Delete 2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/.hydra/config.yaml

@@ -1,163 +0,0 @@
-name: train_llmbc_lowdim
-_target_: llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace
-obs_dim: ${task.obs_dim}
-action_dim: ${task.action_dim}
-task_name: ${task.name}
-exp_name: default
-model_name: ${llm.name}
-horizon: 1
-n_obs_steps: 1
-n_action_steps: 1
-n_latency_steps: 0
-past_action_visible: false
-llm_orig_expert_feedback: true
-llm_do_sample: false
-policy:
-  _target_: llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy
-  model:
-    _target_: llmbc.model.policy.policy_mlp.PolicyMLP
-    input_size: ${eval:'${n_obs_steps}*${obs_dim}'}
-    hidden_size:
-    - 256
-    - 256
-    output_size: ${eval:'${n_action_steps}*${action_dim}'}
-    activation: relu
-    n_obs_steps: ${n_obs_steps}
-    n_action_steps: ${n_action_steps}
-  obs_dim: ${obs_dim}
-  action_dim: ${action_dim}
-  llm_discriminator:
-    _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator
-    task_id: ${task_name}
-    llm_translator:
-      _target_: llmbc.translator.llm_translator.LLMTranslator
-      cfg: ${llm}
-      obs_dim: ${task.obs_dim}
-      action_dim: ${task.action_dim}
-      horizon: ${horizon}
-      n_obs_steps: ${n_obs_steps}
-      n_action_steps: ${n_action_steps}
-  loss_bc_weight: 1.0
-  loss_llm_weight: 0.001
-  horizon: ${horizon}
-  n_obs_steps: ${n_obs_steps}
-  n_action_steps: ${n_action_steps}
-  normalize_llm_loss: true
-dataloader:
-  batch_size: 16
-  num_workers: 0
-  shuffle: true
-  pin_memory: false
-  persistent_workers: false
-val_dataloader:
-  batch_size: 16
-  num_workers: 0
-  shuffle: true
-  pin_memory: false
-  persistent_workers: false
-optimizer:
-  _target_: torch.optim.AdamW
-  lr: 0.01
-  betas:
-  - 0.95
-  - 0.999
-  eps: 1.0e-08
-  weight_decay: 1.0e-06
-training:
-  device: cuda:0
-  seed: 46
-  debug: false
-  resume: false
-  lr_scheduler: cosine
-  lr_warmup_steps: 10
-  num_epochs: 50001
-  gradient_accumulate_every: 8
-  grad_norm_clip: 0.5
-  rollout_every: 250
-  checkpoint_every: 250
-  val_every: 1
-  sample_every: 250
-  sample_max_batch: 128
-  max_train_steps: null
-  max_val_steps: null
-  tqdm_interval_sec: 1.0
-logging:
-  project: ${task.name}-training-split-ablation
-  resume: true
-  mode: online
-  name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
-  tags:
-  - ${name}
-  - ${task_name}
-  - ${exp_name}
-  id: null
-  group: null
-checkpoint:
-  topk:
-    monitor_key: test_success_rate
-    mode: max
-    k: 5
-    format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt
-  save_last_ckpt: true
-  save_last_snapshot: false
-multi_run:
-  run_dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
-  wandb_name_base: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
-task:
-  name: box-close-v2
-  obs_dim: 9
-  action_dim: 4
-  env_runner:
-    _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner
-    env_name: llf-metaworld-box-close-v2
-    n_train: 10
-    n_test: 50
-    n_envs: 10
-    max_steps: 30
-    n_obs_steps: ${n_obs_steps}
-    n_action_steps: ${n_action_steps}
-    instruction_type: b
-    feedback_type:
-    - hp
-    - hn
-    - fp
-    visual: false
-    discount: 0.9
-  dataset:
-    _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
-    data_path: datasets/box-close-v2-split0.02.pt
-    data_path2: datasets/box-close-v2-split0.02.pt
-    horizon: ${horizon}
-    pad_before: ${eval:'${n_obs_steps}-1'}
-    pad_after: ${eval:'${n_action_steps}-1'}
-    obs_eef_target: true
-    use_manual_normalizer: false
-    val_ratio: 0.1
-    dummy_normalizer: true
-  instructor:
-    _target_: llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor
-llm:
-  name: HuggingFaceTB/SmolLM2-135M-Instruct
-  model_name: SmolLM2-135M-Instruct
-  config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
-  causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
-  use_quantization: false
-  use_joint_mlp_projector: true
-  llm_mode: ete-finetuned
-  finetune_mode: orig
-  checkpoint: data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400
-  max_length: 100
-  lora_config:
-    r: 32
-    lora_alpha: 64
-    lora_dropout: 0.05
-    bias: none
-    task_type: CAUSAL_LM
-  prompter:
-    _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
-    use_joint_mlp_projector: true
-  hydra:
-    job:
-      override_dirname: ${model_name}
-    run:
-      dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${model_name}

