Upload folder using huggingface_hub

.gitattributes

@@ -310,3 +310,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 2026.10.28/13.54.19_train_rbc_reward_model_FrankaKitchen-v1/logs.json.txt filter=lfs diff=lfs merge=lfs -text
 2026.10.28/13.54.19_train_rbc_reward_model_FrankaKitchen-v1/wandb/run-20261028_135422-ux76l2ws/run-ux76l2ws.wandb filter=lfs diff=lfs merge=lfs -text
 2026.11.07/11.47.11_train_llm_lowdim_box-close-v2/wandb/run-20261107_114716-n4c76l8i/run-n4c76l8i.wandb filter=lfs diff=lfs merge=lfs -text
+2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/run-d0nbcloa.wandb filter=lfs diff=lfs merge=lfs -text

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/.hydra/config.yaml

@@ -0,0 +1,115 @@
+name: train_llm_lowdim
+_target_: llmbc.workspace.train_llm_workspace.TrainLLMWorkspace
+obs_dim: ${task.obs_dim}
+action_dim: ${task.action_dim}
+horizon: 1
+n_obs_steps: 1
+n_action_steps: 1
+task_name: ${task.name}
+exp_name: train llm
+model_name: ${llm.name}
+use_quantization: ${llm.use_quantization}
+lora_config: ${llm.lora_config}
+dataset:
+  test_data_ratio: 0.01
+debug: false
+training:
+  seed: 42
+  per_device_train_batch_size: 128
+  per_device_eval_batch_size: 128
+  gradient_accumulation_steps: 1
+  optim: paged_adamw_32bit
+  num_train_epochs: 10
+  eval_strategy: steps
+  logging_steps: 1
+  warmup_steps: 100
+  logging_strategy: steps
+  learning_rate: 0.0001
+  fp16: false
+  bf16: true
+  tf32: true
+  group_by_length: true
+  report_to: wandb
+  save_steps: 5000
+  eval_steps: 10
+  use_joint_mlp_projector: ${llm.use_joint_mlp_projector}
+  joint_obs_action_mlp_lr: 0.0001
+trainer:
+  obs_dim: ${obs_dim}
+  action_dim: ${action_dim}
+  use_joint_mlp_projector: ${llm.use_joint_mlp_projector}
+  max_seq_length: ${llm.max_length}
+  dataset_text_field: text
+  packing: false
+logging:
+  project: llm_module_finetuning
+  resume: true
+  mode: online
+  name: ${now:%Y.%m.%d-%H.%M.%S}_${name}_${task_name}
+  tags:
+  - ${name}
+  - ${task_name}
+  - ${exp_name}
+  id: null
+  group: null
+multi_run:
+  run_dir: data/outputs/${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-general.pt
+    data_path2: datasets/box-close-v2.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: 0.05
+    dummy_normalizer: false
+  instructor:
+    _target_: llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor
+llm:
+  name: EleutherAI/pythia-70m-deduped
+  model_name: pythia-70m-deduped
+  config_target: llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXConfig
+  causal_lm_target: llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXForCausalLM
+  use_quantization: false
+  use_joint_mlp_projector: true
+  llm_mode: mlp-finetuned
+  finetune_mode: orig
+  checkpoint: data/outputs/2026.11.07/01.39.14_train_mlp_projector_box-close-v2/checkpoints/latest.ckpt
+  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.pythia_prompter.PythiaPrompter
+    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}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/.hydra/hydra.yaml

@@ -0,0 +1,154 @@
+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: []
+  job:
+    name: train
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: llmdp_llm_box-close-v2_pythia-70m-deduped.yaml
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.2.0
+    version_base: '1.2'
+    cwd: /tmp2/chyang/workspace/LLM-BC
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /tmp2/chyang/workspace/LLM-BC/config/llm_backbone
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2
+    choices:
+      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

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/.hydra/overrides.yaml

@@ -0,0 +1 @@
+[]

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "EleutherAI/pythia-70m-deduped",
+  "action_dim": 4,
+  "architectures": [
+    "LowdimGPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox_lowdim",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "obs_dim": 9,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.1"
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae112871608ab2395a9cca01436766ee032a3c57c11b684b78efe860912af5c8
+size 1081472

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87236be1a8b3a8cabda521a7af0bbf30c1c0c04c7f9e5965acb224a4862243f4
+size 282794968

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdc546fdd42cc6c0bf231fca087107091a072bda0ee20bac6a1218e4615d30d
+size 565619962

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1229178cd3fc53fbbeb2ace48b61cc7f5f11f85a2aa90404bd54a81f04d35cf2
+size 14244

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0afe93d00a35552cbf53efccf9952fb89964795a1fb9059b72d318471d0ae56
+size 1064

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/tokenizer_config.json

@@ -0,0 +1,215 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d3d93aad5886ee976e89239e998b321c2d52aba15653244e69bb1f958d8c98
+size 5944

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "EleutherAI/pythia-70m-deduped",
+  "action_dim": 4,
+  "architectures": [
+    "LowdimGPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox_lowdim",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "obs_dim": 9,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.1"
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c7115b789a51a0e298e93e4b51aa0353d0cf990b006aecaec7ec2a07cfb12d
+size 1081472

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459bf1cf740a697de4472ec2d59372576f5338823ca41c64aec8ff3136c9f5ae
+size 282794968

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdc5632b7920e6d6a4f601fc3b8b5c73a8a77b8a261e67297814b70c3de824f0
+size 565619962

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3efd5afaf0c28c80d40a9eb842707cd94a44c7a47a687677b2160e97b49d52d
+size 14244

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c541a1306e2a80c04885085b048be43bff734699f71340ec300af5de1ee8ab68
+size 1064

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/tokenizer_config.json

@@ -0,0 +1,215 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/checkpoint-5890/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4d3d93aad5886ee976e89239e998b321c2d52aba15653244e69bb1f958d8c98
+size 5944

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "EleutherAI/pythia-70m-deduped",
+  "action_dim": 4,
+  "architectures": [
+    "LowdimGPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox_lowdim",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "obs_dim": 9,
+  "partial_rotary_factor": 0.25,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": true,
+  "use_joint_mlp_projector": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.47.1"
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459bf1cf740a697de4472ec2d59372576f5338823ca41c64aec8ff3136c9f5ae
+size 282794968

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/normalizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1cb28cf65a776a736481b2a05aa3c4cf0d796a0ec84eaa0b9e4aa06bdc79aa
+size 4514

