Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20260202_064313-i4545kqj/run-i4545kqj.wandb filter=lfs diff=lfs merge=lfs -text

.hydra/config.yaml

@@ -0,0 +1,179 @@
+dataset:
+  to_name: gberseth/bridge-data-64px-test
+  num_episodes: 0
+  chunk_size: 1
+  buffer_size: 50000
+  encode_with_t5: false
+  t5_version: t5-small
+  chars_list:
+  - ' '
+  - ','
+  - .
+  - '0'
+  - '1'
+  - '2'
+  - '3'
+  - '4'
+  - '5'
+  - '6'
+  - '7'
+  - '8'
+  - '9'
+  - '!'
+  - '?'
+  - '"'
+  - ''''
+  - (
+  - )
+  - '-'
+  - _
+  - ':'
+  - ;
+  - '@'
+  - '#'
+  - $
+  - '%'
+  - '&'
+  - '*'
+  - +
+  - '='
+  - <
+  - '>'
+  - /
+  - \\
+  - '|'
+  - '~'
+  - '`'
+  - A
+  - B
+  - C
+  - D
+  - E
+  - F
+  - G
+  - H
+  - I
+  - J
+  - K
+  - L
+  - M
+  - 'N'
+  - O
+  - P
+  - Q
+  - R
+  - S
+  - T
+  - U
+  - V
+  - W
+  - X
+  - 'Y'
+  - Z
+  - a
+  - b
+  - c
+  - d
+  - e
+  - f
+  - g
+  - h
+  - i
+  - j
+  - k
+  - l
+  - m
+  - 'n'
+  - o
+  - p
+  - q
+  - r
+  - s
+  - t
+  - u
+  - v
+  - w
+  - x
+  - 'y'
+  - z
+  load_dataset: true
+  download_all: false
+  save_initial_dataset: false
+  use_generator: false
+  dataset_indicies:
+    gs://gresearch/robotics/bridge/0.1.0/:
+      start: 0
+      weight: 1.0
+      dataset_key: bridge_oxe
+      scale: 1.0
+  action_std:
+  - 0.0118407579138875
+  - 0.01651778072118759
+  - 0.01558756735175848
+  - 0.03479960933327675
+  - 0.03878577798604965
+  - 0.05862835422158241
+  - 0.5686280727386475
+  action_mean:
+  - 0.00032659756834618747
+  - 0.0002364425890846178
+  - -0.0001985691487789154
+  - -0.0003516025608405471
+  - -0.0005819069338031113
+  - 0.0006634143064729869
+  - 0.659541130065918
+  gripper_closed_std: 1.0
+experiment:
+  name: grp_stat_3
+  project: mini-grp
+  description: simple env with 64pix images and pose data
+model:
+  type: transformer
+batch_size: 256
+max_block_size: 16
+vocab_size: 32
+n_patches: 8
+patch_size: 8
+max_iters: 25000
+eval_interval: 100
+learning_rate: 0.0003
+lr_schedule: linear
+eval_iters: 5
+policy:
+  action_stacking: 1
+  obs_stacking: 3
+  use_image_augmentations: false
+  dtype: float32
+  use_pose_data: 1
+  random_masking_enabled: false
+testing: false
+eval_vid_iters: 2500
+gradient_accumulation_steps: 1
+simEval: []
+sim:
+  eval_episodes: 1
+  eval_tasks:
+  - 0
+  - 1
+  - 2
+  - 3
+  episode length: 500
+r_seed: 1337
+device: cuda
+n_embd: 512
+n_head: 16
+n_blocks: 4
+dropout: 0.2
+action_dim: 7
+load_action_bounds: true
+image_shape:
+- 64
+- 64
+- 3
+data_shuffel_interval: 1000
+profiler:
+  enable: false
+  params:
+    profile_memory: true
+    with_stack: true
+    use_cuda: true

.hydra/hydra.yaml

@@ -0,0 +1,158 @@
+hydra:
+  run:
+    dir: outputs/${now:%Y-%m-%d}/${now:%H-%M-%S}
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task:
+    - simEval=[]
+    - policy.obs_stacking=3
+    - experiment.name=grp_stat_3
+  job:
+    name: mini_grp
+    chdir: null
+    override_dirname: experiment.name=grp_stat_3,policy.obs_stacking=3,simEval=[]
+    id: ???
+    num: ???
+    config_name: 64pix-pose
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.2.0
+    version_base: '1.1'
+    cwd: /home/o_heidar/robot_learning_2026
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/o_heidar/robot_learning_2026/mini-grp/conf
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12
+    choices:
+      dataset: fast
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

.hydra/overrides.yaml

@@ -0,0 +1,3 @@
+- simEval=[]
+- policy.obs_stacking=3
+- experiment.name=grp_stat_3

checkpoints/grp_stat_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:938de5cc2651702efe41171b52d2b5f12832c31056d501c1bb82e9137a9362b9
+size 51756846

mini_grp.log

@@ -0,0 +1 @@
+[2026-02-02 06:43:22,259][datasets][INFO] - TensorFlow version 2.15.0 available.

wandb/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2026-02-02T06:43:14.373523076-05:00","level":"INFO","msg":"stream: starting","core version":"0.24.1"}
+{"time":"2026-02-02T06:43:14.555022188-05:00","level":"INFO","msg":"stream: created new stream","id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.555098169-05:00","level":"INFO","msg":"handler: started","stream_id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.558136687-05:00","level":"INFO","msg":"stream: started","id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.55822855-05:00","level":"INFO","msg":"writer: started","stream_id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.558251165-05:00","level":"INFO","msg":"sender: started","stream_id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.293657146-05:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-02-02T12:42:50.512070299-05:00","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-02-02T12:42:50.529012161-05:00","level":"INFO","msg":"stream: closing","id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.529025813-05:00","level":"INFO","msg":"handler: closed","stream_id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.531105801-05:00","level":"INFO","msg":"sender: closed","stream_id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.531120425-05:00","level":"INFO","msg":"stream: closed","id":"i4545kqj"}

