Training: 0%| | 0/30000 [00:00<?, ?step/s]INFO 2026-07-23 02:31:48 ot_train.py:613 Start offline training on a fixed dataset, with effective batch size: 64
|
| 41 |
+
Training: 1%| | 200/30000 [05:04<11:42:04, 1.41s/step]INFO 2026-07-23 02:36:52 ot_train.py:658 step:30K smpl:2M ep:44K epch:8.85 loss:0.041 grdn:0.319 lr:5.4e-05 updt_s:0.810 data_s:0.712 smp/s:42 mem_gb:29.84
|
| 42 |
+
Training: 1%|▏ | 400/30000 [09:58<11:50:43, 1.44s/step]INFO 2026-07-23 02:41:46 ot_train.py:658 step:30K smpl:2M ep:44K epch:8.91 loss:0.040 grdn:0.308 lr:5.3e-05 updt_s:0.777 data_s:0.689 smp/s:44 mem_gb:29.84
|
| 43 |
+
Training: 2%|▏ | 600/30000 [14:54<11:47:28, 1.44s/step]INFO 2026-07-23 02:46:42 ot_train.py:658 step:31K smpl:2M ep:44K epch:8.97 loss:0.040 grdn:0.310 lr:5.3e-05 updt_s:0.775 data_s:0.698 smp/s:43 mem_gb:29.84
|
| 44 |
+
Training: 3%|▎ | 800/30000 [19:52<12:08:23, 1.50s/step]INFO 2026-07-23 02:51:40 ot_train.py:658 step:31K smpl:2M ep:45K epch:9.03 loss:0.040 grdn:0.301 lr:5.2e-05 updt_s:0.772 data_s:0.716 smp/s:43 mem_gb:29.84
|
| 45 |
+
Training: 3%|▎ | 1000/30000 [26:19<28:06:38, 3.49s/step]INFO 2026-07-23 02:58:07 ot_train.py:658 step:31K smpl:2M ep:45K epch:9.09 loss:0.039 grdn:0.292 lr:5.2e-05 updt_s:0.762 data_s:1.168 smp/s:33 mem_gb:29.84
|
| 46 |
+
Training: 4%|▍ | 1200/30000 [34:20<17:28:09, 2.18s/step]INFO 2026-07-23 03:06:08 ot_train.py:658 step:31K smpl:2M ep:45K epch:9.14 loss:0.040 grdn:0.304 lr:5.1e-05 updt_s:0.786 data_s:1.620 smp/s:27 mem_gb:29.84
|
| 47 |
+
Training: 5%|▍ | 1400/30000 [40:26<11:57:15, 1.50s/step]INFO 2026-07-23 03:12:14 ot_train.py:658 step:31K smpl:2M ep:45K epch:9.20 loss:0.040 grdn:0.336 lr:5.1e-05 updt_s:0.776 data_s:1.048 smp/s:35 mem_gb:29.84
|
| 48 |
+
Training: 5%|▌ | 1600/30000 [46:11<27:09:05, 3.44s/step]INFO 2026-07-23 03:17:59 ot_train.py:658 step:32K smpl:2M ep:46K epch:9.26 loss:0.039 grdn:0.302 lr:5.0e-05 updt_s:0.825 data_s:0.896 smp/s:37 mem_gb:29.82
|
| 49 |
+
Training: 6%|▌ | 1800/30000 [54:38<24:33:23, 3.13s/step]INFO 2026-07-23 03:26:26 ot_train.py:658 step:32K smpl:2M ep:46K epch:9.32 loss:0.037 grdn:0.286 lr:4.9e-05 updt_s:0.823 data_s:1.707 smp/s:25 mem_gb:29.85
|
| 50 |
+
Training: 7%|▋ | 2000/30000 [1:01:43<14:06:08, 1.81s/step]INFO 2026-07-23 03:33:31 ot_train.py:658 step:32K smpl:2M ep:46K epch:9.38 loss:0.037 grdn:0.297 lr:4.9e-05 updt_s:0.807 data_s:1.319 smp/s:30 mem_gb:29.85
|
| 51 |
+
Training: 7%|▋ | 2200/30000 [1:08:07<13:17:12, 1.72s/step]INFO 2026-07-23 03:39:55 ot_train.py:658 step:32K smpl:2M ep:47K epch:9.44 loss:0.037 grdn:0.289 lr:4.8e-05 updt_s:0.828 data_s:1.087 smp/s:33 mem_gb:29.85
|
| 52 |
+
Training: 8%|▊ | 2400/30000 [1:13:30<9:55:12, 1.29s/step]INFO 2026-07-23 03:45:18 ot_train.py:658 step:32K smpl:2M ep:47K epch:9.50 loss:0.037 grdn:0.298 lr:4.8e-05 updt_s:0.809 data_s:0.801 smp/s:40 mem_gb:29.85
|
| 53 |
+
Training: 9%|▊ | 2600/30000 [1:18:14<9:50:52, 1.29s/step]INFO 2026-07-23 03:50:02 ot_train.py:658 step:33K smpl:2M ep:47K epch:9.55 loss:0.037 grdn:0.286 lr:4.7e-05 updt_s:0.862 data_s:0.553 smp/s:45 mem_gb:29.85
|
| 54 |
+
Training: 9%|▉ | 2800/30000 [1:22:35<9:47:49, 1.30s/step]INFO 2026-07-23 03:54:23 ot_train.py:658 step:33K smpl:2M ep:47K epch:9.61 loss:0.036 grdn:0.301 lr:4.7e-05 updt_s:0.765 data_s:0.539 smp/s:49 mem_gb:29.84
|
| 55 |
+
Training: 10%|█ | 3000/30000 [1:27:06<9:32:39, 1.27s/step]INFO 2026-07-23 03:58:54 ot_train.py:658 step:33K smpl:2M ep:48K epch:9.67 loss:0.036 grdn:0.282 lr:4.6e-05 updt_s:0.772 data_s:0.578 smp/s:47 mem_gb:29.85
|
| 56 |
+
Training: 11%|█ | 3200/30000 [1:32:14<33:05:48, 4.45s/step]INFO 2026-07-23 04:04:02 ot_train.py:658 step:33K smpl:2M ep:48K epch:9.73 loss:0.036 grdn:0.287 lr:4.6e-05 updt_s:0.888 data_s:0.648 smp/s:42 mem_gb:29.84
|
| 57 |
+
Training: 11%|█▏ | 3400/30000 [1:38:58<10:00:45, 1.36s/step]INFO 2026-07-23 04:10:46 ot_train.py:658 step:33K smpl:2M ep:48K epch:9.79 loss:0.037 grdn:0.296 lr:4.5e-05 updt_s:1.109 data_s:0.908 smp/s:32 mem_gb:29.85
|
| 58 |
+
Training: 12%|█▏ | 3600/30000 [1:43:42<9:21:23, 1.28s/step]INFO 2026-07-23 04:15:30 ot_train.py:658 step:34K smpl:2M ep:49K epch:9.85 loss:0.035 grdn:0.276 lr:4.4e-05 updt_s:0.799 data_s:0.618 smp/s:45 mem_gb:29.84
|
| 59 |
+
Training: 13%|█▎ | 3800/30000 [1:48:01<9:15:45, 1.27s/step]INFO 2026-07-23 04:19:49 ot_train.py:658 step:34K smpl:2M ep:49K epch:9.91 loss:0.035 grdn:0.291 lr:4.4e-05 updt_s:0.745 data_s:0.546 smp/s:50 mem_gb:29.84
|
| 60 |
+
Training: 13%|█▎ | 4000/30000 [1:52:21<9:11:59, 1.27s/step]INFO 2026-07-23 04:24:09 ot_train.py:658 step:34K smpl:2M ep:49K epch:9.96 loss:0.034 grdn:0.293 lr:4.3e-05 updt_s:0.744 data_s:0.554 smp/s:49 mem_gb:29.83
|
| 61 |
+
Training: 14%|█▍ | 4200/30000 [1:56:41<9:46:57, 1.37s/step] INFO 2026-07-23 04:28:29 ot_train.py:658 step:34K smpl:2M ep:49K epch:10.02 loss:0.033 grdn:0.270 lr:4.3e-05 updt_s:0.748 data_s:0.550 smp/s:49 mem_gb:29.85
|
| 62 |
+
Training: 15%|█▍ | 4400/30000 [2:00:59<9:23:54, 1.32s/step]INFO 2026-07-23 04:32:48 ot_train.py:658 step:34K smpl:2M ep:50K epch:10.08 loss:0.033 grdn:0.283 lr:4.2e-05 updt_s:0.739 data_s:0.549 smp/s:50 mem_gb:29.85
|
| 63 |
+
Training: 15%|█▌ | 4600/30000 [2:05:24<9:16:51, 1.32s/step]INFO 2026-07-23 04:37:12 ot_train.py:658 step:35K smpl:2M ep:50K epch:10.14 loss:0.033 grdn:0.295 lr:4.2e-05 updt_s:0.753 data_s:0.568 smp/s:48 mem_gb:29.85
|
| 64 |
+
Training: 16%|█▌ | 4800/30000 [2:09:46<9:00:30, 1.29s/step]INFO 2026-07-23 04:41:34 ot_train.py:658 step:35K smpl:2M ep:50K epch:10.20 loss:0.034 grdn:0.310 lr:4.1e-05 updt_s:0.742 data_s:0.563 smp/s:49 mem_gb:29.85
|
| 65 |
+
Training: 17%|█▋ | 5000/30000 [2:14:08<9:19:05, 1.34s/step]INFO 2026-07-23 04:45:56 ot_train.py:658 step:35K smpl:2M ep:51K epch:10.26 loss:0.034 grdn:0.291 lr:4.1e-05 updt_s:0.730 data_s:0.578 smp/s:49 mem_gb:29.85
|
| 66 |
+
INFO 2026-07-23 04:45:56 ot_train.py:703 Checkpoint policy after step 35000
|
| 67 |
+
INFO 2026-07-23 04:46:20 in_yaml.py:1413 Saved verified rolling checkpoint step=35000 slot=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00
|
| 68 |
+
Training: 17%|█▋ | 5200/30000 [2:18:55<8:50:43, 1.28s/step]INFO 2026-07-23 04:50:43 ot_train.py:658 step:35K smpl:2M ep:51K epch:10.32 loss:0.033 grdn:0.286 lr:4.0e-05 updt_s:0.774 data_s:0.539 smp/s:49 mem_gb:29.84
|
| 69 |
+
Training: 18%|█▊ | 5400/30000 [2:23:14<8:57:44, 1.31s/step]INFO 2026-07-23 04:55:02 ot_train.py:658 step:35K smpl:2M ep:51K epch:10.38 loss:0.033 grdn:0.283 lr:4.0e-05 updt_s:0.775 data_s:0.514 smp/s:50 mem_gb:29.84
|
| 70 |
+
Training: 19%|█▊ | 5600/30000 [2:27:37<8:55:10, 1.32s/step]INFO 2026-07-23 04:59:25 ot_train.py:658 step:36K smpl:2M ep:51K epch:10.43 loss:0.033 grdn:0.290 lr:3.9e-05 updt_s:0.784 data_s:0.530 smp/s:49 mem_gb:29.85
|
| 71 |
+
Training: 19%|█▉ | 5800/30000 [2:32:04<8:54:23, 1.32s/step]INFO 2026-07-23 05:03:52 ot_train.py:658 step:36K smpl:2M ep:52K epch:10.49 loss:0.033 grdn:0.281 lr:3.9e-05 updt_s:0.765 data_s:0.569 smp/s:48 mem_gb:29.85
|
| 72 |
+
Training: 20%|██ | 6000/30000 [2:37:07<10:46:18, 1.62s/step]INFO 2026-07-23 05:08:55 ot_train.py:658 step:36K smpl:2M ep:52K epch:10.55 loss:0.032 grdn:0.288 lr:3.8e-05 updt_s:0.824 data_s:0.687 smp/s:42 mem_gb:29.85
|
| 73 |
+
Training: 21%|██ | 6200/30000 [2:42:34<10:40:44, 1.62s/step]INFO 2026-07-23 05:14:22 ot_train.py:658 step:36K smpl:2M ep:52K epch:10.61 loss:0.031 grdn:0.290 lr:3.7e-05 updt_s:0.841 data_s:0.787 smp/s:39 mem_gb:29.83
|
| 74 |
+
Training: 21%|██▏ | 6400/30000 [2:48:24<10:48:23, 1.65s/step]INFO 2026-07-23 05:20:12 ot_train.py:658 step:36K smpl:2M ep:53K epch:10.67 loss:0.031 grdn:0.277 lr:3.7e-05 updt_s:0.876 data_s:0.868 smp/s:37 mem_gb:29.85
|
| 75 |
+
Training: 22%|██▏ | 6600/30000 [2:53:49<10:25:44, 1.60s/step]INFO 2026-07-23 05:25:37 ot_train.py:658 step:37K smpl:2M ep:53K epch:10.73 loss:0.030 grdn:0.260 lr:3.6e-05 updt_s:0.846 data_s:0.777 smp/s:39 mem_gb:29.85
|
| 76 |
+
Training: 23%|██▎ | 6800/30000 [2:59:31<10:51:40, 1.69s/step]INFO 2026-07-23 05:31:19 ot_train.py:658 step:37K smpl:2M ep:53K epch:10.79 loss:0.030 grdn:0.275 lr:3.6e-05 updt_s:0.862 data_s:0.845 smp/s:38 mem_gb:29.85
|
| 77 |
+
Training: 23%|██▎ | 7000/30000 [3:04:57<10:34:46, 1.66s/step]INFO 2026-07-23 05:36:45 ot_train.py:658 step:37K smpl:2M ep:53K epch:10.84 loss:0.030 grdn:0.276 lr:3.5e-05 updt_s:0.834 data_s:0.792 smp/s:39 mem_gb:29.85
|
| 78 |
+
Training: 24%|██▍ | 7200/30000 [3:10:20<10:05:08, 1.59s/step]INFO 2026-07-23 05:42:08 ot_train.py:658 step:37K smpl:2M ep:54K epch:10.90 loss:0.030 grdn:0.268 lr:3.5e-05 updt_s:0.836 data_s:0.771 smp/s:40 mem_gb:29.85
|
| 79 |
+
Training: 25%|██▍ | 7400/30000 [3:15:40<10:13:24, 1.63s/step]INFO 2026-07-23 05:47:28 ot_train.py:658 step:37K smpl:2M ep:54K epch:10.96 loss:0.030 grdn:0.269 lr:3.4e-05 updt_s:0.834 data_s:0.764 smp/s:40 mem_gb:29.85
|
| 80 |
+
Training: 25%|██▌ | 7600/30000 [3:20:55<9:42:54, 1.56s/step]INFO 2026-07-23 05:52:43 ot_train.py:658 step:38K smpl:2M ep:54K epch:11.02 loss:0.030 grdn:0.268 lr:3.4e-05 updt_s:0.816 data_s:0.758 smp/s:41 mem_gb:29.84
|
| 81 |
+
Training: 26%|██▌ | 7800/30000 [3:26:13<9:42:03, 1.57s/step]INFO 2026-07-23 05:58:01 ot_train.py:658 step:38K smpl:2M ep:55K epch:11.08 loss:0.030 grdn:0.291 lr:3.3e-05 updt_s:0.805 data_s:0.777 smp/s:40 mem_gb:29.85
|
| 82 |
+
Training: 27%|██▋ | 8000/30000 [3:31:27<10:16:26, 1.68s/step]INFO 2026-07-23 06:03:15 ot_train.py:658 step:38K smpl:2M ep:55K epch:11.14 loss:0.030 grdn:0.284 lr:3.3e-05 updt_s:0.789 data_s:0.780 smp/s:41 mem_gb:29.84
|
| 83 |
+
Training: 27%|██▋ | 8200/30000 [3:36:42<9:23:31, 1.55s/step]INFO 2026-07-23 06:08:30 ot_train.py:658 step:38K smpl:2M ep:55K epch:11.20 loss:0.030 grdn:0.284 lr:3.2e-05 updt_s:0.840 data_s:0.729 smp/s:41 mem_gb:29.84
|
| 84 |
+
Training: 28%|██▊ | 8400/30000 [3:41:56<8:53:52, 1.48s/step]INFO 2026-07-23 06:13:44 ot_train.py:658 step:38K smpl:2M ep:55K epch:11.25 loss:0.029 grdn:0.282 lr:3.2e-05 updt_s:0.862 data_s:0.706 smp/s:41 mem_gb:29.83
|
| 85 |
+
Training: 29%|██▊ | 8600/30000 [3:47:16<9:34:08, 1.61s/step]INFO 2026-07-23 06:19:04 ot_train.py:658 step:39K smpl:2M ep:56K epch:11.31 loss:0.028 grdn:0.259 lr:3.1e-05 updt_s:0.822 data_s:0.775 smp/s:40 mem_gb:29.84