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/train.log

@@ -0,0 +1,11 @@
+[2026-11-07 09:50:49,853][numexpr.utils][INFO] - Note: NumExpr detected 24 cores but "NUMEXPR_MAX_THREADS" not set, so enforcing safe limit of 16.
+[2026-11-07 09:50:49,853][numexpr.utils][INFO] - NumExpr defaulting to 16 threads.
+[2026-11-07 09:50:52,057][datasets][INFO] - PyTorch version 2.2.2 available.
+[2026-11-07 09:50:52,057][datasets][INFO] - TensorFlow version 2.15.1 available.
+[2026-11-07 09:50:52,058][datasets][INFO] - JAX version 0.4.30 available.
+[2026-11-07 09:51:06,919][datasets.arrow_dataset][WARNING] - Setting TOKENIZERS_PARALLELISM=false for forked processes.
+[2026-11-07 09:51:18,882][datasets.arrow_dataset][WARNING] - Setting TOKENIZERS_PARALLELISM=false for forked processes.
+[2026-11-07 09:51:24,192][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -I/home/chyang/miniconda3/envs/llm-bc/include -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -fPIC -c /tmp/tmps1mulba1/test.c -o /tmp/tmps1mulba1/test.o
+[2026-11-07 09:51:24,237][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat /tmp/tmps1mulba1/test.o -laio -o /tmp/tmps1mulba1/a.out
+[2026-11-07 09:51:25,003][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat -Wno-unused-result -Wsign-compare -DNDEBUG -O2 -Wall -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -I/home/chyang/miniconda3/envs/llm-bc/include -fPIC -O2 -isystem /home/chyang/miniconda3/envs/llm-bc/include -fPIC -c /tmp/tmpejqhnraj/test.c -o /tmp/tmpejqhnraj/test.o
+[2026-11-07 09:51:25,047][root][INFO] - gcc -pthread -B /home/chyang/miniconda3/envs/llm-bc/compiler_compat /tmp/tmpejqhnraj/test.o -L/home/chyang/miniconda3/envs/llm-bc -L/home/chyang/miniconda3/envs/llm-bc/lib64 -lcufile -o /tmp/tmpejqhnraj/a.out

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/debug-internal.log

@@ -0,0 +1,17 @@
+{"time":"2026-11-07T09:50:53.592038827+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
+{"time":"2026-11-07T09:50:53.592065195+08:00","level":"INFO","msg":"created symlink","path":"/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug-core.log"}
+{"time":"2026-11-07T09:50:53.699007609+08:00","level":"INFO","msg":"created new stream","id":"d0nbcloa"}
+{"time":"2026-11-07T09:50:53.69905307+08:00","level":"INFO","msg":"stream: started","id":"d0nbcloa"}
+{"time":"2026-11-07T09:50:53.699072256+08:00","level":"INFO","msg":"sender: started","stream_id":"d0nbcloa"}
+{"time":"2026-11-07T09:50:53.699068072+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T09:50:53.69908682+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T09:50:54.426318415+08:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2026-11-07T10:26:08.400121893+08:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2026-11-07T10:26:08.400943972+08:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2026-11-07T10:26:09.400990261+08:00","level":"INFO","msg":"handler: operation stats","stats":{"operations":[{"desc":"saving job artifact","runtime_seconds":0.331823839},{"desc":"uploading config.yaml","runtime_seconds":0.089839805,"progress":"14.4KB/14.4KB"},{"desc":"uploading output.log","runtime_seconds":0.089825287,"progress":"990.8KB/990.8KB"}],"total_operations":3}}
+{"time":"2026-11-07T10:26:11.273318383+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-11-07T10:26:13.099047371+08:00","level":"INFO","msg":"stream: closing","id":"d0nbcloa"}
+{"time":"2026-11-07T10:26:13.099087573+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T10:26:13.099122038+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T10:26:13.099185666+08:00","level":"INFO","msg":"sender: closed","stream_id":"d0nbcloa"}
+{"time":"2026-11-07T10:26:13.099239802+08:00","level":"INFO","msg":"stream: closed","id":"d0nbcloa"}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/debug.log