wandb/debug.log

@@ -0,0 +1,24 @@
+2026-02-02 06:43:14,007 INFO    MainThread:1212388 [wandb_setup.py:_flush():81] Current SDK version is 0.24.1
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_setup.py:_flush():81] Configure stats pid to 1212388
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12/wandb/run-20260202_064313-i4545kqj/logs/debug.log
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12/wandb/run-20260202_064313-i4545kqj/logs/debug-internal.log
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:init():844] calling init triggers
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'dataset': {'to_name': 'gberseth/bridge-data-64px-test', 'num_episodes': 0, 'chunk_size': 1, 'buffer_size': 50000, 'encode_with_t5': False, 't5_version': 't5-small', 'chars_list': [' ', ',', '.', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '!', '?', '"', "'", '(', ')', '-', '_', ':', ';', '@', '#', '$', '%', '&', '*', '+', '=', '<', '>', '/', '\\\\', '|', '~', '`', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z'], 'load_dataset': True, 'download_all': False, 'save_initial_dataset': False, 'use_generator': False, 'dataset_indicies': {'gs://gresearch/robotics/bridge/0.1.0/': {'start': 0, 'weight': 1.0, 'dataset_key': 'bridge_oxe', 'scale': 1.0}}, 'action_std': [0.0118407579138875, 0.01651778072118759, 0.01558756735175848, 0.03479960933327675, 0.03878577798604965, 0.05862835422158241, 0.5686280727386475], 'action_mean': [0.00032659756834618747, 0.0002364425890846178, -0.0001985691487789154, -0.0003516025608405471, -0.0005819069338031113, 0.0006634143064729869, 0.659541130065918], 'gripper_closed_std': 1.0}, 'experiment': {'name': 'grp_stat_3', 'project': 'mini-grp', 'description': 'simple env with 64pix images and pose data'}, 'model': {'type': 'transformer'}, 'batch_size': 256, 'max_block_size': 16, 'vocab_size': 32, 'n_patches': 8, 'patch_size': 8, 'max_iters': 25000, 'eval_interval': 100, 'learning_rate': 0.0003, 'lr_schedule': 'linear', 'eval_iters': 5, 'policy': {'action_stacking': 1, 'obs_stacking': 3, 'use_image_augmentations': False, 'dtype': 'float32', 'use_pose_data': 1, 'random_masking_enabled': False}, 'testing': False, 'eval_vid_iters': 2500, 'gradient_accumulation_steps': 1, 'simEval': [], 'sim': {'eval_episodes': 1, 'eval_tasks': [0, 1, 2, 3], 'episode length': 500}, 'r_seed': 1337, 'device': 'cuda', 'n_embd': 512, 'n_head': 16, 'n_blocks': 4, 'dropout': 0.2, 'action_dim': 7, 'load_action_bounds': True, 'image_shape': [64, 64, 3], 'data_shuffel_interval': 1000, 'profiler': {'enable': False, 'params': {'profile_memory': True, 'with_stack': True, 'use_cuda': True}}, '_wandb': {}}
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:init():892] starting backend
+2026-02-02 06:43:14,361 INFO    MainThread:1212388 [wandb_init.py:init():895] sending inform_init request
+2026-02-02 06:43:14,370 INFO    MainThread:1212388 [wandb_init.py:init():903] backend started and connected
+2026-02-02 06:43:14,372 INFO    MainThread:1212388 [wandb_init.py:init():973] updated telemetry
+2026-02-02 06:43:14,390 INFO    MainThread:1212388 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-02-02 06:43:14,776 INFO    MainThread:1212388 [wandb_init.py:init():1042] starting run threads in backend
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_console_start():2529] atexit reg
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_redirect():2377] redirect: wrap_raw
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_redirect():2446] Wrapping output streams.
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_redirect():2469] Redirects installed.
+2026-02-02 06:43:15,172 INFO    MainThread:1212388 [wandb_init.py:init():1082] run started, returning control to user process
+2026-02-02 12:42:49,802 INFO    MainThread:1212388 [wandb_run.py:_finish():2295] finishing run omidrezaheidari-concordia-university/mini-grp/i4545kqj
+2026-02-02 12:42:49,804 INFO    MainThread:1212388 [wandb_run.py:_atexit_cleanup():2494] got exitcode: 0
+2026-02-02 12:42:49,805 INFO    MainThread:1212388 [wandb_run.py:_restore():2476] restore
+2026-02-02 12:42:49,805 INFO    MainThread:1212388 [wandb_run.py:_restore():2482] restore done
+2026-02-02 12:42:50,515 INFO    MainThread:1212388 [wandb_run.py:_footer_sync_info():3871] logging synced files

wandb/run-20260202_064313-i4545kqj/files/config.yaml

@@ -0,0 +1,326 @@
+_wandb:
+    value:
+        cli_version: 0.24.1
+        e:
+            q4xofvz8clyq1g2jr4zr21tj3a4wrrs3:
+                args:
+                    - simEval=[]
+                    - policy.obs_stacking=3
+                    - experiment.name=grp_stat_3
+                codePath: mini-grp/mini_grp.py
+                cpu_count: 36
+                cpu_count_logical: 72
+                cudaVersion: "12.9"
+                disk:
+                    /:
+                        total: "470272819200"
+                        used: "31232614400"
+                email: omid.orh@gmail.com
+                executable: /home/o_heidar/rbenv/bin/python
+                git:
+                    commit: a1e45b9ec95f0f09f151f485ba23961058153e48
+                    remote: https://github.com/omid-reza/robot_learning_2026.git
+                gpu: Tesla V100-PCIE-32GB
+                gpu_count: 2
+                gpu_nvidia:
+                    - architecture: Volta
+                      cudaCores: 5120
+                      memoryTotal: "34359738368"
+                      name: Tesla V100-PCIE-32GB
+                      uuid: GPU-28f0e524-a7c5-f287-d873-73f15fb0d817
+                    - architecture: Volta
+                      cudaCores: 5120
+                      memoryTotal: "34359738368"
+                      name: Tesla V100-PCIE-32GB
+                      uuid: GPU-6b13b007-765f-fea0-26ee-f1842182916d
+                host: virya1
+                memory:
+                    total: "405360889856"
+                os: Linux-6.8.0-79-generic-x86_64-with-glibc2.39
+                program: /home/o_heidar/robot_learning_2026/mini-grp/mini_grp.py
+                python: CPython 3.10.19
+                root: /home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12
+                slurm:
+                    array_job_id: "59114"
+                    array_task_count: "5"
+                    array_task_id: "1"
+                    array_task_max: "4"
+                    array_task_min: "0"
+                    array_task_step: "1"
+                    cluster_name: clstr1
+                    conf: /etc/slurm/slurm.conf
+                    cpus_on_node: "10"
+                    gpus: "2"
+                    gpus_on_node: "2"
+                    gtids: "0"
+                    job_account: yang-wang
+                    job_cpus_per_node: "10"
+                    job_end_time: "1770637382"
+                    job_gid: "2184"
+                    job_gpus: 0,3
+                    job_id: "59116"
+                    job_name: H1Stat
+                    job_nodelist: virya1
+                    job_num_nodes: "1"
+                    job_partition: all
+                    job_qos: standard
+                    job_start_time: "1770032582"
+                    job_uid: "2184"
+                    job_user: o_heidar
+                    jobid: "59116"
+                    localid: "0"
+                    mem_per_node: "102400"
+                    nnodes: "1"
+                    nodeid: "0"
+                    nodelist: virya1
+                    prio_process: "0"
+                    procid: "0"
+                    script_context: prolog_task
+                    submit_dir: /home/o_heidar/robot_learning_2026/jobs
+                    submit_host: viryasubmit2
+                    task_pid: "1212375"
+                    tasks_per_node: "10"
+                    topology_addr: virya1
+                    topology_addr_pattern: node
+                startedAt: "2026-02-02T11:43:13.984688Z"
+                writerId: q4xofvz8clyq1g2jr4zr21tj3a4wrrs3
+        m: []
+        python_version: 3.10.19
+        t:
+            "1":
+                - 1
+                - 5
+                - 11
+                - 49
+                - 50
+                - 53
+            "2":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+            "3":
+                - 2
+                - 13
+                - 16
+                - 61
+            "4": 3.10.19
+            "5": 0.24.1
+            "6": 4.48.1
+            "12": 0.24.1
+            "13": linux-x86_64
+action_dim:
+    value: 7
+batch_size:
+    value: 256
+data_shuffel_interval:
+    value: 1000
+dataset:
+    value:
+        action_mean:
+            - 0.00032659756834618747
+            - 0.0002364425890846178
+            - -0.0001985691487789154
+            - -0.0003516025608405471
+            - -0.0005819069338031113
+            - 0.0006634143064729869
+            - 0.659541130065918
+        action_std:
+            - 0.0118407579138875
+            - 0.01651778072118759
+            - 0.01558756735175848
+            - 0.03479960933327675
+            - 0.03878577798604965
+            - 0.05862835422158241
+            - 0.5686280727386475
+        buffer_size: 50000
+        chars_list:
+            - ' '
+            - ','
+            - .
+            - "0"
+            - "1"
+            - "2"
+            - "3"
+            - "4"
+            - "5"
+            - "6"
+            - "7"
+            - "8"
+            - "9"
+            - '!'
+            - '?'
+            - '"'
+            - ''''
+            - (
+            - )
+            - '-'
+            - _
+            - ':'
+            - ;
+            - '@'
+            - '#'
+            - $
+            - '%'
+            - '&'
+            - '*'
+            - +
+            - =
+            - <
+            - '>'
+            - /
+            - \\
+            - '|'
+            - "~"
+            - '`'
+            - A
+            - B
+            - C
+            - D
+            - E
+            - F
+            - G
+            - H
+            - I
+            - J
+            - K
+            - L
+            - M
+            - "N"
+            - O
+            - P
+            - Q
+            - R
+            - S
+            - T
+            - U
+            - V
+            - W
+            - X
+            - "Y"
+            - Z
+            - a
+            - b
+            - c
+            - d
+            - e
+            - f
+            - g
+            - h
+            - i
+            - j
+            - k
+            - l
+            - m
+            - "n"
+            - o
+            - p
+            - q
+            - r
+            - s
+            - t
+            - u
+            - v
+            - w
+            - x
+            - "y"
+            - z
+        chunk_size: 1
+        dataset_indicies:
+            gs://gresearch/robotics/bridge/0.1.0/:
+                dataset_key: bridge_oxe
+                scale: 1
+                start: 0
+                weight: 1
+        download_all: false
+        encode_with_t5: false
+        gripper_closed_std: 1
+        load_dataset: true
+        num_episodes: 0
+        save_initial_dataset: false
+        t5_version: t5-small
+        to_name: gberseth/bridge-data-64px-test
+        use_generator: false
+device:
+    value: cuda
+dropout:
+    value: 0.2
+eval_interval:
+    value: 100
+eval_iters:
+    value: 5
+eval_vid_iters:
+    value: 2500
+experiment:
+    value:
+        description: simple env with 64pix images and pose data
+        name: grp_stat_3
+        project: mini-grp
+gradient_accumulation_steps:
+    value: 1
+image_shape:
+    value:
+        - 64
+        - 64
+        - 3
+learning_rate:
+    value: 0.0003
+load_action_bounds:
+    value: true
+lr_schedule:
+    value: linear
+max_block_size:
+    value: 16
+max_iters:
+    value: 25000
+model:
+    value:
+        type: transformer
+n_blocks:
+    value: 4
+n_embd:
+    value: 512
+n_head:
+    value: 16
+n_patches:
+    value: 8
+patch_size:
+    value: 8
+policy:
+    value:
+        action_stacking: 1
+        dtype: float32
+        obs_stacking: 3
+        random_masking_enabled: false
+        use_image_augmentations: false
+        use_pose_data: 1
+profiler:
+    value:
+        enable: false
+        params:
+            profile_memory: true
+            use_cuda: true
+            with_stack: true
+r_seed:
+    value: 1337
+sim:
+    value:
+        episode length: 500
+        eval_episodes: 1
+        eval_tasks:
+            - 0
+            - 1
+            - 2
+            - 3
+simEval:
+    value: []
+testing:
+    value: false
+vocab_size:
+    value: 32

