Amshaker commited on
Commit
eac2623
·
verified ·
1 Parent(s): 0ae3cea

Upload folder using huggingface_hub

Browse files
bimamba_stage_b_joint_ckpt_40k/wandb/debug-internal.log CHANGED
The diff for this file is too large to render. See raw diff
 
bimamba_stage_b_joint_ckpt_40k/wandb/debug.log CHANGED
@@ -1,26 +1,26 @@
1
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Current SDK version is 0.17.9
2
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Configure stats pid to 409635
3
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Loading settings from /home/x_fahkh/.config/wandb/settings
4
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Loading settings from /proj/cvl/users/x_fahkh2/WorldMem_Repro/wandb/settings
5
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Loading settings from environment variables: {'disabled': 'true'}
6
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Applying setup settings: {'_disable_service': False}
7
- 2026-04-12 19:23:25,279 WARNING MainThread:409635 [wandb_setup.py:_flush():77] Could not find program at -m main
8
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_setup.py:_flush():77] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m main'}
9
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_init.py:_log_setup():524] Logging user logs to /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260412_192325-stage_b_joint_offline/logs/debug.log
10
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_init.py:_log_setup():525] Logging internal logs to /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260412_192325-stage_b_joint_offline/logs/debug-internal.log
11
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_init.py:init():608] calling init triggers
12
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_init.py:init():615] wandb.init called with sweep_config: {}
13
- config: {'experiment': {'debug': '${debug}', 'tasks': ['training'], 'num_nodes': 1, 'training': {'precision': '16-mixed', 'compile': False, 'lr': 2e-05, 'batch_size': 8, 'max_epochs': -1, 'max_steps': 175000, 'max_time': None, 'data': {'num_workers': 4, 'shuffle': True}, 'optim': {'accumulate_grad_batches': 1, 'gradient_clip_val': 1.0}, 'checkpointing': {'every_n_train_steps': 2500, 'every_n_epochs': None, 'train_time_interval': None, 'enable_version_counter': False}}, 'validation': {'precision': '16-mixed', 'compile': False, 'batch_size': 4, 'val_every_n_step': 2500, 'val_every_n_epoch': None, 'limit_batch': 1, 'inference_mode': False, 'data': {'num_workers': 4, 'shuffle': False}}, 'test': {'precision': '16-mixed', 'compile': False, 'batch_size': 1, 'limit_batch': 1, 'inference_mode': False, 'data': {'num_workers': 4, 'shuffle': False}}, 'logging': {'metrics': None}, '_name': 'exp_video'}, 'dataset': {'debug': '${debug}', 'metadata': 'data/${dataset.name}/metadata.json', 'data_mean': 0.5, 'data_std': 0.5, 'save_dir': '/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'n_frames': 200, 'context_length': 1, 'resolution': 128, 'observation_shape': [3, '${dataset.resolution}', '${dataset.resolution}'], 'external_cond_dim': 0, 'validation_multiplier': 1, 'frame_skip': 1, 'action_cond_dim': 25, '_name': 'video_minecraft', 'n_frames_valid': 200, 'angle_range': 110, 'pos_range': 8, 'wo_updown': False, 'customized_validation': True, 'add_timestamp_embedding': True, 'use_explicit_memory_frames': False}, 'algorithm': {'debug': '${debug}', 'lr': '${experiment.training.lr}', 'x_shape': '${dataset.observation_shape}', 'frame_stack': 1, 'frame_skip': '${dataset.frame_skip}', 'data_mean': '${dataset.data_mean}', 'data_std': '${dataset.data_std}', 'external_cond_dim': 0, 'context_frames': 100, 'weight_decay': 0.002, 'warmup_steps': 1000, 'optimizer_beta': [0.9, 0.99], 'uncertainty_scale': 1, 'guidance_scale': 0.0, 'chunk_size': 1, 'scheduling_matrix': 'autoregressive', 'noise_level': 'random_all', 'causal': True, 'diffusion': {'objective': 'pred_v', 'beta_schedule': 'sigmoid', 'schedule_fn_kwargs': {}, 'clip_noise': 20.0, 'use_snr': False, 'use_cum_snr': False, 'use_fused_snr': True, 'snr_clip': 5.0, 'cum_snr_decay': 0.96, 'timesteps': 1000, 'sampling_timesteps': 20, 'ddim_sampling_eta': 0.0, 'stabilization_level': 15, 'architecture': {'network_size': 64, 'attn_heads': 4, 'attn_dim_head': 64, 'dim_mults': [1, 2, 4, 8], 'resolution': '${dataset.resolution}', 'attn_resolutions': [16, 32, 64, 128], 'use_init_temporal_attn': True, 'use_linear_attn': True, 'time_emb_type': 'rotary'}}, 'n_frames': '${dataset.n_frames}', 'metadata': '${dataset.metadata}', 'action_cond_dim': 25, 'use_plucker': True, 'memory_condition_length': 0, 'log_video': True, 'use_mamba_memory_pipeline': True, 'training_stage': 'stage_b_diffusion_training', 'stage_b_joint_training': True, 'stage_b_memory_aux_weight': 0.1, 'diff_window_size': 8, 'memory_gap_aux_weight': 0.1, 'memory_gap_aux_weight_init': 0.5, 'memory_gap_aux_weight_final': 0.1, 'memory_gap_aux_decay_fraction': 0.3, 'memory_gap_aux_decay_steps': 0, 'memory_gap_aux_exp_k': 5.0, 'use_precomputed_features': False, 'mamba_latent_channels': 16, 'mamba_model_dim': 256, 'mamba_depth': 4, 'mamba_cond_dim': 256, 'mamba_d_state': 16, 'mamba_d_conv': 4, 'mamba_expand': 2, 'allow_mamba_fallback': False, 'strict_causal_training': True, 'strict_causal_evaluation': True, 'use_oracle_pose_eval': True, 'enable_memory_noise_curriculum': False, 'curriculum_phase_boundaries': [0.2, 0.7], 'curriculum_noise_ranges': [[600, 1000], [200, 900], [0, 400]], 'curriculum_horizons': [50, 100, 200], '_name': 'df_video_mamba3stage', 'use_memory_attention': False, 'relative_embedding': False, 'memory_retrieval_topk': 32, 'n_tokens': 8}, 'debug': False, 'wandb': {'entity': 'turlin', 'project': 'worldmem', 'mode': 'online'}, 'resume': 'stage_b_joint_offline', 'load': None, 'name': 'train_stage_b_mamba_joint', 'output_dir': '/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/'}
14
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_init.py:init():658] starting backend
15
- 2026-04-12 19:23:25,279 INFO MainThread:409635 [wandb_init.py:init():662] setting up manager
16
- 2026-04-12 19:23:25,301 INFO MainThread:409635 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
- 2026-04-12 19:23:25,309 INFO MainThread:409635 [wandb_init.py:init():670] backend started and connected
18
- 2026-04-12 19:23:25,334 INFO MainThread:409635 [wandb_init.py:init():768] updated telemetry
19
- 2026-04-12 19:23:25,403 INFO MainThread:409635 [wandb_init.py:init():801] communicating run to backend with 90.0 second timeout
20
- 2026-04-12 19:23:25,406 INFO MainThread:409635 [wandb_init.py:init():852] starting run threads in backend
21
- 2026-04-12 19:23:33,168 INFO MainThread:409635 [wandb_run.py:_console_start():2465] atexit reg
22
- 2026-04-12 19:23:33,169 INFO MainThread:409635 [wandb_run.py:_redirect():2311] redirect: wrap_raw
23
- 2026-04-12 19:23:33,169 INFO MainThread:409635 [wandb_run.py:_redirect():2376] Wrapping output streams.
24
- 2026-04-12 19:23:33,169 INFO MainThread:409635 [wandb_run.py:_redirect():2401] Redirects installed.