@@ -0,0 +1,35 @@
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Configure stats pid to 147051
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Loading settings from /tmp2/chyang/workspace/LLM-BC/wandb/settings
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program_abspath': '/tmp2/chyang/workspace/LLM-BC/train.py', 'program': '/tmp2/chyang/workspace/LLM-BC/./train.py'}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Applying login settings: {}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_init.py:_log_setup():533] Logging user logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug.log
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_init.py:_log_setup():534] Logging internal logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug-internal.log
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_init.py:init():619] calling init triggers
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
+config: {'name': 'train_llm_lowdim', '_target_': 'llmbc.workspace.train_llm_workspace.TrainLLMWorkspace', 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'task_name': 'box-close-v2', 'exp_name': 'train llm', 'model_name': 'EleutherAI/pythia-70m-deduped', 'use_quantization': False, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'dataset': {'test_data_ratio': 0.01}, 'debug': False, 'training': {'seed': 42, 'per_device_train_batch_size': 128, 'per_device_eval_batch_size': 128, 'gradient_accumulation_steps': 1, 'optim': 'paged_adamw_32bit', 'num_train_epochs': 10, 'eval_strategy': 'steps', 'logging_steps': 1, 'warmup_steps': 100, 'logging_strategy': 'steps', 'learning_rate': 0.0001, 'fp16': False, 'bf16': True, 'tf32': True, 'group_by_length': True, 'report_to': 'wandb', 'save_steps': 5000, 'eval_steps': 10, 'use_joint_mlp_projector': True, 'joint_obs_action_mlp_lr': 0.0001}, 'trainer': {'obs_dim': 9, 'action_dim': 4, 'use_joint_mlp_projector': True, 'max_seq_length': 100, 'dataset_text_field': 'text', 'packing': False}, 'logging': {'project': 'llm_module_finetuning', 'resume': True, 'mode': 'online', 'name': '2026.11.07-09.50.49_train_llm_lowdim_box-close-v2', 'tags': ['train_llm_lowdim', 'box-close-v2', 'train llm'], 'id': None, 'group': None}, 'multi_run': {'run_dir': 'data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2', 'wandb_name_base': '2026.11.07-09.50.49_train_llm_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-general.pt', 'data_path2': 'datasets/box-close-v2.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}, 'instructor': {'_target_': 'llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor'}}, 'llm': {'name': 'EleutherAI/pythia-70m-deduped', 'model_name': 'pythia-70m-deduped', 'config_target': 'llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXConfig', 'causal_lm_target': 'llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXForCausalLM', 'use_quantization': False, 'use_joint_mlp_projector': True, 'llm_mode': 'mlp-finetuned', 'finetune_mode': 'orig', 'checkpoint': 'data/outputs/2026.11.07/01.39.14_train_mlp_projector_box-close-v2/checkpoints/latest.ckpt', '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.pythia_prompter.PythiaPrompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'EleutherAI/pythia-70m-deduped'}, 'run': {'dir': 'data/outputs/2026.11.07/09.50.49_EleutherAI/pythia-70m-deduped'}}}}
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [wandb_init.py:init():669] starting backend
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [wandb_init.py:init():673] sending inform_init request
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2026-11-07 09:50:53,589 INFO    MainThread:147051 [wandb_init.py:init():686] backend started and connected
+2026-11-07 09:50:53,593 INFO    MainThread:147051 [wandb_init.py:init():781] updated telemetry
+2026-11-07 09:50:53,613 INFO    MainThread:147051 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
+2026-11-07 09:50:54,423 INFO    MainThread:147051 [wandb_init.py:init():867] starting run threads in backend
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_console_start():2451] atexit reg
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_redirect():2299] redirect: wrap_raw
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_redirect():2364] Wrapping output streams.
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_redirect():2389] Redirects installed.
+2026-11-07 09:50:54,532 INFO    MainThread:147051 [wandb_init.py:init():911] run started, returning control to user process
+2026-11-07 09:51:34,173 INFO    MainThread:147051 [wandb_run.py:_config_callback():1389] config_cb None None {'obs_dim': 9, 'action_dim': 4, 'use_joint_mlp_projector': True, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['GPTNeoXForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': None, 'eos_token_id': 0, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'EleutherAI/pythia-70m-deduped', '_attn_implementation_autoset': True, 'transformers_version': '4.47.1', 'model_type': 'gpt_neox_lowdim', 'vocab_size': 50304, 'max_position_embeddings': 2048, 'hidden_size': 512, 'num_hidden_layers': 6, 'num_attention_heads': 8, 'intermediate_size': 2048, 'hidden_act': 'gelu', 'rotary_pct': 0.25, 'partial_rotary_factor': 0.25, 'rotary_emb_base': 10000, 'rope_theta': 10000, 'attention_dropout': 0.0, 'hidden_dropout': 0.0, 'classifier_dropout': 0.1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, 'use_cache': False, 'use_parallel_residual': True, 'rope_scaling': None, 'attention_bias': True, 'output_dir': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 128, 'per_device_eval_batch_size': 128, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 100, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/runs/Nov07_09-51-23_A6000', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': True, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 10, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'dataset_text_field': 'text', 'packing': False, 'max_seq_length': 100, 'dataset_num_proc': None, 'dataset_batch_size': 1000, 'model_init_kwargs': None, 'dataset_kwargs': {}, 'eval_packing': None, 'num_of_sequences': 1024, 'chars_per_token': '<CHARS_PER_TOKEN>', 'use_liger': False, 'joint_obs_action_mlp_lr': 0.0001, 'obs_mlp_lr': None, 'action_mlp_lr': None}
+2026-11-07 09:51:34,174 INFO    MainThread:147051 [wandb_config.py:__setitem__():154] config set model/num_parameters = 70696448 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a2091102fa0>>
+2026-11-07 09:51:34,174 INFO    MainThread:147051 [wandb_run.py:_config_callback():1389] config_cb model/num_parameters 70696448 None
+2026-11-07 10:26:08,398 INFO    MainThread:147051 [wandb_run.py:_finish():2146] finishing run b10902069-national-taiwan-university/llm_module_finetuning/d0nbcloa
+2026-11-07 10:26:08,398 INFO    MainThread:147051 [wandb_run.py:_atexit_cleanup():2414] got exitcode: 0
+2026-11-07 10:26:08,399 INFO    MainThread:147051 [wandb_run.py:_restore():2396] restore
+2026-11-07 10:26:08,399 INFO    MainThread:147051 [wandb_run.py:_restore():2402] restore done
+2026-11-07 10:26:13,092 INFO    MainThread:147051 [wandb_run.py:_footer_history_summary_info():3963] rendering history
+2026-11-07 10:26:13,094 INFO    MainThread:147051 [wandb_run.py:_footer_history_summary_info():3995] rendering summary
+2026-11-07 10:26:13,098 INFO    MainThread:147051 [wandb_run.py:_footer_sync_info():3922] logging synced files