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/.hydra/hydra.yaml

@@ -1,157 +0,0 @@
-hydra:
-  run:
-    dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
-  sweep:
-    dir: data/outputs/${now:%Y.%m.%d}/${now:%H.%M.%S}_${name}_${task_name}
-    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:
-    - training.seed=46
-  job:
-    name: train_llmbc_lowdim_workspace
-    chdir: null
-    override_dirname: training.seed=46
-    id: ???
-    num: ???
-    config_name: train_llmbc_lowdim_workspace
-    env_set: {}
-    env_copy: []
-    config:
-      override_dirname:
-        kv_sep: '='
-        item_sep: ','
-        exclude_keys: []
-  runtime:
-    version: 1.2.0
-    version_base: '1.2'
-    cwd: /home/chyang/workspace/LLM-BC
-    config_sources:
-    - path: hydra.conf
-      schema: pkg
-      provider: hydra
-    - path: /home/chyang/workspace/LLM-BC/llmbc/config
-      schema: file
-      provider: main
-    - path: ''
-      schema: structured
-      provider: schema
-    output_dir: /home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2
-    choices:
-      llm: smollm2-135m-instruct
-      task: box-close-v2
-      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

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/.hydra/overrides.yaml

@@ -1 +0,0 @@
-- training.seed=46

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/checkpoints/epoch=18000-test_success_rate=0.640.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:11f18b8ad667ac753a7d7482f48e0978e9905b20ba16259673fdb78efa9db999
-size 862664

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/checkpoints/epoch=21500-test_success_rate=0.620.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:29753ef86cd07d7c9ff0152220e6350c7fecc32b7c88e85ca293ea8e04f58e07
-size 862664

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/checkpoints/epoch=23000-test_success_rate=0.620.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:deba9406917b8e2a55661b96ea0ed79ec5697c0b8e5798c6febc752992b77a2e
-size 862664

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/checkpoints/epoch=26500-test_success_rate=0.620.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:41b788cb85af24c5fb750b21e441eb2846f5ac52d4970a718cf5002a3af899be
-size 862664

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/checkpoints/epoch=26750-test_success_rate=0.620.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:53cbb5f750181eb7f80cdcf72f809a7e02a0a3cd0b9c7a7318656610badb5c6b
-size 862664

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/checkpoints/latest.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:86bf2da3b85b11600174cd7522ab62960a235e269a3210b0b0cf14f1c9603bfd
-size 862664

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/logs.json.txt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae9fe9f9c5fa9bc2783b2b976ef82780a51ace80b639ac533e294c65f25e38f1
-size 65580536

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/train_llmbc_lowdim_workspace.log

@@ -1,5 +0,0 @@
-[2025-12-08 11:28:02,616][datasets][INFO] - PyTorch version 2.2.2 available.
-[2025-12-08 11:28:02,617][datasets][INFO] - TensorFlow version 2.15.1 available.
-[2025-12-08 11:28:02,617][datasets][INFO] - JAX version 0.4.30 available.
-[2025-12-08 11:28:08,355][absl][INFO] - MUJOCO_GL=osmesa, attempting to import specified OpenGL backend.
-[2025-12-08 11:28:08,361][absl][INFO] - MuJoCo library version is: 2.3.7

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/debug-internal.log

@@ -1,17 +0,0 @@
-{"time":"2025-12-08T11:28:09.99431792+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
-{"time":"2025-12-08T11:28:09.994343994+08:00","level":"INFO","msg":"created symlink","path":"/home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug-core.log"}
-{"time":"2025-12-08T11:28:10.103611381+08:00","level":"INFO","msg":"created new stream","id":"rtrw2cf6"}
-{"time":"2025-12-08T11:28:10.103671071+08:00","level":"INFO","msg":"stream: started","id":"rtrw2cf6"}
-{"time":"2025-12-08T11:28:10.103718367+08:00","level":"INFO","msg":"sender: started","stream_id":"rtrw2cf6"}
-{"time":"2025-12-08T11:28:10.103718216+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-08T11:28:10.103699903+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-08T11:28:10.901817496+08:00","level":"INFO","msg":"Starting system monitor"}
-{"time":"2025-12-09T05:53:11.909759666+08:00","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/chyang25-national-taiwan-university/box-close-v2-training-split-ablation/rtrw2cf6/file_stream"}
-{"time":"2025-12-09T07:04:48.860835699+08:00","level":"INFO","msg":"stream: closing","id":"rtrw2cf6"}
-{"time":"2025-12-09T07:04:48.860855109+08:00","level":"INFO","msg":"Stopping system monitor"}
-{"time":"2025-12-09T07:04:48.861583943+08:00","level":"INFO","msg":"Stopped system monitor"}
-{"time":"2025-12-09T07:04:49.942924018+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
-{"time":"2025-12-09T07:04:50.232060405+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-09T07:04:50.232138009+08:00","level":"INFO","msg":"sender: closed","stream_id":"rtrw2cf6"}
-{"time":"2025-12-09T07:04:50.232133176+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-09T07:04:50.232289178+08:00","level":"INFO","msg":"stream: closed","id":"rtrw2cf6"}