wandb/run-20260202_064313-i4545kqj/files/output.log

@@ -0,0 +1,296 @@
+wandb: WARNING No relevant files were detected in the specified directory. No code will be logged to your run.
+/home/o_heidar/robot_learning_2026/mini-grp/mini_shuffel_buffer.py:614: UserWarning:
+The version_base parameter is not specified.
+Please specify a compatability version level, or None.
+Will assume defaults for version 1.1
+  @hydra.main(config_path="./conf", config_name="64pix-pose")
+Using Transformer model
+vocab_size: 90
+[2026-02-02 06:43:22,259][datasets][INFO] - TensorFlow version 2.15.0 available.
+Time to load huggingface dataset: 2.516728639602661
+Time to load huggingface data and copy:  24.613126277923584
+Loaded dataset with size: 50000
+12.893191 M parameters
+Memory used by the model: 1289.755136 MB
+Memory used by the dataset cBuffer: 0.445692 MB
+Memory used by the dataset cBuffer image: 0.000184 MB
+Memory used by the dataset cBuffer goal image: 0.000184 MB
+Memory used by the dataset cBuffer: t5_language_embedding 1.6e-05 MB
+num <queue.Queue object at 0x7d1d2c793c40>
+step 0: train loss 1.2561, val loss 1.2331, memory 1298.27 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 100: train loss 0.7189, val loss 0.6812, memory 1460.79 MB
+step 200: train loss 0.6676, val loss 0.6790, memory 1460.79 MB
+step 300: train loss 0.6857, val loss 0.6692, memory 1460.79 MB
+step 400: train loss 0.6532, val loss 0.6879, memory 1460.79 MB
+step 500: train loss 0.7244, val loss 0.6382, memory 1460.79 MB
+step 600: train loss 0.6103, val loss 0.5972, memory 1460.79 MB
+step 700: train loss 0.6218, val loss 0.6448, memory 1460.79 MB
+step 800: train loss 0.6331, val loss 0.5831, memory 1460.79 MB
+step 900: train loss 0.6193, val loss 0.5889, memory 1460.79 MB
+step 1000: train loss 0.6111, val loss 0.6234, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 1100: train loss 0.6461, val loss 0.6237, memory 1460.79 MB
+step 1200: train loss 0.6076, val loss 0.6209, memory 1460.79 MB
+step 1300: train loss 0.6120, val loss 0.6172, memory 1460.79 MB
+step 1400: train loss 0.6117, val loss 0.6226, memory 1460.79 MB
+step 1500: train loss 0.6216, val loss 0.6008, memory 1460.79 MB
+step 1600: train loss 0.5858, val loss 0.5804, memory 1460.79 MB
+step 1700: train loss 0.5621, val loss 0.6078, memory 1460.79 MB
+step 1800: train loss 0.5562, val loss 0.5873, memory 1460.79 MB
+step 1900: train loss 0.5499, val loss 0.6078, memory 1460.79 MB
+step 2000: train loss 0.5819, val loss 0.5531, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 2100: train loss 0.5583, val loss 0.5453, memory 1460.79 MB
+step 2200: train loss 0.5972, val loss 0.5706, memory 1460.79 MB
+step 2300: train loss 0.5570, val loss 0.5305, memory 1460.79 MB
+step 2400: train loss 0.5272, val loss 0.5677, memory 1460.79 MB
+step 2500: train loss 0.5377, val loss 0.5141, memory 1460.79 MB
+step 2600: train loss 0.4698, val loss 0.5408, memory 1460.79 MB
+step 2700: train loss 0.5047, val loss 0.5272, memory 1460.79 MB
+step 2800: train loss 0.4769, val loss 0.5125, memory 1460.79 MB
+step 2900: train loss 0.4855, val loss 0.4887, memory 1460.79 MB
+step 3000: train loss 0.4516, val loss 0.4883, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 3100: train loss 0.4782, val loss 0.4545, memory 1460.79 MB
+step 3200: train loss 0.4456, val loss 0.4884, memory 1460.79 MB
+step 3300: train loss 0.4679, val loss 0.4463, memory 1460.79 MB
+step 3400: train loss 0.4192, val loss 0.4447, memory 1460.79 MB
+step 3500: train loss 0.4444, val loss 0.4410, memory 1460.79 MB
+step 3600: train loss 0.3920, val loss 0.4080, memory 1460.79 MB
+step 3700: train loss 0.4098, val loss 0.3948, memory 1460.79 MB
+step 3800: train loss 0.4099, val loss 0.4020, memory 1460.79 MB
+step 3900: train loss 0.3880, val loss 0.3558, memory 1460.79 MB
+step 4000: train loss 0.3801, val loss 0.3811, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 4100: train loss 0.3663, val loss 0.3879, memory 1460.79 MB
+step 4200: train loss 0.3574, val loss 0.3740, memory 1460.79 MB
+step 4300: train loss 0.3654, val loss 0.3690, memory 1460.79 MB
+step 4400: train loss 0.3572, val loss 0.3526, memory 1460.79 MB
+step 4500: train loss 0.3552, val loss 0.3322, memory 1460.79 MB
+step 4600: train loss 0.3343, val loss 0.3532, memory 1460.79 MB
+step 4700: train loss 0.3262, val loss 0.3365, memory 1460.79 MB
+step 4800: train loss 0.3208, val loss 0.3511, memory 1460.79 MB
+step 4900: train loss 0.3113, val loss 0.3042, memory 1460.79 MB
+step 5000: train loss 0.3160, val loss 0.3016, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 5100: train loss 0.2975, val loss 0.2929, memory 1460.79 MB
+step 5200: train loss 0.2701, val loss 0.3149, memory 1460.79 MB
+step 5300: train loss 0.2722, val loss 0.2676, memory 1460.79 MB
+step 5400: train loss 0.2793, val loss 0.2865, memory 1460.79 MB
+step 5500: train loss 0.2713, val loss 0.2626, memory 1460.79 MB
+step 5600: train loss 0.2775, val loss 0.2568, memory 1460.79 MB
+step 5700: train loss 0.2875, val loss 0.2646, memory 1460.79 MB
+step 5800: train loss 0.2501, val loss 0.2609, memory 1460.79 MB
+step 5900: train loss 0.2606, val loss 0.2473, memory 1460.79 MB
+step 6000: train loss 0.2359, val loss 0.2412, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 6100: train loss 0.2321, val loss 0.2516, memory 1460.79 MB
+step 6200: train loss 0.2383, val loss 0.2271, memory 1460.79 MB
+step 6300: train loss 0.2332, val loss 0.2418, memory 1460.79 MB
+step 6400: train loss 0.2387, val loss 0.2397, memory 1460.79 MB
+step 6500: train loss 0.2234, val loss 0.2346, memory 1460.79 MB
+step 6600: train loss 0.2276, val loss 0.2122, memory 1460.79 MB
+step 6700: train loss 0.2049, val loss 0.2185, memory 1460.79 MB
+step 6800: train loss 0.1979, val loss 0.2095, memory 1460.79 MB
+step 6900: train loss 0.2009, val loss 0.2111, memory 1460.79 MB
+step 7000: train loss 0.2004, val loss 0.2184, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 7100: train loss 0.1855, val loss 0.1974, memory 1460.79 MB
+step 7200: train loss 0.1934, val loss 0.1869, memory 1460.79 MB
+step 7300: train loss 0.1823, val loss 0.1964, memory 1460.79 MB
