Done

.gitignore

@@ -0,0 +1,165 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+huggingface/
+venv/
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

Dockerfile

@@ -0,0 +1,29 @@
+# Base image
+FROM python:3.10-slim
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set work directory
+WORKDIR /app
+
+# Copy requirements
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --upgrade pip && pip install -r requirements.txt
+
+# Copy the application code
+COPY . .
+
+# Expose the port Gradio runs on
+EXPOSE 7860
+
+# Run the Gradio app
+CMD ["python", "app.py"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Syed Mohib Uddin
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1,12 +1,2 @@
----
-title: AI Auditor
-emoji: 🦀
-colorFrom: pink
-colorTo: blue
-sdk: docker
-pinned: false
-license: mit
-short_description: AI auditor for smart contracts
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# ML-Auditor
+Smart Contract testing and auditing using ML

app.py

@@ -0,0 +1,142 @@
+# Install necessary packages first (uncomment if not already installed)
+# !pip install transformers datasets peft accelerate gradio
+
+from transformers import AutoTokenizer, AutoModelForCausalLM, TrainingArguments, Trainer, pipeline
+from peft import LoraConfig, get_peft_model, TaskType
+from datasets import load_dataset
+import gradio as gr
+
+# ================== MODEL TRAINING PART ==================
+
+# Load the dataset
+dataset = load_dataset("msc-smart-contract-auditing/audits-with-reasons", split="train")
+
+# Load model and tokenizer
+model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+model_dir = "./huggingface/hub"
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, cache_dir=model_dir)
+
+# Format example for instruction-tuned model
+def format_example(example):
+    return f"""
+### Instruction:
+Please audit the following smart contract and provide a recommendation.
+
+### Code:
+{example['code']}
+
+### Description:
+{example['description']}
+
+### Recommendation:
+{example['recommendation']}
+"""
+
+# Tokenization function
+def tokenize(example):
+    text = format_example(example)
+    tokenized = tokenizer(
+        text,
+        truncation=True,
+        padding="max_length",
+        max_length=512,
+        return_tensors="pt"
+    )
+    return {
+        "input_ids": tokenized["input_ids"][0],
+        "attention_mask": tokenized["attention_mask"][0],
+        "labels": tokenized["input_ids"][0],
+    }
+
+# Tokenize dataset
+tokenized_dataset = dataset.map(tokenize, batched=False, remove_columns=dataset.column_names)
+
+# Load model
+model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Apply LoRA
+lora_config = LoraConfig(
+    r=8,
+    lora_alpha=16,
+    target_modules=["q_proj", "v_proj"],
+    lora_dropout=0.1,
+    bias="none",
+    task_type=TaskType.CAUSAL_LM,
+)
+model = get_peft_model(model, lora_config)
+model.print_trainable_parameters()
+
+# Training config
+training_args = TrainingArguments(
+    output_dir="./audit-model",
+    per_device_train_batch_size=1,
+    gradient_accumulation_steps=8,
+    num_train_epochs=3,
+    learning_rate=5e-5,
+    logging_dir="./logs",
+    logging_steps=10,
+    save_steps=100,
+    save_total_limit=2,
+    report_to="none",
+    fp16=False,
+    remove_unused_columns=False,
+)
+
+# Trainer
+trainer = Trainer(
+    model=model,
+    args=training_args,
+    train_dataset=tokenized_dataset,
+    tokenizer=tokenizer
+)
+
+# Train
+trainer.train()
+
+# Save model
+trainer.save_model("./audit-model")
+tokenizer.save_pretrained("./audit-model")
+
+# ================== INFERENCE + GRADIO UI ==================
+
+# Load inference pipeline
+pipe = pipeline("text-generation", model="./audit-model", tokenizer="./audit-model")
+
+# Function to audit uploaded contract
+def audit_contract(file, description):
+    if file is None:
+        return "Please upload a Solidity contract file."
+    
+    # Read code
+    with open(file.name, "r") as f:
+        contract_code = f.read()
+
+    # Build prompt
+    prompt = f"""### Instruction:
+Please audit the following smart contract and provide a recommendation.
+
+### Code:
+{contract_code}
+
+### Description:
+{description}
+
+### Recommendation:
+"""
+
+    # Generate response
+    output = pipe(prompt, max_new_tokens=100)[0]["generated_text"]
+    return output
+
+# Gradio interface
+gr.Interface(
+    fn=audit_contract,
+    inputs=[
+        gr.File(label="Upload Smart Contract (.sol)"),
+        gr.Textbox(label="Contract Description", placeholder="E.g., This contract handles fund withdrawals...")
+    ],
+    outputs=gr.Textbox(label="Audit Recommendation"),
+    title="Smart Contract Auditor",
+    description="Upload a Solidity contract and get audit recommendations from the TinyLlama-powered model."
+).launch()