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/debug.log

@@ -1,27 +0,0 @@
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Configure stats pid to 19985
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/workspace/LLM-BC/wandb/settings
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'llmbc/workspace/train_llmbc_lowdim_workspace.py', 'program_abspath': '/home/chyang/workspace/LLM-BC/llmbc/workspace/train_llmbc_lowdim_workspace.py', 'program': '/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_llmbc_lowdim_workspace.py'}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Applying login settings: {}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_init.py:_log_setup():533] Logging user logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug.log
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_init.py:_log_setup():534] Logging internal logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug-internal.log
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():619] calling init triggers
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
-config: {'name': 'train_llmbc_lowdim', '_target_': 'llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace', 'obs_dim': 9, 'action_dim': 4, 'task_name': 'box-close-v2', 'exp_name': 'default', 'model_name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'n_latency_steps': 0, 'past_action_visible': False, 'llm_orig_expert_feedback': True, 'llm_do_sample': False, 'policy': {'_target_': 'llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy', 'model': {'_target_': 'llmbc.model.policy.policy_mlp.PolicyMLP', 'input_size': 9, 'hidden_size': [256, 256], 'output_size': 4, 'activation': 'relu', 'n_obs_steps': 1, 'n_action_steps': 1}, 'obs_dim': 9, 'action_dim': 4, 'llm_discriminator': {'_target_': 'llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator', 'task_id': 'box-close-v2', 'llm_translator': {'_target_': 'llmbc.translator.llm_translator.LLMTranslator', 'cfg': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'use_quantization': False, 'use_joint_mlp_projector': True, 'llm_mode': 'ete-finetuned', 'finetune_mode': 'orig', 'checkpoint': 'data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400', 'max_length': 100, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.12.08/11.27.59_HuggingFaceTB/SmolLM2-135M-Instruct'}}}, 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1}}, 'loss_bc_weight': 1.0, 'loss_llm_weight': 0.001, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'normalize_llm_loss': True}, 'dataloader': {'batch_size': 16, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'val_dataloader': {'batch_size': 16, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'optimizer': {'_target_': 'torch.optim.AdamW', 'lr': 0.01, 'betas': [0.95, 0.999], 'eps': 1e-08, 'weight_decay': 1e-06}, 'training': {'device': 'cuda:0', 'seed': 46, 'debug': False, 'resume': False, 'lr_scheduler': 'cosine', 'lr_warmup_steps': 10, 'num_epochs': 50001, 'gradient_accumulate_every': 8, 'grad_norm_clip': 0.5, 'rollout_every': 250, 'checkpoint_every': 250, 'val_every': 1, 'sample_every': 250, 'sample_max_batch': 128, 'max_train_steps': None, 'max_val_steps': None, 'tqdm_interval_sec': 1.0}, 'logging': {'project': 'box-close-v2-training-split-ablation', 'resume': True, 'mode': 'online', 'name': '2025.12.08-11.28.08_train_llmbc_lowdim_box-close-v2', 'tags': ['train_llmbc_lowdim', 'box-close-v2', 'default'], 'id': None, 'group': None}, 'checkpoint': {'topk': {'monitor_key': 'test_success_rate', 'mode': 'max', 'k': 5, 'format_str': 'epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt'}, 'save_last_ckpt': True, 'save_last_snapshot': False}, 'multi_run': {'run_dir': 'data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2', 'wandb_name_base': '2025.12.08-11.28.08_train_llmbc_lowdim_box-close-v2'}, 'task': {'name': 'box-close-v2', 'obs_dim': 9, 'action_dim': 4, 'env_runner': {'_target_': 'llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner', 'env_name': 'llf-metaworld-box-close-v2', 'n_train': 10, 'n_test': 50, 'n_envs': 10, 'max_steps': 30, 'n_obs_steps': 1, 'n_action_steps': 1, 'instruction_type': 'b', 'feedback_type': ['hp', 'hn', 'fp'], 'visual': False, 'discount': 0.9}, 'dataset': {'_target_': 'llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset', 'data_path': 'datasets/box-close-v2-split0.02.pt', 'data_path2': 'datasets/box-close-v2-split0.02.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.1, 'dummy_normalizer': True}, 'instructor': {'_target_': 'llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor'}}, 'llm': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'use_quantization': False, 'use_joint_mlp_projector': True, 'llm_mode': 'ete-finetuned', 'finetune_mode': 'orig', 'checkpoint': 'data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400', 'max_length': 100, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.12.08/11.27.59_HuggingFaceTB/SmolLM2-135M-Instruct'}}}}
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():669] starting backend
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():673] sending inform_init request
-2025-12-08 11:28:09,991 INFO    MainThread:19985 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2025-12-08 11:28:09,991 INFO    MainThread:19985 [wandb_init.py:init():686] backend started and connected
-2025-12-08 11:28:10,003 INFO    MainThread:19985 [wandb_init.py:init():781] updated telemetry
-2025-12-08 11:28:10,078 INFO    MainThread:19985 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
-2025-12-08 11:28:10,896 INFO    MainThread:19985 [wandb_init.py:init():867] starting run threads in backend
-2025-12-08 11:28:11,310 INFO    MainThread:19985 [wandb_run.py:_console_start():2451] atexit reg
-2025-12-08 11:28:11,311 INFO    MainThread:19985 [wandb_run.py:_redirect():2299] redirect: wrap_raw
-2025-12-08 11:28:11,311 INFO    MainThread:19985 [wandb_run.py:_redirect():2364] Wrapping output streams.
-2025-12-08 11:28:11,311 INFO    MainThread:19985 [wandb_run.py:_redirect():2389] Redirects installed.
-2025-12-08 11:28:11,314 INFO    MainThread:19985 [wandb_init.py:init():911] run started, returning control to user process
-2025-12-08 11:28:11,315 INFO    MainThread:19985 [wandb_run.py:_config_callback():1389] config_cb None None {'output_dir': '/home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2'}
-2025-12-09 07:04:48,861 WARNING MsgRouterThr:19985 [router.py:message_loop():75] message_loop has been closed