+step 7400: train loss 0.1751, val loss 0.1777, memory 1460.79 MB
+step 7500: train loss 0.1797, val loss 0.1771, memory 1460.79 MB
+step 7600: train loss 0.1783, val loss 0.1752, memory 1460.79 MB
+step 7700: train loss 0.1677, val loss 0.1797, memory 1460.79 MB
+step 7800: train loss 0.1790, val loss 0.1733, memory 1460.79 MB
+step 7900: train loss 0.1732, val loss 0.1665, memory 1460.79 MB
+step 8000: train loss 0.1663, val loss 0.1714, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 8100: train loss 0.1691, val loss 0.1583, memory 1460.79 MB
+step 8200: train loss 0.1601, val loss 0.1618, memory 1460.79 MB
+step 8300: train loss 0.1620, val loss 0.1706, memory 1460.79 MB
+step 8400: train loss 0.1582, val loss 0.1601, memory 1460.79 MB
+step 8500: train loss 0.1543, val loss 0.1548, memory 1460.79 MB
+step 8600: train loss 0.1489, val loss 0.1563, memory 1460.79 MB
+step 8700: train loss 0.1514, val loss 0.1545, memory 1460.79 MB
+step 8800: train loss 0.1465, val loss 0.1428, memory 1460.79 MB
+step 8900: train loss 0.1435, val loss 0.1434, memory 1460.79 MB
+step 9000: train loss 0.1448, val loss 0.1430, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 9100: train loss 0.1363, val loss 0.1359, memory 1460.79 MB
+step 9200: train loss 0.1371, val loss 0.1419, memory 1460.79 MB
+step 9300: train loss 0.1538, val loss 0.1536, memory 1460.79 MB
+step 9400: train loss 0.1368, val loss 0.1464, memory 1460.79 MB
+step 9500: train loss 0.1357, val loss 0.1397, memory 1460.79 MB
+step 9600: train loss 0.1292, val loss 0.1311, memory 1460.79 MB
+step 9700: train loss 0.1449, val loss 0.1281, memory 1460.79 MB
+step 9800: train loss 0.1317, val loss 0.1258, memory 1460.79 MB
+step 9900: train loss 0.1257, val loss 0.1362, memory 1460.79 MB
+step 10000: train loss 0.1301, val loss 0.1294, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 10100: train loss 0.1274, val loss 0.1299, memory 1460.79 MB
+step 10200: train loss 0.1281, val loss 0.1251, memory 1460.79 MB
+step 10300: train loss 0.1183, val loss 0.1240, memory 1460.79 MB
+step 10400: train loss 0.1250, val loss 0.1221, memory 1460.79 MB
+step 10500: train loss 0.1208, val loss 0.1174, memory 1460.79 MB
+step 10600: train loss 0.1162, val loss 0.1250, memory 1460.79 MB
+step 10700: train loss 0.1062, val loss 0.1123, memory 1460.79 MB
+step 10800: train loss 0.1136, val loss 0.1104, memory 1460.79 MB
+step 10900: train loss 0.1165, val loss 0.1146, memory 1460.79 MB
+step 11000: train loss 0.1109, val loss 0.1181, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 11100: train loss 0.1099, val loss 0.1029, memory 1460.79 MB
+step 11200: train loss 0.1096, val loss 0.1062, memory 1460.79 MB
+step 11300: train loss 0.1060, val loss 0.1040, memory 1460.79 MB
+step 11400: train loss 0.1087, val loss 0.1150, memory 1460.79 MB
+step 11500: train loss 0.0981, val loss 0.1008, memory 1460.79 MB
+step 11600: train loss 0.1054, val loss 0.0998, memory 1460.79 MB
+step 11700: train loss 0.0960, val loss 0.1015, memory 1460.79 MB
+step 11800: train loss 0.1002, val loss 0.1023, memory 1460.79 MB
+step 11900: train loss 0.1119, val loss 0.1163, memory 1460.79 MB
+step 12000: train loss 0.1042, val loss 0.0973, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 12100: train loss 0.0945, val loss 0.0941, memory 1460.79 MB
+step 12200: train loss 0.0948, val loss 0.0967, memory 1460.79 MB
+step 12300: train loss 0.1010, val loss 0.1024, memory 1460.79 MB
+step 12400: train loss 0.0969, val loss 0.1015, memory 1460.79 MB
+step 12500: train loss 0.0985, val loss 0.0940, memory 1460.79 MB
+step 12600: train loss 0.0956, val loss 0.0938, memory 1460.79 MB
+step 12700: train loss 0.0965, val loss 0.1038, memory 1460.79 MB
+step 12800: train loss 0.0963, val loss 0.0992, memory 1460.79 MB
+step 12900: train loss 0.1070, val loss 0.1038, memory 1460.79 MB
+step 13000: train loss 0.0954, val loss 0.0925, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 13100: train loss 0.0886, val loss 0.0903, memory 1460.79 MB
+step 13200: train loss 0.0916, val loss 0.0961, memory 1460.79 MB
+step 13300: train loss 0.0888, val loss 0.0881, memory 1460.79 MB
+step 13400: train loss 0.0819, val loss 0.0901, memory 1460.79 MB
+step 13500: train loss 0.0883, val loss 0.0817, memory 1460.79 MB
+step 13600: train loss 0.0935, val loss 0.0927, memory 1460.79 MB
+step 13700: train loss 0.0920, val loss 0.0883, memory 1460.79 MB
+step 13800: train loss 0.0837, val loss 0.0832, memory 1460.79 MB
+step 13900: train loss 0.0873, val loss 0.0831, memory 1460.79 MB
+step 14000: train loss 0.0841, val loss 0.0814, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 14100: train loss 0.0899, val loss 0.0906, memory 1460.79 MB
+step 14200: train loss 0.0847, val loss 0.0806, memory 1460.79 MB
+step 14300: train loss 0.0820, val loss 0.0833, memory 1460.79 MB
+step 14400: train loss 0.0789, val loss 0.0728, memory 1460.79 MB
+step 14500: train loss 0.0899, val loss 0.0858, memory 1460.79 MB
+step 14600: train loss 0.0744, val loss 0.0775, memory 1460.79 MB
+step 14700: train loss 0.0804, val loss 0.0819, memory 1460.79 MB
+step 14800: train loss 0.0845, val loss 0.0861, memory 1460.79 MB
+step 14900: train loss 0.0777, val loss 0.0793, memory 1460.79 MB
+step 15000: train loss 0.0909, val loss 0.0827, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 15100: train loss 0.0856, val loss 0.0824, memory 1460.79 MB
+step 15200: train loss 0.0719, val loss 0.0800, memory 1460.79 MB
+step 15300: train loss 0.0759, val loss 0.0792, memory 1460.79 MB
+step 15400: train loss 0.0800, val loss 0.0787, memory 1460.79 MB
+step 15500: train loss 0.0875, val loss 0.0789, memory 1460.79 MB
+step 15600: train loss 0.0754, val loss 0.0782, memory 1460.79 MB
+step 15700: train loss 0.0754, val loss 0.0784, memory 1460.79 MB
+step 15800: train loss 0.0766, val loss 0.0771, memory 1460.79 MB
+step 15900: train loss 0.0732, val loss 0.0775, memory 1460.79 MB
+step 16000: train loss 0.0749, val loss 0.0712, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 16100: train loss 0.0693, val loss 0.0694, memory 1460.79 MB
+step 16200: train loss 0.0736, val loss 0.0785, memory 1460.79 MB
