Add files using upload-large-folder tool

.hydra/hydra.yaml

@@ -0,0 +1,154 @@
+hydra:
+  run:
+    dir: ${oc.env:SCRATCH}/llm_negotiation/${now:%Y_%m}/${experiment.name}
+  sweep:
+    dir: multirun/${now:%Y-%m-%d}/${now:%H-%M-%S}
+    subdir: ${hydra.job.num}
+  launcher:
+    _target_: hydra._internal.core_plugins.basic_launcher.BasicLauncher
+  sweeper:
+    _target_: hydra._internal.core_plugins.basic_sweeper.BasicSweeper
+    max_batch_size: null
+    params: null
+  help:
+    app_name: ${hydra.job.name}
+    header: '${hydra.help.app_name} is powered by Hydra.
+
+      '
+    footer: 'Powered by Hydra (https://hydra.cc)
+
+      Use --hydra-help to view Hydra specific help
+
+      '
+    template: '${hydra.help.header}
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (group=option)
+
+
+      $APP_CONFIG_GROUPS
+
+
+      == Config ==
+
+      Override anything in the config (foo.bar=value)
+
+
+      $CONFIG
+
+
+      ${hydra.help.footer}
+
+      '
+  hydra_help:
+    template: 'Hydra (${hydra.runtime.version})
+
+      See https://hydra.cc for more info.
+
+
+      == Flags ==
+
+      $FLAGS_HELP
+
+
+      == Configuration groups ==
+
+      Compose your configuration from those groups (For example, append hydra/job_logging=disabled
+      to command line)
+
+
+      $HYDRA_CONFIG_GROUPS
+
+
+      Use ''--cfg hydra'' to Show the Hydra config.
+
+      '
+    hydra_help: ???
+  hydra_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][HYDRA] %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+    root:
+      level: INFO
+      handlers:
+      - console
+    loggers:
+      logging_example:
+        level: DEBUG
+    disable_existing_loggers: false
+  job_logging:
+    version: 1
+    formatters:
+      simple:
+        format: '[%(asctime)s][%(name)s][%(levelname)s] - %(message)s'
+    handlers:
+      console:
+        class: logging.StreamHandler
+        formatter: simple
+        stream: ext://sys.stdout
+      file:
+        class: logging.FileHandler
+        formatter: simple
+        filename: ${hydra.runtime.output_dir}/${hydra.job.name}.log
+    root:
+      level: INFO
+      handlers:
+      - console
+      - file
+    disable_existing_loggers: false
+  env: {}
+  mode: RUN
+  searchpath: []
+  callbacks: {}
+  output_subdir: .hydra
+  overrides:
+    hydra:
+    - hydra.mode=RUN
+    task: []
+  job:
+    name: generate_and_train
+    chdir: false
+    override_dirname: ''
+    id: ???
+    num: ???
+    config_name: ipd_prev_ad_align_qwen2.5_7b.yaml
+    env_set: {}
+    env_copy: []
+    config:
+      override_dirname:
+        kv_sep: '='
+        item_sep: ','
+        exclude_keys: []
+  runtime:
+    version: 1.3.2
+    version_base: '1.1'
+    cwd: /home/mila/m/mohammed.muqeeth/llm_negotiation
+    config_sources:
+    - path: hydra.conf
+      schema: pkg
+      provider: hydra
+    - path: /home/mila/m/mohammed.muqeeth/llm_negotiation/configs
+      schema: file
+      provider: main
+    - path: ''
+      schema: structured
+      provider: schema
+    output_dir: /network/scratch/m/mohammed.muqeeth/llm_negotiation/2025_08/ipd_prev_ad_align_qwen2.5_7b
+    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

.hydra/overrides.yaml

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

seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- transformers
+---
+
+# 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 0.16.0

seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/agent_adapter/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed_1000/Qwen/Qwen2.5-7B-Instruct/adapters/critic_adapter/adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

seed_1000/iteration_002/agent:Alice_rewards.csv

@@ -0,0 +1,64 @@
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,0,1,5,0,1,5,0,1
+1,5,0,1,5,0,1,5,0,1
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,1,1,1,1,1,1,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,0,1,5,0,1,5,0,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,1,1,1,1,1,1,1,1,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,5,1,1,1,1,1,1,1
+1,0,5,1,0,5,1,0,5,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,5,5,1,0,1,0,1,0,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,1,1,1,1,1,1,1,1,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,0,0,1,5,1,3,1,5,1
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3

seed_1000/iteration_002/agent:Bob_rewards.csv

@@ -0,0 +1,64 @@
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,5,1,0,5,1,0,5,1
+1,0,5,1,0,5,1,0,5,1
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,1,1,1,1,1,1,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,5,1,0,5,1,0,5,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,1,1,1,1,1,1,1,1,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,0,1,1,1,1,1,1,1
+1,5,0,1,5,0,1,5,0,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,0,0,1,5,1,5,1,5,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,1,1,1,1,1,1,1,1,1
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,5,1,5,1,5,1,5,1,5
+1,5,1,5,1,5,1,5,1,5
+1,3,1,3,1,3,1,3,1,3
+1,5,5,1,0,1,3,1,0,1
+1,3,1,3,1,3,1,3,1,3
+1,0,1,0,1,0,1,0,1,0
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3
+1,3,1,3,1,3,1,3,1,3