Upload folder using huggingface_hub

.gitattributes

@@ -107,3 +107,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 2026.02.15/12.44.58_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 2026.02.15/12.44.58_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5890/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 2026.02.15/12.44.58_train_llm_lowdim_box-close-v2/wandb/run-20260215_124507-yy4t6x0o/run-yy4t6x0o.wandb filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/wandb/run-20260224_231158-zzc3dyq3/run-zzc3dyq3.wandb filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.25.46_train_llmbc_lowdim_box-close-v2/logs.json.txt filter=lfs diff=lfs merge=lfs -text
+2026.02.24/23.25.46_train_llmbc_lowdim_box-close-v2/wandb/run-20260224_232605-x2fbtqtp/run-x2fbtqtp.wandb filter=lfs diff=lfs merge=lfs -text

2026.02.24/23.11.45_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: 64
+  per_device_eval_batch_size: 64
+  gradient_accumulation_steps: 2
+  optim: paged_adamw_32bit
+  num_train_epochs: 30
+  eval_strategy: steps
+  logging_steps: 1
+  warmup_steps: 500
+  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-o4-mini.pt
+    data_path2: datasets/box-close-v2-o4-mini.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: Qwen/Qwen2-0.5B-Instruct
+  model_name: Qwen2-0.5B-Instruct
+  config_target: llmbc.model.llm.qwen2_lowdim_model.LowdimQwen2Config
+  causal_lm_target: llmbc.model.llm.qwen2_lowdim_model.LowdimQwen2ForCausalLM
+  use_quantization: false
+  use_joint_mlp_projector: true
+  llm_mode: mlp-finetuned
+  finetune_mode: orig
+  checkpoint: data/outputs/2026.02.11/22.57.59_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.qwen2_prompter.Qwen2Prompter
+    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}

2026.02.24/23.11.45_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_o4-mini_qwen2-0.5b-instruct.yaml
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.2.0
+    version_base: '1.2'
+    cwd: /work/u1131674/LLM-BC
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /work/u1131674/LLM-BC/config/llm_backbone
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /work/u1131674/LLM-BC/data/outputs/2026.02.24/23.11.45_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

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/.hydra/overrides.yaml

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

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "action_dim": 4,
+  "architectures": [
+    "LowdimQwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2_lowdim",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "obs_dim": 9,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.47.1"
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d017c8218ec0a7d2387adad36baf50d313656ba4bd26bfe6047bbe44d9b89caa
+size 3267200

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c19e36c2c3dc187a3ead6069a84b69bc4811a169605d146a1a042edc5e9bc6aa
+size 1979428992

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23778b1f1b3c3251ee7e2314e47a786cca68cef9921e6711d0b9c6a196994780
+size 3958970426

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea7a6a9f9b1bf8fef6e006b9abdee0ea6dcd7eed8a3a81a3822b1f2b7bd1d0ec
+size 14244

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8b080bf4d9132bd5dc533200edda4097ce7f9c8657c1eeb94c749f81f025ca
+size 1064

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e352bbf79fe71f7b32e56f82547a77a248dd86186015e71486b983673d6022f3
+size 5944

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "action_dim": 4,
+  "architectures": [
+    "LowdimQwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2_lowdim",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "obs_dim": 9,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.47.1"
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1949e3f69f34544ade64904e380ebb265a3ccbfd4e57c32c86cb0f0a911aa28e
+size 3267200

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d6a1d4a74b31ee77e75ee23cddc7a44995fe4166910e5109621d01c7534e24
+size 1979428992

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83351d7f1eb26474d8d776225d64b29d1f22eb626172aea836baa21022ec9b9a
+size 3958970426

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0449e6e0cd007dc6ea5d34ae43ef270855a286ad44e4514c4010c473eee2b6
+size 14244

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72faacca39addc62cca7c330084846f9763fbda351a9eef5b29cb4490c2c9143
+size 1064

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-15000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e352bbf79fe71f7b32e56f82547a77a248dd86186015e71486b983673d6022f3
+size 5944

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "action_dim": 4,
+  "architectures": [
+    "LowdimQwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2_lowdim",
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "obs_dim": 9,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.47.1"
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254338976389ad6401d2b1be9eac419b3f1418e1aafdb9b4adb18707d9baaed4
+size 3267200

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:823d212d2b3cd2a22e533675fb1ecdfd36dff77973cf704172081f4ac19ce296
+size 1979428992

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae351c8f2a7ff438249f68d2c04e09a9889def6eb38897c96f5323d22df0ca9
+size 3958970426

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a35eab652c443dd1b6a68e6e80334a969846b068e7ba84d71b7415fc514dd748
+size 14244

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798050277260c8ea3fe4950e8dd7d05d50dbcb666d3589507b86e208056b7f4e
+size 1064

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfe42da0a4497e8b2b172c1f9f4ec423a46dc12907f4349c55025f670422ba9
+size 11418266

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-17670/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e352bbf79fe71f7b32e56f82547a77a248dd86186015e71486b983673d6022f3
+size 5944

2026.02.24/23.11.45_train_llm_lowdim_box-close-v2/Qwen/Qwen2-0.5B-Instruct-finetuned-box-close-v2/checkpoint-5000/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}