25
- 2026-04-12 19:23:33,182 INFO MainThread:409635 [wandb_init.py:init():895] run started, returning control to user process
26
- 2026-04-15 04:37:36,308 WARNING MsgRouterThr:409635 [router.py:message_loop():77] message_loop has been closed
 
1
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Current SDK version is 0.17.9
2
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Configure stats pid to 3907043
3
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Loading settings from /home/x_fahkh/.config/wandb/settings
4
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Loading settings from /proj/cvl/users/x_fahkh2/WorldMem_Repro/wandb/settings
5
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Loading settings from environment variables: {'disabled': 'true'}
6
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Applying setup settings: {'_disable_service': False}
7
+ 2026-04-15 13:32:29,959 WARNING MainThread:3907043 [wandb_setup.py:_flush():77] Could not find program at -m main
8
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m main'}
9
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:_log_setup():524] Logging user logs to /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/logs/debug.log
10
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:_log_setup():525] Logging internal logs to /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/logs/debug-internal.log
11
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():608] calling init triggers
12
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():615] wandb.init called with sweep_config: {}
13
+ config: {'experiment': {'debug': '${debug}', 'tasks': ['training'], 'num_nodes': 1, 'training': {'precision': '16-mixed', 'compile': False, 'lr': 2e-05, 'batch_size': 8, 'max_epochs': -1, 'max_steps': 175000, 'max_time': None, 'data': {'num_workers': 4, 'shuffle': True}, 'optim': {'accumulate_grad_batches': 1, 'gradient_clip_val': 1.0}, 'checkpointing': {'every_n_train_steps': 2500, 'every_n_epochs': None, 'train_time_interval': None, 'enable_version_counter': False}}, 'validation': {'precision': '16-mixed', 'compile': False, 'batch_size': 4, 'val_every_n_step': 2500, 'val_every_n_epoch': None, 'limit_batch': 1, 'inference_mode': False, 'data': {'num_workers': 4, 'shuffle': False}}, 'test': {'precision': '16-mixed', 'compile': False, 'batch_size': 1, 'limit_batch': 1, 'inference_mode': False, 'data': {'num_workers': 4, 'shuffle': False}}, 'logging': {'metrics': None}, '_name': 'exp_video'}, 'dataset': {'debug': '${debug}', 'metadata': 'data/${dataset.name}/metadata.json', 'data_mean': 0.5, 'data_std': 0.5, 'save_dir': '/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'n_frames': 200, 'context_length': 1, 'resolution': 128, 'observation_shape': [3, '${dataset.resolution}', '${dataset.resolution}'], 'external_cond_dim': 0, 'validation_multiplier': 1, 'frame_skip': 1, 'action_cond_dim': 25, '_name': 'video_minecraft', 'n_frames_valid': 200, 'angle_range': 110, 'pos_range': 8, 'wo_updown': False, 'customized_validation': True, 'add_timestamp_embedding': True, 'use_explicit_memory_frames': False}, 'algorithm': {'debug': '${debug}', 'lr': '${experiment.training.lr}', 'x_shape': '${dataset.observation_shape}', 'frame_stack': 1, 'frame_skip': '${dataset.frame_skip}', 'data_mean': '${dataset.data_mean}', 'data_std': '${dataset.data_std}', 'external_cond_dim': 0, 'context_frames': 100, 'weight_decay': 0.002, 'warmup_steps': 1000, 'optimizer_beta': [0.9, 0.99], 'uncertainty_scale': 1, 'guidance_scale': 0.0, 'chunk_size': 1, 'scheduling_matrix': 'autoregressive', 'noise_level': 'random_all', 'causal': True, 'diffusion': {'objective': 'pred_v', 'beta_schedule': 'sigmoid', 'schedule_fn_kwargs': {}, 'clip_noise': 20.0, 'use_snr': False, 'use_cum_snr': False, 'use_fused_snr': True, 'snr_clip': 5.0, 'cum_snr_decay': 0.96, 'timesteps': 1000, 'sampling_timesteps': 20, 'ddim_sampling_eta': 0.0, 'stabilization_level': 15, 'architecture': {'network_size': 64, 'attn_heads': 4, 'attn_dim_head': 64, 'dim_mults': [1, 2, 4, 8], 'resolution': '${dataset.resolution}', 'attn_resolutions': [16, 32, 64, 128], 'use_init_temporal_attn': True, 'use_linear_attn': True, 'time_emb_type': 'rotary'}}, 'n_frames': '${dataset.n_frames}', 'metadata': '${dataset.metadata}', 'action_cond_dim': 25, 'use_plucker': True, 'memory_condition_length': 0, 'log_video': True, 'use_mamba_memory_pipeline': True, 'training_stage': 'stage_b_diffusion_training', 'stage_b_joint_training': True, 'stage_b_memory_aux_weight': 0.1, 'diff_window_size': 8, 'memory_gap_aux_weight': 0.1, 'memory_gap_aux_weight_init': 0.5, 'memory_gap_aux_weight_final': 0.1, 'memory_gap_aux_decay_fraction': 0.3, 'memory_gap_aux_decay_steps': 0, 'memory_gap_aux_exp_k': 5.0, 'use_precomputed_features': False, 'mamba_latent_channels': 16, 'mamba_summary_dim': 1024, 'mamba_model_dim': 1024, 'mamba_depth': 4, 'mamba_cond_dim': 1024, 'mamba_d_state': 16, 'mamba_d_conv': 4, 'mamba_expand': 2, 'allow_mamba_fallback': False, 'strict_causal_training': True, 'strict_causal_evaluation': True, 'use_oracle_pose_eval': True, 'enable_memory_noise_curriculum': False, 'curriculum_phase_boundaries': [0.2, 0.7], 'curriculum_noise_ranges': [[600, 1000], [200, 900], [0, 400]], 'curriculum_horizons': [50, 100, 200], '_name': 'df_video_mamba3stage', 'use_memory_attention': False, 'relative_embedding': False, 'memory_retrieval_topk': 32, 'n_tokens': 8}, 'debug': False, 'wandb': {'entity': 'turlin', 'project': 'worldmem', 'mode': 'online'}, 'resume': 'stage_b_joint_offline', 'load': None, 'name': 'train_stage_b_mamba_joint', 'output_dir': '/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/'}
14
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():658] starting backend
15
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():662] setting up manager
16
+ 2026-04-15 13:32:29,978 INFO MainThread:3907043 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
+ 2026-04-15 13:32:29,984 INFO MainThread:3907043 [wandb_init.py:init():670] backend started and connected
18
+ 2026-04-15 13:32:30,020 INFO MainThread:3907043 [wandb_init.py:init():768] updated telemetry
19
+ 2026-04-15 13:32:30,086 INFO MainThread:3907043 [wandb_init.py:init():801] communicating run to backend with 90.0 second timeout
20
+ 2026-04-15 13:32:30,089 INFO MainThread:3907043 [wandb_init.py:init():852] starting run threads in backend
21
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_console_start():2465] atexit reg
22
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_redirect():2311] redirect: wrap_raw
23
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_redirect():2376] Wrapping output streams.
24
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_redirect():2401] Redirects installed.
25
+ 2026-04-15 13:32:38,714 INFO MainThread:3907043 [wandb_init.py:init():895] run started, returning control to user process
26
+ 2026-04-15 13:32:52,119 WARNING MsgRouterThr:3907043 [router.py:message_loop():77] message_loop has been closed
bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/files/conda-environment.yaml ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ name: worldmem
2
+ channels:
3
+ - defaults
4
+ prefix: /home/x_fahkh/.conda/envs/worldmem
bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/files/wandb-metadata.json ADDED
@@ -0,0 +1,1228 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "os": "Linux-5.14.0-611.45.1.el9_7.x86_64-x86_64-with-glibc2.34",
3
+ "python": "3.10.19",
4
+ "heartbeatAt": "2026-04-15T11:32:30.245614",
5
+ "startedAt": "2026-04-15T11:32:29.926045",
6
+ "docker": null,
7
+ "cuda": null,
8
+ "args": [
9
+ "+name=train_stage_b_mamba_joint",