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/files/config.yaml

@@ -1,271 +0,0 @@
-_target_:
-    value: llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace
-_wandb:
-    value:
-        cli_version: 0.18.6
-        m: []
-        python_version: 3.9.21
-        t:
-            "1":
-                - 1
-                - 2
-                - 3
-                - 5
-                - 11
-                - 12
-                - 41
-                - 49
-                - 50
-                - 51
-                - 53
-                - 55
-                - 71
-                - 83
-                - 95
-                - 98
-                - 100
-                - 105
-            "2":
-                - 1
-                - 2
-                - 3
-                - 5
-                - 11
-                - 12
-                - 41
-                - 49
-                - 50
-                - 51
-                - 53
-                - 55
-                - 71
-                - 83
-                - 95
-                - 98
-                - 100
-                - 105
-            "3":
-                - 13
-                - 15
-                - 16
-                - 23
-                - 55
-                - 61
-            "4": 3.9.21
-            "5": 0.18.6
-            "6": 4.47.1
-            "8":
-                - 5
-            "12": 0.18.6
-            "13": linux-x86_64
-action_dim:
-    value: 4
-checkpoint:
-    value:
-        save_last_ckpt: true
-        save_last_snapshot: false
-        topk:
-            format_str: epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt
-            k: 5
-            mode: max
-            monitor_key: test_success_rate
-dataloader:
-    value:
-        batch_size: 16
-        num_workers: 0
-        persistent_workers: false
-        pin_memory: false
-        shuffle: true
-exp_name:
-    value: default
-horizon:
-    value: 1
-llm:
-    value:
-        causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
-        checkpoint: data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400
-        config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
-        finetune_mode: orig
-        hydra:
-            job:
-                override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct
-            run:
-                dir: data/outputs/2025.12.08/11.27.59_HuggingFaceTB/SmolLM2-135M-Instruct
-        llm_mode: ete-finetuned
-        lora_config:
-            bias: none
-            lora_alpha: 64
-            lora_dropout: 0.05
-            r: 32
-            task_type: CAUSAL_LM
-        max_length: 100
-        model_name: SmolLM2-135M-Instruct
-        name: HuggingFaceTB/SmolLM2-135M-Instruct
-        prompter:
-            _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
-            use_joint_mlp_projector: true
-        use_joint_mlp_projector: true
-        use_quantization: false
-llm_do_sample:
-    value: false
-llm_orig_expert_feedback:
-    value: true
-logging:
-    value:
-        group: null
-        id: null
-        mode: online
-        name: 2025.12.08-11.28.08_train_llmbc_lowdim_box-close-v2
-        project: box-close-v2-training-split-ablation
-        resume: true
-        tags:
-            - train_llmbc_lowdim
-            - box-close-v2
-            - default
-model_name:
-    value: HuggingFaceTB/SmolLM2-135M-Instruct
-multi_run:
-    value:
-        run_dir: data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2
-        wandb_name_base: 2025.12.08-11.28.08_train_llmbc_lowdim_box-close-v2
-n_action_steps:
-    value: 1
-n_latency_steps:
-    value: 0
-n_obs_steps:
-    value: 1
-name:
-    value: train_llmbc_lowdim
-obs_dim:
-    value: 9
-optimizer:
-    value:
-        _target_: torch.optim.AdamW
-        betas:
-            - 0.95
-            - 0.999
-        eps: 1e-08
-        lr: 0.01
-        weight_decay: 1e-06
-output_dir:
-    value: /home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2
-past_action_visible:
-    value: false
-policy:
-    value:
-        _target_: llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy
-        action_dim: 4
-        horizon: 1
-        llm_discriminator:
-            _target_: llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator
-            llm_translator:
-                _target_: llmbc.translator.llm_translator.LLMTranslator
-                action_dim: 4
-                cfg:
-                    causal_lm_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM
-                    checkpoint: data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400
-                    config_target: llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig
-                    finetune_mode: orig
-                    hydra:
-                        job:
-                            override_dirname: HuggingFaceTB/SmolLM2-135M-Instruct
-                        run:
-                            dir: data/outputs/2025.12.08/11.27.59_HuggingFaceTB/SmolLM2-135M-Instruct
-                    llm_mode: ete-finetuned
-                    lora_config:
-                        bias: none
-                        lora_alpha: 64
-                        lora_dropout: 0.05
-                        r: 32
-                        task_type: CAUSAL_LM
-                    max_length: 100
-                    model_name: SmolLM2-135M-Instruct
-                    name: HuggingFaceTB/SmolLM2-135M-Instruct
-                    prompter:
-                        _target_: llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter
-                        use_joint_mlp_projector: true
-                    use_joint_mlp_projector: true
-                    use_quantization: false
-                horizon: 1
-                n_action_steps: 1
-                n_obs_steps: 1
-                obs_dim: 9
-            task_id: box-close-v2
-        loss_bc_weight: 1
-        loss_llm_weight: 0.001
-        model:
-            _target_: llmbc.model.policy.policy_mlp.PolicyMLP
-            activation: relu
-            hidden_size:
-                - 256
-                - 256
-            input_size: 9
-            n_action_steps: 1
-            n_obs_steps: 1
-            output_size: 4
-        n_action_steps: 1
-        n_obs_steps: 1
-        normalize_llm_loss: true
-        obs_dim: 9
-task:
-    value:
-        action_dim: 4
-        dataset:
-            _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
-            data_path: datasets/box-close-v2-split0.02.pt
-            data_path2: datasets/box-close-v2-split0.02.pt
-            dummy_normalizer: true
-            horizon: 1
-            obs_eef_target: true
-            pad_after: 0
-            pad_before: 0
-            use_manual_normalizer: false
-            val_ratio: 0.1
-        env_runner:
-            _target_: llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner
-            discount: 0.9
-            env_name: llf-metaworld-box-close-v2
-            feedback_type:
-                - hp
-                - hn
-                - fp
-            instruction_type: b
-            max_steps: 30
-            n_action_steps: 1
-            n_envs: 10
-            n_obs_steps: 1
-            n_test: 50
-            n_train: 10
-            visual: false
-        instructor:
-            _target_: llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor
-        name: box-close-v2
-        obs_dim: 9
-task_name:
-    value: box-close-v2
-training:
-    value:
-        checkpoint_every: 250
-        debug: false
-        device: cuda:0
-        grad_norm_clip: 0.5
-        gradient_accumulate_every: 8
-        lr_scheduler: cosine
-        lr_warmup_steps: 10
-        max_train_steps: null
-        max_val_steps: null
-        num_epochs: 50001
-        resume: false
-        rollout_every: 250
-        sample_every: 250
-        sample_max_batch: 128
-        seed: 46
-        tqdm_interval_sec: 1
-        val_every: 1
-val_dataloader:
-    value:
-        batch_size: 16
-        num_workers: 0
-        persistent_workers: false
-        pin_memory: false
-        shuffle: true

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/files/output.log

@@ -1,3 +0,0 @@
-Eval MetaworldLowdimRunner 1/6:   0%|                                                                                                                              | 0/30 [00:00<?, ?it/s]/home/chyang/workspace/LLM-BC/llmbc/common/llfbench_util.py:39: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:275.)
-  obs = torch.tensor(obs, dtype=torch.float32).unsqueeze(dim=0).to(device)
-                                                                                                                                                                                          