|
| 86 |
+
Training: 29%|██▉ | 8800/30000 [3:53:46<27:38:09, 4.69s/step]INFO 2026-07-23 06:25:34 ot_train.py:658 step:39K smpl:2M ep:56K epch:11.37 loss:0.027 grdn:0.265 lr:3.1e-05 updt_s:0.770 data_s:1.176 smp/s:33 mem_gb:29.85
|
| 87 |
+
Training: 30%|███ | 9000/30000 [4:02:29<13:54:12, 2.38s/step]INFO 2026-07-23 06:34:17 ot_train.py:658 step:39K smpl:2M ep:56K epch:11.43 loss:0.027 grdn:0.269 lr:3.0e-05 updt_s:0.786 data_s:1.826 smp/s:24 mem_gb:29.85
|
| 88 |
+
Training: 31%|███ | 9200/30000 [4:09:19<10:05:13, 1.75s/step]INFO 2026-07-23 06:41:07 ot_train.py:658 step:39K smpl:3M ep:57K epch:11.49 loss:0.027 grdn:0.259 lr:3.0e-05 updt_s:0.772 data_s:1.273 smp/s:31 mem_gb:29.85
|
| 89 |
+
Training: 31%|███▏ | 9400/30000 [4:17:43<14:44:45, 2.58s/step]INFO 2026-07-23 06:49:31 ot_train.py:658 step:39K smpl:3M ep:57K epch:11.55 loss:0.027 grdn:0.261 lr:2.9e-05 updt_s:0.739 data_s:1.778 smp/s:25 mem_gb:29.85
|
| 90 |
+
Training: 32%|███▏ | 9600/30000 [4:23:55<9:45:19, 1.72s/step]INFO 2026-07-23 06:55:43 ot_train.py:658 step:40K smpl:3M ep:57K epch:11.61 loss:0.026 grdn:0.270 lr:2.9e-05 updt_s:0.854 data_s:1.001 smp/s:35 mem_gb:29.84
|
| 91 |
+
Training: 33%|███▎ | 9800/30000 [4:29:32<9:19:33, 1.66s/step]INFO 2026-07-23 07:01:20 ot_train.py:658 step:40K smpl:3M ep:58K epch:11.66 loss:0.027 grdn:0.270 lr:2.8e-05 updt_s:0.820 data_s:0.858 smp/s:38 mem_gb:29.84
|
| 92 |
+
Training: 33%|███▎ | 10000/30000 [4:35:41<9:49:56, 1.77s/step]INFO 2026-07-23 07:07:29 ot_train.py:658 step:40K smpl:3M ep:58K epch:11.72 loss:0.026 grdn:0.253 lr:2.8e-05 updt_s:0.834 data_s:1.007 smp/s:35 mem_gb:29.85
|
| 93 |
+
INFO 2026-07-23 07:07:29 ot_train.py:703 Checkpoint policy after step 40000
|
| 94 |
+
INFO 2026-07-23 07:07:58 in_yaml.py:1413 Saved verified rolling checkpoint step=40000 slot=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01
|
| 95 |
+
Training: 34%|███▍ | 10200/30000 [4:42:42<8:51:50, 1.61s/step]INFO 2026-07-23 07:14:31 ot_train.py:658 step:40K smpl:3M ep:58K epch:11.78 loss:0.027 grdn:0.264 lr:2.7e-05 updt_s:0.815 data_s:1.142 smp/s:33 mem_gb:29.84
|
| 96 |
+
Training: 35%|███▍ | 10400/30000 [4:48:12<9:06:45, 1.67s/step]INFO 2026-07-23 07:20:00 ot_train.py:658 step:40K smpl:3M ep:58K epch:11.84 loss:0.026 grdn:0.257 lr:2.7e-05 updt_s:0.838 data_s:0.805 smp/s:39 mem_gb:29.84
|
| 97 |
+
Training: 35%|███▌ | 10600/30000 [4:53:30<8:13:24, 1.53s/step]INFO 2026-07-23 07:25:18 ot_train.py:658 step:41K smpl:3M ep:59K epch:11.90 loss:0.027 grdn:0.266 lr:2.6e-05 updt_s:0.792 data_s:0.792 smp/s:40 mem_gb:29.85
|
| 98 |
+
Training: 36%|███▌ | 10800/30000 [4:58:55<9:23:44, 1.76s/step]INFO 2026-07-23 07:30:43 ot_train.py:658 step:41K smpl:3M ep:59K epch:11.96 loss:0.024 grdn:0.242 lr:2.6e-05 updt_s:0.810 data_s:0.815 smp/s:39 mem_gb:29.83
|
| 99 |
+
Training: 37%|███▋ | 11000/30000 [5:04:48<9:02:44, 1.71s/step]INFO 2026-07-23 07:36:36 ot_train.py:658 step:41K smpl:3M ep:59K epch:12.02 loss:0.025 grdn:0.246 lr:2.5e-05 updt_s:0.870 data_s:0.890 smp/s:36 mem_gb:29.85
|
| 100 |
+
Training: 37%|███▋ | 11200/30000 [5:10:37<8:47:55, 1.68s/step]INFO 2026-07-23 07:42:25 ot_train.py:658 step:41K smpl:3M ep:60K epch:12.08 loss:0.025 grdn:0.249 lr:2.5e-05 updt_s:0.850 data_s:0.891 smp/s:37 mem_gb:29.84
|
| 101 |
+
Training: 38%|███▊ | 11400/30000 [5:16:48<18:00:35, 3.49s/step]INFO 2026-07-23 07:48:36 ot_train.py:658 step:41K smpl:3M ep:60K epch:12.13 loss:0.024 grdn:0.246 lr:2.4e-05 updt_s:0.818 data_s:1.029 smp/s:35 mem_gb:29.85
|
| 102 |
+
Training: 39%|███▊ | 11600/30000 [5:24:19<11:00:04, 2.15s/step]INFO 2026-07-23 07:56:07 ot_train.py:658 step:42K smpl:3M ep:60K epch:12.19 loss:0.024 grdn:0.258 lr:2.4e-05 updt_s:0.789 data_s:1.466 smp/s:28 mem_gb:29.85
|
| 103 |
+
Training: 39%|███▉ | 11800/30000 [5:30:49<16:03:56, 3.18s/step]INFO 2026-07-23 08:02:37 ot_train.py:658 step:42K smpl:3M ep:60K epch:12.25 loss:0.024 grdn:0.246 lr:2.3e-05 updt_s:0.792 data_s:1.154 smp/s:33 mem_gb:29.85
|
| 104 |
+
Training: 40%|████ | 12000/30000 [5:37:13<8:10:00, 1.63s/step]INFO 2026-07-23 08:09:01 ot_train.py:658 step:42K smpl:3M ep:61K epch:12.31 loss:0.024 grdn:0.243 lr:2.3e-05 updt_s:0.796 data_s:1.117 smp/s:33 mem_gb:29.85
|
| 105 |
+
Training: 41%|████ | 12200/30000 [5:43:13<14:44:41, 2.98s/step]INFO 2026-07-23 08:15:01 ot_train.py:658 step:42K smpl:3M ep:61K epch:12.37 loss:0.023 grdn:0.255 lr:2.2e-05 updt_s:0.802 data_s:0.994 smp/s:36 mem_gb:29.85
|
| 106 |
+
Training: 41%|████▏ | 12400/30000 [5:48:53<9:33:34, 1.96s/step] INFO 2026-07-23 08:20:41 ot_train.py:658 step:42K smpl:3M ep:61K epch:12.43 loss:0.024 grdn:0.250 lr:2.2e-05 updt_s:0.832 data_s:0.865 smp/s:38 mem_gb:29.84
|
| 107 |
+
Training: 42%|████▏ | 12600/30000 [5:56:03<13:31:05, 2.80s/step]INFO 2026-07-23 08:27:51 ot_train.py:658 step:43K smpl:3M ep:62K epch:12.49 loss:0.025 grdn:0.248 lr:2.2e-05 updt_s:0.807 data_s:1.341 smp/s:30 mem_gb:29.84
|
| 108 |
+
Training: 43%|████▎ | 12800/30000 [6:06:50<60:52:50, 12.74s/step]INFO 2026-07-23 08:38:38 ot_train.py:658 step:43K smpl:3M ep:62K epch:12.54 loss:0.024 grdn:0.252 lr:2.1e-05 updt_s:0.798 data_s:2.432 smp/s:20 mem_gb:29.84
|
| 109 |
+
Training: 43%|████▎ | 13000/30000 [6:14:13<7:49:04, 1.66s/step]INFO 2026-07-23 08:46:01 ot_train.py:658 step:43K smpl:3M ep:62K epch:12.60 loss:0.023 grdn:0.256 lr:2.1e-05 updt_s:0.821 data_s:1.391 smp/s:29 mem_gb:29.83
|
| 110 |
+
Training: 44%|████▍ | 13200/30000 [6:19:43<7:34:42, 1.62s/step]INFO 2026-07-23 08:51:31 ot_train.py:658 step:43K smpl:3M ep:62K epch:12.66 loss:0.021 grdn:0.227 lr:2.0e-05 updt_s:0.812 data_s:0.834 smp/s:39 mem_gb:29.85
|
| 111 |
+
Training: 45%|████▍ | 13400/30000 [6:25:08<7:51:44, 1.71s/step]INFO 2026-07-23 08:56:56 ot_train.py:658 step:43K smpl:3M ep:63K epch:12.72 loss:0.022 grdn:0.244 lr:2.0e-05 updt_s:0.804 data_s:0.816 smp/s:39 mem_gb:29.85
|
| 112 |
+
Training: 45%|████▌ | 13600/30000 [6:30:32<7:26:31, 1.63s/step]INFO 2026-07-23 09:02:20 ot_train.py:658 step:44K smpl:3M ep:63K epch:12.78 loss:0.022 grdn:0.225 lr:1.9e-05 updt_s:0.802 data_s:0.813 smp/s:40 mem_gb:29.85
|
| 113 |
+
Training: 46%|████▌ | 13800/30000 [6:36:38<7:49:33, 1.74s/step]INFO 2026-07-23 09:08:26 ot_train.py:658 step:44K smpl:3M ep:63K epch:12.84 loss:0.022 grdn:0.260 lr:1.9e-05 updt_s:0.789 data_s:1.036 smp/s:35 mem_gb:29.84
|
| 114 |
+
Training: 47%|████▋ | 14000/30000 [6:42:39<7:57:32, 1.79s/step]INFO 2026-07-23 09:14:27 ot_train.py:658 step:44K smpl:3M ep:64K epch:12.90 loss:0.022 grdn:0.231 lr:1.8e-05 updt_s:0.811 data_s:0.993 smp/s:35 mem_gb:29.84
|
| 115 |
+
Training: 47%|████▋ | 14200/30000 [6:48:23<8:18:40, 1.89s/step]INFO 2026-07-23 09:20:11 ot_train.py:658 step:44K smpl:3M ep:64K epch:12.95 loss:0.022 grdn:0.246 lr:1.8e-05 updt_s:0.830 data_s:0.883 smp/s:37 mem_gb:29.84
|
| 116 |
+
Training: 48%|████▊ | 14400/30000 [6:55:47<9:01:51, 2.08s/step]INFO 2026-07-23 09:27:35 ot_train.py:658 step:44K smpl:3M ep:64K epch:13.01 loss:0.021 grdn:0.230 lr:1.8e-05 updt_s:0.799 data_s:1.417 smp/s:29 mem_gb:29.85
|
| 117 |
+
Training: 49%|████▊ | 14600/30000 [7:01:25<6:27:45, 1.51s/step]INFO 2026-07-23 09:33:13 ot_train.py:658 step:45K smpl:3M ep:64K epch:13.07 loss:0.021 grdn:0.236 lr:1.7e-05 updt_s:0.804 data_s:0.885 smp/s:38 mem_gb:29.85
|
| 118 |
+
Training: 49%|████▉ | 14800/30000 [7:06:44<7:06:24, 1.68s/step]INFO 2026-07-23 09:38:32 ot_train.py:658 step:45K smpl:3M ep:65K epch:13.13 loss:0.021 grdn:0.246 lr:1.7e-05 updt_s:0.824 data_s:0.765 smp/s:40 mem_gb:29.85
|
| 119 |
+
Training: 50%|█████ | 15000/30000 [7:12:11<6:49:49, 1.64s/step]INFO 2026-07-23 09:43:59 ot_train.py:658 step:45K smpl:3M ep:65K epch:13.19 loss:0.022 grdn:0.227 lr:1.6e-05 updt_s:0.829 data_s:0.802 smp/s:39 mem_gb:29.85
|
| 120 |
+
INFO 2026-07-23 09:43:59 ot_train.py:703 Checkpoint policy after step 45000
|
| 121 |
+
INFO 2026-07-23 09:44:25 in_yaml.py:1413 Saved verified rolling checkpoint step=45000 slot=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00
|
| 122 |
+
Training: 51%|█████ | 15200/30000 [7:18:00<7:01:12, 1.71s/step]INFO 2026-07-23 09:49:48 ot_train.py:658 step:45K smpl:3M ep:65K epch:13.25 loss:0.021 grdn:0.233 lr:1.6e-05 updt_s:0.812 data_s:0.800 smp/s:40 mem_gb:29.83
|
| 123 |
+
Training: 51%|█████▏ | 15400/30000 [7:23:32<6:44:54, 1.66s/step]INFO 2026-07-23 09:55:20 ot_train.py:658 step:45K smpl:3M ep:66K epch:13.31 loss:0.020 grdn:0.218 lr:1.6e-05 updt_s:0.859 data_s:0.793 smp/s:39 mem_gb:29.85
|
| 124 |
+
Training: 52%|█████▏ | 15600/30000 [7:28:51<6:04:24, 1.52s/step]INFO 2026-07-23 10:00:39 ot_train.py:658 step:46K smpl:3M ep:66K epch:13.36 loss:0.020 grdn:0.226 lr:1.5e-05 updt_s:0.814 data_s:0.777 smp/s:40 mem_gb:29.85
|
| 125 |
+
Training: 53%|█████▎ | 15800/30000 [7:34:16<6:18:25, 1.60s/step]INFO 2026-07-23 10:06:04 ot_train.py:658 step:46K smpl:3M ep:66K epch:13.42 loss:0.020 grdn:0.241 lr:1.5e-05 updt_s:0.816 data_s:0.806 smp/s:39 mem_gb:29.85
|
| 126 |
+
Training: 53%|█████▎ | 16000/30000 [7:40:32<6:54:11, 1.78s/step]INFO 2026-07-23 10:12:20 ot_train.py:658 step:46K smpl:3M ep:66K epch:13.48 loss:0.020 grdn:0.223 lr:1.4e-05 updt_s:0.801 data_s:1.074 smp/s:34 mem_gb:29.84
|
| 127 |
+
Training: 54%|█████▍ | 16200/30000 [7:47:00<6:49:38, 1.78s/step]INFO 2026-07-23 10:18:48 ot_train.py:658 step:46K smpl:3M ep:67K epch:13.54 loss:0.020 grdn:0.233 lr:1.4e-05 updt_s:0.857 data_s:1.081 smp/s:33 mem_gb:29.85
|
| 128 |
+
Training: 55%|█████▍ | 16400/30000 [7:53:59<6:23:57, 1.69s/step]INFO 2026-07-23 10:25:47 ot_train.py:658 step:46K smpl:3M ep:67K epch:13.60 loss:0.020 grdn:0.228 lr:1.4e-05 updt_s:0.825 data_s:1.264 smp/s:31 mem_gb:29.85
|
| 129 |
+
Training: 55%|█████▌ | 16600/30000 [8:01:35<6:11:47, 1.66s/step]INFO 2026-07-23 10:33:23 ot_train.py:658 step:47K smpl:3M ep:67K epch:13.66 loss:0.019 grdn:0.227 lr:1.3e-05 updt_s:0.838 data_s:1.439 smp/s:28 mem_gb:29.85
|
| 130 |
+
Training: 56%|█████▌ | 16800/30000 [8:07:39<5:53:47, 1.61s/step]INFO 2026-07-23 10:39:27 ot_train.py:658 step:47K smpl:3M ep:68K epch:13.72 loss:0.020 grdn:0.228 lr:1.3e-05 updt_s:0.856 data_s:0.960 smp/s:35 mem_gb:29.84