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/files/config.yaml

@@ -0,0 +1,708 @@
+_attn_implementation_autoset:
+    value: true
+_name_or_path:
+    value: EleutherAI/pythia-70m-deduped
+_target_:
+    value: llmbc.workspace.train_llm_workspace.TrainLLMWorkspace
+_wandb:
+    value:
+        cli_version: 0.18.6
+        m:
+            - "1": eval/steps_per_second
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/global_step
+              "6":
+                - 3
+              "7": []
+            - "1": train/epoch
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/loss
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": eval/loss
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/learning_rate
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": train/grad_norm
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": eval/runtime
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+            - "1": eval/samples_per_second
+              "5": 2
+              "6":
+                - 1
+                - 3
+              "7": []
+        python_version: 3.9.25
+        t:
+            "1":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+                - 55
+                - 71
+                - 84
+                - 98
+                - 105
+            "2":
+                - 1
+                - 2
+                - 3
+                - 5
+                - 11
+                - 12
+                - 41
+                - 49
+                - 50
+                - 51
+                - 53
+                - 55
+                - 71
+                - 84
+                - 98
+                - 105
+            "3":
+                - 2
+                - 7
+                - 13
+                - 15
+                - 16
+                - 19
+                - 23
+                - 55
+                - 62
+                - 66
+            "4": 3.9.25
+            "5": 0.18.6
+            "6": 4.47.1
+            "8":
+                - 5
+            "9":
+                "1": transformers_trainer
+            "12": 0.18.6
+            "13": linux-x86_64
+accelerator_config:
+    value:
+        dispatch_batches: null
+        even_batches: true
+        gradient_accumulation_kwargs: null
+        non_blocking: false
+        split_batches: false
+        use_seedable_sampler: true
+action_dim:
+    value: 4
+action_mlp_lr:
+    value: null
+adafactor:
+    value: false
+adam_beta1:
+    value: 0.9
+adam_beta2:
+    value: 0.999
+adam_epsilon:
+    value: 1e-08
+add_cross_attention:
+    value: false
+architectures:
+    value:
+        - GPTNeoXForCausalLM
+attention_bias:
+    value: true
+attention_dropout:
+    value: 0
+auto_find_batch_size:
+    value: false
+average_tokens_across_devices:
+    value: false
+bad_words_ids:
+    value: null
+batch_eval_metrics:
+    value: false
+begin_suppress_tokens:
+    value: null
+bf16:
+    value: true
+bf16_full_eval:
+    value: false
+bos_token_id:
+    value: 0
+chars_per_token:
+    value: <CHARS_PER_TOKEN>
+chunk_size_feed_forward:
+    value: 0
+classifier_dropout:
+    value: 0.1
+cross_attention_hidden_size:
+    value: null
+data_seed:
+    value: null
+dataloader_drop_last:
+    value: false
+dataloader_num_workers:
+    value: 0
+dataloader_persistent_workers:
+    value: false
+dataloader_pin_memory:
+    value: true
+dataloader_prefetch_factor:
+    value: null
+dataset:
+    value:
+        test_data_ratio: 0.01
+dataset_batch_size:
+    value: 1000
+dataset_num_proc:
+    value: null
+dataset_text_field:
+    value: text
+ddp_backend:
+    value: null
+ddp_broadcast_buffers:
+    value: null
+ddp_bucket_cap_mb:
+    value: null
+ddp_find_unused_parameters:
+    value: null
+ddp_timeout:
+    value: 1800
+debug:
+    value: []
+decoder_start_token_id:
+    value: null
+deepspeed:
+    value: null
+disable_tqdm:
+    value: false
+dispatch_batches:
+    value: null
+diversity_penalty:
+    value: 0
+do_eval:
+    value: true
+do_predict:
+    value: false
+do_sample:
+    value: false
+do_train:
+    value: false
+early_stopping:
+    value: false
+encoder_no_repeat_ngram_size:
+    value: 0
+eos_token_id:
+    value: 0
+eval_accumulation_steps:
+    value: null
+eval_delay:
+    value: 0
+eval_do_concat_batches:
+    value: true
+eval_on_start:
+    value: false
+eval_packing:
+    value: null
+eval_steps:
+    value: 10
+eval_strategy:
+    value: steps
+eval_use_gather_object:
+    value: false
+evaluation_strategy:
+    value: null
+exp_name:
+    value: train llm
+exponential_decay_length_penalty:
+    value: null
+finetuning_task:
+    value: null
+forced_bos_token_id:
+    value: null
+forced_eos_token_id:
+    value: null
+fp16:
+    value: false
+fp16_backend:
+    value: auto
+fp16_full_eval:
+    value: false
+fp16_opt_level:
+    value: O1
+fsdp:
+    value: []
+fsdp_config:
+    value:
+        min_num_params: 0
+        xla: false
+        xla_fsdp_grad_ckpt: false
+        xla_fsdp_v2: false
+fsdp_min_num_params:
+    value: 0
+fsdp_transformer_layer_cls_to_wrap:
+    value: null
+full_determinism:
+    value: false
+gradient_accumulation_steps:
+    value: 1
+gradient_checkpointing:
+    value: false
+gradient_checkpointing_kwargs:
+    value: null
+greater_is_better:
+    value: null
+group_by_length:
+    value: true
+half_precision_backend:
+    value: auto
+hidden_act:
+    value: gelu
+hidden_dropout:
+    value: 0
+hidden_size:
+    value: 512
+horizon:
+    value: 1
+hub_always_push:
+    value: false
+hub_model_id:
+    value: null
+hub_private_repo:
+    value: null
+hub_strategy:
+    value: every_save
+hub_token:
+    value: <HUB_TOKEN>
+id2label:
+    value:
+        "0": LABEL_0
+        "1": LABEL_1
+ignore_data_skip:
+    value: false
+include_for_metrics:
+    value: []
+include_inputs_for_metrics:
+    value: false
+include_num_input_tokens_seen:
+    value: false
+include_tokens_per_second:
+    value: false
+initializer_range:
+    value: 0.02
+intermediate_size:
+    value: 2048
+is_decoder:
+    value: false
+is_encoder_decoder:
+    value: false
+jit_mode_eval:
+    value: false
+joint_obs_action_mlp_lr:
+    value: 0.0001
+label_names:
+    value: null
+label_smoothing_factor:
+    value: 0
+label2id:
+    value:
+        LABEL_0: 0
+        LABEL_1: 1
+layer_norm_eps:
+    value: 1e-05
+learning_rate:
+    value: 0.0001
+length_column_name:
+    value: length
+length_penalty:
+    value: 1
+llm:
+    value:
+        causal_lm_target: llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXForCausalLM
+        checkpoint: data/outputs/2026.11.07/01.39.14_train_mlp_projector_box-close-v2/checkpoints/latest.ckpt
+        config_target: llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXConfig
+        finetune_mode: orig
+        hydra:
+            job:
+                override_dirname: EleutherAI/pythia-70m-deduped
+            run:
+                dir: data/outputs/2026.11.07/09.50.49_EleutherAI/pythia-70m-deduped