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/files/wandb-metadata.json

@@ -1,52 +0,0 @@
-{
-  "os": "Linux-5.15.0-138-generic-x86_64-with-glibc2.31",
-  "python": "3.9.21",
-  "startedAt": "2025-12-08T03:28:09.991887Z",
-  "args": [
-    "training.seed=46"
-  ],
-  "program": "/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_llmbc_lowdim_workspace.py",
-  "codePath": "llmbc/workspace/train_llmbc_lowdim_workspace.py",
-  "git": {
-    "remote": "https://github.com/CHYang25/LLM-BC.git",
-    "commit": "59a021679dd0d2c0352cee6709283f473dc7cf69"
-  },
-  "email": "chris920325@gmail.com",
-  "root": "/home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2",
-  "host": "rllab1012",
-  "username": "chyang",
-  "executable": "/home/chyang/miniconda3/envs/llm-bc/bin/python3",
-  "codePathLocal": "llmbc/workspace/train_llmbc_lowdim_workspace.py",
-  "cpu_count": 10,
-  "cpu_count_logical": 20,
-  "gpu": "NVIDIA GeForce RTX 4070 Ti",
-  "gpu_count": 2,
-  "disk": {
-    "/": {
-      "total": "982820896768",
-      "used": "774051282944"
-    }
-  },
-  "memory": {
-    "total": "134733299712"
-  },
-  "cpu": {
-    "count": 10,
-    "countLogical": 20
-  },
-  "gpu_nvidia": [
-    {
-      "name": "NVIDIA GeForce RTX 4070 Ti",
-      "memoryTotal": "12878610432",
-      "cudaCores": 7680,
-      "architecture": "Ada"
-    },
-    {
-      "name": "NVIDIA GeForce RTX 4070 Ti",
-      "memoryTotal": "12878610432",
-      "cudaCores": 7680,
-      "architecture": "Ada"
-    }
-  ],
-  "cudaVersion": "12.9"
-}

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/files/wandb-summary.json

@@ -1 +0,0 @@
-{"train_loss":1.4745885816106844e-07,"global_step":300005,"lr":1.755532497149659e-11,"test/mean_score":5.599872730683683,"epoch":50000,"val_loss":0.0050710104405879974,"grad_norm":4.450846972758882e-05,"_runtime":70598.868959903,"_step":300005,"_timestamp":1.765235088841392e+09,"_wandb":{"runtime":70598},"train_loss_llm":0.00026977062225341797,"train_action_mse_error":8.575035082003524e-08,"train/cumulative_reward":13.728138014246534,"test/success_rate":0.54,"train_loss_bc":8.999647604923666e-08,"train/success_rate":0.6,"train/mean_score":5.2624352748384275,"test/cumulative_reward":11.966684356272252}

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug-core.log

@@ -1,14 +0,0 @@
-{"time":"2025-12-08T11:28:08.688872167+08:00","level":"INFO","msg":"started logging, with flags","port-filename":"/tmp/tmpwugdyz8s/port-19985.txt","pid":19985,"debug":false,"disable-analytics":false}
-{"time":"2025-12-08T11:28:08.68889654+08:00","level":"INFO","msg":"FeatureState","shutdownOnParentExitEnabled":false}
-{"time":"2025-12-08T11:28:08.694265998+08:00","level":"INFO","msg":"Will exit if parent process dies.","ppid":19985}
-{"time":"2025-12-08T11:28:08.694205129+08:00","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":40237,"Zone":""}}
-{"time":"2025-12-08T11:28:08.88667094+08:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"127.0.0.1:53258"}
-{"time":"2025-12-08T11:28:09.99406677+08:00","level":"INFO","msg":"handleInformInit: received","streamId":"rtrw2cf6","id":"127.0.0.1:53258"}
-{"time":"2025-12-08T11:28:10.103681743+08:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"rtrw2cf6","id":"127.0.0.1:53258"}
-{"time":"2025-12-09T07:04:48.860788265+08:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"127.0.0.1:53258"}
-{"time":"2025-12-09T07:04:48.860862903+08:00","level":"INFO","msg":"server is shutting down"}
-{"time":"2025-12-09T07:04:48.86085774+08:00","level":"INFO","msg":"connection: Close: initiating connection closure","id":"127.0.0.1:53258"}
-{"time":"2025-12-09T07:04:48.860969071+08:00","level":"INFO","msg":"connection: Close: connection successfully closed","id":"127.0.0.1:53258"}
-{"time":"2025-12-09T07:04:50.232391112+08:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"127.0.0.1:53258"}
-{"time":"2025-12-09T07:04:50.232439945+08:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"127.0.0.1:53258"}
-{"time":"2025-12-09T07:04:50.232472192+08:00","level":"INFO","msg":"server is closed"}