|
| 131 |
+
Training: 57%|█████▋ | 17000/30000 [8:12:56<6:00:32, 1.66s/step]INFO 2026-07-23 10:44:44 ot_train.py:658 step:47K smpl:3M ep:68K epch:13.77 loss:0.019 grdn:0.228 lr:1.2e-05 updt_s:0.889 data_s:0.692 smp/s:40 mem_gb:29.84
|
| 132 |
+
Training: 57%|█████▋ | 17200/30000 [8:27:00<17:27:42, 4.91s/step]INFO 2026-07-23 10:58:48 ot_train.py:658 step:47K smpl:3M ep:68K epch:13.83 loss:0.020 grdn:0.228 lr:1.2e-05 updt_s:3.367 data_s:0.850 smp/s:15 mem_gb:29.85
|
| 133 |
+
Training: 58%|█████▊ | 17400/30000 [8:41:30<13:58:08, 3.99s/step]INFO 2026-07-23 11:13:18 ot_train.py:658 step:47K smpl:3M ep:68K epch:13.89 loss:0.019 grdn:0.225 lr:1.2e-05 updt_s:3.355 data_s:0.992 smp/s:15 mem_gb:29.83
|
| 134 |
+
Training: 59%|█████▊ | 17600/30000 [8:55:45<18:19:28, 5.32s/step]INFO 2026-07-23 11:27:33 ot_train.py:658 step:48K smpl:3M ep:69K epch:13.95 loss:0.019 grdn:0.236 lr:1.1e-05 updt_s:3.422 data_s:0.849 smp/s:15 mem_gb:29.85
|
| 135 |
+
Training: 59%|█████▉ | 17800/30000 [9:11:33<13:40:01, 4.03s/step]INFO 2026-07-23 11:43:21 ot_train.py:658 step:48K smpl:3M ep:69K epch:14.01 loss:0.018 grdn:0.225 lr:1.1e-05 updt_s:3.145 data_s:1.591 smp/s:14 mem_gb:29.85
|
| 136 |
+
Training: 60%|██████ | 18000/30000 [9:25:29<13:42:28, 4.11s/step]INFO 2026-07-23 11:57:17 ot_train.py:658 step:48K smpl:3M ep:69K epch:14.07 loss:0.019 grdn:0.227 lr:1.1e-05 updt_s:3.320 data_s:0.854 smp/s:15 mem_gb:29.84
|
| 137 |
+
Training: 61%|██████ | 18200/30000 [9:39:49<14:15:11, 4.35s/step]INFO 2026-07-23 12:11:37 ot_train.py:658 step:48K smpl:3M ep:70K epch:14.13 loss:0.018 grdn:0.230 lr:1.0e-05 updt_s:3.414 data_s:0.886 smp/s:15 mem_gb:29.85
|
| 138 |
+
Training: 61%|██████▏ | 18400/30000 [9:53:56<14:28:13, 4.49s/step]INFO 2026-07-23 12:25:44 ot_train.py:658 step:48K smpl:3M ep:70K epch:14.19 loss:0.018 grdn:0.218 lr:1.0e-05 updt_s:3.465 data_s:0.766 smp/s:15 mem_gb:29.85
|
| 139 |
+
Training: 62%|██████▏ | 18600/30000 [10:07:35<13:01:01, 4.11s/step]INFO 2026-07-23 12:39:23 ot_train.py:658 step:49K smpl:3M ep:70K epch:14.24 loss:0.018 grdn:0.226 lr:9.7e-06 updt_s:3.424 data_s:0.669 smp/s:16 mem_gb:29.85
|
| 140 |
+
Training: 63%|██████▎ | 18800/30000 [10:21:17<13:50:28, 4.45s/step]INFO 2026-07-23 12:53:05 ot_train.py:658 step:49K smpl:3M ep:71K epch:14.30 loss:0.018 grdn:0.217 lr:9.4e-06 updt_s:3.456 data_s:0.649 smp/s:16 mem_gb:29.84
|
| 141 |
+
Training: 63%|██████▎ | 19000/30000 [10:35:21<13:52:13, 4.54s/step]INFO 2026-07-23 13:07:09 ot_train.py:658 step:49K smpl:3M ep:71K epch:14.36 loss:0.018 grdn:0.209 lr:9.1e-06 updt_s:3.570 data_s:0.644 smp/s:15 mem_gb:29.84
|
| 142 |
+
Training: 64%|██████▍ | 19200/30000 [10:48:56<10:50:18, 3.61s/step]INFO 2026-07-23 13:20:44 ot_train.py:658 step:49K smpl:3M ep:71K epch:14.42 loss:0.018 grdn:0.219 lr:8.8e-06 updt_s:3.473 data_s:0.600 smp/s:16 mem_gb:29.84
|
| 143 |
+
Training: 65%|██████▍ | 19400/30000 [11:03:04<12:04:34, 4.10s/step]INFO 2026-07-23 13:34:52 ot_train.py:658 step:49K smpl:3M ep:71K epch:14.48 loss:0.018 grdn:0.217 lr:8.4e-06 updt_s:3.473 data_s:0.765 smp/s:15 mem_gb:29.84
|
| 144 |
+
Training: 65%|██████▌ | 19600/30000 [11:17:00<10:49:27, 3.75s/step]INFO 2026-07-23 13:48:48 ot_train.py:658 step:50K smpl:3M ep:72K epch:14.54 loss:0.017 grdn:0.226 lr:8.1e-06 updt_s:3.486 data_s:0.694 smp/s:15 mem_gb:29.85
|
| 145 |
+
Training: 66%|██████▌ | 19800/30000 [11:30:48<12:12:01, 4.31s/step]INFO 2026-07-23 14:02:36 ot_train.py:658 step:50K smpl:3M ep:72K epch:14.60 loss:0.017 grdn:0.216 lr:7.8e-06 updt_s:3.490 data_s:0.643 smp/s:15 mem_gb:29.83
|
| 146 |
+
Training: 67%|██████▋ | 20000/30000 [11:44:24<11:03:22, 3.98s/step]INFO 2026-07-23 14:16:12 ot_train.py:658 step:50K smpl:3M ep:72K epch:14.65 loss:0.017 grdn:0.210 lr:7.5e-06 updt_s:3.495 data_s:0.583 smp/s:16 mem_gb:29.84
|
| 147 |
+
INFO 2026-07-23 14:16:12 ot_train.py:703 Checkpoint policy after step 50000
|
| 148 |
+
INFO 2026-07-23 14:16:43 in_yaml.py:1413 Saved verified rolling checkpoint step=50000 slot=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01
|
| 149 |
+
Training: 67%|██████▋ | 20082/30000 [11:50:29<10:53:43, 3.95s/step]
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/files/requirements.txt
ADDED
|
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
tzdata==2026.3
|
| 2 |
+
nvidia-cufile-cu12==1.13.1.3
|
| 3 |
+
wandb==0.27.2
|
| 4 |
+
six==1.17.0
|
| 5 |
+
peft==0.19.1
|
| 6 |
+
nvidia-curand-cu12==10.3.9.90
|
| 7 |
+
nvidia-cuda-runtime-cu12==12.8.90
|
| 8 |
+
datasets==4.8.5
|
| 9 |
+
attrs==26.1.0
|
| 10 |
+
cloudpickle==3.1.2
|
| 11 |
+
packaging==25.0
|
| 12 |
+
nvidia-cublas-cu12==12.8.4.1
|
| 13 |
+
cmake==4.1.3
|
| 14 |
+
psutil==7.2.2
|
| 15 |
+
pydantic==2.13.4
|
| 16 |
+
GitPython==3.1.51
|
| 17 |
+
pillow==12.2.0
|
| 18 |
+
pytz==2026.2
|
| 19 |
+
cuda-pathfinder==1.2.2
|
| 20 |
+
nvidia-cusparse-cu12==12.5.8.93
|
| 21 |
+
typing_extensions==4.15.0
|
| 22 |
+
urllib3==2.7.0
|
| 23 |
+
pydantic_core==2.46.4
|
| 24 |
+
draccus==0.10.0
|
| 25 |
+
mypy_extensions==1.1.0
|
| 26 |
+
dill==0.4.1
|
| 27 |
+
typer==0.26.8
|
| 28 |
+
decord==0.6.0
|
| 29 |
+
tqdm==4.68.4
|
| 30 |
+
triton==3.6.0
|
| 31 |
+
idna==3.18
|
| 32 |
+
requests==2.34.2
|
| 33 |
+
nvidia-cudnn-cu12==9.19.0.56
|
| 34 |
+
mdurl==0.1.2
|
| 35 |
+
shellingham==1.5.4
|
| 36 |
+
zipp==4.1.0
|
| 37 |
+
timm==1.0.28
|
| 38 |
+
torch==2.11.0+cu128
|
| 39 |
+
tokenizers==0.22.2
|
| 40 |
+
nvidia-cusparselt-cu12==0.7.1
|
| 41 |
+
nvidia-cufft-cu12==11.3.3.83
|
| 42 |
+
nvidia-cusolver-cu12==11.7.3.90
|
| 43 |
+
opencv-python-headless==4.13.0.92
|
| 44 |
+
httpx==0.28.1
|
| 45 |
+
Jinja2==3.1.6
|
| 46 |
+
einops==0.8.2
|
| 47 |
+
mergedeep==1.3.4
|
| 48 |
+
platformdirs==4.10.0
|
| 49 |
+
nvidia-nvjitlink-cu12==12.8.93
|
| 50 |
+
lerobot==0.6.0
|
| 51 |
+
PyYAML==6.0.3
|
| 52 |
+
accelerate==1.14.0
|
| 53 |
+
anyio==4.14.2
|
| 54 |
+
gymnasium==1.3.0
|
| 55 |
+
pip==26.1.2
|
| 56 |
+
huggingface_hub==1.23.0
|
| 57 |
+
diffusers==0.35.2
|
| 58 |
+
annotated-doc==0.0.4
|
| 59 |
+
pyarrow==25.0.0
|
| 60 |
+
python-dateutil==2.9.0.post0
|
| 61 |
+
termcolor==3.3.0
|
| 62 |
+
nvidia-nccl-cu12==2.28.9
|
| 63 |
+
sentry-sdk==2.65.0
|
| 64 |
+
torchcodec==0.11.1
|
| 65 |
+
pyyaml-include==1.4.1
|
| 66 |
+
multiprocess==0.70.19
|
| 67 |
+
wrapt==2.2.2
|
| 68 |
+
typing-inspection==0.4.2
|
| 69 |
+
nvidia-cuda-nvrtc-cu12==12.8.93
|
| 70 |
+
Pygments==2.20.0
|
| 71 |
+
nvidia-cuda-cupti-cu12==12.8.90
|
| 72 |
+
certifi==2026.6.17
|
| 73 |
+
setuptools==78.1.0
|
| 74 |
+
charset-normalizer==3.4.9
|
| 75 |
+
propcache==0.5.2
|
| 76 |
+
multidict==6.7.1
|
| 77 |
+
regex==2026.7.10
|
| 78 |
+
frozenlist==1.8.0
|
| 79 |
+
smmap==5.0.3
|
| 80 |
+
hf-xet==1.5.1
|
| 81 |
+
torchvision==0.26.0+cu128
|
| 82 |
+
gitdb==4.0.12
|
| 83 |
+
transformers==5.5.4
|
| 84 |
+
rich==15.0.0
|
| 85 |
+
cuda-bindings==12.9.4
|
| 86 |
+
protobuf==7.35.1
|
| 87 |
+
aiosignal==1.4.0
|
| 88 |
+
jsonlines==4.0.0
|
| 89 |
+
yarl==1.24.2
|
| 90 |
+
filelock==3.29.0
|
| 91 |
+
av==15.1.0
|
| 92 |
+
networkx==3.6.1
|
| 93 |
+
sympy==1.14.0
|
| 94 |
+
wheel==0.47.0
|
| 95 |
+
nvidia-nvtx-cu12==12.8.90
|
| 96 |
+
xxhash==3.8.1
|
| 97 |
+
toml==0.10.2
|
| 98 |
+
MarkupSafe==3.0.3
|
| 99 |
+
pandas==2.3.3
|
| 100 |
+
safetensors==0.8.0
|
| 101 |
+
click==8.4.2
|
| 102 |
+
fsspec==2026.2.0
|
| 103 |
+
dm-tree==0.1.10
|
| 104 |
+
absl-py==2.5.0
|
| 105 |
+
Farama-Notifications==0.0.6
|
| 106 |
+
mpmath==1.3.0
|
| 107 |
+
importlib_metadata==9.0.0
|
| 108 |
+
markdown-it-py==4.2.0
|
| 109 |
+
h11==0.16.0
|
| 110 |
+
typing-inspect==0.9.0
|
| 111 |
+
httpcore==1.0.9
|
| 112 |
+
annotated-types==0.7.0
|
| 113 |
+
numpy==2.2.6
|
| 114 |
+
nvidia-nvshmem-cu12==3.4.5
|
| 115 |
+
aiohappyeyeballs==2.7.1
|
| 116 |
+
cuda-toolkit==12.8.1
|
| 117 |
+
aiohttp==3.14.1
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/files/wandb-metadata.json
ADDED
|
@@ -0,0 +1,53 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"os": "Linux-6.8.0-55-generic-x86_64-with-glibc2.39",
|
| 3 |
+
"python": "CPython 3.12.13",
|
| 4 |
+
"startedAt": "2026-07-23T02:31:25.059506Z",
|
| 5 |
+
"args": [
|
| 6 |
+
"--config_path=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model/train_config.json",
|
| 7 |
+
"--resume=true",
|
| 8 |
+
"--output_dir=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K",
|
| 9 |
+
"--dataset.root=/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2",
|
| 10 |
+
"--wandb.run_id=rs1egwv8"
|
| 11 |
+
],
|
| 12 |
+
"program": "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py",
|
| 13 |
+
"codePath": "benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py",
|
| 14 |
+
"codePathLocal": "my_scripts/lerobot_train_yaml.py",
|
| 15 |
+
"git": {
|
| 16 |
+
"remote": "git@github.com:paragon7060/clvla.git",
|
| 17 |
+
"commit": "a329728c2c9524d79b966c4a7a82ee56a4c2abf7"
|
| 18 |
+
},
|
| 19 |
+
"root": "/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K",
|
| 20 |
+
"host": "ext_minje-box",
|
| 21 |
+
"executable": "/home/ext_minje/miniconda3/envs/lerobot060_groot/bin/python",
|
| 22 |
+
"cpu_count": 112,
|
| 23 |
+
"cpu_count_logical": 224,
|
| 24 |
+
"gpu": "NVIDIA H200",
|
| 25 |
+
"gpu_count": 2,
|
| 26 |
+
"disk": {
|
| 27 |
+
"/": {
|
| 28 |
+
"total": "1888425144320",
|
| 29 |
+
"used": "1138103234560"
|
| 30 |
+
}
|
| 31 |
+
},
|
| 32 |
+
"memory": {
|
| 33 |
+
"total": "2164176568320"
|
| 34 |
+
},
|
| 35 |
+
"gpu_nvidia": [
|
| 36 |
+
{
|
| 37 |
+
"name": "NVIDIA H200",
|
| 38 |
+
"memoryTotal": "150754820096",
|
| 39 |
+
"cudaCores": 16896,
|
| 40 |
+
"architecture": "Hopper",
|
| 41 |
+
"uuid": "GPU-86be6e5b-fb48-fa1c-9bd7-83d336cb2991"
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"name": "NVIDIA H200",
|
| 45 |
+
"memoryTotal": "150754820096",
|
| 46 |
+
"cudaCores": 16896,
|
| 47 |
+
"architecture": "Hopper",
|
| 48 |
+
"uuid": "GPU-24eb1ba2-7313-ff93-1435-748768ebdbdc"
|
| 49 |
+
}
|
| 50 |
+
],
|
| 51 |
+
"cudaVersion": "12.8",
|
| 52 |
+
"writerId": "rcam6hzew8b6nlqutd1m9r4avsa0csph"
|