+        llm_mode: mlp-finetuned
+        lora_config:
+            bias: none
+            lora_alpha: 64
+            lora_dropout: 0.05
+            r: 32
+            task_type: CAUSAL_LM
+        max_length: 100
+        model_name: pythia-70m-deduped
+        name: EleutherAI/pythia-70m-deduped
+        prompter:
+            _target_: llmbc.translator.prompter.pythia_prompter.PythiaPrompter
+            use_joint_mlp_projector: true
+        use_joint_mlp_projector: true
+        use_quantization: false
+load_best_model_at_end:
+    value: false
+local_rank:
+    value: 0
+log_level:
+    value: passive
+log_level_replica:
+    value: warning
+log_on_each_node:
+    value: true
+logging:
+    value:
+        group: null
+        id: null
+        mode: online
+        name: 2026.11.07-09.50.49_train_llm_lowdim_box-close-v2
+        project: llm_module_finetuning
+        resume: true
+        tags:
+            - train_llm_lowdim
+            - box-close-v2
+            - train llm
+logging_dir:
+    value: /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/runs/Nov07_09-51-23_A6000
+logging_first_step:
+    value: false
+logging_nan_inf_filter:
+    value: true
+logging_steps:
+    value: 1
+logging_strategy:
+    value: steps
+lora_config:
+    value:
+        bias: none
+        lora_alpha: 64
+        lora_dropout: 0.05
+        r: 32
+        task_type: CAUSAL_LM
+lr_scheduler_type:
+    value: linear
+max_grad_norm:
+    value: 1
+max_length:
+    value: 20
+max_position_embeddings:
+    value: 2048
+max_seq_length:
+    value: 100
+max_steps:
+    value: -1
+metric_for_best_model:
+    value: null
+min_length:
+    value: 0
+model/num_parameters:
+    value: 70696448
+model_init_kwargs:
+    value: null
+model_name:
+    value: EleutherAI/pythia-70m-deduped
+model_type:
+    value: gpt_neox_lowdim
+mp_parameters:
+    value: ""
+multi_run:
+    value:
+        run_dir: data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2
+        wandb_name_base: 2026.11.07-09.50.49_train_llm_lowdim_box-close-v2
+n_action_steps:
+    value: 1
+n_obs_steps:
+    value: 1
+name:
+    value: train_llm_lowdim
+neftune_noise_alpha:
+    value: null
+no_cuda:
+    value: false
+no_repeat_ngram_size:
+    value: 0
+num_attention_heads:
+    value: 8
+num_beam_groups:
+    value: 1
+num_beams:
+    value: 1
+num_hidden_layers:
+    value: 6
+num_of_sequences:
+    value: 1024
+num_return_sequences:
+    value: 1
+num_train_epochs:
+    value: 10
+obs_dim:
+    value: 9
+obs_mlp_lr:
+    value: null
+optim:
+    value: paged_adamw_32bit
+optim_args:
+    value: null
+optim_target_modules:
+    value: null
+output_attentions:
+    value: false
+output_dir:
+    value: /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2
+output_hidden_states:
+    value: false
+output_scores:
+    value: false
+overwrite_output_dir:
+    value: false
+packing:
+    value: false
+pad_token_id:
+    value: null
+partial_rotary_factor:
+    value: 0.25
+past_index:
+    value: -1
+per_device_eval_batch_size:
+    value: 128
+per_device_train_batch_size:
+    value: 128
+per_gpu_eval_batch_size:
+    value: null
+per_gpu_train_batch_size:
+    value: null
+prediction_loss_only:
+    value: false
+prefix:
+    value: null
+problem_type:
+    value: null
+push_to_hub:
+    value: false
+push_to_hub_model_id:
+    value: null
+push_to_hub_organization:
+    value: null
+push_to_hub_token:
+    value: <PUSH_TO_HUB_TOKEN>
+ray_scope:
+    value: last
+remove_invalid_values:
+    value: false
+remove_unused_columns:
+    value: true
+repetition_penalty:
+    value: 1
+report_to:
+    value:
+        - wandb
+restore_callback_states_from_checkpoint:
+    value: false
+resume_from_checkpoint:
+    value: null
+return_dict:
+    value: true
+return_dict_in_generate:
+    value: false
+rope_scaling:
+    value: null
+rope_theta:
+    value: 10000
+rotary_emb_base:
+    value: 10000
+rotary_pct:
+    value: 0.25
+run_name:
+    value: /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2
+save_on_each_node:
+    value: false
+save_only_model:
+    value: false
+save_safetensors:
+    value: true
+save_steps:
+    value: 5000
+save_strategy:
+    value: steps
+save_total_limit:
+    value: null
+seed:
+    value: 42
+sep_token_id:
+    value: null
+skip_memory_metrics:
+    value: true
+split_batches:
+    value: null
+suppress_tokens:
+    value: null
+task:
+    value:
+        action_dim: 4
+        dataset:
+            _target_: llmbc.dataset.metaworld_lowdim_dataset.MetaworldLowdimDataset
+            data_path: datasets/box-close-v2-general.pt
+            data_path2: datasets/box-close-v2.pt
+            dummy_normalizer: false
+            horizon: 1
+            obs_eef_target: true
+            pad_after: 0
+            pad_before: 0
+            use_manual_normalizer: false
+            val_ratio: 0.05
+        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
+task_specific_params:
+    value: null
+temperature:
+    value: 1
+tf_legacy_loss:
+    value: false
+tf32:
+    value: true
+tie_encoder_decoder:
+    value: false
+tie_word_embeddings:
+    value: false
+tokenizer_class:
+    value: null
+top_k:
+    value: 50
+top_p:
+    value: 1
+torch_compile:
+    value: false
+torch_compile_backend:
+    value: null
+torch_compile_mode:
+    value: null
+torch_dtype:
+    value: float16
+torch_empty_cache_steps:
+    value: null
+torchdynamo:
+    value: null
+torchscript:
+    value: false
+tpu_metrics_debug:
+    value: false
+tpu_num_cores:
+    value: null
+trainer:
+    value:
+        action_dim: 4
+        dataset_text_field: text
+        max_seq_length: 100
+        obs_dim: 9
+        packing: false
+        use_joint_mlp_projector: true
+training:
+    value:
+        bf16: true
+        eval_steps: 10
+        eval_strategy: steps
+        fp16: false
+        gradient_accumulation_steps: 1
+        group_by_length: true
+        joint_obs_action_mlp_lr: 0.0001
+        learning_rate: 0.0001
+        logging_steps: 1
+        logging_strategy: steps
+        num_train_epochs: 10
+        optim: paged_adamw_32bit
+        per_device_eval_batch_size: 128
+        per_device_train_batch_size: 128
+        report_to: wandb
+        save_steps: 5000
+        seed: 42
+        tf32: true
+        use_joint_mlp_projector: true
+        warmup_steps: 100
+transformers_version:
+    value: 4.47.1
+typical_p:
+    value: 1
+use_bfloat16:
+    value: false
+use_cache:
+    value: false
+use_cpu:
+    value: false
+use_ipex:
+    value: false
+use_joint_mlp_projector:
+    value: true
+use_legacy_prediction_loop:
+    value: false
+use_liger:
+    value: false
+use_liger_kernel:
+    value: false
+use_mps_device:
+    value: false
+use_parallel_residual:
+    value: true
+use_quantization:
+    value: false
+vocab_size:
+    value: 50304
+warmup_ratio:
+    value: 0
+warmup_steps:
+    value: 100
+weight_decay:
+    value: 0