audit-model/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.12.0

audit-model/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

audit-model/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d033b586daf2a7319110bf104c08a9dfbef330c7508114de1b17b210971a51e2
+size 4517152

audit-model/checkpoint-900/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.12.0

audit-model/checkpoint-900/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

audit-model/checkpoint-900/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4c6f8de7780dabc7f654a09ca82c7ea1211489e30e9430c36d29e6dabe64cf
+size 4517152

audit-model/checkpoint-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedf44f55757566c97e5de360665f0d2743bc8297684273a5d376ac634019a35
+size 9085370

audit-model/checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a18bb82dce417c46eaccbf3fba32dec2caff0f32011c9040a8cdf814e396ea
+size 14244

audit-model/checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee90a154b01533f0c339534ce958394e611633b977afe8daa52834a1ad2ee838
+size 1064

audit-model/checkpoint-900/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

audit-model/checkpoint-900/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

audit-model/checkpoint-900/trainer_state.json

@@ -0,0 +1,663 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.912621359223301,
+  "eval_steps": 500,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032362459546925564,
+      "grad_norm": 11.313185691833496,
+      "learning_rate": 4.946062567421791e-05,
+      "loss": 4.4527,
+      "step": 10
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 10.617666244506836,
+      "learning_rate": 4.892125134843581e-05,
+      "loss": 3.9824,
+      "step": 20
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 19.003602981567383,
+      "learning_rate": 4.838187702265373e-05,
+      "loss": 3.6846,
+      "step": 30
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 18.550548553466797,
+      "learning_rate": 4.784250269687163e-05,
+      "loss": 2.351,
+      "step": 40
+    },
+    {
+      "epoch": 0.16181229773462782,
+      "grad_norm": 5.793719291687012,
+      "learning_rate": 4.730312837108954e-05,
+      "loss": 1.9381,
+      "step": 50
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 1.2957172393798828,
+      "learning_rate": 4.676375404530744e-05,
+      "loss": 1.3053,
+      "step": 60
+    },
+    {
+      "epoch": 0.22653721682847897,
+      "grad_norm": 0.6527612209320068,
+      "learning_rate": 4.622437971952535e-05,
+      "loss": 1.2609,
+      "step": 70
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.49805423617362976,
+      "learning_rate": 4.568500539374326e-05,
+      "loss": 1.0638,
+      "step": 80
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.4786827564239502,
+      "learning_rate": 4.514563106796117e-05,
+      "loss": 1.0933,
+      "step": 90
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.462676465511322,
+      "learning_rate": 4.460625674217908e-05,
+      "loss": 1.0909,
+      "step": 100
+    },
+    {
+      "epoch": 0.3559870550161812,
+      "grad_norm": 0.5132231116294861,
+      "learning_rate": 4.406688241639698e-05,
+      "loss": 1.1627,
+      "step": 110
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.7181512713432312,
+      "learning_rate": 4.352750809061489e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.42071197411003236,
+      "grad_norm": 0.6864293813705444,