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug-internal.log

@@ -1,17 +0,0 @@
-{"time":"2025-12-08T11:28:09.99431792+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
-{"time":"2025-12-08T11:28:09.994343994+08:00","level":"INFO","msg":"created symlink","path":"/home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug-core.log"}
-{"time":"2025-12-08T11:28:10.103611381+08:00","level":"INFO","msg":"created new stream","id":"rtrw2cf6"}
-{"time":"2025-12-08T11:28:10.103671071+08:00","level":"INFO","msg":"stream: started","id":"rtrw2cf6"}
-{"time":"2025-12-08T11:28:10.103718367+08:00","level":"INFO","msg":"sender: started","stream_id":"rtrw2cf6"}
-{"time":"2025-12-08T11:28:10.103718216+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-08T11:28:10.103699903+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-08T11:28:10.901817496+08:00","level":"INFO","msg":"Starting system monitor"}
-{"time":"2025-12-09T05:53:11.909759666+08:00","level":"INFO","msg":"api: retrying HTTP error","status":502,"url":"https://api.wandb.ai/files/chyang25-national-taiwan-university/box-close-v2-training-split-ablation/rtrw2cf6/file_stream"}
-{"time":"2025-12-09T07:04:48.860835699+08:00","level":"INFO","msg":"stream: closing","id":"rtrw2cf6"}
-{"time":"2025-12-09T07:04:48.860855109+08:00","level":"INFO","msg":"Stopping system monitor"}
-{"time":"2025-12-09T07:04:48.861583943+08:00","level":"INFO","msg":"Stopped system monitor"}
-{"time":"2025-12-09T07:04:49.942924018+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
-{"time":"2025-12-09T07:04:50.232060405+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-09T07:04:50.232138009+08:00","level":"INFO","msg":"sender: closed","stream_id":"rtrw2cf6"}
-{"time":"2025-12-09T07:04:50.232133176+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"rtrw2cf6"}}
-{"time":"2025-12-09T07:04:50.232289178+08:00","level":"INFO","msg":"stream: closed","id":"rtrw2cf6"}