10
+ "algorithm=df_video_mamba3stage",
11
+ "experiment.num_nodes=1",
12
+ "dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft",
13
+ "dataset.n_frames=200",
14
+ "+dataset.n_frames_valid=200",
15
+ "+dataset.angle_range=110",
16
+ "+dataset.pos_range=8",
17
+ "+dataset.wo_updown=false",
18
+ "+dataset.customized_validation=true",
19
+ "+dataset.add_timestamp_embedding=true",
20
+ "+dataset.use_explicit_memory_frames=false",
21
+ "algorithm.training_stage=stage_b_diffusion_training",
22
+ "algorithm.stage_b_joint_training=true",
23
+ "algorithm.stage_b_memory_aux_weight=0.1",
24
+ "algorithm.use_mamba_memory_pipeline=true",
25
+ "algorithm.use_oracle_pose_eval=true",
26
+ "algorithm.enable_memory_noise_curriculum=false",
27
+ "+algorithm.use_memory_attention=false",
28
+ "+algorithm.relative_embedding=false",
29
+ "+algorithm.memory_retrieval_topk=32",
30
+ "algorithm.diff_window_size=8",
31
+ "algorithm.memory_condition_length=0",
32
+ "algorithm.context_frames=100",
33
+ "+algorithm.n_tokens=8",
34
+ "experiment.training.lr=2e-5",
35
+ "experiment.training.batch_size=8",
36
+ "experiment.training.checkpointing.every_n_train_steps=2500",
37
+ "experiment.training.max_steps=175000",
38
+ "experiment.validation.val_every_n_step=2500",
39
+ "resume=stage_b_joint_offline",
40
+ "+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/"
41
+ ],
42
+ "state": "running",
43
+ "program": "-m main",
44
+ "codePathLocal": null,
45
+ "git": {
46
+ "remote": "https://huggingface.co/BonanDing/WorldMem_Repro",
47
+ "commit": "02748d25aa0f9db1e2671978dbef7b00ce028e80"
48
+ },
49
+ "email": "fahad.khan@liu.se",
50
+ "root": "/proj/cvl/users/x_fahkh2/WorldMem_Repro",
51
+ "host": "node108",
52
+ "username": "x_fahkh",
53
+ "executable": "/proj/cvl/users/x_fahkh2/envs/worldmem/bin/python",
54
+ "cpu_count": 112,
55
+ "cpu_count_logical": 224,
56
+ "cpu_freq": {
57
+ "current": 1108.489669642857,
58
+ "min": 800.0,
59
+ "max": 3800.0
60
+ },
61
+ "cpu_freq_per_core": [
62
+ {
63
+ "current": 3747.675,
64
+ "min": 800.0,
65
+ "max": 3800.0
66
+ },
67
+ {
68
+ "current": 800.0,
69
+ "min": 800.0,
70
+ "max": 3800.0
71
+ },
72
+ {
73
+ "current": 800.0,
74
+ "min": 800.0,
75
+ "max": 3800.0
76
+ },
77
+ {
78
+ "current": 800.0,
79
+ "min": 800.0,
80
+ "max": 3800.0
81
+ },
82
+ {
83
+ "current": 800.0,
84
+ "min": 800.0,
85
+ "max": 3800.0
86
+ },
87
+ {
88
+ "current": 800.0,
89
+ "min": 800.0,
90
+ "max": 3800.0
91
+ },
92
+ {
93
+ "current": 800.0,
94
+ "min": 800.0,
95
+ "max": 3800.0
96
+ },
97
+ {
98
+ "current": 3800.038,
99
+ "min": 800.0,
100
+ "max": 3800.0
101
+ },
102
+ {
103
+ "current": 800.0,
104
+ "min": 800.0,
105
+ "max": 3800.0
106
+ },
107
+ {
108
+ "current": 800.0,
109
+ "min": 800.0,
110
+ "max": 3800.0
111
+ },
112
+ {
113
+ "current": 3800.038,
114
+ "min": 800.0,
115
+ "max": 3800.0
116
+ },
117
+ {
118
+ "current": 800.0,
119
+ "min": 800.0,
120
+ "max": 3800.0
121
+ },
122
+ {
123
+ "current": 800.0,
124
+ "min": 800.0,
125
+ "max": 3800.0
126
+ },
127
+ {
128
+ "current": 3267.173,
129
+ "min": 800.0,
130
+ "max": 3800.0
131
+ },
132
+ {
133
+ "current": 800.0,
134
+ "min": 800.0,
135
+ "max": 3800.0
136
+ },
137
+ {
138
+ "current": 800.0,
139
+ "min": 800.0,
140
+ "max": 3800.0
141
+ },
142
+ {
143
+ "current": 800.0,
144
+ "min": 800.0,
145
+ "max": 3800.0
146
+ },
147
+ {
148
+ "current": 800.0,
149
+ "min": 800.0,
150
+ "max": 3800.0
151
+ },
152
+ {
153
+ "current": 800.0,
154
+ "min": 800.0,
155
+ "max": 3800.0
156
+ },
157
+ {
158
+ "current": 800.0,
159
+ "min": 800.0,
160
+ "max": 3800.0
161
+ },
162
+ {
163
+ "current": 800.0,
164
+ "min": 800.0,
165
+ "max": 3800.0
166
+ },
167
+ {
168
+ "current": 800.0,
169
+ "min": 800.0,
170
+ "max": 3800.0
171
+ },
172
+ {
173
+ "current": 800.0,
174
+ "min": 800.0,
175
+ "max": 3800.0
176
+ },
177
+ {
178
+ "current": 800.0,
179
+ "min": 800.0,
180
+ "max": 3800.0
181
+ },
182
+ {
183
+ "current": 800.0,
184
+ "min": 800.0,
185
+ "max": 3800.0
186
+ },
187
+ {
188
+ "current": 800.0,
189
+ "min": 800.0,
190
+ "max": 3800.0
191
+ },
192
+ {
193
+ "current": 800.0,
194
+ "min": 800.0,
195
+ "max": 3800.0
196
+ },
197
+ {
198
+ "current": 800.0,
199
+ "min": 800.0,
200
+ "max": 3800.0
201
+ },
202
+ {
203
+ "current": 800.0,
204
+ "min": 800.0,
205
+ "max": 3800.0
206
+ },
207
+ {
208
+ "current": 800.0,
209
+ "min": 800.0,
210
+ "max": 3800.0
211
+ },
212
+ {
213
+ "current": 3744.959,
214
+ "min": 800.0,
215
+ "max": 3800.0
216
+ },
217
+ {
218
+ "current": 800.0,
219
+ "min": 800.0,
220
+ "max": 3800.0
221
+ },
222
+ {
223
+ "current": 800.0,
224
+ "min": 800.0,
225
+ "max": 3800.0
226
+ },
227
+ {
228
+ "current": 800.0,
229
+ "min": 800.0,
230
+ "max": 3800.0
231
+ },
232
+ {
233
+ "current": 800.0,
234
+ "min": 800.0,
235
+ "max": 3800.0
236
+ },
237
+ {
238
+ "current": 800.0,
239
+ "min": 800.0,
240
+ "max": 3800.0
241
+ },
242
+ {
243
+ "current": 800.0,
244
+ "min": 800.0,
245
+ "max": 3800.0
246
+ },
247
+ {
248
+ "current": 800.0,
249
+ "min": 800.0,
250
+ "max": 3800.0
251
+ },
252
+ {
253
+ "current": 800.0,
254
+ "min": 800.0,
255
+ "max": 3800.0
256
+ },
257
+ {
258
+ "current": 3798.49,
259
+ "min": 800.0,
260
+ "max": 3800.0
261
+ },
262
+ {
263
+ "current": 800.0,
264
+ "min": 800.0,
265
+ "max": 3800.0
266
+ },
267
+ {
268
+ "current": 800.0,
269
+ "min": 800.0,
270
+ "max": 3800.0
271
+ },
272
+ {
273
+ "current": 800.0,
274
+ "min": 800.0,
275
+ "max": 3800.0
276
+ },
277
+ {
278
+ "current": 800.0,
279
+ "min": 800.0,
280
+ "max": 3800.0
281
+ },
282
+ {
283
+ "current": 800.0,
284
+ "min": 800.0,
285
+ "max": 3800.0
286
+ },
287
+ {
288
+ "current": 800.0,
289
+ "min": 800.0,
290
+ "max": 3800.0
291
+ },
292
+ {
293
+ "current": 800.0,
294
+ "min": 800.0,
295
+ "max": 3800.0
296
+ },
297
+ {
298
+ "current": 800.0,
299
+ "min": 800.0,
300
+ "max": 3800.0
301
+ },
302
+ {
303
+ "current": 800.0,
304
+ "min": 800.0,
305
+ "max": 3800.0
306
+ },
307
+ {
308
+ "current": 800.0,
309
+ "min": 800.0,
310
+ "max": 3800.0
311
+ },
312
+ {
313
+ "current": 800.0,
314
+ "min": 800.0,
315
+ "max": 3800.0
316
+ },
317
+ {
318
+ "current": 800.0,
319
+ "min": 800.0,
320
+ "max": 3800.0
321
+ },
322
+ {
323
+ "current": 800.0,
324
+ "min": 800.0,
325
+ "max": 3800.0
326
+ },
327
+ {
328
+ "current": 800.0,
329
+ "min": 800.0,
330
+ "max": 3800.0
331
+ },
332
+ {
333
+ "current": 800.0,
334
+ "min": 800.0,
335
+ "max": 3800.0
336
+ },
337
+ {
338
+ "current": 800.0,
339
+ "min": 800.0,
340
+ "max": 3800.0
341
+ },
342
+ {
343
+ "current": 3800.0,
344
+ "min": 800.0,
345
+ "max": 3800.0
346
+ },
347
+ {
348
+ "current": 800.0,
349
+ "min": 800.0,
350
+ "max": 3800.0
351
+ },
352
+ {
353
+ "current": 800.0,
354
+ "min": 800.0,
355
+ "max": 3800.0
356
+ },
357
+ {
358
+ "current": 800.0,
359
+ "min": 800.0,
360
+ "max": 3800.0
361
+ },
362
+ {
363
+ "current": 800.0,
364
+ "min": 800.0,
365
+ "max": 3800.0
366
+ },
367
+ {
368
+ "current": 800.0,
369
+ "min": 800.0,
370
+ "max": 3800.0
371
+ },
372
+ {
373
+ "current": 800.0,
374
+ "min": 800.0,
375
+ "max": 3800.0
376
+ },
377
+ {
378
+ "current": 3800.0,
379
+ "min": 800.0,
380
+ "max": 3800.0
381
+ },
382
+ {
383
+ "current": 800.0,
384
+ "min": 800.0,
385
+ "max": 3800.0
386
+ },
387
+ {
388
+ "current": 800.0,
389
+ "min": 800.0,
390
+ "max": 3800.0
391
+ },
392
+ {
393
+ "current": 800.0,
394
+ "min": 800.0,
395
+ "max": 3800.0
396
+ },
397
+ {
398
+ "current": 800.0,
399
+ "min": 800.0,
400
+ "max": 3800.0
401
+ },
402
+ {
403
+ "current": 800.0,
404
+ "min": 800.0,
405
+ "max": 3800.0
406
+ },
407
+ {
408
+ "current": 800.0,
409
+ "min": 800.0,
410
+ "max": 3800.0
411
+ },
412
+ {
413
+ "current": 800.0,