+      "learning_rate": 4.29881337648328e-05,
+      "loss": 0.974,
+      "step": 130
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5242889523506165,
+      "learning_rate": 4.2448759439050706e-05,
+      "loss": 1.0578,
+      "step": 140
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.43969759345054626,
+      "learning_rate": 4.1909385113268615e-05,
+      "loss": 0.9293,
+      "step": 150
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.41124609112739563,
+      "learning_rate": 4.137001078748652e-05,
+      "loss": 0.7604,
+      "step": 160
+    },
+    {
+      "epoch": 0.5501618122977346,
+      "grad_norm": 0.4797498285770416,
+      "learning_rate": 4.0830636461704426e-05,
+      "loss": 1.0593,
+      "step": 170
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.395654559135437,
+      "learning_rate": 4.029126213592233e-05,
+      "loss": 0.8929,
+      "step": 180
+    },
+    {
+      "epoch": 0.6148867313915858,
+      "grad_norm": 0.5006524920463562,
+      "learning_rate": 3.9751887810140237e-05,
+      "loss": 0.9012,
+      "step": 190
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.43280333280563354,
+      "learning_rate": 3.9212513484358145e-05,
+      "loss": 1.0251,
+      "step": 200
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.39595478773117065,
+      "learning_rate": 3.8673139158576054e-05,
+      "loss": 0.9151,
+      "step": 210
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.44638216495513916,
+      "learning_rate": 3.813376483279396e-05,
+      "loss": 0.8771,
+      "step": 220
+    },
+    {
+      "epoch": 0.7443365695792881,
+      "grad_norm": 0.4109503924846649,
+      "learning_rate": 3.7594390507011865e-05,
+      "loss": 0.8672,
+      "step": 230
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.438164085149765,
+      "learning_rate": 3.7055016181229774e-05,
+      "loss": 0.8855,
+      "step": 240
+    },
+    {
+      "epoch": 0.8090614886731392,
+      "grad_norm": 0.4250308871269226,
+      "learning_rate": 3.651564185544768e-05,
+      "loss": 0.953,
+      "step": 250
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4708111882209778,
+      "learning_rate": 3.597626752966559e-05,
+      "loss": 0.9524,
+      "step": 260
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.3774057626724243,
+      "learning_rate": 3.54368932038835e-05,
+      "loss": 0.8109,
+      "step": 270
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.4693313539028168,
+      "learning_rate": 3.48975188781014e-05,
+      "loss": 0.9636,
+      "step": 280
+    },
+    {
+      "epoch": 0.9385113268608414,
+      "grad_norm": 0.46089011430740356,
+      "learning_rate": 3.435814455231931e-05,
+      "loss": 0.798,
+      "step": 290
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.38023099303245544,
+      "learning_rate": 3.3818770226537214e-05,
+      "loss": 0.9137,
+      "step": 300
+    },
+    {
+      "epoch": 1.0032362459546926,
+      "grad_norm": 0.40833815932273865,
+      "learning_rate": 3.327939590075513e-05,
+      "loss": 0.9773,
+      "step": 310
+    },
+    {
+      "epoch": 1.035598705501618,
+      "grad_norm": 0.3781765103340149,
+      "learning_rate": 3.274002157497303e-05,
+      "loss": 0.8947,
+      "step": 320
+    },
+    {
+      "epoch": 1.0679611650485437,
+      "grad_norm": 0.5418028235435486,
+      "learning_rate": 3.220064724919094e-05,
+      "loss": 0.8948,