| 53 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug-core.log
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-07-23T02:31:25.095933268Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmphmwi8v6n/port-2501080.txt","pid":2501080,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 2 |
+
{"time":"2026-07-23T02:31:25.096932569Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2501080}
|
| 3 |
+
{"time":"2026-07-23T02:31:25.096927661Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2501080-2501865-1162647384/socket","Net":"unix"}}
|
| 4 |
+
{"time":"2026-07-23T02:31:25.169461847Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmp4t2rwfks/port-2500816.txt","pid":2500816,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 5 |
+
{"time":"2026-07-23T02:31:25.170134264Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-2500816-2501888-288489369/socket","Net":"unix"}}
|
| 6 |
+
{"time":"2026-07-23T02:31:25.170259549Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":2500816}
|
| 7 |
+
{"time":"2026-07-23T02:31:25.27857788Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 8 |
+
{"time":"2026-07-23T02:31:25.285691576Z","level":"INFO","msg":"handleInformInit: received","streamId":"rs1egwv8","id":"1(@)"}
|
| 9 |
+
{"time":"2026-07-23T02:31:25.348726979Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 10 |
+
{"time":"2026-07-23T02:31:25.356108831Z","level":"INFO","msg":"handleInformInit: received","streamId":"x6da8gup","id":"1(@)"}
|
| 11 |
+
{"time":"2026-07-23T02:31:25.661339067Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"rs1egwv8","id":"1(@)"}
|
| 12 |
+
{"time":"2026-07-23T02:31:25.811527394Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"x6da8gup","id":"1(@)"}
|
| 13 |
+
{"time":"2026-07-23T02:31:31.694097963Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"7skxzehhhgck"}
|
| 14 |
+
{"time":"2026-07-23T02:31:31.708133393Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"b3q6giuvspld"}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug-internal.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug.log
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
|
| 2 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_setup.py:_flush():81] Configure stats pid to 2501080
|
| 3 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_setup.py:_flush():81] Loading settings from environment variables
|
| 4 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug.log
|
| 5 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_023125-rs1egwv8/logs/debug-internal.log
|
| 6 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_init.py:init():766] calling init triggers
|
| 7 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
|
| 8 |
+
config: {'dataset': {'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2', 'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2', 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}, 'affine': {'weight': 1.0, 'type': 'RandomAffine', 'kwargs': {'degrees': [-5.0, 5.0], 'translate': [0.05, 0.05]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'torchcodec', 'return_uint8': False, 'depth_output_unit': 'mm', 'streaming': False, 'eval_split': 0.0}, 'env': None, 'policy': {'type': 'groot_rkd', 'n_obs_steps': 1, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [16]}, 'observation.images.wrist': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.right_shoulder': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.guide': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [10]}}, 'device': 'cuda', 'use_amp': False, 'use_peft': False, 'push_to_hub': False, 'repo_id': None, 'private': None, 'tags': None, 'license': None, 'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000/pretrained_model', 'pretrained_revision': None, 'chunk_size': 16, 'n_action_steps': 16, 'max_state_dim': 132, 'max_action_dim': 132, 'normalization_mapping': {'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'STATE': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'ACTION': <NormalizationMode.IDENTITY: 'IDENTITY'>}, 'base_model_path': 'nvidia/GR00T-N1.7-3B', 'action_decode_transform': None, 'embodiment_tag': 'new_embodiment', 'tune_llm': False, 'tune_visual': False, 'tune_projector': True, 'tune_diffusion_model': True, 'tune_vlln': True, 'tune_top_llm_layers': 0, 'num_inference_timesteps': None, 'rtc_ramp_rate': None, 'use_flash_attention': False, 'use_relative_actions': False, 'relative_exclude_joints': [], 'optimizer_lr': 0.0001, 'optimizer_betas': [0.9, 0.999], 'optimizer_eps': 1e-08, 'optimizer_weight_decay': 1e-05, 'warmup_steps': 3000, 'warmup_ratio': 0.05, 'use_bf16': True, 'model_params_fp32': True, 'image_size': [256, 256], 'tokenizer_assets_repo': None, 'lora_rank': 0, 'lora_alpha': 16, 'lora_dropout': 0.1, 'lora_full_model': False, 'video_backend': 'decord', 'balance_dataset_weights': True, 'balance_trajectory_weights': True, 'dataset_paths': None, 'output_dir': './tmp/gr00t', 'save_steps': 1000, 'max_steps': 10000, 'batch_size': 32, 'dataloader_num_workers': 8, 'report_to': 'wandb', 'resume': False, 'action_expert_num_layers': 16, 'rkd_enabled': True, 'rkd_vae_checkpoint': '/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11', 'rkd_student_pooling': 'attention', 'rkd_student_attention_hidden_dim': 512, 'rkd_student_attention_output_dim': 512, 'rkd_fm_loss_weight': 1.0, 'rkd_loss_weight': 1.0, 'rkd_distance_weight': 1.0, 'rkd_angle_weight': 2.0}, 'reward_model': None, 'output_dir': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K', 'job_name': 'INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60', 'resume': True, 'seed': 42, 'cudnn_deterministic': False, 'num_workers': 4, 'batch_size': 64, 'prefetch_factor': 4, 'persistent_workers': True, 'steps': 60000, 'env_eval_freq': 20000, 'log_freq': 200, 'eval_steps': 0, 'max_eval_samples': 0, 'tolerance_s': 0.0001, 'save_checkpoint': True, 'save_freq': 20000, 'use_policy_training_preset': True, 'optimizer': {'type': 'adamw', 'lr': 0.0001, 'weight_decay': 1e-05, 'grad_clip_norm': 1.0, 'betas': [0.9, 0.999], 'eps': 1e-08}, 'scheduler': {'type': 'diffuser', 'num_warmup_steps': 3000, 'name': 'cosine'}, 'eval': {'n_episodes': 50, 'batch_size': 50, 'use_async_envs': True, 'recording': False, 'recording_repo_id': None, 'recording_private': False}, 'wandb': {'enable': True, 'disable_artifact': True, 'project': 'lerobot', 'entity': None, 'notes': None, 'run_id': 'rs1egwv8', 'mode': None, 'add_tags': True}, 'peft': None, 'job': {'target': None, 'image': 'huggingface/lerobot-gpu:latest', 'timeout': '2d', 'detach': False, 'tags': []}, 'save_checkpoint_to_hub': False, 'sample_weighting': None, 'rename_map': {}, 'checkpoint_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/030000', '_wandb': {}}
|
| 9 |
+
2026-07-23 02:31:25,060 INFO MainThread:2501080 [wandb_init.py:init():814] starting backend
|
| 10 |
+
2026-07-23 02:31:25,278 INFO MainThread:2501080 [wandb_init.py:init():829] sending inform_init request
|
| 11 |
+
2026-07-23 02:31:25,662 INFO MainThread:2501080 [wandb_init.py:init():834] backend started and connected
|
| 12 |
+
2026-07-23 02:31:25,664 INFO MainThread:2501080 [wandb_init.py:init():904] updated telemetry
|
| 13 |
+
2026-07-23 02:31:25,668 INFO MainThread:2501080 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
|
| 14 |
+
2026-07-23 02:31:26,617 INFO MainThread:2501080 [wandb_init.py:init():972] starting run threads in backend
|
| 15 |
+
2026-07-23 02:31:26,676 INFO MainThread:2501080 [wandb_run.py:_console_start():2523] atexit reg
|
| 16 |
+
2026-07-23 02:31:26,677 INFO MainThread:2501080 [wandb_run.py:_redirect():2373] redirect: wrap_raw
|
| 17 |
+
2026-07-23 02:31:26,677 INFO MainThread:2501080 [wandb_run.py:_redirect():2442] Wrapping output streams.
|
| 18 |
+
2026-07-23 02:31:26,677 INFO MainThread:2501080 [wandb_run.py:_redirect():2465] Redirects installed.
|
| 19 |
+
2026-07-23 02:31:26,678 INFO MainThread:2501080 [wandb_init.py:init():1010] run started, returning control to user process
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/config.yaml
ADDED
|
@@ -0,0 +1,329 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
_wandb:
|
| 2 |
+
value:
|
| 3 |
+
cli_version: 0.27.2
|
| 4 |
+
e:
|
| 5 |
+
3vx7sedbdsz3uay6fuuuh2e3qlqtbnr9:
|
| 6 |
+
args:
|
| 7 |
+
- --config_path=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/train_config.json
|
| 8 |
+
- --resume=true
|
| 9 |
+
codePath: clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py
|
| 10 |
+
codePathLocal: clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py
|
| 11 |
+
cpu_count: 112
|
| 12 |
+
cpu_count_logical: 224
|
| 13 |
+
cudaVersion: "12.9"
|
| 14 |
+
disk:
|
| 15 |
+
/:
|
| 16 |
+
total: "1888425144320"
|
| 17 |
+
used: "1327086579712"
|
| 18 |
+
executable: /home/ext_minje/miniconda3/envs/lerobot060_groot/bin/python
|
| 19 |
+
gpu: NVIDIA H200
|
| 20 |
+
gpu_count: 2
|
| 21 |
+
gpu_nvidia:
|
| 22 |
+
- architecture: Hopper
|
| 23 |
+
cudaCores: 16896
|
| 24 |
+
memoryTotal: "150754820096"
|
| 25 |
+
name: NVIDIA H200
|
| 26 |
+
uuid: GPU-86be6e5b-fb48-fa1c-9bd7-83d336cb2991
|
| 27 |
+
- architecture: Hopper
|
| 28 |
+
cudaCores: 16896
|
| 29 |
+
memoryTotal: "150754820096"
|
| 30 |
+
name: NVIDIA H200
|
| 31 |
+
uuid: GPU-24eb1ba2-7313-ff93-1435-748768ebdbdc
|
| 32 |
+
host: ext_minje-box
|
| 33 |
+
memory:
|
| 34 |
+
total: "2164176568320"
|
| 35 |
+
os: Linux-6.8.0-55-generic-x86_64-with-glibc2.39
|
| 36 |
+
program: /home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py
|
| 37 |
+
python: CPython 3.12.13
|
| 38 |
+
root: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 39 |
+
startedAt: "2026-07-23T16:35:01.611693Z"
|
| 40 |
+
writerId: 3vx7sedbdsz3uay6fuuuh2e3qlqtbnr9
|
| 41 |
+
m: []
|
| 42 |
+
python_version: 3.12.13
|
| 43 |
+
t:
|
| 44 |
+
"1":
|
| 45 |
+
- 1
|
| 46 |
+
- 11
|
| 47 |
+
- 41
|
| 48 |
+
- 49
|
| 49 |
+
- 51
|
| 50 |
+
- 71
|
| 51 |
+
- 83
|
| 52 |
+
- 98
|
| 53 |
+
"2":
|
| 54 |
+
- 1
|
| 55 |
+
- 11
|
| 56 |
+
- 41
|
| 57 |
+
- 49
|
| 58 |
+
- 51
|
| 59 |
+
- 71
|
| 60 |
+
- 83
|
| 61 |