+step 16300: train loss 0.0781, val loss 0.0776, memory 1460.79 MB
+step 16400: train loss 0.0694, val loss 0.0737, memory 1460.79 MB
+step 16500: train loss 0.0744, val loss 0.0779, memory 1460.79 MB
+step 16600: train loss 0.0691, val loss 0.0694, memory 1460.79 MB
+step 16700: train loss 0.0712, val loss 0.0807, memory 1460.79 MB
+step 16800: train loss 0.0732, val loss 0.0764, memory 1460.79 MB
+step 16900: train loss 0.0784, val loss 0.0750, memory 1460.79 MB
+step 17000: train loss 0.0702, val loss 0.0710, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 17100: train loss 0.0700, val loss 0.0707, memory 1460.79 MB
+step 17200: train loss 0.0693, val loss 0.0717, memory 1460.79 MB
+step 17300: train loss 0.0683, val loss 0.0668, memory 1460.79 MB
+step 17400: train loss 0.0710, val loss 0.0755, memory 1460.79 MB
+step 17500: train loss 0.0669, val loss 0.0653, memory 1460.79 MB
+step 17600: train loss 0.0703, val loss 0.0677, memory 1460.79 MB
+step 17700: train loss 0.0675, val loss 0.0645, memory 1460.79 MB
+step 17800: train loss 0.0726, val loss 0.0678, memory 1460.79 MB
+step 17900: train loss 0.0711, val loss 0.0682, memory 1460.79 MB
+step 18000: train loss 0.0678, val loss 0.0726, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 18100: train loss 0.0668, val loss 0.0661, memory 1460.79 MB
+step 18200: train loss 0.0703, val loss 0.0685, memory 1460.79 MB
+step 18300: train loss 0.0673, val loss 0.0644, memory 1460.79 MB
+step 18400: train loss 0.0675, val loss 0.0661, memory 1460.79 MB
+step 18500: train loss 0.0688, val loss 0.0697, memory 1460.79 MB
+step 18600: train loss 0.0677, val loss 0.0648, memory 1460.79 MB
+step 18700: train loss 0.0643, val loss 0.0602, memory 1460.79 MB
+step 18800: train loss 0.0629, val loss 0.0622, memory 1460.79 MB
+step 18900: train loss 0.0597, val loss 0.0630, memory 1460.79 MB
+step 19000: train loss 0.0665, val loss 0.0696, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 19100: train loss 0.0626, val loss 0.0617, memory 1460.79 MB
+step 19200: train loss 0.0612, val loss 0.0595, memory 1460.79 MB
+step 19300: train loss 0.0608, val loss 0.0632, memory 1460.79 MB
+step 19400: train loss 0.0556, val loss 0.0599, memory 1460.79 MB
+step 19500: train loss 0.0544, val loss 0.0580, memory 1460.79 MB
+step 19600: train loss 0.0631, val loss 0.0612, memory 1460.79 MB
+step 19700: train loss 0.0607, val loss 0.0625, memory 1460.79 MB
+step 19800: train loss 0.0672, val loss 0.0644, memory 1460.79 MB
+step 19900: train loss 0.0598, val loss 0.0593, memory 1460.79 MB
+step 20000: train loss 0.0630, val loss 0.0627, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 20100: train loss 0.0612, val loss 0.0596, memory 1460.79 MB
+step 20200: train loss 0.0635, val loss 0.0598, memory 1460.79 MB
+step 20300: train loss 0.0585, val loss 0.0535, memory 1460.79 MB
+step 20400: train loss 0.0556, val loss 0.0560, memory 1460.79 MB
+step 20500: train loss 0.0620, val loss 0.0649, memory 1460.79 MB
+step 20600: train loss 0.0602, val loss 0.0626, memory 1460.79 MB
+step 20700: train loss 0.0580, val loss 0.0559, memory 1460.79 MB
+step 20800: train loss 0.0558, val loss 0.0596, memory 1460.79 MB
+step 20900: train loss 0.0586, val loss 0.0568, memory 1460.79 MB
+step 21000: train loss 0.0585, val loss 0.0599, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 21100: train loss 0.0558, val loss 0.0544, memory 1460.79 MB
+step 21200: train loss 0.0588, val loss 0.0583, memory 1460.79 MB
+step 21300: train loss 0.0546, val loss 0.0584, memory 1460.79 MB
+step 21400: train loss 0.0541, val loss 0.0524, memory 1460.79 MB
+step 21500: train loss 0.0545, val loss 0.0603, memory 1460.79 MB
+step 21600: train loss 0.0579, val loss 0.0561, memory 1460.79 MB
+step 21700: train loss 0.0593, val loss 0.0601, memory 1460.79 MB
+step 21800: train loss 0.0504, val loss 0.0516, memory 1460.79 MB
+step 21900: train loss 0.0530, val loss 0.0507, memory 1460.79 MB
+step 22000: train loss 0.0583, val loss 0.0604, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 22100: train loss 0.0569, val loss 0.0583, memory 1460.79 MB
+step 22200: train loss 0.0523, val loss 0.0506, memory 1460.79 MB
+step 22300: train loss 0.0543, val loss 0.0574, memory 1460.79 MB
+step 22400: train loss 0.0561, val loss 0.0541, memory 1460.79 MB
+step 22500: train loss 0.0568, val loss 0.0548, memory 1460.79 MB
+step 22600: train loss 0.0553, val loss 0.0519, memory 1460.79 MB
+step 22700: train loss 0.0544, val loss 0.0543, memory 1460.79 MB
+step 22800: train loss 0.0570, val loss 0.0561, memory 1460.79 MB
+step 22900: train loss 0.0563, val loss 0.0556, memory 1460.79 MB
+step 23000: train loss 0.0506, val loss 0.0529, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 23100: train loss 0.0521, val loss 0.0511, memory 1460.79 MB
+step 23200: train loss 0.0575, val loss 0.0574, memory 1460.79 MB
+step 23300: train loss 0.0554, val loss 0.0509, memory 1460.79 MB
+step 23400: train loss 0.0573, val loss 0.0539, memory 1460.79 MB
+step 23500: train loss 0.0550, val loss 0.0547, memory 1460.79 MB
+step 23600: train loss 0.0545, val loss 0.0524, memory 1460.79 MB
+step 23700: train loss 0.0504, val loss 0.0529, memory 1460.79 MB
+step 23800: train loss 0.0465, val loss 0.0516, memory 1460.79 MB
+step 23900: train loss 0.0510, val loss 0.0502, memory 1460.79 MB
+step 24000: train loss 0.0497, val loss 0.0490, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth
+step 24100: train loss 0.0533, val loss 0.0567, memory 1460.79 MB
+step 24200: train loss 0.0532, val loss 0.0540, memory 1460.79 MB
+step 24300: train loss 0.0453, val loss 0.0507, memory 1460.79 MB
+step 24400: train loss 0.0473, val loss 0.0528, memory 1460.79 MB
+step 24500: train loss 0.0509, val loss 0.0537, memory 1460.79 MB
+step 24600: train loss 0.0527, val loss 0.0562, memory 1460.79 MB
+step 24700: train loss 0.0546, val loss 0.0554, memory 1460.79 MB
+step 24800: train loss 0.0490, val loss 0.0484, memory 1460.79 MB
+step 24900: train loss 0.0476, val loss 0.0493, memory 1460.79 MB
+step 24999: train loss 0.0538, val loss 0.0502, memory 1460.79 MB
+Model saved to ./checkpoints/grp_stat_3.pth