+      "step": 330
+    },
+    {
+      "epoch": 1.1003236245954693,
+      "grad_norm": 0.4426631033420563,
+      "learning_rate": 3.166127292340885e-05,
+      "loss": 0.8272,
+      "step": 340
+    },
+    {
+      "epoch": 1.132686084142395,
+      "grad_norm": 0.462091863155365,
+      "learning_rate": 3.112189859762675e-05,
+      "loss": 0.8894,
+      "step": 350
+    },
+    {
+      "epoch": 1.1650485436893203,
+      "grad_norm": 0.3814358413219452,
+      "learning_rate": 3.058252427184466e-05,
+      "loss": 0.9384,
+      "step": 360
+    },
+    {
+      "epoch": 1.197411003236246,
+      "grad_norm": 0.4682667553424835,
+      "learning_rate": 3.0043149946062572e-05,
+      "loss": 0.9448,
+      "step": 370
+    },
+    {
+      "epoch": 1.2297734627831716,
+      "grad_norm": 0.44027456641197205,
+      "learning_rate": 2.9503775620280478e-05,
+      "loss": 0.882,
+      "step": 380
+    },
+    {
+      "epoch": 1.262135922330097,
+      "grad_norm": 0.33765849471092224,
+      "learning_rate": 2.8964401294498383e-05,
+      "loss": 0.8233,
+      "step": 390
+    },
+    {
+      "epoch": 1.2944983818770226,
+      "grad_norm": 0.41791439056396484,
+      "learning_rate": 2.842502696871629e-05,
+      "loss": 0.8723,
+      "step": 400
+    },
+    {
+      "epoch": 1.3268608414239482,
+      "grad_norm": 0.5905632376670837,
+      "learning_rate": 2.7885652642934197e-05,
+      "loss": 0.9817,
+      "step": 410
+    },
+    {
+      "epoch": 1.3592233009708738,
+      "grad_norm": 0.43448638916015625,
+      "learning_rate": 2.7346278317152106e-05,
+      "loss": 0.8918,
+      "step": 420
+    },
+    {
+      "epoch": 1.3915857605177995,
+      "grad_norm": 0.5770216584205627,
+      "learning_rate": 2.6806903991370015e-05,
+      "loss": 0.8559,
+      "step": 430
+    },
+    {
+      "epoch": 1.4239482200647249,
+      "grad_norm": 0.4389037787914276,
+      "learning_rate": 2.626752966558792e-05,
+      "loss": 0.8687,
+      "step": 440
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 0.5336058735847473,
+      "learning_rate": 2.5728155339805826e-05,
+      "loss": 0.9136,
+      "step": 450
+    },
+    {
+      "epoch": 1.4886731391585761,
+      "grad_norm": 0.5232294797897339,
+      "learning_rate": 2.518878101402373e-05,
+      "loss": 0.9582,
+      "step": 460
+    },
+    {
+      "epoch": 1.5210355987055015,
+      "grad_norm": 0.42966699600219727,
+      "learning_rate": 2.464940668824164e-05,
+      "loss": 0.9858,
+      "step": 470
+    },
+    {
+      "epoch": 1.5533980582524272,
+      "grad_norm": 0.5163992643356323,
+      "learning_rate": 2.411003236245955e-05,
+      "loss": 0.916,
+      "step": 480
+    },
+    {
+      "epoch": 1.5857605177993528,
+      "grad_norm": 0.47947341203689575,
+      "learning_rate": 2.3570658036677458e-05,
+      "loss": 0.8943,
+      "step": 490
+    },
+    {
+      "epoch": 1.6181229773462782,
+      "grad_norm": 0.42414242029190063,
+      "learning_rate": 2.3031283710895363e-05,
+      "loss": 0.901,
+      "step": 500
+    },
+    {
+      "epoch": 1.650485436893204,
+      "grad_norm": 0.4730052947998047,
+      "learning_rate": 2.249190938511327e-05,
+      "loss": 0.7823,
+      "step": 510
+    },
+    {
+      "epoch": 1.6828478964401294,
+      "grad_norm": 0.4772244393825531,
+      "learning_rate": 2.1952535059331178e-05,
+      "loss": 0.8497,
+      "step": 520
+    },
+    {
+      "epoch": 1.715210355987055,