+
- 98
|
| 62 |
+
"3":
|
| 63 |
+
- 5
|
| 64 |
+
- 13
|
| 65 |
+
- 14
|
| 66 |
+
- 15
|
| 67 |
+
- 16
|
| 68 |
+
- 61
|
| 69 |
+
- 62
|
| 70 |
+
"4": 3.12.13
|
| 71 |
+
"5": 0.27.2
|
| 72 |
+
"6": 5.5.4
|
| 73 |
+
"10":
|
| 74 |
+
- 21
|
| 75 |
+
"12": 0.27.2
|
| 76 |
+
"13": linux-x86_64
|
| 77 |
+
batch_size:
|
| 78 |
+
value: 64
|
| 79 |
+
checkpoint_path:
|
| 80 |
+
value: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01
|
| 81 |
+
cudnn_deterministic:
|
| 82 |
+
value: false
|
| 83 |
+
dataset:
|
| 84 |
+
value:
|
| 85 |
+
depth_output_unit: mm
|
| 86 |
+
episodes: null
|
| 87 |
+
eval_split: 0
|
| 88 |
+
image_transforms:
|
| 89 |
+
enable: false
|
| 90 |
+
max_num_transforms: 3
|
| 91 |
+
random_order: false
|
| 92 |
+
tfs:
|
| 93 |
+
affine:
|
| 94 |
+
kwargs:
|
| 95 |
+
degrees:
|
| 96 |
+
- -5
|
| 97 |
+
- 5
|
| 98 |
+
translate:
|
| 99 |
+
- 0.05
|
| 100 |
+
- 0.05
|
| 101 |
+
type: RandomAffine
|
| 102 |
+
weight: 1
|
| 103 |
+
brightness:
|
| 104 |
+
kwargs:
|
| 105 |
+
brightness:
|
| 106 |
+
- 0.8
|
| 107 |
+
- 1.2
|
| 108 |
+
type: ColorJitter
|
| 109 |
+
weight: 1
|
| 110 |
+
contrast:
|
| 111 |
+
kwargs:
|
| 112 |
+
contrast:
|
| 113 |
+
- 0.8
|
| 114 |
+
- 1.2
|
| 115 |
+
type: ColorJitter
|
| 116 |
+
weight: 1
|
| 117 |
+
hue:
|
| 118 |
+
kwargs:
|
| 119 |
+
hue:
|
| 120 |
+
- -0.05
|
| 121 |
+
- 0.05
|
| 122 |
+
type: ColorJitter
|
| 123 |
+
weight: 1
|
| 124 |
+
saturation:
|
| 125 |
+
kwargs:
|
| 126 |
+
saturation:
|
| 127 |
+
- 0.5
|
| 128 |
+
- 1.5
|
| 129 |
+
type: ColorJitter
|
| 130 |
+
weight: 1
|
| 131 |
+
sharpness:
|
| 132 |
+
kwargs:
|
| 133 |
+
sharpness:
|
| 134 |
+
- 0.5
|
| 135 |
+
- 1.5
|
| 136 |
+
type: SharpnessJitter
|
| 137 |
+
weight: 1
|
| 138 |
+
repo_id: Whalswp/INSIGHTfixposV4_filtered_multispace_v2
|
| 139 |
+
return_uint8: false
|
| 140 |
+
revision: null
|
| 141 |
+
root: /home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2
|
| 142 |
+
streaming: false
|
| 143 |
+
use_imagenet_stats: true
|
| 144 |
+
video_backend: torchcodec
|
| 145 |
+
env:
|
| 146 |
+
value: null
|
| 147 |
+
env_eval_freq:
|
| 148 |
+
value: 20000
|
| 149 |
+
eval:
|
| 150 |
+
value:
|
| 151 |
+
batch_size: 50
|
| 152 |
+
n_episodes: 50
|
| 153 |
+
recording: false
|
| 154 |
+
recording_private: false
|
| 155 |
+
recording_repo_id: null
|
| 156 |
+
use_async_envs: true
|
| 157 |
+
eval_steps:
|
| 158 |
+
value: 0
|
| 159 |
+
job:
|
| 160 |
+
value:
|
| 161 |
+
detach: false
|
| 162 |
+
image: huggingface/lerobot-gpu:latest
|
| 163 |
+
tags: []
|
| 164 |
+
target: null
|
| 165 |
+
timeout: 2d
|
| 166 |
+
job_name:
|
| 167 |
+
value: INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60
|
| 168 |
+
log_freq:
|
| 169 |
+
value: 200
|
| 170 |
+
max_eval_samples:
|
| 171 |
+
value: 0
|
| 172 |
+
num_workers:
|
| 173 |
+
value: 4
|
| 174 |
+
optimizer:
|
| 175 |
+
value:
|
| 176 |
+
betas:
|
| 177 |
+
- 0.9
|
| 178 |
+
- 0.999
|
| 179 |
+
eps: 1e-08
|
| 180 |
+
grad_clip_norm: 1
|
| 181 |
+
lr: 0.0001
|
| 182 |
+
type: adamw
|
| 183 |
+
weight_decay: 1e-05
|
| 184 |
+
output_dir:
|
| 185 |
+
value: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 186 |
+
peft:
|
| 187 |
+
value: null
|
| 188 |
+
persistent_workers:
|
| 189 |
+
value: true
|
| 190 |
+
policy:
|
| 191 |
+
value:
|
| 192 |
+
action_decode_transform: null
|
| 193 |
+
action_expert_num_layers: 16
|
| 194 |
+
balance_dataset_weights: true
|
| 195 |
+
balance_trajectory_weights: true
|
| 196 |
+
base_model_path: nvidia/GR00T-N1.7-3B
|
| 197 |
+
batch_size: 32
|
| 198 |
+
chunk_size: 16
|
| 199 |
+
dataloader_num_workers: 8
|
| 200 |
+
dataset_paths: null
|
| 201 |
+
device: cuda
|
| 202 |
+
embodiment_tag: new_embodiment
|
| 203 |
+
image_size:
|
| 204 |
+
- 256
|
| 205 |
+
- 256
|
| 206 |
+
input_features:
|
| 207 |
+
observation.images.guide:
|
| 208 |
+
shape:
|
| 209 |
+
- 3
|
| 210 |
+
- 224
|
| 211 |
+
- 224
|
| 212 |
+
type: VISUAL
|
| 213 |
+
observation.images.right_shoulder:
|
| 214 |
+
shape:
|
| 215 |
+
- 3
|
| 216 |
+
- 224
|
| 217 |
+
- 224
|
| 218 |
+
type: VISUAL
|
| 219 |
+
observation.images.wrist:
|
| 220 |
+
shape:
|
| 221 |
+
- 3
|
| 222 |
+
- 224
|
| 223 |
+
- 224
|
| 224 |
+
type: VISUAL
|
| 225 |
+
observation.state:
|
| 226 |
+
shape:
|
| 227 |
+
- 16
|
| 228 |
+
type: STATE
|
| 229 |
+
license: null
|
| 230 |
+
lora_alpha: 16
|
| 231 |
+
lora_dropout: 0.1
|
| 232 |
+
lora_full_model: false
|
| 233 |
+
lora_rank: 0
|
| 234 |
+
max_action_dim: 132
|
| 235 |
+
max_state_dim: 132
|
| 236 |
+
max_steps: 10000
|
| 237 |
+
model_params_fp32: true
|
| 238 |
+
n_action_steps: 16
|
| 239 |
+
n_obs_steps: 1
|
| 240 |
+
normalization_mapping:
|
| 241 |
+
ACTION: IDENTITY
|
| 242 |
+
STATE: IDENTITY
|
| 243 |
+
VISUAL: IDENTITY
|
| 244 |
+
num_inference_timesteps: null
|
| 245 |
+
optimizer_betas:
|
| 246 |
+
- 0.9
|
| 247 |
+
- 0.999
|
| 248 |
+
optimizer_eps: 1e-08
|
| 249 |
+
optimizer_lr: 0.0001
|
| 250 |
+
optimizer_weight_decay: 1e-05
|
| 251 |
+
output_dir: ./tmp/gr00t
|
| 252 |
+
output_features:
|
| 253 |
+
action:
|
| 254 |
+
shape:
|
| 255 |
+
- 10
|
| 256 |
+
type: ACTION
|
| 257 |
+
pretrained_path: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model
|
| 258 |
+
pretrained_revision: null
|
| 259 |
+
private: null
|
| 260 |
+
push_to_hub: false
|
| 261 |
+
relative_exclude_joints: []
|
| 262 |
+
repo_id: null
|
| 263 |
+
report_to: wandb
|
| 264 |
+
resume: false
|
| 265 |
+
rkd_angle_weight: 2
|
| 266 |
+
rkd_distance_weight: 1
|
| 267 |
+
rkd_enabled: true
|
| 268 |
+
rkd_fm_loss_weight: 1
|
| 269 |
+
rkd_loss_weight: 1
|
| 270 |
+
rkd_student_attention_hidden_dim: 512
|
| 271 |
+
rkd_student_attention_output_dim: 512
|
| 272 |
+
rkd_student_pooling: attention
|
| 273 |
+
rkd_vae_checkpoint: /home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11
|
| 274 |
+
rtc_ramp_rate: null
|
| 275 |
+
save_steps: 1000
|
| 276 |
+
tags: null
|
| 277 |
+
tokenizer_assets_repo: null
|
| 278 |
+
tune_diffusion_model: true
|
| 279 |
+
tune_llm: false
|
| 280 |
+
tune_projector: true
|
| 281 |
+
tune_top_llm_layers: 0
|
| 282 |
+
tune_visual: false
|
| 283 |
+
tune_vlln: true
|
| 284 |
+
type: groot_rkd
|
| 285 |
+
use_amp: false
|
| 286 |
+
use_bf16: true
|
| 287 |
+
use_flash_attention: false
|
| 288 |
+
use_peft: false
|
| 289 |
+
use_relative_actions: false
|
| 290 |
+
video_backend: decord
|
| 291 |
+
warmup_ratio: 0.05
|
| 292 |
+
warmup_steps: 3000
|
| 293 |
+
prefetch_factor:
|
| 294 |
+
value: 4
|
| 295 |
+
resume:
|
| 296 |
+
value: true
|
| 297 |
+
reward_model:
|
| 298 |
+
value: null
|
| 299 |
+
sample_weighting:
|
| 300 |
+
value: null
|
| 301 |
+
save_checkpoint:
|
| 302 |
+
value: true
|
| 303 |
+
save_checkpoint_to_hub:
|
| 304 |
+
value: false
|
| 305 |
+
save_freq:
|
| 306 |
+
value: 20000
|
| 307 |
+
scheduler:
|
| 308 |
+
value:
|
| 309 |
+
name: cosine
|
| 310 |
+
num_warmup_steps: 3000
|
| 311 |
+
type: diffuser
|
| 312 |
+
seed:
|
| 313 |
+
value: 42
|
| 314 |
+
steps:
|
| 315 |
+
value: 60000
|
| 316 |
+
tolerance_s:
|
| 317 |
+
value: 0.0001
|
| 318 |
+
use_policy_training_preset:
|
| 319 |
+
value: true
|
| 320 |
+
wandb:
|
| 321 |
+
value:
|
| 322 |
+
add_tags: true
|
| 323 |
+
disable_artifact: true
|
| 324 |
+
enable: true
|
| 325 |
+
entity: null
|
| 326 |
+
mode: null
|
| 327 |
+
notes: null
|
| 328 |
+
project: lerobot
|
| 329 |
+
run_id: rs1egwv8
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/output.log
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
INFO 2026-07-23 16:35:03 db_utils.py:126 Logs will be synced with wandb.
|
| 2 |
+
INFO 2026-07-23 16:35:03 db_utils.py:127 Track this run --> https://wandb.ai/minje227_hyu-hanyang-university/lerobot/runs/rs1egwv8
|
| 3 |
+
INFO 2026-07-23 16:35:03 ot_train.py:310 Creating dataset
|
| 4 |
+
INFO 2026-07-23 16:35:05 ot_train.py:344 Creating policy
|
| 5 |
+
INFO 2026-07-23 16:35:05 ng_groot.py:193 The Groot policy wraps NVIDIA's GR00T n1.7 model. Loading pretrained model from: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model
|
| 6 |
+
INFO 2026-07-23 16:35:05 ng_groot.py:227 Detected fine-tuned LeRobot checkpoint, loading with state dict...
|
| 7 |
+
Fetching 27 files: 100%|██████████| 27/27 [00:00<00:00, 5334.76it/s]
|
| 8 |
+
`torch_dtype` is deprecated! Use `dtype` instead!
|
| 9 |
+
Loading weights: 100%|██████████| 807/807 [00:04<00:00, 187.16it/s]
|
| 10 |
+
[1mGR00TN17 LOAD REPORT[0m from: /home/ext_minje/.cache/huggingface/hub/models--nvidia--GR00T-N1.7-3B/snapshots/2fc962b973bccdd5d8ce4f67cc63b264d6886495
|
| 11 |
+
Key | Status | |
|
| 12 |
+
---------------------------------------------------------------------+------------+--+-
|
| 13 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_q.bias | UNEXPECTED | |
|
| 14 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_q.weight | UNEXPECTED | |
|
| 15 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_out.0.weight | UNEXPECTED | |
|
| 16 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_out.0.bias | UNEXPECTED | |
|
| 17 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.2.weight | UNEXPECTED | |
|
| 18 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_k.bias | UNEXPECTED | |
|
| 19 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_v.weight | UNEXPECTED | |
|
| 20 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_k.weight | UNEXPECTED | |
|
| 21 |
+
action_head.model.transformer_blocks.{16...31}.norm1.linear.weight | UNEXPECTED | |
|
| 22 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.2.bias | UNEXPECTED | |
|
| 23 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.0.proj.weight | UNEXPECTED | |
|
| 24 |
+
action_head.model.transformer_blocks.{16...31}.norm1.linear.bias | UNEXPECTED | |
|
| 25 |
+
action_head.model.transformer_blocks.{16...31}.attn1.to_v.bias | UNEXPECTED | |
|
| 26 |
+
action_head.model.transformer_blocks.{16...31}.ff.net.0.proj.bias | UNEXPECTED | |
|
| 27 |
+
|
| 28 |
+
Notes:
|
| 29 |
+
- UNEXPECTED: can be ignored when loading from different task/architecture; not ok if you expect identical arch.