414
+ "min": 800.0,
415
+ "max": 3800.0
416
+ },
417
+ {
418
+ "current": 800.0,
419
+ "min": 800.0,
420
+ "max": 3800.0
421
+ },
422
+ {
423
+ "current": 800.0,
424
+ "min": 800.0,
425
+ "max": 3800.0
426
+ },
427
+ {
428
+ "current": 800.0,
429
+ "min": 800.0,
430
+ "max": 3800.0
431
+ },
432
+ {
433
+ "current": 800.0,
434
+ "min": 800.0,
435
+ "max": 3800.0
436
+ },
437
+ {
438
+ "current": 800.0,
439
+ "min": 800.0,
440
+ "max": 3800.0
441
+ },
442
+ {
443
+ "current": 800.0,
444
+ "min": 800.0,
445
+ "max": 3800.0
446
+ },
447
+ {
448
+ "current": 800.0,
449
+ "min": 800.0,
450
+ "max": 3800.0
451
+ },
452
+ {
453
+ "current": 800.0,
454
+ "min": 800.0,
455
+ "max": 3800.0
456
+ },
457
+ {
458
+ "current": 800.0,
459
+ "min": 800.0,
460
+ "max": 3800.0
461
+ },
462
+ {
463
+ "current": 800.0,
464
+ "min": 800.0,
465
+ "max": 3800.0
466
+ },
467
+ {
468
+ "current": 800.0,
469
+ "min": 800.0,
470
+ "max": 3800.0
471
+ },
472
+ {
473
+ "current": 3800.0,
474
+ "min": 800.0,
475
+ "max": 3800.0
476
+ },
477
+ {
478
+ "current": 800.0,
479
+ "min": 800.0,
480
+ "max": 3800.0
481
+ },
482
+ {
483
+ "current": 800.0,
484
+ "min": 800.0,
485
+ "max": 3800.0
486
+ },
487
+ {
488
+ "current": 800.0,
489
+ "min": 800.0,
490
+ "max": 3800.0
491
+ },
492
+ {
493
+ "current": 800.0,
494
+ "min": 800.0,
495
+ "max": 3800.0
496
+ },
497
+ {
498
+ "current": 800.0,
499
+ "min": 800.0,
500
+ "max": 3800.0
501
+ },
502
+ {
503
+ "current": 800.0,
504
+ "min": 800.0,
505
+ "max": 3800.0
506
+ },
507
+ {
508
+ "current": 800.0,
509
+ "min": 800.0,
510
+ "max": 3800.0
511
+ },
512
+ {
513
+ "current": 800.0,
514
+ "min": 800.0,
515
+ "max": 3800.0
516
+ },
517
+ {
518
+ "current": 800.0,
519
+ "min": 800.0,
520
+ "max": 3800.0
521
+ },
522
+ {
523
+ "current": 800.0,
524
+ "min": 800.0,
525
+ "max": 3800.0
526
+ },
527
+ {
528
+ "current": 800.0,
529
+ "min": 800.0,
530
+ "max": 3800.0
531
+ },
532
+ {
533
+ "current": 3544.656,
534
+ "min": 800.0,
535
+ "max": 3800.0
536
+ },
537
+ {
538
+ "current": 800.0,
539
+ "min": 800.0,
540
+ "max": 3800.0
541
+ },
542
+ {
543
+ "current": 800.0,
544
+ "min": 800.0,
545
+ "max": 3800.0
546
+ },
547
+ {
548
+ "current": 800.0,
549
+ "min": 800.0,
550
+ "max": 3800.0
551
+ },
552
+ {
553
+ "current": 800.0,
554
+ "min": 800.0,
555
+ "max": 3800.0
556
+ },
557
+ {
558
+ "current": 800.0,
559
+ "min": 800.0,
560
+ "max": 3800.0
561
+ },
562
+ {
563
+ "current": 800.0,
564
+ "min": 800.0,
565
+ "max": 3800.0
566
+ },
567
+ {
568
+ "current": 800.0,
569
+ "min": 800.0,
570
+ "max": 3800.0
571
+ },
572
+ {
573
+ "current": 800.0,
574
+ "min": 800.0,
575
+ "max": 3800.0
576
+ },
577
+ {
578
+ "current": 800.0,
579
+ "min": 800.0,
580
+ "max": 3800.0
581
+ },
582
+ {
583
+ "current": 3790.699,
584
+ "min": 800.0,
585
+ "max": 3800.0
586
+ },
587
+ {
588
+ "current": 800.0,
589
+ "min": 800.0,
590
+ "max": 3800.0
591
+ },
592
+ {
593
+ "current": 3773.57,
594
+ "min": 800.0,
595
+ "max": 3800.0
596
+ },
597
+ {
598
+ "current": 800.0,
599
+ "min": 800.0,
600
+ "max": 3800.0
601
+ },
602
+ {
603
+ "current": 800.0,
604
+ "min": 800.0,
605
+ "max": 3800.0
606
+ },
607
+ {
608
+ "current": 800.0,
609
+ "min": 800.0,
610
+ "max": 3800.0
611
+ },
612
+ {
613
+ "current": 800.0,
614
+ "min": 800.0,
615
+ "max": 3800.0
616
+ },
617
+ {
618
+ "current": 800.0,
619
+ "min": 800.0,
620
+ "max": 3800.0
621
+ },
622
+ {
623
+ "current": 800.0,
624
+ "min": 800.0,
625
+ "max": 3800.0
626
+ },
627
+ {
628
+ "current": 800.0,
629
+ "min": 800.0,
630
+ "max": 3800.0
631
+ },
632
+ {
633
+ "current": 800.0,
634
+ "min": 800.0,
635
+ "max": 3800.0
636
+ },
637
+ {
638
+ "current": 800.0,
639
+ "min": 800.0,
640
+ "max": 3800.0
641
+ },
642
+ {
643
+ "current": 800.0,
644
+ "min": 800.0,
645
+ "max": 3800.0
646
+ },
647
+ {
648
+ "current": 800.0,
649
+ "min": 800.0,
650
+ "max": 3800.0
651
+ },
652
+ {
653
+ "current": 3800.0,
654
+ "min": 800.0,
655
+ "max": 3800.0
656
+ },
657
+ {
658
+ "current": 800.0,
659
+ "min": 800.0,
660
+ "max": 3800.0
661
+ },
662
+ {
663
+ "current": 800.0,
664
+ "min": 800.0,
665
+ "max": 3800.0
666
+ },
667
+ {
668
+ "current": 800.0,
669
+ "min": 800.0,
670
+ "max": 3800.0
671
+ },
672
+ {
673
+ "current": 800.0,
674
+ "min": 800.0,
675
+ "max": 3800.0
676
+ },
677
+ {
678
+ "current": 800.0,
679
+ "min": 800.0,
680
+ "max": 3800.0
681
+ },
682
+ {
683
+ "current": 800.0,
684
+ "min": 800.0,
685
+ "max": 3800.0
686
+ },
687
+ {
688
+ "current": 800.0,
689
+ "min": 800.0,
690
+ "max": 3800.0
691
+ },
692
+ {
693
+ "current": 800.0,
694
+ "min": 800.0,
695
+ "max": 3800.0
696
+ },
697
+ {
698
+ "current": 800.0,
699
+ "min": 800.0,
700
+ "max": 3800.0
701
+ },
702
+ {
703
+ "current": 800.0,
704
+ "min": 800.0,
705
+ "max": 3800.0
706
+ },
707
+ {
708
+ "current": 800.0,
709
+ "min": 800.0,
710
+ "max": 3800.0
711
+ },
712
+ {
713
+ "current": 800.0,
714
+ "min": 800.0,
715
+ "max": 3800.0
716
+ },
717
+ {
718
+ "current": 800.0,
719
+ "min": 800.0,
720
+ "max": 3800.0
721
+ },
722
+ {
723
+ "current": 800.0,
724
+ "min": 800.0,
725
+ "max": 3800.0
726
+ },
727
+ {
728
+ "current": 800.0,
729
+ "min": 800.0,
730
+ "max": 3800.0
731
+ },
732
+ {
733
+ "current": 800.0,
734
+ "min": 800.0,
735
+ "max": 3800.0
736
+ },
737
+ {
738
+ "current": 800.0,
739
+ "min": 800.0,
740
+ "max": 3800.0
741
+ },
742
+ {
743
+ "current": 800.0,
744
+ "min": 800.0,
745
+ "max": 3800.0
746
+ },
747
+ {
748
+ "current": 800.0,
749
+ "min": 800.0,
750
+ "max": 3800.0
751
+ },
752
+ {
753
+ "current": 800.0,
754
+ "min": 800.0,
755
+ "max": 3800.0
756
+ },
757
+ {
758
+ "current": 800.0,
759
+ "min": 800.0,
760
+ "max": 3800.0
761
+ },
762
+ {
763
+ "current": 800.0,
764
+ "min": 800.0,
765
+ "max": 3800.0
766
+ },
767
+ {
768
+ "current": 800.0,
769
+ "min": 800.0,
770
+ "max": 3800.0
771
+ },
772
+ {
773
+ "current": 800.0,
774
+ "min": 800.0,
775
+ "max": 3800.0
776
+ },
777
+ {
778
+ "current": 800.0,
779
+ "min": 800.0,
780
+ "max": 3800.0
781
+ },
782
+ {
783
+ "current": 3802.009,
784
+ "min": 800.0,
785
+ "max": 3800.0
786
+ },
787
+ {
788
+ "current": 3801.87,
789
+ "min": 800.0,
790
+ "max": 3800.0
791
+ },
792
+ {
793
+ "current": 800.0,
794
+ "min": 800.0,
795
+ "max": 3800.0
796
+ },
797
+ {
798
+ "current": 800.0,
799
+ "min": 800.0,
800
+ "max": 3800.0
801
+ },
802
+ {
803
+ "current": 3797.97,
804
+ "min": 800.0,
805
+ "max": 3800.0
806
+ },
807
+ {
808
+ "current": 800.0,
809
+ "min": 800.0,
810
+ "max": 3800.0
811
+ },
812
+ {
813
+ "current": 800.0,
814
+ "min": 800.0,
815
+ "max": 3800.0
816
+ },
817
+ {
818
+ "current": 3802.113,
819
+ "min": 800.0,
820
+ "max": 3800.0
821
+ },
822
+ {
823
+ "current": 3800.145,
824
+ "min": 800.0,
825
+ "max": 3800.0
826
+ },
827
+ {
828
+ "current": 800.0,
829
+ "min": 800.0,
830
+ "max": 3800.0
831
+ },
832
+ {
833
+ "current": 800.0,
834
+ "min": 800.0,
835
+ "max": 3800.0
836
+ },
837
+ {
838
+ "current": 800.0,
839
+ "min": 800.0,
840
+ "max": 3800.0
841
+ },
842
+ {
843
+ "current": 800.0,
844
+ "min": 800.0,
845
+ "max": 3800.0
846
+ },
847
+ {
848
+ "current": 800.0,
849
+ "min": 800.0,
850
+ "max": 3800.0
851
+ },
852
+ {
853
+ "current": 800.0,
854
+ "min": 800.0,
855
+ "max": 3800.0
856
+ },
857
+ {
858
+ "current": 800.0,
859
+ "min": 800.0,
860
+ "max": 3800.0
861
+ },
862
+ {
863
+ "current": 3693.754,
864
+ "min": 800.0,
865
+ "max": 3800.0
866
+ },
867
+ {
868
+ "current": 800.0,
869
+ "min": 800.0,
870
+ "max": 3800.0
871
+ },
872
+ {
873
+ "current": 800.0,
874
+ "min": 800.0,
875
+ "max": 3800.0
876
+ },
877
+ {
878
+ "current": 800.0,
879
+ "min": 800.0,
880
+ "max": 3800.0
881
+ },
882
+ {
883
+ "current": 800.0,
884
+ "min": 800.0,
885