+      "grad_norm": 0.5551290512084961,
+      "learning_rate": 2.1413160733549083e-05,
+      "loss": 0.8933,
+      "step": 530
+    },
+    {
+      "epoch": 1.7475728155339807,
+      "grad_norm": 0.4729432761669159,
+      "learning_rate": 2.0873786407766992e-05,
+      "loss": 0.9068,
+      "step": 540
+    },
+    {
+      "epoch": 1.779935275080906,
+      "grad_norm": 0.4728154242038727,
+      "learning_rate": 2.03344120819849e-05,
+      "loss": 0.8927,
+      "step": 550
+    },
+    {
+      "epoch": 1.8122977346278317,
+      "grad_norm": 0.468170166015625,
+      "learning_rate": 1.9795037756202806e-05,
+      "loss": 0.8018,
+      "step": 560
+    },
+    {
+      "epoch": 1.8446601941747574,
+      "grad_norm": 0.4387604892253876,
+      "learning_rate": 1.9255663430420712e-05,
+      "loss": 0.9354,
+      "step": 570
+    },
+    {
+      "epoch": 1.8770226537216828,
+      "grad_norm": 0.4523237943649292,
+      "learning_rate": 1.871628910463862e-05,
+      "loss": 0.97,
+      "step": 580
+    },
+    {
+      "epoch": 1.9093851132686084,
+      "grad_norm": 0.35041147470474243,
+      "learning_rate": 1.8176914778856526e-05,
+      "loss": 0.7746,
+      "step": 590
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.415325790643692,
+      "learning_rate": 1.763754045307443e-05,
+      "loss": 0.9324,
+      "step": 600
+    },
+    {
+      "epoch": 1.9741100323624594,
+      "grad_norm": 0.4483698010444641,
+      "learning_rate": 1.7098166127292344e-05,
+      "loss": 0.9117,
+      "step": 610
+    },
+    {
+      "epoch": 2.0064724919093853,
+      "grad_norm": 0.5569983720779419,
+      "learning_rate": 1.655879180151025e-05,
+      "loss": 0.7934,
+      "step": 620
+    },
+    {
+      "epoch": 2.0388349514563107,
+      "grad_norm": 0.5829730033874512,
+      "learning_rate": 1.6019417475728158e-05,
+      "loss": 0.8655,
+      "step": 630
+    },
+    {
+      "epoch": 2.071197411003236,
+      "grad_norm": 0.5252796411514282,
+      "learning_rate": 1.5480043149946064e-05,
+      "loss": 0.8609,
+      "step": 640
+    },
+    {
+      "epoch": 2.103559870550162,
+      "grad_norm": 0.48137661814689636,
+      "learning_rate": 1.4940668824163969e-05,
+      "loss": 0.8301,
+      "step": 650
+    },
+    {
+      "epoch": 2.1359223300970873,
+      "grad_norm": 0.5046062469482422,
+      "learning_rate": 1.440129449838188e-05,
+      "loss": 0.829,
+      "step": 660
+    },
+    {
+      "epoch": 2.168284789644013,
+      "grad_norm": 0.4735497236251831,
+      "learning_rate": 1.3861920172599785e-05,
+      "loss": 0.9003,
+      "step": 670
+    },
+    {
+      "epoch": 2.2006472491909386,
+      "grad_norm": 0.5104610323905945,
+      "learning_rate": 1.332254584681769e-05,
+      "loss": 0.9015,
+      "step": 680
+    },
+    {
+      "epoch": 2.233009708737864,
+      "grad_norm": 0.5547719597816467,
+      "learning_rate": 1.27831715210356e-05,
+      "loss": 0.9294,
+      "step": 690
+    },
+    {
+      "epoch": 2.26537216828479,
+      "grad_norm": 0.5612460970878601,
+      "learning_rate": 1.2243797195253506e-05,
+      "loss": 1.0278,
+      "step": 700
+    },
+    {
+      "epoch": 2.2977346278317152,
+      "grad_norm": 0.5788902044296265,
+      "learning_rate": 1.1704422869471414e-05,
+      "loss": 0.9947,
+      "step": 710
+    },
+    {
+      "epoch": 2.3300970873786406,
+      "grad_norm": 0.4961574375629425,