|
| 30 |
+
Loading weights from local directory
|
| 31 |
+
INFO 2026-07-23 16:35:27 ot_train.py:417 Creating optimizer and scheduler
|
| 32 |
+
INFO 2026-07-23 16:35:31 ot_train.py:451 Output dir: /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K
|
| 33 |
+
INFO 2026-07-23 16:35:31 ot_train.py:458 cfg.steps=60000 (60K)
|
| 34 |
+
INFO 2026-07-23 16:35:31 ot_train.py:459 dataset.num_frames=218367 (218K)
|
| 35 |
+
INFO 2026-07-23 16:35:31 ot_train.py:460 dataset.num_episodes=4930
|
| 36 |
+
INFO 2026-07-23 16:35:31 ot_train.py:463 Effective batch size: 64 x 1 = 64
|
| 37 |
+
INFO 2026-07-23 16:35:31 ot_train.py:464 num_learnable_params=1080755329 (1B)
|
| 38 |
+
INFO 2026-07-23 16:35:31 ot_train.py:465 num_total_params=2604374177 (3B)
|
| 39 |
+
INFO 2026-07-23 16:35:31 ot_train.py:506 Resuming data order at epoch 22, sample 22144
|
| 40 |
+
Training: 0%| | 0/10000 [00:00<?, ?step/s]INFO 2026-07-23 16:35:31 ot_train.py:616 Start offline training on a fixed dataset, with effective batch size: 64
|
| 41 |
+
Training: 2%|▏ | 200/10000 [13:50<10:59:57, 4.04s/step]INFO 2026-07-23 16:49:22 ot_train.py:661 step:50K smpl:3M ep:73K epch:14.71 loss:0.017 grdn:0.208 lr:7.3e-06 updt_s:3.597 data_s:0.554 smp/s:15 mem_gb:29.84 flow_matching_loss:0.017 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.017 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.066 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.389 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 42 |
+
Training: 4%|▍ | 400/10000 [27:29<10:27:16, 3.92s/step]INFO 2026-07-23 17:03:00 ot_train.py:661 step:50K smpl:3M ep:73K epch:14.77 loss:0.017 grdn:0.211 lr:7.0e-06 updt_s:3.559 data_s:0.531 smp/s:16 mem_gb:29.84 flow_matching_loss:0.017 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.017 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.063 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.330 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 43 |
+
Training: 6%|▌ | 600/10000 [41:05<10:16:11, 3.93s/step]INFO 2026-07-23 17:16:36 ot_train.py:661 step:51K smpl:3M ep:73K epch:14.83 loss:0.017 grdn:0.226 lr:6.7e-06 updt_s:3.547 data_s:0.530 smp/s:16 mem_gb:29.84 flow_matching_loss:0.017 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.017 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.061 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.348 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 44 |
+
Training: 8%|▊ | 800/10000 [54:43<10:41:44, 4.19s/step]INFO 2026-07-23 17:30:15 ot_train.py:661 step:51K smpl:3M ep:73K epch:14.89 loss:0.016 grdn:0.214 lr:6.4e-06 updt_s:3.563 data_s:0.529 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.058 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.331 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 45 |
+
Training: 10%|█ | 1000/10000 [1:08:20<10:21:49, 4.15s/step]INFO 2026-07-23 17:43:51 ot_train.py:661 step:51K smpl:3M ep:74K epch:14.95 loss:0.016 grdn:0.210 lr:6.2e-06 updt_s:3.548 data_s:0.530 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.056 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.340 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 46 |
+
Training: 12%|█▏ | 1200/10000 [1:21:55<10:12:47, 4.18s/step]INFO 2026-07-23 17:57:27 ot_train.py:661 step:51K smpl:3M ep:74K epch:15.01 loss:0.016 grdn:0.210 lr:5.9e-06 updt_s:3.543 data_s:0.531 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.053 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.291 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 47 |
+
Training: 14%|█▍ | 1400/10000 [1:35:34<10:08:33, 4.25s/step]INFO 2026-07-23 18:11:05 ot_train.py:661 step:51K smpl:3M ep:74K epch:15.06 loss:0.016 grdn:0.213 lr:5.6e-06 updt_s:3.560 data_s:0.530 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.051 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.284 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 48 |
+
Training: 16%|█▌ | 1600/10000 [1:49:11<9:27:12, 4.05s/step]INFO 2026-07-23 18:24:42 ot_train.py:661 step:52K smpl:3M ep:75K epch:15.12 loss:0.016 grdn:0.212 lr:5.4e-06 updt_s:3.564 data_s:0.521 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.049 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.236 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 49 |
+
Training: 18%|█▊ | 1800/10000 [2:02:49<8:58:00, 3.94s/step]INFO 2026-07-23 18:38:20 ot_train.py:661 step:52K smpl:3M ep:75K epch:15.18 loss:0.017 grdn:0.215 lr:5.1e-06 updt_s:3.563 data_s:0.525 smp/s:16 mem_gb:29.83 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.046 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.253 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 50 |
+
Training: 20%|██ | 2000/10000 [2:16:31<9:08:44, 4.12s/step]INFO 2026-07-23 18:52:03 ot_train.py:661 step:52K smpl:3M ep:75K epch:15.24 loss:0.016 grdn:0.220 lr:4.9e-06 updt_s:3.584 data_s:0.527 smp/s:16 mem_gb:29.82 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.044 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.249 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 51 |
+
Training: 22%|██▏ | 2200/10000 [2:30:16<9:17:43, 4.29s/step]INFO 2026-07-23 19:05:48 ot_train.py:661 step:52K smpl:3M ep:75K epch:15.30 loss:0.016 grdn:0.216 lr:4.7e-06 updt_s:3.590 data_s:0.531 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.042 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.216 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 52 |
+
Training: 24%|██▍ | 2400/10000 [2:43:59<9:00:55, 4.27s/step]INFO 2026-07-23 19:19:31 ot_train.py:661 step:52K smpl:3M ep:76K epch:15.36 loss:0.016 grdn:0.205 lr:4.4e-06 updt_s:3.586 data_s:0.528 smp/s:16 mem_gb:29.85 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.040 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.197 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 53 |
+
Training: 26%|██▌ | 2600/10000 [2:57:34<8:36:33, 4.19s/step]INFO 2026-07-23 19:33:06 ot_train.py:661 step:53K smpl:3M ep:76K epch:15.42 loss:0.015 grdn:0.201 lr:4.2e-06 updt_s:3.546 data_s:0.527 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.038 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.223 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 54 |
+
Training: 28%|██▊ | 2800/10000 [3:11:19<8:27:43, 4.23s/step]INFO 2026-07-23 19:46:51 ot_train.py:661 step:53K smpl:3M ep:76K epch:15.47 loss:0.016 grdn:0.206 lr:4.0e-06 updt_s:3.593 data_s:0.530 smp/s:16 mem_gb:29.84 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.036 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.215 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 55 |
+
Training: 30%|███ | 3000/10000 [3:24:53<8:18:47, 4.28s/step]INFO 2026-07-23 20:00:24 ot_train.py:661 step:53K smpl:3M ep:77K epch:15.53 loss:0.016 grdn:0.211 lr:3.8e-06 updt_s:3.536 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.034 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.220 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 56 |
+
Training: 32%|███▏ | 3200/10000 [3:38:26<7:18:43, 3.87s/step]INFO 2026-07-23 20:13:57 ot_train.py:661 step:53K smpl:3M ep:77K epch:15.59 loss:0.016 grdn:0.219 lr:3.6e-06 updt_s:3.536 data_s:0.528 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.032 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.196 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 57 |
+
Training: 34%|███▍ | 3400/10000 [3:52:03<7:36:05, 4.15s/step]INFO 2026-07-23 20:27:35 ot_train.py:661 step:53K smpl:3M ep:77K epch:15.65 loss:0.016 grdn:0.205 lr:3.4e-06 updt_s:3.557 data_s:0.527 smp/s:16 mem_gb:29.85 flow_matching_loss:0.016 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.016 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.030 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.206 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 58 |
+
Training: 36%|███▌ | 3600/10000 [4:05:39<7:04:13, 3.98s/step]INFO 2026-07-23 20:41:11 ot_train.py:661 step:54K smpl:3M ep:77K epch:15.71 loss:0.015 grdn:0.208 lr:3.2e-06 updt_s:3.551 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.029 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.184 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 59 |
+
Training: 38%|███▊ | 3800/10000 [4:19:18<6:57:11, 4.04s/step]INFO 2026-07-23 20:54:50 ot_train.py:661 step:54K smpl:3M ep:78K epch:15.77 loss:0.015 grdn:0.198 lr:3.0e-06 updt_s:3.566 data_s:0.526 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.027 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.188 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 60 |
+
Training: 40%|████ | 4000/10000 [4:32:56<6:54:03, 4.14s/step]INFO 2026-07-23 21:08:28 ot_train.py:661 step:54K smpl:3M ep:78K epch:15.83 loss:0.016 grdn:0.206 lr:2.8e-06 updt_s:3.556 data_s:0.533 smp/s:16 mem_gb:29.84 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.025 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.214 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 61 |
+
Training: 42%|████▏ | 4200/10000 [4:46:35<6:24:18, 3.98s/step]INFO 2026-07-23 21:22:07 ot_train.py:661 step:54K smpl:3M ep:78K epch:15.89 loss:0.015 grdn:0.207 lr:2.6e-06 updt_s:3.561 data_s:0.531 smp/s:16 mem_gb:29.83 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.024 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.198 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 62 |
+
Training: 44%|████▍ | 4400/10000 [5:00:15<6:04:48, 3.91s/step]INFO 2026-07-23 21:35:47 ot_train.py:661 step:54K smpl:3M ep:79K epch:15.94 loss:0.015 grdn:0.204 lr:2.4e-06 updt_s:3.570 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.022 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.194 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 63 |
+
Training: 46%|████▌ | 4600/10000 [5:13:56<6:00:53, 4.01s/step]INFO 2026-07-23 21:49:28 ot_train.py:661 step:55K smpl:3M ep:79K epch:16.00 loss:0.015 grdn:0.206 lr:2.3e-06 updt_s:3.574 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.021 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.198 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 64 |
+
Training: 48%|████▊ | 4800/10000 [5:27:34<6:00:41, 4.16s/step]INFO 2026-07-23 22:03:06 ot_train.py:661 step:55K smpl:4M ep:79K epch:16.06 loss:0.015 grdn:0.207 lr:2.1e-06 updt_s:3.560 data_s:0.527 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.019 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.200 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 65 |
+
Training: 50%|█████ | 5000/10000 [5:41:10<4:26:09, 3.19s/step]INFO 2026-07-23 22:16:42 ot_train.py:661 step:55K smpl:4M ep:79K epch:16.12 loss:0.015 grdn:0.206 lr:2.0e-06 updt_s:3.550 data_s:0.530 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.018 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.203 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 66 |
+
INFO 2026-07-23 22:16:42 ot_train.py:707 Checkpoint policy after step 55000
|
| 67 |
+
INFO 2026-07-23 22:17:00 in_yaml.py:1414 Saved verified rolling checkpoint step=55000 slot=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_00
|
| 68 |
+
Training: 52%|█████▏ | 5200/10000 [5:55:11<5:27:42, 4.10s/step]INFO 2026-07-23 22:30:43 ot_train.py:661 step:55K smpl:4M ep:80K epch:16.18 loss:0.015 grdn:0.200 lr:1.8e-06 updt_s:3.582 data_s:0.530 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.016 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.189 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 69 |
+
Training: 54%|█████▍ | 5400/10000 [6:08:50<5:03:22, 3.96s/step]INFO 2026-07-23 22:44:21 ot_train.py:661 step:55K smpl:4M ep:80K epch:16.24 loss:0.015 grdn:0.215 lr:1.7e-06 updt_s:3.561 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.015 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.212 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 70 |
+
Training: 56%|█████▌ | 5600/10000 [6:22:31<5:13:40, 4.28s/step]INFO 2026-07-23 22:58:02 ot_train.py:661 step:56K smpl:4M ep:80K epch:16.30 loss:0.015 grdn:0.206 lr:1.5e-06 updt_s:3.573 data_s:0.530 smp/s:16 mem_gb:29.84 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.014 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.192 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 71 |
+
Training: 58%|█████▊ | 5800/10000 [6:36:07<4:38:04, 3.97s/step]INFO 2026-07-23 23:11:39 ot_train.py:661 step:56K smpl:4M ep:81K epch:16.35 loss:0.015 grdn:0.205 lr:1.4e-06 updt_s:3.551 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.013 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.155 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 72 |
+
Training: 60%|██████ | 6000/10000 [6:49:37<4:33:48, 4.11s/step]INFO 2026-07-23 23:25:09 ot_train.py:661 step:56K smpl:4M ep:81K epch:16.41 loss:0.015 grdn:0.201 lr:1.3e-06 updt_s:3.520 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.011 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.122 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 73 |
+
Training: 62%|██████▏ | 6200/10000 [7:03:15<4:17:22, 4.06s/step]INFO 2026-07-23 23:38:47 ot_train.py:661 step:56K smpl:4M ep:81K epch:16.47 loss:0.015 grdn:0.201 lr:1.2e-06 updt_s:3.556 data_s:0.530 smp/s:16 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.010 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.126 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 74 |
+
Training: 64%|██████▍ | 6400/10000 [7:16:53<4:03:36, 4.06s/step]INFO 2026-07-23 23:52:24 ot_train.py:661 step:56K smpl:4M ep:81K epch:16.53 loss:0.015 grdn:0.199 lr:1.0e-06 updt_s:3.558 data_s:0.527 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.009 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.127 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 75 |
+
Training: 66%|██████▌ | 6600/10000 [7:30:32<3:53:04, 4.11s/step]INFO 2026-07-24 00:06:03 ot_train.py:661 step:57K smpl:4M ep:82K epch:16.59 loss:0.015 grdn:0.200 lr:9.3e-07 updt_s:3.565 data_s:0.529 smp/s:16 mem_gb:29.83 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.008 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.126 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 76 |
+
Training: 68%|██████▊ | 6800/10000 [7:44:09<3:46:36, 4.25s/step]INFO 2026-07-24 00:19:40 ot_train.py:661 step:57K smpl:4M ep:82K epch:16.65 loss:0.015 grdn:0.207 lr:8.2e-07 updt_s:3.551 data_s:0.531 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.007 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.137 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 77 |
+
Training: 70%|███████ | 7000/10000 [7:57:46<3:25:39, 4.11s/step]INFO 2026-07-24 00:33:17 ot_train.py:661 step:57K smpl:4M ep:82K epch:16.71 loss:0.015 grdn:0.207 lr:7.3e-07 updt_s:3.554 data_s:0.529 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.007 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.128 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 78 |
+
Training: 72%|███████▏ | 7200/10000 [8:11:20<3:15:16, 4.18s/step]INFO 2026-07-24 00:46:51 ot_train.py:661 step:57K smpl:4M ep:83K epch:16.76 loss:0.015 grdn:0.201 lr:6.4e-07 updt_s:3.535 data_s:0.532 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.006 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.146 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 79 |
+
Training: 74%|███████▍ | 7400/10000 [8:24:58<2:50:34, 3.94s/step]INFO 2026-07-24 01:00:30 ot_train.py:661 step:57K smpl:4M ep:83K epch:16.82 loss:0.015 grdn:0.201 lr:5.5e-07 updt_s:3.552 data_s:0.539 smp/s:16 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.005 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.119 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 80 |
+
Training: 76%|███████▌ | 7600/10000 [8:38:55<2:39:14, 3.98s/step]INFO 2026-07-24 01:14:27 ot_train.py:661 step:58K smpl:4M ep:83K epch:16.88 loss:0.014 grdn:0.205 lr:4.7e-07 updt_s:3.595 data_s:0.586 smp/s:15 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.004 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.128 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 81 |