+ "max": 3800.0
886
+ },
887
+ {
888
+ "current": 800.0,
889
+ "min": 800.0,
890
+ "max": 3800.0
891
+ },
892
+ {
893
+ "current": 800.0,
894
+ "min": 800.0,
895
+ "max": 3800.0
896
+ },
897
+ {
898
+ "current": 3796.613,
899
+ "min": 800.0,
900
+ "max": 3800.0
901
+ },
902
+ {
903
+ "current": 800.0,
904
+ "min": 800.0,
905
+ "max": 3800.0
906
+ },
907
+ {
908
+ "current": 800.0,
909
+ "min": 800.0,
910
+ "max": 3800.0
911
+ },
912
+ {
913
+ "current": 800.0,
914
+ "min": 800.0,
915
+ "max": 3800.0
916
+ },
917
+ {
918
+ "current": 800.0,
919
+ "min": 800.0,
920
+ "max": 3800.0
921
+ },
922
+ {
923
+ "current": 800.0,
924
+ "min": 800.0,
925
+ "max": 3800.0
926
+ },
927
+ {
928
+ "current": 800.0,
929
+ "min": 800.0,
930
+ "max": 3800.0
931
+ },
932
+ {
933
+ "current": 800.0,
934
+ "min": 800.0,
935
+ "max": 3800.0
936
+ },
937
+ {
938
+ "current": 800.0,
939
+ "min": 800.0,
940
+ "max": 3800.0
941
+ },
942
+ {
943
+ "current": 800.0,
944
+ "min": 800.0,
945
+ "max": 3800.0
946
+ },
947
+ {
948
+ "current": 3800.358,
949
+ "min": 800.0,
950
+ "max": 3800.0
951
+ },
952
+ {
953
+ "current": 800.0,
954
+ "min": 800.0,
955
+ "max": 3800.0
956
+ },
957
+ {
958
+ "current": 800.0,
959
+ "min": 800.0,
960
+ "max": 3800.0
961
+ },
962
+ {
963
+ "current": 800.0,
964
+ "min": 800.0,
965
+ "max": 3800.0
966
+ },
967
+ {
968
+ "current": 800.0,
969
+ "min": 800.0,
970
+ "max": 3800.0
971
+ },
972
+ {
973
+ "current": 3800.0,
974
+ "min": 800.0,
975
+ "max": 3800.0
976
+ },
977
+ {
978
+ "current": 800.0,
979
+ "min": 800.0,
980
+ "max": 3800.0
981
+ },
982
+ {
983
+ "current": 3799.961,
984
+ "min": 800.0,
985
+ "max": 3800.0
986
+ },
987
+ {
988
+ "current": 800.0,
989
+ "min": 800.0,
990
+ "max": 3800.0
991
+ },
992
+ {
993
+ "current": 800.0,
994
+ "min": 800.0,
995
+ "max": 3800.0
996
+ },
997
+ {
998
+ "current": 800.0,
999
+ "min": 800.0,
1000
+ "max": 3800.0
1001
+ },
1002
+ {
1003
+ "current": 800.0,
1004
+ "min": 800.0,
1005
+ "max": 3800.0
1006
+ },
1007
+ {
1008
+ "current": 800.0,
1009
+ "min": 800.0,
1010
+ "max": 3800.0
1011
+ },
1012
+ {
1013
+ "current": 800.0,
1014
+ "min": 800.0,
1015
+ "max": 3800.0
1016
+ },
1017
+ {
1018
+ "current": 800.0,
1019
+ "min": 800.0,
1020
+ "max": 3800.0
1021
+ },
1022
+ {
1023
+ "current": 800.0,
1024
+ "min": 800.0,
1025
+ "max": 3800.0
1026
+ },
1027
+ {
1028
+ "current": 800.0,
1029
+ "min": 800.0,
1030
+ "max": 3800.0
1031
+ },
1032
+ {
1033
+ "current": 800.0,
1034
+ "min": 800.0,
1035
+ "max": 3800.0
1036
+ },
1037
+ {
1038
+ "current": 800.0,
1039
+ "min": 800.0,
1040
+ "max": 3800.0
1041
+ },
1042
+ {
1043
+ "current": 800.0,
1044
+ "min": 800.0,
1045
+ "max": 3800.0
1046
+ },
1047
+ {
1048
+ "current": 800.0,
1049
+ "min": 800.0,
1050
+ "max": 3800.0
1051
+ },
1052
+ {
1053
+ "current": 800.0,
1054
+ "min": 800.0,
1055
+ "max": 3800.0
1056
+ },
1057
+ {
1058
+ "current": 800.0,
1059
+ "min": 800.0,
1060
+ "max": 3800.0
1061
+ },
1062
+ {
1063
+ "current": 800.0,
1064
+ "min": 800.0,
1065
+ "max": 3800.0
1066
+ },
1067
+ {
1068
+ "current": 800.0,
1069
+ "min": 800.0,
1070
+ "max": 3800.0
1071
+ },
1072
+ {
1073
+ "current": 800.0,
1074
+ "min": 800.0,
1075
+ "max": 3800.0
1076
+ },
1077
+ {
1078
+ "current": 800.0,
1079
+ "min": 800.0,
1080
+ "max": 3800.0
1081
+ },
1082
+ {
1083
+ "current": 800.0,
1084
+ "min": 800.0,
1085
+ "max": 3800.0
1086
+ },
1087
+ {
1088
+ "current": 800.0,
1089
+ "min": 800.0,
1090
+ "max": 3800.0
1091
+ },
1092
+ {
1093
+ "current": 800.0,
1094
+ "min": 800.0,
1095
+ "max": 3800.0
1096
+ },
1097
+ {
1098
+ "current": 800.0,
1099
+ "min": 800.0,
1100
+ "max": 3800.0
1101
+ },
1102
+ {
1103
+ "current": 800.0,
1104
+ "min": 800.0,
1105
+ "max": 3800.0
1106
+ },
1107
+ {
1108
+ "current": 800.0,
1109
+ "min": 800.0,
1110
+ "max": 3800.0
1111
+ },
1112
+ {
1113
+ "current": 800.0,
1114
+ "min": 800.0,
1115
+ "max": 3800.0
1116
+ },
1117
+ {
1118
+ "current": 3800.0,
1119
+ "min": 800.0,
1120
+ "max": 3800.0
1121
+ },
1122
+ {
1123
+ "current": 3799.961,
1124
+ "min": 800.0,
1125
+ "max": 3800.0
1126
+ },
1127
+ {
1128
+ "current": 800.0,
1129
+ "min": 800.0,
1130
+ "max": 3800.0
1131
+ },
1132
+ {
1133
+ "current": 800.0,
1134
+ "min": 800.0,
1135
+ "max": 3800.0
1136
+ },
1137
+ {
1138
+ "current": 800.0,
1139
+ "min": 800.0,
1140
+ "max": 3800.0
1141
+ },
1142
+ {
1143
+ "current": 800.0,
1144
+ "min": 800.0,
1145
+ "max": 3800.0
1146
+ },
1147
+ {
1148
+ "current": 3804.004,
1149
+ "min": 800.0,
1150
+ "max": 3800.0
1151
+ },
1152
+ {
1153
+ "current": 800.0,
1154
+ "min": 800.0,
1155
+ "max": 3800.0
1156
+ },
1157
+ {
1158
+ "current": 800.0,
1159
+ "min": 800.0,
1160
+ "max": 3800.0
1161
+ },
1162
+ {
1163
+ "current": 3797.388,
1164
+ "min": 800.0,
1165
+ "max": 3800.0
1166
+ },
1167
+ {
1168
+ "current": 3800.0,
1169
+ "min": 800.0,
1170
+ "max": 3800.0
1171
+ },
1172
+ {
1173
+ "current": 3800.0,
1174
+ "min": 800.0,
1175
+ "max": 3800.0
1176
+ },
1177
+ {
1178
+ "current": 800.0,
1179
+ "min": 800.0,
1180
+ "max": 3800.0
1181
+ }
1182
+ ],
1183
+ "disk": {
1184
+ "/": {
1185
+ "total": 30.58770751953125,
1186
+ "used": 16.40554428100586
1187
+ }
1188
+ },
1189
+ "gpu": "NVIDIA H200",
1190
+ "gpu_count": 8,
1191
+ "gpu_devices": [
1192
+ {
1193
+ "name": "NVIDIA H200",
1194
+ "memory_total": 150754820096
1195
+ },
1196
+ {
1197
+ "name": "NVIDIA H200",
1198
+ "memory_total": 150754820096
1199
+ },
1200
+ {
1201
+ "name": "NVIDIA H200",
1202
+ "memory_total": 150754820096
1203
+ },
1204
+ {
1205
+ "name": "NVIDIA H200",
1206
+ "memory_total": 150754820096
1207
+ },
1208
+ {
1209
+ "name": "NVIDIA H200",
1210
+ "memory_total": 150754820096
1211
+ },
1212
+ {
1213
+ "name": "NVIDIA H200",
1214
+ "memory_total": 150754820096
1215
+ },
1216
+ {
1217
+ "name": "NVIDIA H200",
1218
+ "memory_total": 150754820096
1219
+ },
1220
+ {
1221
+ "name": "NVIDIA H200",
1222
+ "memory_total": 150754820096
1223
+ }
1224
+ ],
1225
+ "memory": {
1226
+ "total": 2015.5592346191406
1227
+ }
1228
+ }
bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/files/wandb-summary.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"_wandb": {"runtime": 19}}
bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/logs/debug-internal.log ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-04-15 13:32:29,982 INFO StreamThr :3910583 [internal.py:wandb_internal():85] W&B internal server running at pid: 3910583, started at: 2026-04-15 13:32:29.979444
2
+ 2026-04-15 13:32:29,984 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: status
3
+ 2026-04-15 13:32:30,021 INFO WriterThread:3910583 [datastore.py:open_for_write():87] open: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/run-stage_b_joint_offline.wandb
4
+ 2026-04-15 13:32:30,154 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: run_start
5
+ 2026-04-15 13:32:30,189 DEBUG HandlerThread:3910583 [system_info.py:__init__():26] System info init
6
+ 2026-04-15 13:32:30,189 DEBUG HandlerThread:3910583 [system_info.py:__init__():41] System info init done
7
+ 2026-04-15 13:32:30,189 INFO HandlerThread:3910583 [system_monitor.py:start():194] Starting system monitor
8
+ 2026-04-15 13:32:30,189 INFO SystemMonitor:3910583 [system_monitor.py:_start():158] Starting system asset monitoring threads
9
+ 2026-04-15 13:32:30,189 INFO HandlerThread:3910583 [system_monitor.py:probe():214] Collecting system info
10
+ 2026-04-15 13:32:30,190 INFO SystemMonitor:3910583 [interfaces.py:start():188] Started cpu monitoring
11
+ 2026-04-15 13:32:30,191 INFO SystemMonitor:3910583 [interfaces.py:start():188] Started disk monitoring
12
+ 2026-04-15 13:32:30,191 INFO SystemMonitor:3910583 [interfaces.py:start():188] Started gpu monitoring
13