+      "learning_rate": 1.116504854368932e-05,
+      "loss": 0.8979,
+      "step": 720
+    },
+    {
+      "epoch": 2.3624595469255665,
+      "grad_norm": 0.475431889295578,
+      "learning_rate": 1.0625674217907228e-05,
+      "loss": 0.7793,
+      "step": 730
+    },
+    {
+      "epoch": 2.394822006472492,
+      "grad_norm": 0.44658321142196655,
+      "learning_rate": 1.0086299892125135e-05,
+      "loss": 0.8751,
+      "step": 740
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 0.4376422166824341,
+      "learning_rate": 9.546925566343042e-06,
+      "loss": 0.8552,
+      "step": 750
+    },
+    {
+      "epoch": 2.459546925566343,
+      "grad_norm": 0.49501657485961914,
+      "learning_rate": 9.00755124056095e-06,
+      "loss": 0.9324,
+      "step": 760
+    },
+    {
+      "epoch": 2.4919093851132685,
+      "grad_norm": 0.5048530697822571,
+      "learning_rate": 8.468176914778857e-06,
+      "loss": 0.9295,
+      "step": 770
+    },
+    {
+      "epoch": 2.524271844660194,
+      "grad_norm": 0.42359548807144165,
+      "learning_rate": 7.928802588996764e-06,
+      "loss": 0.7242,
+      "step": 780
+    },
+    {
+      "epoch": 2.55663430420712,
+      "grad_norm": 0.5107340812683105,
+      "learning_rate": 7.389428263214672e-06,
+      "loss": 0.8196,
+      "step": 790
+    },
+    {
+      "epoch": 2.588996763754045,
+      "grad_norm": 0.5559754967689514,
+      "learning_rate": 6.850053937432578e-06,
+      "loss": 0.8591,
+      "step": 800
+    },
+    {
+      "epoch": 2.6213592233009706,
+      "grad_norm": 0.6188119053840637,
+      "learning_rate": 6.310679611650486e-06,
+      "loss": 0.8992,
+      "step": 810
+    },
+    {
+      "epoch": 2.6537216828478964,
+      "grad_norm": 0.4786069691181183,
+      "learning_rate": 5.771305285868392e-06,
+      "loss": 0.8756,
+      "step": 820
+    },
+    {
+      "epoch": 2.686084142394822,
+      "grad_norm": 0.4293358623981476,
+      "learning_rate": 5.2319309600863e-06,
+      "loss": 0.7657,
+      "step": 830
+    },
+    {
+      "epoch": 2.7184466019417477,
+      "grad_norm": 0.5650451183319092,
+      "learning_rate": 4.6925566343042074e-06,
+      "loss": 0.8836,
+      "step": 840
+    },
+    {
+      "epoch": 2.750809061488673,
+      "grad_norm": 0.5144199728965759,
+      "learning_rate": 4.153182308522115e-06,
+      "loss": 0.9088,
+      "step": 850
+    },
+    {
+      "epoch": 2.783171521035599,
+      "grad_norm": 0.4247129261493683,
+      "learning_rate": 3.6138079827400217e-06,
+      "loss": 0.8326,
+      "step": 860
+    },
+    {
+      "epoch": 2.8155339805825244,
+      "grad_norm": 0.5197082161903381,
+      "learning_rate": 3.074433656957929e-06,
+      "loss": 0.9088,
+      "step": 870
+    },
+    {
+      "epoch": 2.8478964401294498,
+      "grad_norm": 0.5575164556503296,
+      "learning_rate": 2.535059331175836e-06,
+      "loss": 0.8786,
+      "step": 880
+    },
+    {
+      "epoch": 2.8802588996763756,
+      "grad_norm": 0.49595561623573303,
+      "learning_rate": 1.995685005393743e-06,
+      "loss": 0.8106,
+      "step": 890
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.5974913239479065,
+      "learning_rate": 1.4563106796116506e-06,
+      "loss": 0.9802,
+      "step": 900
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 927,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.29066728800256e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