+
Training: 78%|███████▊ | 7800/10000 [8:52:32<2:24:37, 3.94s/step]INFO 2026-07-24 01:28:03 ot_train.py:661 step:58K smpl:4M ep:84K epch:16.94 loss:0.014 grdn:0.199 lr:4.0e-07 updt_s:3.538 data_s:0.544 smp/s:16 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.004 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.134 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 82 |
+
Training: 80%|████████ | 8000/10000 [9:06:27<2:13:40, 4.01s/step]INFO 2026-07-24 01:41:59 ot_train.py:661 step:58K smpl:4M ep:84K epch:17.00 loss:0.015 grdn:0.209 lr:3.3e-07 updt_s:3.560 data_s:0.612 smp/s:15 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.003 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.131 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 83 |
+
Training: 82%|████████▏ | 8200/10000 [9:20:26<2:00:16, 4.01s/step]INFO 2026-07-24 01:55:57 ot_train.py:661 step:58K smpl:4M ep:84K epch:17.06 loss:0.015 grdn:0.202 lr:2.7e-07 updt_s:3.582 data_s:0.609 smp/s:15 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.002 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.130 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 84 |
+
Training: 84%|████████▍ | 8400/10000 [9:36:41<2:06:49, 4.76s/step]INFO 2026-07-24 02:12:12 ot_train.py:661 step:58K smpl:4M ep:84K epch:17.12 loss:0.014 grdn:0.193 lr:2.2e-07 updt_s:3.983 data_s:0.887 smp/s:13 mem_gb:29.84 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.002 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.127 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 85 |
+
Training: 86%|████████▌ | 8600/10000 [9:51:48<1:37:09, 4.16s/step]INFO 2026-07-24 02:27:20 ot_train.py:661 step:59K smpl:4M ep:85K epch:17.17 loss:0.015 grdn:0.212 lr:1.7e-07 updt_s:3.602 data_s:0.930 smp/s:14 mem_gb:29.84 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.002 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.149 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 86 |
+
Training: 88%|████████▊ | 8800/10000 [10:05:55<1:21:37, 4.08s/step]INFO 2026-07-24 02:41:27 ot_train.py:661 step:59K smpl:4M ep:85K epch:17.23 loss:0.015 grdn:0.202 lr:1.3e-07 updt_s:3.527 data_s:0.705 smp/s:15 mem_gb:29.83 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.001 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.132 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 87 |
+
Training: 90%|█████████ | 9000/10000 [10:20:01<1:15:04, 4.50s/step]INFO 2026-07-24 02:55:32 ot_train.py:661 step:59K smpl:4M ep:85K epch:17.29 loss:0.014 grdn:0.197 lr:9.2e-08 updt_s:3.561 data_s:0.662 smp/s:15 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.001 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.136 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 88 |
+
Training: 92%|█████████▏| 9200/10000 [10:34:22<59:02, 4.43s/step]INFO 2026-07-24 03:09:54 ot_train.py:661 step:59K smpl:4M ep:86K epch:17.35 loss:0.014 grdn:0.190 lr:6.2e-08 updt_s:3.625 data_s:0.681 smp/s:15 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.001 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.118 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 89 |
+
Training: 94%|█████████▍| 9400/10000 [10:50:58<59:54, 5.99s/step] INFO 2026-07-24 03:26:29 ot_train.py:661 step:59K smpl:4M ep:86K epch:17.41 loss:0.015 grdn:0.206 lr:3.7e-08 updt_s:3.835 data_s:1.134 smp/s:13 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.000 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.130 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 90 |
+
Training: 96%|█████████▌| 9600/10000 [11:05:41<28:38, 4.30s/step]INFO 2026-07-24 03:41:13 ot_train.py:661 step:60K smpl:4M ep:86K epch:17.47 loss:0.015 grdn:0.200 lr:1.9e-08 updt_s:3.621 data_s:0.793 smp/s:15 mem_gb:29.85 flow_matching_loss:0.015 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.015 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.000 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.128 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 91 |
+
Training: 98%|█████████▊| 9800/10000 [11:19:44<14:04, 4.22s/step]INFO 2026-07-24 03:55:15 ot_train.py:661 step:60K smpl:4M ep:86K epch:17.53 loss:0.014 grdn:0.196 lr:7.1e-09 updt_s:3.584 data_s:0.626 smp/s:15 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.000 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.124 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 92 |
+
Training: 100%|██████████| 10000/10000 [11:33:57<00:00, 3.37s/step]INFO 2026-07-24 04:09:29 ot_train.py:661 step:60K smpl:4M ep:87K epch:17.59 loss:0.014 grdn:0.208 lr:1.0e-09 updt_s:3.553 data_s:0.712 smp/s:15 mem_gb:29.85 flow_matching_loss:0.014 rkd_loss:0.003 rkd_distance_loss:0.001 rkd_angle_loss:0.001 weighted_flow_matching_loss:0.014 weighted_rkd_loss:0.000 rkd_fm_loss_weight:1.000 rkd_loss_weight:0.000 rkd_runtime_enabled:1.000 rkd_student_pooling_id:1.000 rkd_teacher_latent_norm:1.000 rkd_student_feature_norm:15.128 training_phase_index:0.000 training_phase_start_step:0.000 training_phase_until_step:60000.000 training_phase_trainable_params:1080755329.000
|
| 93 |
+
INFO 2026-07-24 04:09:29 ot_train.py:707 Checkpoint policy after step 60000
|
| 94 |
+
INFO 2026-07-24 04:10:06 in_yaml.py:1414 Saved verified rolling checkpoint step=60000 slot=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01
|
| 95 |
+
Training: 100%|██████████| 10000/10000 [11:34:35<00:00, 4.17s/step]
|
| 96 |
+
INFO 2026-07-24 04:10:06 ot_train.py:793 End of training
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/requirements.txt
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
lerobot==0.6.1
|
| 2 |
+
tzdata==2026.3
|
| 3 |
+
nvidia-cufile-cu12==1.13.1.3
|
| 4 |
+
wandb==0.27.2
|
| 5 |
+
six==1.17.0
|
| 6 |
+
peft==0.19.1
|
| 7 |
+
nvidia-curand-cu12==10.3.9.90
|
| 8 |
+
nvidia-cuda-runtime-cu12==12.8.90
|
| 9 |
+
datasets==4.8.5
|
| 10 |
+
attrs==26.1.0
|
| 11 |
+
cloudpickle==3.1.2
|
| 12 |
+
packaging==25.0
|
| 13 |
+
nvidia-cublas-cu12==12.8.4.1
|
| 14 |
+
cmake==4.1.3
|
| 15 |
+
psutil==7.2.2
|
| 16 |
+
pydantic==2.13.4
|
| 17 |
+
GitPython==3.1.51
|
| 18 |
+
pillow==12.2.0
|
| 19 |
+
pytz==2026.2
|
| 20 |
+
cuda-pathfinder==1.2.2
|
| 21 |
+
nvidia-cusparse-cu12==12.5.8.93
|
| 22 |
+
typing_extensions==4.15.0
|
| 23 |
+
urllib3==2.7.0
|
| 24 |
+
pydantic_core==2.46.4
|
| 25 |
+
draccus==0.10.0
|
| 26 |
+
mypy_extensions==1.1.0
|
| 27 |
+
dill==0.4.1
|
| 28 |
+
typer==0.26.8
|
| 29 |
+
decord==0.6.0
|
| 30 |
+
tqdm==4.68.4
|
| 31 |
+
triton==3.6.0
|
| 32 |
+
idna==3.18
|
| 33 |
+
requests==2.34.2
|
| 34 |
+
nvidia-cudnn-cu12==9.19.0.56
|
| 35 |
+
mdurl==0.1.2
|
| 36 |
+
shellingham==1.5.4
|
| 37 |
+
zipp==4.1.0
|
| 38 |
+
timm==1.0.28
|
| 39 |
+
torch==2.11.0+cu128
|
| 40 |
+
tokenizers==0.22.2
|
| 41 |
+
nvidia-cusparselt-cu12==0.7.1
|
| 42 |
+
nvidia-cufft-cu12==11.3.3.83
|
| 43 |
+
nvidia-cusolver-cu12==11.7.3.90
|
| 44 |
+
opencv-python-headless==4.13.0.92
|
| 45 |
+
httpx==0.28.1
|
| 46 |
+
Jinja2==3.1.6
|
| 47 |
+
einops==0.8.2
|
| 48 |
+
mergedeep==1.3.4
|
| 49 |
+
platformdirs==4.10.0
|
| 50 |
+
nvidia-nvjitlink-cu12==12.8.93
|
| 51 |
+
lerobot==0.6.0
|
| 52 |
+
PyYAML==6.0.3
|
| 53 |
+
accelerate==1.14.0
|
| 54 |
+
anyio==4.14.2
|
| 55 |
+
gymnasium==1.3.0
|
| 56 |
+
pip==26.1.2
|
| 57 |
+
huggingface_hub==1.23.0
|
| 58 |
+
diffusers==0.35.2
|
| 59 |
+
annotated-doc==0.0.4
|
| 60 |
+
pyarrow==25.0.0
|
| 61 |
+
python-dateutil==2.9.0.post0
|
| 62 |
+
termcolor==3.3.0
|
| 63 |
+
nvidia-nccl-cu12==2.28.9
|
| 64 |
+
sentry-sdk==2.65.0
|
| 65 |
+
torchcodec==0.11.1
|
| 66 |
+
pyyaml-include==1.4.1
|
| 67 |
+
multiprocess==0.70.19
|
| 68 |
+
wrapt==2.2.2
|
| 69 |
+
typing-inspection==0.4.2
|
| 70 |
+
nvidia-cuda-nvrtc-cu12==12.8.93
|
| 71 |
+
Pygments==2.20.0
|
| 72 |
+
nvidia-cuda-cupti-cu12==12.8.90
|
| 73 |
+
certifi==2026.6.17
|
| 74 |
+
setuptools==78.1.0
|
| 75 |
+
charset-normalizer==3.4.9
|
| 76 |
+
propcache==0.5.2
|
| 77 |
+
multidict==6.7.1
|
| 78 |
+
regex==2026.7.10
|
| 79 |
+
frozenlist==1.8.0
|
| 80 |
+
smmap==5.0.3
|
| 81 |
+
hf-xet==1.5.1
|
| 82 |
+
torchvision==0.26.0+cu128
|
| 83 |
+
gitdb==4.0.12
|
| 84 |
+
transformers==5.5.4
|
| 85 |
+
rich==15.0.0
|
| 86 |
+
cuda-bindings==12.9.4
|
| 87 |
+
protobuf==7.35.1
|
| 88 |
+
aiosignal==1.4.0
|
| 89 |
+
jsonlines==4.0.0
|
| 90 |
+
yarl==1.24.2
|
| 91 |
+
filelock==3.29.0
|
| 92 |
+
av==15.1.0
|
| 93 |
+
networkx==3.6.1
|
| 94 |
+
sympy==1.14.0
|
| 95 |
+
wheel==0.47.0
|
| 96 |
+
nvidia-nvtx-cu12==12.8.90
|
| 97 |
+
xxhash==3.8.1
|
| 98 |
+
toml==0.10.2
|
| 99 |
+
MarkupSafe==3.0.3
|
| 100 |
+
pandas==2.3.3
|
| 101 |
+
safetensors==0.8.0
|
| 102 |
+
click==8.4.2
|
| 103 |
+
fsspec==2026.2.0
|
| 104 |
+
dm-tree==0.1.10
|
| 105 |
+
absl-py==2.5.0
|
| 106 |
+
Farama-Notifications==0.0.6
|
| 107 |
+
mpmath==1.3.0
|
| 108 |
+
importlib_metadata==9.0.0
|
| 109 |
+
markdown-it-py==4.2.0
|
| 110 |
+
h11==0.16.0
|
| 111 |
+
typing-inspect==0.9.0
|
| 112 |
+
httpcore==1.0.9
|
| 113 |
+
annotated-types==0.7.0
|
| 114 |
+
numpy==2.2.6
|
| 115 |
+
nvidia-nvshmem-cu12==3.4.5
|
| 116 |
+
aiohappyeyeballs==2.7.1
|
| 117 |
+
cuda-toolkit==12.8.1
|
| 118 |
+
aiohttp==3.14.1
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/wandb-metadata.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"os": "Linux-6.8.0-55-generic-x86_64-with-glibc2.39",
|
| 3 |
+
"python": "CPython 3.12.13",
|
| 4 |
+
"startedAt": "2026-07-23T16:35:01.611693Z",
|
| 5 |
+
"args": [
|
| 6 |
+
"--config_path=/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model/train_config.json",
|
| 7 |
+
"--resume=true"
|
| 8 |
+
],
|
| 9 |
+
"program": "/home/ext_minje/clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py",
|
| 10 |
+
"codePath": "clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py",
|
| 11 |
+
"codePathLocal": "clvla/benchmarks/INSIGHT/my_scripts/lerobot_train_yaml.py",
|
| 12 |
+
"root": "/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K",
|
| 13 |
+
"host": "ext_minje-box",
|
| 14 |
+
"executable": "/home/ext_minje/miniconda3/envs/lerobot060_groot/bin/python",
|
| 15 |
+
"cpu_count": 112,
|
| 16 |
+
"cpu_count_logical": 224,
|
| 17 |
+
"gpu": "NVIDIA H200",
|
| 18 |
+
"gpu_count": 2,
|
| 19 |
+
"disk": {
|
| 20 |
+
"/": {
|
| 21 |
+
"total": "1888425144320",
|
| 22 |
+
"used": "1327086579712"
|
| 23 |
+
}
|
| 24 |
+
},
|
| 25 |
+
"memory": {
|
| 26 |
+
"total": "2164176568320"
|
| 27 |
+
},
|
| 28 |
+
"gpu_nvidia": [
|
| 29 |
+
{
|
| 30 |
+
"name": "NVIDIA H200",
|
| 31 |
+
"memoryTotal": "150754820096",
|
| 32 |
+
"cudaCores": 16896,
|
| 33 |
+
"architecture": "Hopper",
|
| 34 |
+
"uuid": "GPU-86be6e5b-fb48-fa1c-9bd7-83d336cb2991"
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"name": "NVIDIA H200",
|
| 38 |
+
"memoryTotal": "150754820096",
|
| 39 |
+
"cudaCores": 16896,
|
| 40 |
+
"architecture": "Hopper",
|
| 41 |
+
"uuid": "GPU-24eb1ba2-7313-ff93-1435-748768ebdbdc"
|
| 42 |
+
}
|
| 43 |
+
],
|
| 44 |
+
"cudaVersion": "12.9",
|
| 45 |
+
"writerId": "3vx7sedbdsz3uay6fuuuh2e3qlqtbnr9"
|
| 46 |
+
}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/files/wandb-summary.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"train/training_phase_trainable_params":1.080755329e+09,"train/update_s":3.5525975197848676,"train/rkd_teacher_latent_norm":1,"train/rkd_student_pooling_id":1,"train/weighted_rkd_loss":2.6304401752318693e-08,"train/rkd_runtime_enabled":1,"train/episodes":86694.41811262691,"train/training_phase_index":0,"train/samples_per_s":15.006542098698269,"train/flow_matching_loss":0.014334074733778835,"train/epochs":17.58507466787564,"train/rkd_loss_weight":9.207125008732775e-06,"_runtime":83988,"train/lr":1.0049909226259037e-09,"train/loss":0.014334101057611405,"train/rkd_student_feature_norm":15.128039054870605,"_timestamp":1.7848661692599273e+09,"train/rkd_fm_loss_weight":1,"train/rkd_angle_loss":0.0010985716705908999,"_step":60000,"train/dataloading_s":0.712209094495156,"train/gpu_mem_gb":29.8462087392807,"train/steps":60000,"train/samples":3840000,"train/weighted_flow_matching_loss":0.014334074733778835,"_wandb":{"runtime":83988},"train/training_phase_start_step":0,"train/rkd_loss":0.0028473387891426684,"train/rkd_distance_loss":0.0006501954395207577,"train/training_phase_until_step":60000,"train/grad_norm":0.20803156722337007}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug-core.log
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"time":"2026-07-23T16:35:01.682970498Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpa9piztjm/port-1456.txt","pid":1456,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 2 |
+
{"time":"2026-07-23T16:35:01.682978333Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmplz0alzhu/port-1457.txt","pid":1457,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 3 |
+
{"time":"2026-07-23T16:35:01.682985044Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpwunx93cw/port-1458.txt","pid":1458,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 4 |
+
{"time":"2026-07-23T16:35:01.6829908Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpf4abll73/port-1459.txt","pid":1459,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 5 |
+
{"time":"2026-07-23T16:35:01.68360802Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1456}
|
| 6 |
+
{"time":"2026-07-23T16:35:01.683616029Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1457}
|
| 7 |
+
{"time":"2026-07-23T16:35:01.683634398Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1458}
|
| 8 |
+
{"time":"2026-07-23T16:35:01.683603455Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1456-2506-1311874521/socket","Net":"unix"}}
|
| 9 |
+
{"time":"2026-07-23T16:35:01.68361302Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1457-2507-772500566/socket","Net":"unix"}}
|
| 10 |
+
{"time":"2026-07-23T16:35:01.683630442Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1458-2509-4014368169/socket","Net":"unix"}}
|
| 11 |
+
{"time":"2026-07-23T16:35:01.683627313Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1459-2508-1604368573/socket","Net":"unix"}}
|
| 12 |
+
{"time":"2026-07-23T16:35:01.683696179Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1459}
|
| 13 |
+
{"time":"2026-07-23T16:35:01.832927644Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 14 |
+
{"time":"2026-07-23T16:35:01.833171958Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 15 |
+
{"time":"2026-07-23T16:35:01.833208155Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 16 |
+
{"time":"2026-07-23T16:35:01.833275727Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 17 |
+
{"time":"2026-07-23T16:35:01.837817931Z","level":"INFO","msg":"handleInformInit: received","streamId":"rs1egwv8","id":"1(@)"}
|
| 18 |
+
{"time":"2026-07-23T16:35:01.837959217Z","level":"INFO","msg":"handleInformInit: received","streamId":"2vl3enlf","id":"1(@)"}
|
| 19 |
+
{"time":"2026-07-23T16:35:01.838627327Z","level":"INFO","msg":"handleInformInit: received","streamId":"jeqgwsec","id":"1(@)"}
|
| 20 |
+
{"time":"2026-07-23T16:35:01.838419673Z","level":"INFO","msg":"handleInformInit: received","streamId":"x6da8gup","id":"1(@)"}
|
| 21 |
+
{"time":"2026-07-23T16:35:01.918297888Z","level":"INFO","msg":"main: starting server","port-filename":"/tmp/tmpuyiti7pv/port-1460.txt","pid":1460,"detached":false,"idle-timeout":600000000000,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
|
| 22 |
+
{"time":"2026-07-23T16:35:01.91863949Z","level":"INFO","msg":"server: will exit if parent process dies","ppid":1460}
|
| 23 |
+
{"time":"2026-07-23T16:35:01.918628695Z","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/tmp/wandb-1460-2829-1778593576/socket","Net":"unix"}}
|
| 24 |
+
{"time":"2026-07-23T16:35:02.074586625Z","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
|
| 25 |
+