+ 2026-04-15 13:32:30,191 INFO SystemMonitor:3910583 [interfaces.py:start():188] Started memory monitoring
14
+ 2026-04-15 13:32:30,192 INFO SystemMonitor:3910583 [interfaces.py:start():188] Started network monitoring
15
+ 2026-04-15 13:32:30,245 DEBUG HandlerThread:3910583 [system_info.py:probe():152] Probing system
16
+ 2026-04-15 13:32:30,247 DEBUG HandlerThread:3910583 [system_info.py:_probe_git():137] Probing git
17
+ 2026-04-15 13:32:30,310 DEBUG HandlerThread:3910583 [system_info.py:_probe_git():145] Probing git done
18
+ 2026-04-15 13:32:30,310 DEBUG HandlerThread:3910583 [system_info.py:probe():200] Probing system done
19
+ 2026-04-15 13:32:30,310 DEBUG HandlerThread:3910583 [system_monitor.py:probe():223] {'os': 'Linux-5.14.0-611.45.1.el9_7.x86_64-x86_64-with-glibc2.34', 'python': '3.10.19', 'heartbeatAt': '2026-04-15T11:32:30.245614', 'startedAt': '2026-04-15T11:32:29.926045', 'docker': None, 'cuda': None, 'args': ('+name=train_stage_b_mamba_joint', 'algorithm=df_video_mamba3stage', 'experiment.num_nodes=1', 'dataset.save_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'dataset.n_frames=200', '+dataset.n_frames_valid=200', '+dataset.angle_range=110', '+dataset.pos_range=8', '+dataset.wo_updown=false', '+dataset.customized_validation=true', '+dataset.add_timestamp_embedding=true', '+dataset.use_explicit_memory_frames=false', 'algorithm.training_stage=stage_b_diffusion_training', 'algorithm.stage_b_joint_training=true', 'algorithm.stage_b_memory_aux_weight=0.1', 'algorithm.use_mamba_memory_pipeline=true', 'algorithm.use_oracle_pose_eval=true', 'algorithm.enable_memory_noise_curriculum=false', '+algorithm.use_memory_attention=false', '+algorithm.relative_embedding=false', '+algorithm.memory_retrieval_topk=32', 'algorithm.diff_window_size=8', 'algorithm.memory_condition_length=0', 'algorithm.context_frames=100', '+algorithm.n_tokens=8', 'experiment.training.lr=2e-5', 'experiment.training.batch_size=8', 'experiment.training.checkpointing.every_n_train_steps=2500', 'experiment.training.max_steps=175000', 'experiment.validation.val_every_n_step=2500', 'resume=stage_b_joint_offline', '+output_dir=/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/'), 'state': 'running', 'program': '-m main', 'codePathLocal': None, 'git': {'remote': 'https://huggingface.co/BonanDing/WorldMem_Repro', 'commit': '02748d25aa0f9db1e2671978dbef7b00ce028e80'}, 'email': 'fahad.khan@liu.se', 'root': '/proj/cvl/users/x_fahkh2/WorldMem_Repro', 'host': 'node108', 'username': 'x_fahkh', 'executable': '/proj/cvl/users/x_fahkh2/envs/worldmem/bin/python', 'cpu_count': 112, 'cpu_count_logical': 224, 'cpu_freq': {'current': 1108.489669642857, 'min': 800.0, 'max': 3800.0}, 'cpu_freq_per_core': [{'current': 3747.675, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.038, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.038, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3267.173, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3744.959, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3798.49, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3544.656, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3790.699, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3773.57, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3802.009, 'min': 800.0, 'max': 3800.0}, {'current': 3801.87, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3797.97, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3802.113, 'min': 800.0, 'max': 3800.0}, {'current': 3800.145, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3693.754, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3796.613, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.358, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3799.961, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3799.961, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3804.004, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3797.388, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 3800.0, 'min': 800.0, 'max': 3800.0}, {'current': 800.0, 'min': 800.0, 'max': 3800.0}], 'disk': {'/': {'total': 30.58770751953125, 'used': 16.40554428100586}}, 'gpu': 'NVIDIA H200', 'gpu_count': 8, 'gpu_devices': [{'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}, {'name': 'NVIDIA H200', 'memory_total': 150754820096}], 'memory': {'total': 2015.5592346191406}}
20
+ 2026-04-15 13:32:30,310 INFO HandlerThread:3910583 [system_monitor.py:probe():224] Finished collecting system info
21
+ 2026-04-15 13:32:30,310 INFO HandlerThread:3910583 [system_monitor.py:probe():227] Publishing system info
22
+ 2026-04-15 13:32:30,311 DEBUG HandlerThread:3910583 [system_info.py:_save_conda():209] Saving list of conda packages installed into the current environment
23
+ 2026-04-15 13:32:36,797 DEBUG HandlerThread:3910583 [system_info.py:_save_conda():224] Saving conda packages done
24
+ 2026-04-15 13:32:36,804 INFO HandlerThread:3910583 [system_monitor.py:probe():229] Finished publishing system info
25
+ 2026-04-15 13:32:36,820 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: keepalive
26
+ 2026-04-15 13:32:36,820 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: status_report
27
+ 2026-04-15 13:32:36,820 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: status_report
28
+ 2026-04-15 13:32:38,704 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: python_packages
29
+ 2026-04-15 13:32:40,821 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: status_report
30
+ 2026-04-15 13:32:40,822 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: status_report
31
+ 2026-04-15 13:32:45,823 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: status_report
32
+ 2026-04-15 13:32:45,823 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: status_report
33
+ 2026-04-15 13:32:49,979 DEBUG SenderThread:3910583 [sender.py:send():391] send: exit
34
+ 2026-04-15 13:32:49,979 INFO SenderThread:3910583 [sender.py:send_exit():598] handling exit code: 1
35
+ 2026-04-15 13:32:49,979 INFO SenderThread:3910583 [sender.py:send_exit():600] handling runtime: 19
36
+ 2026-04-15 13:32:49,983 INFO SenderThread:3910583 [sender.py:_save_file():1466] saving file wandb-summary.json with policy end
37
+ 2026-04-15 13:32:49,983 INFO SenderThread:3910583 [sender.py:send_exit():606] send defer
38
+ 2026-04-15 13:32:49,984 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
39
+ 2026-04-15 13:32:49,984 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 0
40
+ 2026-04-15 13:32:49,984 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
41
+ 2026-04-15 13:32:49,984 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 0
42
+ 2026-04-15 13:32:49,984 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 1
43
+ 2026-04-15 13:32:49,984 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
44
+ 2026-04-15 13:32:49,984 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 1
45
+ 2026-04-15 13:32:49,984 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
46
+ 2026-04-15 13:32:49,984 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 1
47
+ 2026-04-15 13:32:49,985 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 2
48
+ 2026-04-15 13:32:49,985 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
49
+ 2026-04-15 13:32:49,985 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 2
50
+ 2026-04-15 13:32:49,985 INFO HandlerThread:3910583 [system_monitor.py:finish():203] Stopping system monitor
51
+ 2026-04-15 13:32:49,986 DEBUG SystemMonitor:3910583 [system_monitor.py:_start():172] Starting system metrics aggregation loop
52
+ 2026-04-15 13:32:49,986 DEBUG SystemMonitor:3910583 [system_monitor.py:_start():179] Finished system metrics aggregation loop