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug.log

@@ -1,27 +0,0 @@
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Configure stats pid to 19985
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/workspace/LLM-BC/wandb/settings
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'llmbc/workspace/train_llmbc_lowdim_workspace.py', 'program_abspath': '/home/chyang/workspace/LLM-BC/llmbc/workspace/train_llmbc_lowdim_workspace.py', 'program': '/home/chyang/workspace/LLM-BC/./llmbc/workspace/train_llmbc_lowdim_workspace.py'}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_setup.py:_flush():79] Applying login settings: {}
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_init.py:_log_setup():533] Logging user logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug.log
-2025-12-08 11:28:09,987 INFO    MainThread:19985 [wandb_init.py:_log_setup():534] Logging internal logs to /home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/logs/debug-internal.log
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():619] calling init triggers
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
-config: {'name': 'train_llmbc_lowdim', '_target_': 'llmbc.workspace.train_llmbc_lowdim_workspace.TrainLLMBCLowdimWorkspace', 'obs_dim': 9, 'action_dim': 4, 'task_name': 'box-close-v2', 'exp_name': 'default', 'model_name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'n_latency_steps': 0, 'past_action_visible': False, 'llm_orig_expert_feedback': True, 'llm_do_sample': False, 'policy': {'_target_': 'llmbc.policy.llmbc_lowdim_policy.LLMBCLowdimPolicy', 'model': {'_target_': 'llmbc.model.policy.policy_mlp.PolicyMLP', 'input_size': 9, 'hidden_size': [256, 256], 'output_size': 4, 'activation': 'relu', 'n_obs_steps': 1, 'n_action_steps': 1}, 'obs_dim': 9, 'action_dim': 4, 'llm_discriminator': {'_target_': 'llmbc.discriminator.llm_ce_discriminator.LLMCEDiscriminator', 'task_id': 'box-close-v2', 'llm_translator': {'_target_': 'llmbc.translator.llm_translator.LLMTranslator', 'cfg': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'use_quantization': False, 'use_joint_mlp_projector': True, 'llm_mode': 'ete-finetuned', 'finetune_mode': 'orig', 'checkpoint': 'data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400', 'max_length': 100, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.12.08/11.27.59_HuggingFaceTB/SmolLM2-135M-Instruct'}}}, 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1}}, 'loss_bc_weight': 1.0, 'loss_llm_weight': 0.001, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'normalize_llm_loss': True}, 'dataloader': {'batch_size': 16, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'val_dataloader': {'batch_size': 16, 'num_workers': 0, 'shuffle': True, 'pin_memory': False, 'persistent_workers': False}, 'optimizer': {'_target_': 'torch.optim.AdamW', 'lr': 0.01, 'betas': [0.95, 0.999], 'eps': 1e-08, 'weight_decay': 1e-06}, 'training': {'device': 'cuda:0', 'seed': 46, 'debug': False, 'resume': False, 'lr_scheduler': 'cosine', 'lr_warmup_steps': 10, 'num_epochs': 50001, 'gradient_accumulate_every': 8, 'grad_norm_clip': 0.5, 'rollout_every': 250, 'checkpoint_every': 250, 'val_every': 1, 'sample_every': 250, 'sample_max_batch': 128, 'max_train_steps': None, 'max_val_steps': None, 'tqdm_interval_sec': 1.0}, 'logging': {'project': 'box-close-v2-training-split-ablation', 'resume': True, 'mode': 'online', 'name': '2025.12.08-11.28.08_train_llmbc_lowdim_box-close-v2', 'tags': ['train_llmbc_lowdim', 'box-close-v2', 'default'], 'id': None, 'group': None}, 'checkpoint': {'topk': {'monitor_key': 'test_success_rate', 'mode': 'max', 'k': 5, 'format_str': 'epoch={epoch:04d}-test_success_rate={test_success_rate:.3f}.ckpt'}, 'save_last_ckpt': True, 