{"time":"2026-07-23T16:35:02.079634061Z","level":"INFO","msg":"handleInformInit: received","streamId":"brma7856","id":"1(@)"}
|
| 26 |
+
{"time":"2026-07-23T16:35:02.303790584Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"2vl3enlf","id":"1(@)"}
|
| 27 |
+
{"time":"2026-07-23T16:35:02.30665649Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"x6da8gup","id":"1(@)"}
|
| 28 |
+
{"time":"2026-07-23T16:35:02.307741694Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"jeqgwsec","id":"1(@)"}
|
| 29 |
+
{"time":"2026-07-23T16:35:02.32303733Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"rs1egwv8","id":"1(@)"}
|
| 30 |
+
{"time":"2026-07-23T16:35:02.493177984Z","level":"INFO","msg":"handleInformInit: stream started","streamId":"brma7856","id":"1(@)"}
|
| 31 |
+
{"time":"2026-07-23T16:35:08.314840933Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"pomu74zdcjwn"}
|
| 32 |
+
{"time":"2026-07-23T16:35:08.415606838Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"u8kbql7lf4bh"}
|
| 33 |
+
{"time":"2026-07-23T16:35:08.420996327Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"bhwn826heh2c"}
|
| 34 |
+
{"time":"2026-07-23T16:35:08.623677864Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"0dnh3nypnhfm"}
|
| 35 |
+
{"time":"2026-07-23T16:35:09.044152431Z","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"4z6b40zq3yfu"}
|
| 36 |
+
{"time":"2026-07-23T18:11:27.126647161Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 37 |
+
{"time":"2026-07-23T18:11:27.126779892Z","level":"INFO","msg":"server is shutting down"}
|
| 38 |
+
{"time":"2026-07-23T18:11:27.12683822Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1457-2507-772500566/socket","Net":"unix"}}
|
| 39 |
+
{"time":"2026-07-23T18:11:27.126852003Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 40 |
+
{"time":"2026-07-23T18:11:27.126886112Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 41 |
+
{"time":"2026-07-23T18:11:27.126932287Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 42 |
+
{"time":"2026-07-23T18:11:27.378619144Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 43 |
+
{"time":"2026-07-23T18:11:27.37874002Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 44 |
+
{"time":"2026-07-23T18:11:27.378802617Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 45 |
+
{"time":"2026-07-23T18:11:27.378812716Z","level":"INFO","msg":"server is shutting down"}
|
| 46 |
+
{"time":"2026-07-23T18:11:27.378878838Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1456-2506-1311874521/socket","Net":"unix"}}
|
| 47 |
+
{"time":"2026-07-23T18:11:27.378895674Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 48 |
+
{"time":"2026-07-23T18:11:35.494138091Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 49 |
+
{"time":"2026-07-23T18:11:35.494189389Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 50 |
+
{"time":"2026-07-23T18:11:35.494201536Z","level":"INFO","msg":"server is closed"}
|
| 51 |
+
{"time":"2026-07-23T18:12:28.994694228Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 52 |
+
{"time":"2026-07-23T18:12:28.994728432Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 53 |
+
{"time":"2026-07-23T18:12:28.994736061Z","level":"INFO","msg":"server is closed"}
|
| 54 |
+
{"time":"2026-07-24T04:08:45.417129571Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 55 |
+
{"time":"2026-07-24T04:08:45.417350121Z","level":"INFO","msg":"server is shutting down"}
|
| 56 |
+
{"time":"2026-07-24T04:08:45.417341706Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 57 |
+
{"time":"2026-07-24T04:08:45.417373499Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 58 |
+
{"time":"2026-07-24T04:08:45.41745467Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 59 |
+
{"time":"2026-07-24T04:08:45.417448026Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1458-2509-4014368169/socket","Net":"unix"}}
|
| 60 |
+
{"time":"2026-07-24T04:08:47.515259401Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 61 |
+
{"time":"2026-07-24T04:08:47.515290273Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 62 |
+
{"time":"2026-07-24T04:08:47.515301151Z","level":"INFO","msg":"server is closed"}
|
| 63 |
+
{"time":"2026-07-24T04:10:06.98288621Z","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
|
| 64 |
+
{"time":"2026-07-24T04:10:06.983062676Z","level":"INFO","msg":"connection: closing","id":"1(@)"}
|
| 65 |
+
{"time":"2026-07-24T04:10:06.983136342Z","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
|
| 66 |
+
{"time":"2026-07-24T04:10:06.983144044Z","level":"INFO","msg":"server is shutting down"}
|
| 67 |
+
{"time":"2026-07-24T04:10:06.98322588Z","level":"INFO","msg":"server: listener closed","addr":{"Name":"/tmp/wandb-1459-2508-1604368573/socket","Net":"unix"}}
|
| 68 |
+
{"time":"2026-07-24T04:10:06.983271294Z","level":"INFO","msg":"processOutgoingData: finished","id":"1(@)"}
|
| 69 |
+
{"time":"2026-07-24T04:10:23.060371611Z","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
|
| 70 |
+
{"time":"2026-07-24T04:10:23.060399527Z","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
|
| 71 |
+
{"time":"2026-07-24T04:10:23.060415126Z","level":"INFO","msg":"server is closed"}
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug-internal.log
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug.log
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_setup.py:_flush():81] Current SDK version is 0.27.2
|
| 2 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_setup.py:_flush():81] Configure stats pid to 1459
|
| 3 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_setup.py:_flush():81] Loading settings from environment variables
|
| 4 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:setup_run_log_directory():723] Logging user logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug.log
|
| 5 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:setup_run_log_directory():724] Logging internal logs to /home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/wandb/run-20260723_163501-rs1egwv8/logs/debug-internal.log
|
| 6 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:init():766] calling init triggers
|
| 7 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:init():771] wandb.init called with sweep_config: {}
|
| 8 |
+
config: {'dataset': {'repo_id': 'Whalswp/INSIGHTfixposV4_filtered_multispace_v2', 'root': '/home/ext_minje/INSIGHTfixposV4_filtered_multispace_v2', 'episodes': None, 'image_transforms': {'enable': False, 'max_num_transforms': 3, 'random_order': False, 'tfs': {'brightness': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'brightness': [0.8, 1.2]}}, 'contrast': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'contrast': [0.8, 1.2]}}, 'saturation': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'saturation': [0.5, 1.5]}}, 'hue': {'weight': 1.0, 'type': 'ColorJitter', 'kwargs': {'hue': [-0.05, 0.05]}}, 'sharpness': {'weight': 1.0, 'type': 'SharpnessJitter', 'kwargs': {'sharpness': [0.5, 1.5]}}, 'affine': {'weight': 1.0, 'type': 'RandomAffine', 'kwargs': {'degrees': [-5.0, 5.0], 'translate': [0.05, 0.05]}}}}, 'revision': None, 'use_imagenet_stats': True, 'video_backend': 'torchcodec', 'return_uint8': False, 'depth_output_unit': 'mm', 'streaming': False, 'eval_split': 0.0}, 'env': None, 'policy': {'type': 'groot_rkd', 'n_obs_steps': 1, 'input_features': {'observation.state': {'type': <FeatureType.STATE: 'STATE'>, 'shape': [16]}, 'observation.images.wrist': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.right_shoulder': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}, 'observation.images.guide': {'type': <FeatureType.VISUAL: 'VISUAL'>, 'shape': [3, 224, 224]}}, 'output_features': {'action': {'type': <FeatureType.ACTION: 'ACTION'>, 'shape': [10]}}, 'device': 'cuda', 'use_amp': False, 'use_peft': False, 'push_to_hub': False, 'repo_id': None, 'private': None, 'tags': None, 'license': None, 'pretrained_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01/pretrained_model', 'pretrained_revision': None, 'chunk_size': 16, 'n_action_steps': 16, 'max_state_dim': 132, 'max_action_dim': 132, 'normalization_mapping': {'VISUAL': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'STATE': <NormalizationMode.IDENTITY: 'IDENTITY'>, 'ACTION': <NormalizationMode.IDENTITY: 'IDENTITY'>}, 'base_model_path': 'nvidia/GR00T-N1.7-3B', 'action_decode_transform': None, 'embodiment_tag': 'new_embodiment', 'tune_llm': False, 'tune_visual': False, 'tune_projector': True, 'tune_diffusion_model': True, 'tune_vlln': True, 'tune_top_llm_layers': 0, 'num_inference_timesteps': None, 'rtc_ramp_rate': None, 'use_flash_attention': False, 'use_relative_actions': False, 'relative_exclude_joints': [], 'optimizer_lr': 0.0001, 'optimizer_betas': [0.9, 0.999], 'optimizer_eps': 1e-08, 'optimizer_weight_decay': 1e-05, 'warmup_steps': 3000, 'warmup_ratio': 0.05, 'use_bf16': True, 'model_params_fp32': True, 'image_size': [256, 256], 'tokenizer_assets_repo': None, 'lora_rank': 0, 'lora_alpha': 16, 'lora_dropout': 0.1, 'lora_full_model': False, 'video_backend': 'decord', 'balance_dataset_weights': True, 'balance_trajectory_weights': True, 'dataset_paths': None, 'output_dir': './tmp/gr00t', 'save_steps': 1000, 'max_steps': 10000, 'batch_size': 32, 'dataloader_num_workers': 8, 'report_to': 'wandb', 'resume': False, 'action_expert_num_layers': 16, 'rkd_enabled': True, 'rkd_vae_checkpoint': '/home/ext_minje/groot_insight/TimewarpVAE_ckpt/TimewarpVAE_combo_top8_30k/C8_01_C3_008_beta_5em05_latent_dim_16_granularity_4_decoder_hidden_dim_512/checkpoint-step-30000-epoch-39.11', 'rkd_student_pooling': 'attention', 'rkd_student_attention_hidden_dim': 512, 'rkd_student_attention_output_dim': 512, 'rkd_fm_loss_weight': 1.0, 'rkd_loss_weight': 1.0, 'rkd_distance_weight': 1.0, 'rkd_angle_weight': 2.0}, 'reward_model': None, 'output_dir': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K', 'job_name': 'INSIGHT_6D_DiT16_RKD_TimewarpVAE_RSCLstyle_C60', 'resume': True, 'seed': 42, 'cudnn_deterministic': False, 'num_workers': 4, 'batch_size': 64, 'prefetch_factor': 4, 'persistent_workers': True, 'steps': 60000, 'env_eval_freq': 20000, 'log_freq': 200, 'eval_steps': 0, 'max_eval_samples': 0, 'tolerance_s': 0.0001, 'save_checkpoint': True, 'save_freq': 20000, 'use_policy_training_preset': True, 'optimizer': {'type': 'adamw', 'lr': 0.0001, 'weight_decay': 1e-05, 'grad_clip_norm': 1.0, 'betas': [0.9, 0.999], 'eps': 1e-08}, 'scheduler': {'type': 'diffuser', 'num_warmup_steps': 3000, 'name': 'cosine'}, 'eval': {'n_episodes': 50, 'batch_size': 50, 'use_async_envs': True, 'recording': False, 'recording_repo_id': None, 'recording_private': False}, 'wandb': {'enable': True, 'disable_artifact': True, 'project': 'lerobot', 'entity': None, 'notes': None, 'run_id': 'rs1egwv8', 'mode': None, 'add_tags': True}, 'peft': None, 'job': {'target': None, 'image': 'huggingface/lerobot-gpu:latest', 'timeout': '2d', 'detach': False, 'tags': []}, 'save_checkpoint_to_hub': False, 'sample_weighting': None, 'rename_map': {}, 'checkpoint_path': '/home/ext_minje/groot_insight/train_ckpt/Abs_6D/DiT_Layer/16/RSCLstyle_cosine_60K/checkpoints/rolling_01', '_wandb': {}}
|
| 9 |
+
2026-07-23 16:35:01,612 INFO MainThread:1459 [wandb_init.py:init():814] starting backend
|
| 10 |
+
2026-07-23 16:35:01,833 INFO MainThread:1459 [wandb_init.py:init():829] sending inform_init request
|
| 11 |
+
2026-07-23 16:35:02,323 INFO MainThread:1459 [wandb_init.py:init():834] backend started and connected
|
| 12 |
+
2026-07-23 16:35:02,325 INFO MainThread:1459 [wandb_init.py:init():904] updated telemetry
|
| 13 |
+
2026-07-23 16:35:02,326 INFO MainThread:1459 [wandb_init.py:init():927] communicating run to backend with 90.0 second timeout
|
| 14 |
+
2026-07-23 16:35:03,342 INFO MainThread:1459 [wandb_init.py:init():967] run resumed
|
| 15 |
+
2026-07-23 16:35:03,344 INFO MainThread:1459 [wandb_init.py:init():972] starting run threads in backend
|
| 16 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_console_start():2523] atexit reg
|
| 17 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_redirect():2373] redirect: wrap_raw
|
| 18 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_redirect():2442] Wrapping output streams.
|
| 19 |
+
2026-07-23 16:35:03,396 INFO MainThread:1459 [wandb_run.py:_redirect():2465] Redirects installed.
|
| 20 |
+
2026-07-23 16:35:03,398 INFO MainThread:1459 [wandb_init.py:init():1010] run started, returning control to user process
|
| 21 |
+
2026-07-24 04:10:06,982 INFO wandb-AsyncioManager-main:1459 [service_client.py:_forward_responses():122] Reached EOF.
|
| 22 |
+
2026-07-24 04:10:06,983 INFO wandb-AsyncioManager-main:1459 [mailbox.py:close():154] Closing mailbox, abandoning 2 handles.
|
| 23 |
+
2026-07-24 04:10:06,983 ERROR wandb-AsyncioManager-main:1459 [asyncio_manager.py:fn_wrap_exceptions():184] Uncaught exception in run_soon callback.
|
| 24 |
+
Traceback (most recent call last):
|
| 25 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_manager.py", line 182, in fn_wrap_exceptions
|
| 26 |
+
await fn()
|
| 27 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_messages.py", line 90, in loop
|
| 28 |
+
await asyncio_compat.race(
|
| 29 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 278, in race
|
| 30 |
+
async with open_task_group(race=True) as tg:
|
| 31 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 32 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/contextlib.py", line 217, in __aexit__
|
| 33 |
+
await anext(self.gen)
|
| 34 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 240, in open_task_group
|
| 35 |
+
await task_group._wait_all(race=race, timeout=exit_timeout)
|
| 36 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_compat.py", line 180, in _wait_all
|
| 37 |
+
raise exc
|
| 38 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_messages.py", line 113, in _print_all
|
| 39 |
+
result = await handle.wait_async(timeout=None)
|
| 40 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 41 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/mailbox_handle.py", line 127, in wait_async
|
| 42 |
+
response = await self._handle.wait_async(timeout=timeout)
|
| 43 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 44 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/response_handle.py", line 123, in wait_async
|
| 45 |
+
raise HandleAbandonedError()
|
| 46 |
+
wandb.sdk.mailbox.mailbox_handle.HandleAbandonedError
|
| 47 |
+
2026-07-24 04:10:14,759 ERROR wandb-AsyncioManager-main:1459 [asyncio_manager.py:fn_wrap_exceptions():184] Uncaught exception in run_soon callback.
|
| 48 |
+
Traceback (most recent call last):
|
| 49 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/asyncio_manager.py", line 182, in fn_wrap_exceptions
|
| 50 |
+
await fn()
|
| 51 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_stopping.py", line 87, in loop
|
| 52 |
+
should_stop = await self._check_should_stop()
|
| 53 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 54 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/run_stopping.py", line 115, in _check_should_stop
|
| 55 |
+
handle = await self._interface.deliver_async(request)
|
| 56 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 57 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/interface/interface_sock.py", line 58, in deliver_async
|
| 58 |
+
handle = await self._client.deliver(request)
|
| 59 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 60 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/lib/service/service_client.py", line 57, in deliver
|
| 61 |
+
handle = self._mailbox.require_response(request)
|
| 62 |
+
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
|
| 63 |
+
File "/home/ext_minje/miniconda3/envs/lerobot060_groot/lib/python3.12/site-packages/wandb/sdk/mailbox/mailbox.py", line 89, in require_response
|
| 64 |
+
raise MailboxClosedError()
|
| 65 |
+
wandb.sdk.mailbox.mailbox.MailboxClosedError
|