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/files/wandb-metadata.json

@@ -0,0 +1,55 @@
+{
+  "os": "Linux-6.8.0-138-generic-x86_64-with-glibc2.39",
+  "python": "3.9.25",
+  "startedAt": "2026-11-07T01:50:53.589118Z",
+  "args": [
+    "--config-path",
+    "config/llm_backbone",
+    "--config-name",
+    "llmdp_llm_box-close-v2_pythia-70m-deduped.yaml"
+  ],
+  "program": "/tmp2/chyang/workspace/LLM-BC/./train.py",
+  "codePath": "train.py",
+  "git": {
+    "remote": "https://github.com/CHYang25/LLM-BC.git",
+    "commit": "b986d300a4656b4611ccfc7f623631112b5de2e8"
+  },
+  "email": "chris920325@gmail.com",
+  "root": "/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2",
+  "host": "A6000",
+  "username": "chyang",
+  "executable": "/home/chyang/miniconda3/envs/llm-bc/bin/python3",
+  "codePathLocal": "train.py",
+  "cpu_count": 12,
+  "cpu_count_logical": 24,
+  "gpu": "NVIDIA RTX A6000",
+  "gpu_count": 2,
+  "disk": {
+    "/": {
+      "total": "982820896768",
+      "used": "680385912832"
+    }
+  },
+  "memory": {
+    "total": "134538604544"
+  },
+  "cpu": {
+    "count": 12,
+    "countLogical": 24
+  },
+  "gpu_nvidia": [
+    {
+      "name": "NVIDIA RTX A6000",
+      "memoryTotal": "51527024640",
+      "cudaCores": 10752,
+      "architecture": "Ampere"
+    },
+    {
+      "name": "NVIDIA RTX A6000",
+      "memoryTotal": "51527024640",
+      "cudaCores": 10752,
+      "architecture": "Ampere"
+    }
+  ],
+  "cudaVersion": "13.2"
+}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train_loss":0.7388594108394937,"_wandb":{"runtime":2114},"train/grad_norm":63.07209014892578,"train/epoch":10,"eval/loss":0.623070478439331,"_runtime":2114.809156464,"total_flos":2.496428183808e+16,"_timestamp":1.7940183683976324e+09,"eval/runtime":0.6163,"train_runtime":2074.2483,"train_steps_per_second":2.84,"eval/samples_per_second":1234.693,"train_samples_per_second":362.878,"train/learning_rate":0,"_step":6479,"train/global_step":5890,"eval/steps_per_second":9.735,"train/loss":0.4822}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug-core.log

@@ -0,0 +1,16 @@
+{"time":"2026-11-07T09:50:52.420254724+08:00","level":"INFO","msg":"started logging, with flags","port-filename":"/tmp/tmppc8lr5bp/port-147051.txt","pid":147051,"debug":false,"disable-analytics":false}
+{"time":"2026-11-07T09:50:52.420281805+08:00","level":"INFO","msg":"FeatureState","shutdownOnParentExitEnabled":false}
+{"time":"2026-11-07T09:50:52.425074755+08:00","level":"INFO","msg":"server is running","addr":{"IP":"127.0.0.1","Port":34143,"Zone":""}}
+{"time":"2026-11-07T09:50:52.425112764+08:00","level":"INFO","msg":"Will exit if parent process dies.","ppid":147051}
+{"time":"2026-11-07T09:50:52.617814049+08:00","level":"INFO","msg":"connection: ManageConnectionData: new connection created","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T09:50:53.591745404+08:00","level":"INFO","msg":"handleInformInit: received","streamId":"d0nbcloa","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T09:50:53.699058828+08:00","level":"INFO","msg":"handleInformInit: stream started","streamId":"d0nbcloa","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:13.09893658+08:00","level":"INFO","msg":"handleInformFinish: finish message received","streamId":"d0nbcloa","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:13.09925827+08:00","level":"INFO","msg":"handleInformFinish: stream closed","streamId":"d0nbcloa","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:14.15301606+08:00","level":"INFO","msg":"handleInformTeardown: server teardown initiated","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:14.153081485+08:00","level":"INFO","msg":"handleInformTeardown: server shutdown complete","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:14.153095932+08:00","level":"INFO","msg":"server is shutting down"}
+{"time":"2026-11-07T10:26:14.153139836+08:00","level":"INFO","msg":"connection: Close: initiating connection closure","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:14.153384475+08:00","level":"INFO","msg":"connection: Close: connection successfully closed","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:14.15339756+08:00","level":"INFO","msg":"connection: ManageConnectionData: connection closed","id":"127.0.0.1:42100"}
+{"time":"2026-11-07T10:26:14.153411084+08:00","level":"INFO","msg":"server is closed"}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug-internal.log

@@ -0,0 +1,17 @@
+{"time":"2026-11-07T09:50:53.592038827+08:00","level":"INFO","msg":"using version","core version":"0.18.6"}
+{"time":"2026-11-07T09:50:53.592065195+08:00","level":"INFO","msg":"created symlink","path":"/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug-core.log"}
+{"time":"2026-11-07T09:50:53.699007609+08:00","level":"INFO","msg":"created new stream","id":"d0nbcloa"}
+{"time":"2026-11-07T09:50:53.69905307+08:00","level":"INFO","msg":"stream: started","id":"d0nbcloa"}
+{"time":"2026-11-07T09:50:53.699072256+08:00","level":"INFO","msg":"sender: started","stream_id":"d0nbcloa"}
+{"time":"2026-11-07T09:50:53.699068072+08:00","level":"INFO","msg":"handler: started","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T09:50:53.69908682+08:00","level":"INFO","msg":"writer: Do: started","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T09:50:54.426318415+08:00","level":"INFO","msg":"Starting system monitor"}
+{"time":"2026-11-07T10:26:08.400121893+08:00","level":"INFO","msg":"Stopping system monitor"}
+{"time":"2026-11-07T10:26:08.400943972+08:00","level":"INFO","msg":"Stopped system monitor"}
+{"time":"2026-11-07T10:26:09.400990261+08:00","level":"INFO","msg":"handler: operation stats","stats":{"operations":[{"desc":"saving job artifact","runtime_seconds":0.331823839},{"desc":"uploading config.yaml","runtime_seconds":0.089839805,"progress":"14.4KB/14.4KB"},{"desc":"uploading output.log","runtime_seconds":0.089825287,"progress":"990.8KB/990.8KB"}],"total_operations":3}}
+{"time":"2026-11-07T10:26:11.273318383+08:00","level":"INFO","msg":"fileTransfer: Close: file transfer manager closed"}
+{"time":"2026-11-07T10:26:13.099047371+08:00","level":"INFO","msg":"stream: closing","id":"d0nbcloa"}
+{"time":"2026-11-07T10:26:13.099087573+08:00","level":"INFO","msg":"handler: closed","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T10:26:13.099122038+08:00","level":"INFO","msg":"writer: Close: closed","stream_id":{"value":"d0nbcloa"}}
+{"time":"2026-11-07T10:26:13.099185666+08:00","level":"INFO","msg":"sender: closed","stream_id":"d0nbcloa"}
+{"time":"2026-11-07T10:26:13.099239802+08:00","level":"INFO","msg":"stream: closed","id":"d0nbcloa"}