wandb/run-20260202_064313-i4545kqj/files/requirements.txt

@@ -0,0 +1,249 @@
+httpx==0.27.2
+marshmallow==3.20.2
+sniffio==1.3.1
+optree==0.11.0
+multiprocess==0.70.16
+biom-format==2.1.16
+typing-inspect==0.9.0
+kornia_rs==0.1.7
+loky==3.4.1
+llama_stack_client==0.0.54
+randaugment==1.0.2
+numba==0.60.0
+annotated-types==0.7.0
+llama_stack==0.0.54
+tomli==2.2.1
+kornia==0.7.4
+terminaltables==3.1.10
+tensorrt-cu12==10.6.0
+schedule==1.2.2
+mdurl==0.1.2
+responses==0.18.0
+awscli==1.32.41
+libclang==18.1.1
+torchvision==0.20.1
+timm==0.9.16
+addict==2.4.0
+pyarrow-hotfix==0.6
+tensorboard-data-server==0.7.2
+threadpoolctl==3.4.0
+contourpy==1.3.1
+blobfile==3.0.0
+llama_models==0.0.54
+python-dateutil==2.8.2
+mypy-extensions==1.0.0
+moviepy==1.0.3
+namex==0.0.7
+pyaml==24.9.0
+s3transfer==0.10.0
+rouge-score==0.1.2
+httpcore==1.0.7
+pycryptodomex==3.21.0
+jmespath==1.0.1
+docutils==0.16
+h11==0.14.0
+ete3==3.1.3
+boto3==1.34.44
+MarkupSafe==3.0.2
+tensorrt==10.6.0
+nltk==3.9.1
+tiktoken==0.8.0
+pbr==6.1.0
+Pygments==2.17.2
+pydantic_core==2.27.1
+ego4d==1.6.1
+tensorrt-cu12-bindings==10.6.0
+tensorrt-cu12-libs==10.6.0
+bgzip==0.5.0
+cogent3==2024.11.29a2
+dataclasses-json==0.6.4
+platformdirs==4.3.8
+exceptiongroup==1.2.2
+mpmath==1.3.0
+inquirerpy==0.3.4
+packaging==23.2
+inplace-abn==1.1.0
+astunparse==1.6.3
+google-pasta==0.2.0
+joblib==1.3.2
+prompt_toolkit==3.0.48
+llvmlite==0.43.0
+torchaudio==2.5.1
+pydantic==2.10.1
+scikit-learn==1.6.1
+fire==0.7.0
+Werkzeug==3.1.3
+scitrack==2024.10.8
+pfzy==0.3.4
+cvbase==0.5.5
+pysam==0.22.1
+tensorboardX==2.6.2.2
+bert-score==0.3.13
+anyio==4.6.2.post1
+evaluate==0.4.1
+yapf==0.43.0
+wheel==0.41.2
+iopath==0.1.10
+dominate==2.9.1
+cycler==0.12.1
+meteor==2.0.17
+portalocker==2.8.2
+lxml==5.3.0
+decord==0.6.0
+keras==2.15.0
+nvidia-nvtx-cu12==12.4.127
+kiwisolver==1.4.9
+decorator==4.4.2
+nvidia-cudnn-cu12==9.1.0.70
+huggingface==0.0.1
+cliff==4.11.0
+nvidia-cusolver-cu12==11.6.1.9
+packaging==25.0
+frozenlist==1.7.0
+Farama-Notifications==0.0.4
+fsspec==2025.9.0
+pyarrow==21.0.0
+Pympler==1.1
+tensorboard==2.15.2
+einops==0.8.0
+wandb==0.24.1
+rich==14.1.0
+colorlog==6.9.0
+hydra-optuna-sweeper==1.2.0
+absl-py==2.3.1
+gymnasium==0.28.1
+nvidia-cublas-cu12==12.4.5.8
+hydra-submitit-launcher==1.2.0
+psutil==7.2.2
+urllib3==2.5.0
+opencv-python==4.11.0.86
+python-box==7.3.2
+nvidia-cuda-nvrtc-cu12==12.4.127
+smmap==5.0.2
+cmaes==0.12.0
+xxhash==3.5.0
+hydra-core==1.2.0
+PyYAML==6.0.2
+tensorflow==2.15.0
+filelock==3.19.1
+rlds==0.1.8
+tensorflow-estimator==2.15.0
+termcolor==3.1.0
+tensorflow-datasets==4.9.2
+sentry-sdk==2.38.0
+typing_extensions==4.15.0
+requests==2.32.5
+antlr4-python3-runtime==4.9.3
+flatbuffers==25.2.10
+rich-argparse==1.7.1
+stevedore==5.5.0
+aiohappyeyeballs==2.6.1
+pandas==2.2.2
+Jinja2==3.1.4
+dm-tree==0.1.9
+SQLAlchemy==2.0.43
+zipp==3.23.0
+rsa==4.9.1
+hf-xet==1.1.10
+networkx==3.3
+pyasn1==0.6.1
+gast==0.6.0
+async-timeout==5.0.1
+charset-normalizer==3.4.3
+transformers==4.48.1
+wcwidth==0.2.13
+opt_einsum==3.4.0
+safetensors==0.6.2
+google-auth-oauthlib==1.2.2
+imageio-ffmpeg==0.6.0
+docker-pycreds==0.4.0
+cmd2==2.7.0
+optuna==2.10.1
+gitdb==4.0.12
+aiosignal==1.4.0
+propcache==0.3.2
+pytz==2025.2
+pyasn1_modules==0.4.2
+regex==2025.9.18
+prettytable==3.16.0
+protobuf==3.20.3
+nvidia-cufft-cu12==11.2.1.3
+yarl==1.20.1
+dill==0.4.0
+tensorflow-io-gcs-filesystem==0.37.1
+nvidia-curand-cu12==10.3.5.147
+certifi==2025.8.3
+proglog==0.1.12
+attrs==25.3.0
+idna==3.10
+ml-dtypes==0.2.0
+matplotlib==3.5.3
+nvidia-cusparse-cu12==12.3.1.170
+greenlet==3.2.4
+imageio==2.37.0
+scipy==1.15.3
+setproctitle==1.3.7
+dm-reverb==0.14.0
+triton==3.1.0
+jax-jumpy==1.0.0
+torch==2.5.1
+pathtools==0.1.2
+tzdata==2025.2
+tokenizers==0.21.4
+tqdm==4.67.1
+numpy==1.26.4
+cachetools==5.5.2
+submitit==1.5.3
+cloudpickle==3.1.1
+wheel==0.46.3
+oauthlib==3.3.1
+aiohttp==3.12.15
+setuptools==80.10.1
+tensorflow-metadata==1.16.1
+six==1.17.0
+fonttools==4.60.0
+omegaconf==2.3.0
+shortuuid==1.0.13
+nvidia-cuda-cupti-cu12==12.4.127
+markdown-it-py==4.0.0
+promise==2.3
+h5py==3.14.0
+pip==26.0
+nvidia-nvjitlink-cu12==12.4.127
+google-auth==2.40.3
+nvidia-cuda-runtime-cu12==12.4.127
+nvidia-nccl-cu12==2.21.5
+autopage==0.5.2
+click==8.3.0
+array_record==0.8.1
+multidict==6.6.4
+Mako==1.3.10
+etils==1.13.0
+pyparsing==3.2.4
+Markdown==3.9
+huggingface-hub==0.35.0
+datasets==4.1.1
+portpicker==1.6.0
+sympy==1.13.1
+Pillow==9.4.0
+grpcio==1.75.0
+requests-oauthlib==2.0.0
+sentencepiece==0.2.0
+GitPython==3.1.45
+wrapt==1.14.2
+toml==0.10.2
+alembic==1.16.5
+importlib_resources==6.5.2
+pyperclip==1.10.0
+more-itertools==10.8.0
+jaraco.context==6.1.0
+zipp==3.23.0
+backports.tarfile==1.2.0
+jaraco.functools==4.4.0
+autocommand==2.2.2
+jaraco.text==4.0.0
+wheel==0.45.1
+tomli==2.4.0
+platformdirs==4.4.0
+importlib_metadata==8.7.1
+packaging==25.0