53
+ 2026-04-15 13:32:49,986 DEBUG SystemMonitor:3910583 [system_monitor.py:_start():183] Publishing last batch of metrics
54
+ 2026-04-15 13:32:49,987 INFO HandlerThread:3910583 [interfaces.py:finish():200] Joined cpu monitor
55
+ 2026-04-15 13:32:49,987 INFO HandlerThread:3910583 [interfaces.py:finish():200] Joined disk monitor
56
+ 2026-04-15 13:32:51,097 INFO HandlerThread:3910583 [interfaces.py:finish():200] Joined gpu monitor
57
+ 2026-04-15 13:32:51,098 INFO HandlerThread:3910583 [interfaces.py:finish():200] Joined memory monitor
58
+ 2026-04-15 13:32:51,098 INFO HandlerThread:3910583 [interfaces.py:finish():200] Joined network monitor
59
+ 2026-04-15 13:32:51,098 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: poll_exit
60
+ 2026-04-15 13:32:51,098 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: status_report
61
+ 2026-04-15 13:32:51,099 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
62
+ 2026-04-15 13:32:51,099 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 2
63
+ 2026-04-15 13:32:51,099 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 3
64
+ 2026-04-15 13:32:51,099 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: poll_exit
65
+ 2026-04-15 13:32:51,099 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: status_report
66
+ 2026-04-15 13:32:51,099 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
67
+ 2026-04-15 13:32:51,099 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 3
68
+ 2026-04-15 13:32:51,099 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
69
+ 2026-04-15 13:32:51,099 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 3
70
+ 2026-04-15 13:32:51,099 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 4
71
+ 2026-04-15 13:32:51,100 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
72
+ 2026-04-15 13:32:51,100 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 4
73
+ 2026-04-15 13:32:51,100 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
74
+ 2026-04-15 13:32:51,100 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 4
75
+ 2026-04-15 13:32:51,100 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 5
76
+ 2026-04-15 13:32:51,100 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
77
+ 2026-04-15 13:32:51,100 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 5
78
+ 2026-04-15 13:32:51,101 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
79
+ 2026-04-15 13:32:51,101 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 5
80
+ 2026-04-15 13:32:51,101 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 6
81
+ 2026-04-15 13:32:51,101 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
82
+ 2026-04-15 13:32:51,101 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 6
83
+ 2026-04-15 13:32:51,102 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
84
+ 2026-04-15 13:32:51,102 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 6
85
+ 2026-04-15 13:32:51,102 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 7
86
+ 2026-04-15 13:32:51,102 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: status_report
87
+ 2026-04-15 13:32:51,102 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
88
+ 2026-04-15 13:32:51,102 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 7
89
+ 2026-04-15 13:32:51,102 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: status_report
90
+ 2026-04-15 13:32:51,102 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
91
+ 2026-04-15 13:32:51,102 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 7
92
+ 2026-04-15 13:32:51,102 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 8
93
+ 2026-04-15 13:32:51,103 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
94
+ 2026-04-15 13:32:51,103 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 8
95
+ 2026-04-15 13:32:51,103 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
96
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 8
97
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 9
98
+ 2026-04-15 13:32:51,103 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
99
+ 2026-04-15 13:32:51,103 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 9
100
+ 2026-04-15 13:32:51,103 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
101
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 9
102
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 10
103
+ 2026-04-15 13:32:51,103 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
104
+ 2026-04-15 13:32:51,103 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 10
105
+ 2026-04-15 13:32:51,103 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
106
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 10
107
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 11
108
+ 2026-04-15 13:32:51,103 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
109
+ 2026-04-15 13:32:51,103 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 11
110
+ 2026-04-15 13:32:51,103 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
111
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 11
112
+ 2026-04-15 13:32:51,103 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 12
113
+ 2026-04-15 13:32:51,103 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
114
+ 2026-04-15 13:32:51,103 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 12
115
+ 2026-04-15 13:32:51,103 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
116
+ 2026-04-15 13:32:51,104 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 12
117
+ 2026-04-15 13:32:51,104 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 13
118
+ 2026-04-15 13:32:51,104 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
119
+ 2026-04-15 13:32:51,104 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 13
120
+ 2026-04-15 13:32:51,104 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
121
+ 2026-04-15 13:32:51,104 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 13
122
+ 2026-04-15 13:32:51,104 INFO SenderThread:3910583 [sender.py:transition_state():626] send defer: 14
123
+ 2026-04-15 13:32:51,104 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: defer
124
+ 2026-04-15 13:32:51,104 INFO HandlerThread:3910583 [handler.py:handle_request_defer():184] handle defer: 14
125
+ 2026-04-15 13:32:51,104 DEBUG SenderThread:3910583 [sender.py:send():391] send: final
126
+ 2026-04-15 13:32:51,104 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: defer
127
+ 2026-04-15 13:32:51,104 INFO SenderThread:3910583 [sender.py:send_request_defer():622] handle sender defer: 14
128
+ 2026-04-15 13:32:51,105 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: poll_exit
129
+ 2026-04-15 13:32:51,105 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: poll_exit
130
+ 2026-04-15 13:32:51,105 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: server_info
131
+ 2026-04-15 13:32:51,105 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: server_info
132
+ 2026-04-15 13:32:51,106 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: poll_exit
133
+ 2026-04-15 13:32:51,106 DEBUG SenderThread:3910583 [sender.py:send_request():418] send_request: poll_exit
134
+ 2026-04-15 13:32:51,106 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: get_summary
135
+ 2026-04-15 13:32:51,106 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: sampled_history
136
+ 2026-04-15 13:32:51,107 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: internal_messages
137
+ 2026-04-15 13:32:51,107 INFO MainThread:3910583 [wandb_run.py:_footer_history_summary_info():4088] rendering history
138
+ 2026-04-15 13:32:51,107 INFO MainThread:3910583 [wandb_run.py:_footer_history_summary_info():4120] rendering summary
139