'save_last_snapshot': False}, 'multi_run': {'run_dir': 'data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2', 'wandb_name_base': '2025.12.08-11.28.08_train_llmbc_lowdim_box-close-v2'}, 'task': {'name': 'box-close-v2', 'obs_dim': 9, 'action_dim': 4, 'env_runner': {'_target_': 'llmbc.env_runner.metaworld_lowdim_runner.MetaworldLowdimRunner', 'env_name': 'llf-metaworld-box-close-v2', 'n_train': 10, 'n_test': 50, 'n_envs': 10, 'max_steps': 30, 'n_obs_steps': 1, 'n_action_steps': 1, 'instruction_type': 'b', 'feedback_type': ['hp', 'hn', 'fp'], 'visual': False, 'discount': 0.9}, 'dataset': {'_target_': 'llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset', 'data_path': 'datasets/box-close-v2-split0.02.pt', 'data_path2': 'datasets/box-close-v2-split0.02.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.1, 'dummy_normalizer': True}, 'instructor': {'_target_': 'llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor'}}, 'llm': {'name': 'HuggingFaceTB/SmolLM2-135M-Instruct', 'model_name': 'SmolLM2-135M-Instruct', 'config_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaConfig', 'causal_lm_target': 'llmbc.model.llm.llama_lowdim_model.LowdimLlamaForCausalLM', 'use_quantization': False, 'use_joint_mlp_projector': True, 'llm_mode': 'ete-finetuned', 'finetune_mode': 'orig', 'checkpoint': 'data/outputs/2025.10.07/20.08.11_train_llm_lowdim_box-close-v2/HuggingFaceTB/SmolLM2-135M-Instruct-finetuned-box-close-v2/checkpoint-2400', 'max_length': 100, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'prompter': {'_target_': 'llmbc.translator.prompter.smollm2_prompter.SmolLM2Prompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'HuggingFaceTB/SmolLM2-135M-Instruct'}, 'run': {'dir': 'data/outputs/2025.12.08/11.27.59_HuggingFaceTB/SmolLM2-135M-Instruct'}}}}
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():669] starting backend
-2025-12-08 11:28:09,988 INFO    MainThread:19985 [wandb_init.py:init():673] sending inform_init request
-2025-12-08 11:28:09,991 INFO    MainThread:19985 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2025-12-08 11:28:09,991 INFO    MainThread:19985 [wandb_init.py:init():686] backend started and connected
-2025-12-08 11:28:10,003 INFO    MainThread:19985 [wandb_init.py:init():781] updated telemetry
-2025-12-08 11:28:10,078 INFO    MainThread:19985 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
-2025-12-08 11:28:10,896 INFO    MainThread:19985 [wandb_init.py:init():867] starting run threads in backend
-2025-12-08 11:28:11,310 INFO    MainThread:19985 [wandb_run.py:_console_start():2451] atexit reg
-2025-12-08 11:28:11,311 INFO    MainThread:19985 [wandb_run.py:_redirect():2299] redirect: wrap_raw
-2025-12-08 11:28:11,311 INFO    MainThread:19985 [wandb_run.py:_redirect():2364] Wrapping output streams.
-2025-12-08 11:28:11,311 INFO    MainThread:19985 [wandb_run.py:_redirect():2389] Redirects installed.
-2025-12-08 11:28:11,314 INFO    MainThread:19985 [wandb_init.py:init():911] run started, returning control to user process
-2025-12-08 11:28:11,315 INFO    MainThread:19985 [wandb_run.py:_config_callback():1389] config_cb None None {'output_dir': '/home/chyang/workspace/LLM-BC/data/outputs/2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2'}
-2025-12-09 07:04:48,861 WARNING MsgRouterThr:19985 [router.py:message_loop():75] message_loop has been closed

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/run-20251208_112809-rtrw2cf6/run-rtrw2cf6.wandb

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:48a2a84398117807e1004ad343a002e184f6824c9891607b0f45209948f5b838
-size 312261931

2025.12.08/11.27.59_train_llmbc_lowdim_box-close-v2/wandb/wandb-resume.json

@@ -1 +0,0 @@
-{"run_id": "rtrw2cf6"}