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug.log

@@ -0,0 +1,35 @@
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Current SDK version is 0.18.6
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Configure stats pid to 147051
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Loading settings from /home/chyang/.config/wandb/settings
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Loading settings from /tmp2/chyang/workspace/LLM-BC/wandb/settings
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Loading settings from environment variables: {}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Applying setup settings: {'mode': 'online', '_disable_service': None}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Inferring run settings from compute environment: {'program_relpath': 'train.py', 'program_abspath': '/tmp2/chyang/workspace/LLM-BC/train.py', 'program': '/tmp2/chyang/workspace/LLM-BC/./train.py'}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_setup.py:_flush():79] Applying login settings: {}
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_init.py:_log_setup():533] Logging user logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug.log
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_init.py:_log_setup():534] Logging internal logs to /tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/logs/debug-internal.log
+2026-11-07 09:50:53,587 INFO    MainThread:147051 [wandb_init.py:init():619] calling init triggers
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [wandb_init.py:init():626] wandb.init called with sweep_config: {}
+config: {'name': 'train_llm_lowdim', '_target_': 'llmbc.workspace.train_llm_workspace.TrainLLMWorkspace', 'obs_dim': 9, 'action_dim': 4, 'horizon': 1, 'n_obs_steps': 1, 'n_action_steps': 1, 'task_name': 'box-close-v2', 'exp_name': 'train llm', 'model_name': 'EleutherAI/pythia-70m-deduped', 'use_quantization': False, 'lora_config': {'r': 32, 'lora_alpha': 64, 'lora_dropout': 0.05, 'bias': 'none', 'task_type': 'CAUSAL_LM'}, 'dataset': {'test_data_ratio': 0.01}, 'debug': False, 'training': {'seed': 42, 'per_device_train_batch_size': 128, 'per_device_eval_batch_size': 128, 'gradient_accumulation_steps': 1, 'optim': 'paged_adamw_32bit', 'num_train_epochs': 10, 'eval_strategy': 'steps', 'logging_steps': 1, 'warmup_steps': 100, 'logging_strategy': 'steps', 'learning_rate': 0.0001, 'fp16': False, 'bf16': True, 'tf32': True, 'group_by_length': True, 'report_to': 'wandb', 'save_steps': 5000, 'eval_steps': 10, 'use_joint_mlp_projector': True, 'joint_obs_action_mlp_lr': 0.0001}, 'trainer': {'obs_dim': 9, 'action_dim': 4, 'use_joint_mlp_projector': True, 'max_seq_length': 100, 'dataset_text_field': 'text', 'packing': False}, 'logging': {'project': 'llm_module_finetuning', 'resume': True, 'mode': 'online', 'name': '2026.11.07-09.50.49_train_llm_lowdim_box-close-v2', 'tags': ['train_llm_lowdim', 'box-close-v2', 'train llm'], 'id': None, 'group': None}, 'multi_run': {'run_dir': 'data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2', 'wandb_name_base': '2026.11.07-09.50.49_train_llm_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-general.pt', 'data_path2': 'datasets/box-close-v2.pt', 'horizon': 1, 'pad_before': 0, 'pad_after': 0, 'obs_eef_target': True, 'use_manual_normalizer': False, 'val_ratio': 0.05, 'dummy_normalizer': False}, 'instructor': {'_target_': 'llmbc.translator.instructor.metaworld_instructor.box_close_v2_instructor.BoxCloseV2Instructor'}}, 'llm': {'name': 'EleutherAI/pythia-70m-deduped', 'model_name': 'pythia-70m-deduped', 'config_target': 'llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXConfig', 'causal_lm_target': 'llmbc.model.llm.gpt_neox_lowdim_model.LowdimGPTNeoXForCausalLM', 'use_quantization': False, 'use_joint_mlp_projector': True, 'llm_mode': 'mlp-finetuned', 'finetune_mode': 'orig', 'checkpoint': 'data/outputs/2026.11.07/01.39.14_train_mlp_projector_box-close-v2/checkpoints/latest.ckpt', '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.pythia_prompter.PythiaPrompter', 'use_joint_mlp_projector': True}, 'hydra': {'job': {'override_dirname': 'EleutherAI/pythia-70m-deduped'}, 'run': {'dir': 'data/outputs/2026.11.07/09.50.49_EleutherAI/pythia-70m-deduped'}}}}
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [wandb_init.py:init():669] starting backend
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [wandb_init.py:init():673] sending inform_init request
+2026-11-07 09:50:53,588 INFO    MainThread:147051 [backend.py:_multiprocessing_setup():104] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2026-11-07 09:50:53,589 INFO    MainThread:147051 [wandb_init.py:init():686] backend started and connected
+2026-11-07 09:50:53,593 INFO    MainThread:147051 [wandb_init.py:init():781] updated telemetry
+2026-11-07 09:50:53,613 INFO    MainThread:147051 [wandb_init.py:init():814] communicating run to backend with 90.0 second timeout
+2026-11-07 09:50:54,423 INFO    MainThread:147051 [wandb_init.py:init():867] starting run threads in backend
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_console_start():2451] atexit reg
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_redirect():2299] redirect: wrap_raw
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_redirect():2364] Wrapping output streams.
+2026-11-07 09:50:54,530 INFO    MainThread:147051 [wandb_run.py:_redirect():2389] Redirects installed.
+2026-11-07 09:50:54,532 INFO    MainThread:147051 [wandb_init.py:init():911] run started, returning control to user process