+ 2026-04-15 13:32:51,107 DEBUG HandlerThread:3910583 [handler.py:handle_request():158] handle_request: shutdown
140
+ 2026-04-15 13:32:51,107 INFO HandlerThread:3910583 [handler.py:finish():884] shutting down handler
141
+ 2026-04-15 13:32:52,106 INFO WriterThread:3910583 [datastore.py:close():296] close: /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/run-stage_b_joint_offline.wandb
142
+ 2026-04-15 13:32:52,106 INFO SenderThread:3910583 [sender.py:finish():1631] shutting down sender
bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/logs/debug.log ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Current SDK version is 0.17.9
2
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Configure stats pid to 3907043
3
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Loading settings from /home/x_fahkh/.config/wandb/settings
4
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Loading settings from /proj/cvl/users/x_fahkh2/WorldMem_Repro/wandb/settings
5
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Loading settings from environment variables: {'disabled': 'true'}
6
+ 2026-04-15 13:32:29,959 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Applying setup settings: {'_disable_service': False}
7
+ 2026-04-15 13:32:29,959 WARNING MainThread:3907043 [wandb_setup.py:_flush():77] Could not find program at -m main
8
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_setup.py:_flush():77] Inferring run settings from compute environment: {'program_relpath': None, 'program': '-m main'}
9
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:_log_setup():524] Logging user logs to /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/logs/debug.log
10
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:_log_setup():525] Logging internal logs to /proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/logs/debug-internal.log
11
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():608] calling init triggers
12
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():615] wandb.init called with sweep_config: {}
13
+ config: {'experiment': {'debug': '${debug}', 'tasks': ['training'], 'num_nodes': 1, 'training': {'precision': '16-mixed', 'compile': False, 'lr': 2e-05, 'batch_size': 8, 'max_epochs': -1, 'max_steps': 175000, 'max_time': None, 'data': {'num_workers': 4, 'shuffle': True}, 'optim': {'accumulate_grad_batches': 1, 'gradient_clip_val': 1.0}, 'checkpointing': {'every_n_train_steps': 2500, 'every_n_epochs': None, 'train_time_interval': None, 'enable_version_counter': False}}, 'validation': {'precision': '16-mixed', 'compile': False, 'batch_size': 4, 'val_every_n_step': 2500, 'val_every_n_epoch': None, 'limit_batch': 1, 'inference_mode': False, 'data': {'num_workers': 4, 'shuffle': False}}, 'test': {'precision': '16-mixed', 'compile': False, 'batch_size': 1, 'limit_batch': 1, 'inference_mode': False, 'data': {'num_workers': 4, 'shuffle': False}}, 'logging': {'metrics': None}, '_name': 'exp_video'}, 'dataset': {'debug': '${debug}', 'metadata': 'data/${dataset.name}/metadata.json', 'data_mean': 0.5, 'data_std': 0.5, 'save_dir': '/proj/cvl/users/x_fahkh2/WorldMem_Repro/datasets/minecraft', 'n_frames': 200, 'context_length': 1, 'resolution': 128, 'observation_shape': [3, '${dataset.resolution}', '${dataset.resolution}'], 'external_cond_dim': 0, 'validation_multiplier': 1, 'frame_skip': 1, 'action_cond_dim': 25, '_name': 'video_minecraft', 'n_frames_valid': 200, 'angle_range': 110, 'pos_range': 8, 'wo_updown': False, 'customized_validation': True, 'add_timestamp_embedding': True, 'use_explicit_memory_frames': False}, 'algorithm': {'debug': '${debug}', 'lr': '${experiment.training.lr}', 'x_shape': '${dataset.observation_shape}', 'frame_stack': 1, 'frame_skip': '${dataset.frame_skip}', 'data_mean': '${dataset.data_mean}', 'data_std': '${dataset.data_std}', 'external_cond_dim': 0, 'context_frames': 100, 'weight_decay': 0.002, 'warmup_steps': 1000, 'optimizer_beta': [0.9, 0.99], 'uncertainty_scale': 1, 'guidance_scale': 0.0, 'chunk_size': 1, 'scheduling_matrix': 'autoregressive', 'noise_level': 'random_all', 'causal': True, 'diffusion': {'objective': 'pred_v', 'beta_schedule': 'sigmoid', 'schedule_fn_kwargs': {}, 'clip_noise': 20.0, 'use_snr': False, 'use_cum_snr': False, 'use_fused_snr': True, 'snr_clip': 5.0, 'cum_snr_decay': 0.96, 'timesteps': 1000, 'sampling_timesteps': 20, 'ddim_sampling_eta': 0.0, 'stabilization_level': 15, 'architecture': {'network_size': 64, 'attn_heads': 4, 'attn_dim_head': 64, 'dim_mults': [1, 2, 4, 8], 'resolution': '${dataset.resolution}', 'attn_resolutions': [16, 32, 64, 128], 'use_init_temporal_attn': True, 'use_linear_attn': True, 'time_emb_type': 'rotary'}}, 'n_frames': '${dataset.n_frames}', 'metadata': '${dataset.metadata}', 'action_cond_dim': 25, 'use_plucker': True, 'memory_condition_length': 0, 'log_video': True, 'use_mamba_memory_pipeline': True, 'training_stage': 'stage_b_diffusion_training', 'stage_b_joint_training': True, 'stage_b_memory_aux_weight': 0.1, 'diff_window_size': 8, 'memory_gap_aux_weight': 0.1, 'memory_gap_aux_weight_init': 0.5, 'memory_gap_aux_weight_final': 0.1, 'memory_gap_aux_decay_fraction': 0.3, 'memory_gap_aux_decay_steps': 0, 'memory_gap_aux_exp_k': 5.0, 'use_precomputed_features': False, 'mamba_latent_channels': 16, 'mamba_summary_dim': 1024, 'mamba_model_dim': 1024, 'mamba_depth': 4, 'mamba_cond_dim': 1024, 'mamba_d_state': 16, 'mamba_d_conv': 4, 'mamba_expand': 2, 'allow_mamba_fallback': False, 'strict_causal_training': True, 'strict_causal_evaluation': True, 'use_oracle_pose_eval': True, 'enable_memory_noise_curriculum': False, 'curriculum_phase_boundaries': [0.2, 0.7], 'curriculum_noise_ranges': [[600, 1000], [200, 900], [0, 400]], 'curriculum_horizons': [50, 100, 200], '_name': 'df_video_mamba3stage', 'use_memory_attention': False, 'relative_embedding': False, 'memory_retrieval_topk': 32, 'n_tokens': 8}, 'debug': False, 'wandb': {'entity': 'turlin', 'project': 'worldmem', 'mode': 'online'}, 'resume': 'stage_b_joint_offline', 'load': None, 'name': 'train_stage_b_mamba_joint', 'output_dir': '/proj/cvl/users/x_fahkh2/WorldMem_Repro/checkpoints/bimamba_stage_b_joint_ckpt_40k/'}
14
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():658] starting backend
15
+ 2026-04-15 13:32:29,960 INFO MainThread:3907043 [wandb_init.py:init():662] setting up manager
16
+ 2026-04-15 13:32:29,978 INFO MainThread:3907043 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
17
+ 2026-04-15 13:32:29,984 INFO MainThread:3907043 [wandb_init.py:init():670] backend started and connected
18
+ 2026-04-15 13:32:30,020 INFO MainThread:3907043 [wandb_init.py:init():768] updated telemetry
19
+ 2026-04-15 13:32:30,086 INFO MainThread:3907043 [wandb_init.py:init():801] communicating run to backend with 90.0 second timeout
20
+ 2026-04-15 13:32:30,089 INFO MainThread:3907043 [wandb_init.py:init():852] starting run threads in backend
21
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_console_start():2465] atexit reg
22
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_redirect():2311] redirect: wrap_raw
23
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_redirect():2376] Wrapping output streams.
24
+ 2026-04-15 13:32:38,704 INFO MainThread:3907043 [wandb_run.py:_redirect():2401] Redirects installed.
25
+ 2026-04-15 13:32:38,714 INFO MainThread:3907043 [wandb_init.py:init():895] run started, returning control to user process
26
+ 2026-04-15 13:32:52,119 WARNING MsgRouterThr:3907043 [router.py:message_loop():77] message_loop has been closed
bimamba_stage_b_joint_ckpt_40k/wandb/offline-run-20260415_133229-stage_b_joint_offline/run-stage_b_joint_offline.wandb ADDED
Binary file (70.4 kB). View file