wandb/run-20260202_064313-i4545kqj/files/wandb-metadata.json

@@ -0,0 +1,94 @@
+{
+  "os":  "Linux-6.8.0-79-generic-x86_64-with-glibc2.39",
+  "python":  "CPython 3.10.19",
+  "startedAt":  "2026-02-02T11:43:13.984688Z",
+  "args":  [
+    "simEval=[]",
+    "policy.obs_stacking=3",
+    "experiment.name=grp_stat_3"
+  ],
+  "program":  "/home/o_heidar/robot_learning_2026/mini-grp/mini_grp.py",
+  "codePath":  "mini-grp/mini_grp.py",
+  "git":  {
+    "remote":  "https://github.com/omid-reza/robot_learning_2026.git",
+    "commit":  "a1e45b9ec95f0f09f151f485ba23961058153e48"
+  },
+  "email":  "omid.orh@gmail.com",
+  "root":  "/home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12",
+  "host":  "virya1",
+  "executable":  "/home/o_heidar/rbenv/bin/python",
+  "cpu_count":  36,
+  "cpu_count_logical":  72,
+  "gpu":  "Tesla V100-PCIE-32GB",
+  "gpu_count":  2,
+  "disk":  {
+    "/":  {
+      "total":  "470272819200",
+      "used":  "31232614400"
+    }
+  },
+  "memory":  {
+    "total":  "405360889856"
+  },
+  "gpu_nvidia":  [
+    {
+      "name":  "Tesla V100-PCIE-32GB",
+      "memoryTotal":  "34359738368",
+      "cudaCores":  5120,
+      "architecture":  "Volta",
+      "uuid":  "GPU-28f0e524-a7c5-f287-d873-73f15fb0d817"
+    },
+    {
+      "name":  "Tesla V100-PCIE-32GB",
+      "memoryTotal":  "34359738368",
+      "cudaCores":  5120,
+      "architecture":  "Volta",
+      "uuid":  "GPU-6b13b007-765f-fea0-26ee-f1842182916d"
+    }
+  ],
+  "cudaVersion":  "12.9",
+  "slurm":  {
+    "array_job_id":  "59114",
+    "array_task_count":  "5",
+    "array_task_id":  "1",
+    "array_task_max":  "4",
+    "array_task_min":  "0",
+    "array_task_step":  "1",
+    "cluster_name":  "clstr1",
+    "conf":  "/etc/slurm/slurm.conf",
+    "cpus_on_node":  "10",
+    "gpus":  "2",
+    "gpus_on_node":  "2",
+    "gtids":  "0",
+    "job_account":  "yang-wang",
+    "job_cpus_per_node":  "10",
+    "job_end_time":  "1770637382",
+    "job_gid":  "2184",
+    "job_gpus":  "0,3",
+    "job_id":  "59116",
+    "job_name":  "H1Stat",
+    "job_nodelist":  "virya1",
+    "job_num_nodes":  "1",
+    "job_partition":  "all",
+    "job_qos":  "standard",
+    "job_start_time":  "1770032582",
+    "job_uid":  "2184",
+    "job_user":  "o_heidar",
+    "jobid":  "59116",
+    "localid":  "0",
+    "mem_per_node":  "102400",
+    "nnodes":  "1",
+    "nodeid":  "0",
+    "nodelist":  "virya1",
+    "prio_process":  "0",
+    "procid":  "0",
+    "script_context":  "prolog_task",
+    "submit_dir":  "/home/o_heidar/robot_learning_2026/jobs",
+    "submit_host":  "viryasubmit2",
+    "task_pid":  "1212375",
+    "tasks_per_node":  "10",
+    "topology_addr":  "virya1",
+    "topology_addr_pattern":  "node"
+  },
+  "writerId":  "q4xofvz8clyq1g2jr4zr21tj3a4wrrs3"
+}

wandb/run-20260202_064313-i4545kqj/files/wandb-summary.json

@@ -0,0 +1 @@
+{"memory":1460.792832,"buffer_size":6.139024,"_timestamp":1.7700541689873946e+09,"_step":24999,"_wandb":{"runtime":21575},"_runtime":21575.028241367,"train loss":0.05379915237426758,"val loss":0.05018728971481323}

wandb/run-20260202_064313-i4545kqj/logs/debug-core.log

@@ -0,0 +1,19 @@
+{"time":"2026-02-02T06:43:14.178755309-05:00","level":"INFO","msg":"main: starting server","port-filename":"/data/scratch/59116/tmpv5gcseoc/port-1212388.txt","pid":1212388,"log-level":0,"disable-analytics":false,"shutdown-on-parent-exit":false,"enable-dcgm-profiling":false}
+{"time":"2026-02-02T06:43:14.179492502-05:00","level":"INFO","msg":"server: will exit if parent process dies","ppid":1212388}
+{"time":"2026-02-02T06:43:14.179479484-05:00","level":"INFO","msg":"server: accepting connections","addr":{"Name":"/data/scratch/59116/wandb-1212388-1212414-3650282769/socket","Net":"unix"}}
+{"time":"2026-02-02T06:43:14.36183203-05:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"1(@)"}
+{"time":"2026-02-02T06:43:14.372324765-05:00","level":"INFO","msg":"handleInformInit: received","streamId":"i4545kqj","id":"1(@)"}
+{"time":"2026-02-02T06:43:14.558146241-05:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"i4545kqj","id":"1(@)"}
+{"time":"2026-02-02T06:43:20.172246764-05:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"3rrl05d4577k"}
+{"time":"2026-02-02T12:42:49.805601091-05:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"3rrl05d4577k"}
+{"time":"2026-02-02T12:42:50.515546133-05:00","level":"INFO","msg":"connection: cancelling request","id":"1(@)","requestId":"3rrl05d4577k"}
+{"time":"2026-02-02T12:42:50.528979645-05:00","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"i4545kqj","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.539325608-05:00","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"i4545kqj","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.539352327-05:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.53937482-05:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.539393953-05:00","level":"INFO","msg":"connection: closing","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.539410057-05:00","level":"INFO","msg":"server is shutting down"}
+{"time":"2026-02-02T12:42:50.539463306-05:00","level":"INFO","msg":"connection: closed successfully","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.539474128-05:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"1(@)"}
+{"time":"2026-02-02T12:42:50.539587306-05:00","level":"INFO","msg":"server: listener closed","addr":{"Name":"/data/scratch/59116/wandb-1212388-1212414-3650282769/socket","Net":"unix"}}
+{"time":"2026-02-02T12:42:50.539642147-05:00","level":"INFO","msg":"server is closed"}