+2026-11-07 09:51:34,173 INFO    MainThread:147051 [wandb_run.py:_config_callback():1389] config_cb None None {'obs_dim': 9, 'action_dim': 4, 'use_joint_mlp_projector': True, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float16', 'use_bfloat16': False, 'tf_legacy_loss': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'chunk_size_feed_forward': 0, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'suppress_tokens': None, 'begin_suppress_tokens': None, 'architectures': ['GPTNeoXForCausalLM'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': None, 'eos_token_id': 0, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'EleutherAI/pythia-70m-deduped', '_attn_implementation_autoset': True, 'transformers_version': '4.47.1', 'model_type': 'gpt_neox_lowdim', 'vocab_size': 50304, 'max_position_embeddings': 2048, 'hidden_size': 512, 'num_hidden_layers': 6, 'num_attention_heads': 8, 'intermediate_size': 2048, 'hidden_act': 'gelu', 'rotary_pct': 0.25, 'partial_rotary_factor': 0.25, 'rotary_emb_base': 10000, 'rope_theta': 10000, 'attention_dropout': 0.0, 'hidden_dropout': 0.0, 'classifier_dropout': 0.1, 'initializer_range': 0.02, 'layer_norm_eps': 1e-05, 'use_cache': False, 'use_parallel_residual': True, 'rope_scaling': None, 'attention_bias': True, 'output_dir': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2', 'overwrite_output_dir': False, 'do_train': False, 'do_eval': True, 'do_predict': False, 'eval_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 128, 'per_device_eval_batch_size': 128, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'eval_delay': 0, 'torch_empty_cache_steps': None, 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 10, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'lr_scheduler_kwargs': {}, 'warmup_ratio': 0.0, 'warmup_steps': 100, 'log_level': 'passive', 'log_level_replica': 'warning', 'log_on_each_node': True, 'logging_dir': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2/runs/Nov07_09-51-23_A6000', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 5000, 'save_total_limit': None, 'save_safetensors': True, 'save_on_each_node': False, 'save_only_model': False, 'restore_callback_states_from_checkpoint': False, 'no_cuda': False, 'use_cpu': False, 'use_mps_device': False, 'seed': 42, 'data_seed': None, 'jit_mode_eval': False, 'use_ipex': False, 'bf16': True, 'fp16': False, 'fp16_opt_level': 'O1', 'half_precision_backend': 'auto', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': True, 'local_rank': 0, 'ddp_backend': None, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 10, 'dataloader_num_workers': 0, 'dataloader_prefetch_factor': None, 'past_index': -1, 'run_name': '/tmp2/chyang/workspace/LLM-BC/data/outputs/2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/EleutherAI/pythia-70m-deduped-finetuned-box-close-v2', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'fsdp': [], 'fsdp_min_num_params': 0, 'fsdp_config': {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, 'fsdp_transformer_layer_cls_to_wrap': None, 'accelerator_config': {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}, 'deepspeed': None, 'label_smoothing_factor': 0.0, 'optim': 'paged_adamw_32bit', 'optim_args': None, 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': ['wandb'], 'ddp_find_unused_parameters': None, 'ddp_bucket_cap_mb': None, 'ddp_broadcast_buffers': None, 'dataloader_pin_memory': True, 'dataloader_persistent_workers': False, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': False, 'resume_from_checkpoint': None, 'hub_model_id': None, 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': None, 'hub_always_push': False, 'gradient_checkpointing': False, 'gradient_checkpointing_kwargs': None, 'include_inputs_for_metrics': False, 'include_for_metrics': [], 'eval_do_concat_batches': True, 'fp16_backend': 'auto', 'evaluation_strategy': None, 'push_to_hub_model_id': None, 'push_to_hub_organization': None, 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', 'mp_parameters': '', 'auto_find_batch_size': False, 'full_determinism': False, 'torchdynamo': None, 'ray_scope': 'last', 'ddp_timeout': 1800, 'torch_compile': False, 'torch_compile_backend': None, 'torch_compile_mode': None, 'dispatch_batches': None, 'split_batches': None, 'include_tokens_per_second': False, 'include_num_input_tokens_seen': False, 'neftune_noise_alpha': None, 'optim_target_modules': None, 'batch_eval_metrics': False, 'eval_on_start': False, 'use_liger_kernel': False, 'eval_use_gather_object': False, 'average_tokens_across_devices': False, 'dataset_text_field': 'text', 'packing': False, 'max_seq_length': 100, 'dataset_num_proc': None, 'dataset_batch_size': 1000, 'model_init_kwargs': None, 'dataset_kwargs': {}, 'eval_packing': None, 'num_of_sequences': 1024, 'chars_per_token': '<CHARS_PER_TOKEN>', 'use_liger': False, 'joint_obs_action_mlp_lr': 0.0001, 'obs_mlp_lr': None, 'action_mlp_lr': None}
+2026-11-07 09:51:34,174 INFO    MainThread:147051 [wandb_config.py:__setitem__():154] config set model/num_parameters = 70696448 - <bound method Run._config_callback of <wandb.sdk.wandb_run.Run object at 0x7a2091102fa0>>
+2026-11-07 09:51:34,174 INFO    MainThread:147051 [wandb_run.py:_config_callback():1389] config_cb model/num_parameters 70696448 None
+2026-11-07 10:26:08,398 INFO    MainThread:147051 [wandb_run.py:_finish():2146] finishing run b10902069-national-taiwan-university/llm_module_finetuning/d0nbcloa
+2026-11-07 10:26:08,398 INFO    MainThread:147051 [wandb_run.py:_atexit_cleanup():2414] got exitcode: 0
+2026-11-07 10:26:08,399 INFO    MainThread:147051 [wandb_run.py:_restore():2396] restore
+2026-11-07 10:26:08,399 INFO    MainThread:147051 [wandb_run.py:_restore():2402] restore done
+2026-11-07 10:26:13,092 INFO    MainThread:147051 [wandb_run.py:_footer_history_summary_info():3963] rendering history
+2026-11-07 10:26:13,094 INFO    MainThread:147051 [wandb_run.py:_footer_history_summary_info():3995] rendering summary
+2026-11-07 10:26:13,098 INFO    MainThread:147051 [wandb_run.py:_footer_sync_info():3922] logging synced files

2026.11.07/09.50.49_train_llm_lowdim_box-close-v2/wandb/run-20261107_095053-d0nbcloa/run-d0nbcloa.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e3edff44108fef68ba0bba8f042c6c522bdf7f63dbc07b2bd6d297dc0553276
+size 14943834