Upload folder using huggingface_hub

.gitattributes

@@ -229,3 +229,12 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 2025.04.09/15.53.34_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-14000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 2025.04.09/15.53.34_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-14562/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 2025.04.09/15.53.34_train_llm_lowdim_blockpush_lowdim_seed/wandb/run-20250409_155335-vtnkssol/run-vtnkssol.wandb filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-14658/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-9000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/wandb/run-20250421_093901-kdsfeucx/run-kdsfeucx.wandb filter=lfs diff=lfs merge=lfs -text

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/.hydra/config.yaml

@@ -0,0 +1,116 @@
+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: 1
+  per_device_eval_batch_size: 1
+  gradient_accumulation_steps: 32
+  optim: paged_adamw_32bit
+  num_train_epochs: 3
+  eval_strategy: steps
+  logging_steps: 1
+  warmup_steps: 10
+  logging_strategy: steps
+  learning_rate: 5.0e-05
+  fp16: false
+  bf16: true
+  tf32: true
+  group_by_length: true
+  report_to: wandb
+  save_steps: 1000
+  eval_steps: 10
+  use_joint_mlp_projector: ${llm.use_joint_mlp_projector}
+  joint_obs_action_mlp_lr: 1.0e-06
+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: blockpush_lowdim_seed
+  obs_dim: 16
+  action_dim: 2
+  keypoint_dim: 2
+  obs_eef_target: true
+  env_runner:
+    _target_: llmbc.env_runner.blockpushing_lowdim_runner.BlockPushingLowdimRunner
+    env_name: llf-blockpushing-BlockPushMultimodal-v0
+    instruction_type: b
+    feedback_type:
+    - hp
+    - hn
+    - fp
+    visual: false
+    max_steps: 350
+    n_obs_steps: ${n_obs_steps}
+    n_action_steps: ${n_action_steps}
+  dataset:
+    _target_: llmbc.dataset.blockpush_lowdim_dataset.BlockPushLowdimDataset
+    data_path: datasets/BlockPushMultimodal-v0-general.pt
+    data_path2: datasets/BlockPushMultimodal-v0.pt
+    horizon: ${horizon}
+    pad_before: ${eval:'${n_obs_steps}-1'}
+    pad_after: ${eval:'${n_action_steps}-1'}
+    obs_eef_target: ${task.obs_eef_target}
+    use_manual_normalizer: false
+    seed: 42
+    val_ratio: 0.02
+    dummy_normalizer: false
+  instructor:
+    _target_: llmbc.translator.instructor.blockpush_instructor.BlockPushMultimodal_v0_instructor.BlockPushMultimodalV0Instructor
+llm:
+  name: Qwen/Qwen2-0.5B-Instruct
+  model_name: Qwen2-0.5B-Instruct
+  use_quantization: false
+  load_from_checkpoint: false
+  adaptor_path: /home/chyang/workspace/LLM-BC/data/outputs/2025.04.09/15.53.34_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-14562
+  use_orig_model: false
+  use_joint_mlp_projector: true
+  load_from_mlp_projector_checkpoint: true
+  mlp_projector_checkpoint_path: /home/chyang/workspace/LLM-BC/data/outputs/2025.04.20/16.50.02_train_mlp_projector_blockpush_lowdim_seed/checkpoints/latest.ckpt
+  max_length: 100
+  config_target: llmbc.model.llm.qwen2_lowdim_model.LowdimQwen2Config
+  causal_lm_target: llmbc.model.llm.qwen2_lowdim_model.LowdimQwen2ForCausalLM
+  lora_config:
+    r: 16
+    lora_alpha: 32
+    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}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/.hydra/hydra.yaml

@@ -0,0 +1,156 @@
+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_llm_workspace
+    chdir: null
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: train_llm_workspace
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.2.0
+    version_base: '1.2'
+    cwd: /home/chyang/workspace/LLM-BC
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/chyang/workspace/LLM-BC/llmbc/config
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /home/chyang/workspace/LLM-BC/data/outputs/2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed
+    choices:
+      llm: qwen-2-0.5b-instruct
+      task: BlockPushMultimodal-v0
+      hydra/env: default
+      hydra/callbacks: null
+      hydra/job_logging: default
+      hydra/hydra_logging: default
+      hydra/hydra_help: default
+      hydra/help: default
+      hydra/sweeper: basic
+      hydra/launcher: basic
+      hydra/output: default
+  verbose: false

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/.hydra/overrides.yaml

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

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:254048edc2a383e2f181b205ae0523d9aff1f285c616c36b1746f5e172d2ec6d
+size 35237104

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6f7a109d006108deeab42c34f30ff2ecd0a893d9249a0cf2215a4685502fb78
+size 35237104

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/added_tokens.json

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

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "action_dim": 2,
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "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": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ccd97cd9fa829329f834ffb83a6cbfe6dc49c1826315812d2a7625f0984b514
+size 3285184

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c02afd49955364ea22b159a382df29d2e94aa30729df96a9d8bf56d4d014772
+size 77153338

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301ce654de00e3d4781e43abb88fc593cf04d760d0f11fc436a64c6513dbcdc3
+size 14244

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2d60bb72b0c0a1afca673ac1f16a5fd40f24dc867a5696aeda8c45b1ced56f
+size 1064

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/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
+  }
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/tokenizer.json

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

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/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
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed0c811af16994cd40dd5048018038dea5d339fa52de63dfe4a4e30f62734df
+size 6008

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1f9184e723ff57c1a701218e755f47e2c82cac78c9a89ac7d89bb4c9576629
+size 35237104

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/added_tokens.json

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

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "action_dim": 2,
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "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": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bed0b4f82594db4bfd2c5a79a91194beaf17176b1f7f5b9e3279fd64eb5ee9ba
+size 3285184

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4155fea7637ad668e320e4288e4e25d4d88e04b85849ca94224328df10e4b8c8
+size 77153338

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0967e7342b73cc8d48d6c7fd516c0e8f3f6c9d016138bb7ba443fa4ebc7f3593
+size 14244

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f462e2a7559cc4be212e52a0c0a754b462be6a5610c7e342cbac42803c3b8300
+size 1064

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/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
+  }
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/tokenizer.json

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

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/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
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-11000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed0c811af16994cd40dd5048018038dea5d339fa52de63dfe4a4e30f62734df
+size 6008

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5454c5eb42acfa48b0c8836c010c6ec73e45fc784b116dcac11e7a20fb04419e
+size 35237104

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/added_tokens.json

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

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "Qwen/Qwen2-0.5B-Instruct",
+  "action_dim": 2,
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "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": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_joint_mlp_projector": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/mlp_projector.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c5154b75cb759ae0a844dc1342e0b55d3f5305efd03acc0ae79f055c406799
+size 3285184

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13bf6abdfd0f103b85908e8c78c60188d882b696495c52f0fc970b6fcb65bc3
+size 77153338

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e35de1aa4a7a0c70cf7926eb01cbfb1609e6a8b5d8df841aa1ac21e0e8be7a9
+size 14244

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73c5a16b59ac31281693ac5c6e06d8b5a19d91245e20285c7f08976f93c578d
+size 1064

2025.04.21/09.39.00_train_llm_lowdim_blockpush_lowdim_seed/Qwen/Qwen2-0.5B-Instruct-finetuned-blockpush_lowdim_seed/checkpoint-13000/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
+  }
+}