wandb/run-20260202_064313-i4545kqj/logs/debug-internal.log

@@ -0,0 +1,12 @@
+{"time":"2026-02-02T06:43:14.373523076-05:00","level":"INFO","msg":"stream: starting","core version":"0.24.1"}
+{"time":"2026-02-02T06:43:14.555022188-05:00","level":"INFO","msg":"stream: created new stream","id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.555098169-05:00","level":"INFO","msg":"handler: started","stream_id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.558136687-05:00","level":"INFO","msg":"stream: started","id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.55822855-05:00","level":"INFO","msg":"writer: started","stream_id":"i4545kqj"}
+{"time":"2026-02-02T06:43:14.558251165-05:00","level":"INFO","msg":"sender: started","stream_id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.293657146-05:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-02-02T12:42:50.512070299-05:00","level":"INFO","msg":"handler: operation stats","stats":{}}
+{"time":"2026-02-02T12:42:50.529012161-05:00","level":"INFO","msg":"stream: closing","id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.529025813-05:00","level":"INFO","msg":"handler: closed","stream_id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.531105801-05:00","level":"INFO","msg":"sender: closed","stream_id":"i4545kqj"}
+{"time":"2026-02-02T12:42:50.531120425-05:00","level":"INFO","msg":"stream: closed","id":"i4545kqj"}

wandb/run-20260202_064313-i4545kqj/logs/debug.log

@@ -0,0 +1,24 @@
+2026-02-02 06:43:14,007 INFO    MainThread:1212388 [wandb_setup.py:_flush():81] Current SDK version is 0.24.1
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_setup.py:_flush():81] Configure stats pid to 1212388
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_setup.py:_flush():81] Loading settings from environment variables
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:setup_run_log_directory():717] Logging user logs to /home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12/wandb/run-20260202_064313-i4545kqj/logs/debug.log
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:setup_run_log_directory():718] Logging internal logs to /home/o_heidar/robot_learning_2026/outputs/2026-02-02/06-43-12/wandb/run-20260202_064313-i4545kqj/logs/debug-internal.log
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:init():844] calling init triggers
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:init():849] wandb.init called with sweep_config: {}
+config: {'dataset': {'to_name': 'gberseth/bridge-data-64px-test', 'num_episodes': 0, 'chunk_size': 1, 'buffer_size': 50000, 'encode_with_t5': False, 't5_version': 't5-small', 'chars_list': [' ', ',', '.', '0', '1', '2', '3', '4', '5', '6', '7', '8', '9', '!', '?', '"', "'", '(', ')', '-', '_', ':', ';', '@', '#', '$', '%', '&', '*', '+', '=', '<', '>', '/', '\\\\', '|', '~', '`', 'A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q', 'R', 'S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z', 'a', 'b', 'c', 'd', 'e', 'f', 'g', 'h', 'i', 'j', 'k', 'l', 'm', 'n', 'o', 'p', 'q', 'r', 's', 't', 'u', 'v', 'w', 'x', 'y', 'z'], 'load_dataset': True, 'download_all': False, 'save_initial_dataset': False, 'use_generator': False, 'dataset_indicies': {'gs://gresearch/robotics/bridge/0.1.0/': {'start': 0, 'weight': 1.0, 'dataset_key': 'bridge_oxe', 'scale': 1.0}}, 'action_std': [0.0118407579138875, 0.01651778072118759, 0.01558756735175848, 0.03479960933327675, 0.03878577798604965, 0.05862835422158241, 0.5686280727386475], 'action_mean': [0.00032659756834618747, 0.0002364425890846178, -0.0001985691487789154, -0.0003516025608405471, -0.0005819069338031113, 0.0006634143064729869, 0.659541130065918], 'gripper_closed_std': 1.0}, 'experiment': {'name': 'grp_stat_3', 'project': 'mini-grp', 'description': 'simple env with 64pix images and pose data'}, 'model': {'type': 'transformer'}, 'batch_size': 256, 'max_block_size': 16, 'vocab_size': 32, 'n_patches': 8, 'patch_size': 8, 'max_iters': 25000, 'eval_interval': 100, 'learning_rate': 0.0003, 'lr_schedule': 'linear', 'eval_iters': 5, 'policy': {'action_stacking': 1, 'obs_stacking': 3, 'use_image_augmentations': False, 'dtype': 'float32', 'use_pose_data': 1, 'random_masking_enabled': False}, 'testing': False, 'eval_vid_iters': 2500, 'gradient_accumulation_steps': 1, 'simEval': [], 'sim': {'eval_episodes': 1, 'eval_tasks': [0, 1, 2, 3], 'episode length': 500}, 'r_seed': 1337, 'device': 'cuda', 'n_embd': 512, 'n_head': 16, 'n_blocks': 4, 'dropout': 0.2, 'action_dim': 7, 'load_action_bounds': True, 'image_shape': [64, 64, 3], 'data_shuffel_interval': 1000, 'profiler': {'enable': False, 'params': {'profile_memory': True, 'with_stack': True, 'use_cuda': True}}, '_wandb': {}}
+2026-02-02 06:43:14,008 INFO    MainThread:1212388 [wandb_init.py:init():892] starting backend
+2026-02-02 06:43:14,361 INFO    MainThread:1212388 [wandb_init.py:init():895] sending inform_init request
+2026-02-02 06:43:14,370 INFO    MainThread:1212388 [wandb_init.py:init():903] backend started and connected
+2026-02-02 06:43:14,372 INFO    MainThread:1212388 [wandb_init.py:init():973] updated telemetry
+2026-02-02 06:43:14,390 INFO    MainThread:1212388 [wandb_init.py:init():997] communicating run to backend with 90.0 second timeout
+2026-02-02 06:43:14,776 INFO    MainThread:1212388 [wandb_init.py:init():1042] starting run threads in backend
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_console_start():2529] atexit reg
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_redirect():2377] redirect: wrap_raw
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_redirect():2446] Wrapping output streams.
+2026-02-02 06:43:15,167 INFO    MainThread:1212388 [wandb_run.py:_redirect():2469] Redirects installed.
+2026-02-02 06:43:15,172 INFO    MainThread:1212388 [wandb_init.py:init():1082] run started, returning control to user process
+2026-02-02 12:42:49,802 INFO    MainThread:1212388 [wandb_run.py:_finish():2295] finishing run omidrezaheidari-concordia-university/mini-grp/i4545kqj
+2026-02-02 12:42:49,804 INFO    MainThread:1212388 [wandb_run.py:_atexit_cleanup():2494] got exitcode: 0
+2026-02-02 12:42:49,805 INFO    MainThread:1212388 [wandb_run.py:_restore():2476] restore
+2026-02-02 12:42:49,805 INFO    MainThread:1212388 [wandb_run.py:_restore():2482] restore done
+2026-02-02 12:42:50,515 INFO    MainThread:1212388 [wandb_run.py:_footer_sync_info():3871] logging synced files

wandb/run-20260202_064313-i4545kqj/run-i4545kqj.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e21e67c3d2de80457b1ae740def25c1cca64da32bc8a606ed980259d2aee2a
+size 1964255