audit-model/checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644c0428fb02cac178615829c2997bb8df92212208f0ad1949508909926dcc04
+size 5112

audit-model/checkpoint-927/README.md

@@ -0,0 +1,202 @@
+---
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+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 0.12.0

audit-model/checkpoint-927/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

audit-model/checkpoint-927/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d033b586daf2a7319110bf104c08a9dfbef330c7508114de1b17b210971a51e2
+size 4517152

audit-model/checkpoint-927/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfa2ce00f71638b29e5879250128fa6fb7a4a28f15ad7f7cd1dd63809fccb00
+size 9085370

audit-model/checkpoint-927/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3496cd2f876804a3137aaed890f2a03b91460a7697939915c950dcd989f11f67
+size 14244

audit-model/checkpoint-927/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a513404a883f83b0bc3719fda4769a722cfd4ece54fc322c4e3e78974f03b25f
+size 1064

audit-model/checkpoint-927/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

audit-model/checkpoint-927/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

audit-model/checkpoint-927/trainer_state.json

@@ -0,0 +1,677 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 927,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032362459546925564,
+      "grad_norm": 11.313185691833496,
+      "learning_rate": 4.946062567421791e-05,
+      "loss": 4.4527,
+      "step": 10
+    },
+    {
+      "epoch": 0.06472491909385113,
+      "grad_norm": 10.617666244506836,
+      "learning_rate": 4.892125134843581e-05,
+      "loss": 3.9824,
+      "step": 20
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "grad_norm": 19.003602981567383,
+      "learning_rate": 4.838187702265373e-05,
+      "loss": 3.6846,
+      "step": 30
+    },
+    {
+      "epoch": 0.12944983818770225,
+      "grad_norm": 18.550548553466797,
+      "learning_rate": 4.784250269687163e-05,
+      "loss": 2.351,
+      "step": 40
+    },
+    {
+      "epoch": 0.16181229773462782,
+      "grad_norm": 5.793719291687012,
+      "learning_rate": 4.730312837108954e-05,
+      "loss": 1.9381,
+      "step": 50
+    },
+    {
+      "epoch": 0.1941747572815534,
+      "grad_norm": 1.2957172393798828,
+      "learning_rate": 4.676375404530744e-05,
+      "loss": 1.3053,
+      "step": 60
+    },
+    {
+      "epoch": 0.22653721682847897,
+      "grad_norm": 0.6527612209320068,
+      "learning_rate": 4.622437971952535e-05,
+      "loss": 1.2609,
+      "step": 70
+    },
+    {
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.49805423617362976,
+      "learning_rate": 4.568500539374326e-05,
+      "loss": 1.0638,
+      "step": 80
+    },
+    {
+      "epoch": 0.2912621359223301,
+      "grad_norm": 0.4786827564239502,
+      "learning_rate": 4.514563106796117e-05,
+      "loss": 1.0933,
+      "step": 90
+    },
+    {
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.462676465511322,
+      "learning_rate": 4.460625674217908e-05,
+      "loss": 1.0909,
+      "step": 100
+    },
+    {
+      "epoch": 0.3559870550161812,
+      "grad_norm": 0.5132231116294861,
+      "learning_rate": 4.406688241639698e-05,
+      "loss": 1.1627,
+      "step": 110
+    },
+    {
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.7181512713432312,
+      "learning_rate": 4.352750809061489e-05,
+      "loss": 1.058,
+      "step": 120
+    },
+    {
+      "epoch": 0.42071197411003236,
+      "grad_norm": 0.6864293813705444,
+      "learning_rate": 4.29881337648328e-05,
+      "loss": 0.974,
+      "step": 130
+    },
+    {
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.5242889523506165,
+      "learning_rate": 4.2448759439050706e-05,
+      "loss": 1.0578,
+      "step": 140
+    },
+    {
+      "epoch": 0.4854368932038835,
+      "grad_norm": 0.43969759345054626,
+      "learning_rate": 4.1909385113268615e-05,
+      "loss": 0.9293,
+      "step": 150
+    },
+    {
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.41124609112739563,
+      "learning_rate": 4.137001078748652e-05,
+      "loss": 0.7604,
+      "step": 160
+    },
+    {
+      "epoch": 0.5501618122977346,
+      "grad_norm": 0.4797498285770416,
+      "learning_rate": 4.0830636461704426e-05,
+      "loss": 1.0593,
+      "step": 170
+    },
+    {
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.395654559135437,
+      "learning_rate": 4.029126213592233e-05,
+      "loss": 0.8929,
+      "step": 180
+    },
+    {
+      "epoch": 0.6148867313915858,
+      "grad_norm": 0.5006524920463562,
+      "learning_rate": 3.9751887810140237e-05,
+      "loss": 0.9012,
+      "step": 190
+    },
+    {
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.43280333280563354,
+      "learning_rate": 3.9212513484358145e-05,
+      "loss": 1.0251,
+      "step": 200
+    },
+    {
+      "epoch": 0.6796116504854369,
+      "grad_norm": 0.39595478773117065,
+      "learning_rate": 3.8673139158576054e-05,
+      "loss": 0.9151,
+      "step": 210
+    },
+    {
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.44638216495513916,
+      "learning_rate": 3.813376483279396e-05,
+      "loss": 0.8771,
+      "step": 220
+    },
+    {
+      "epoch": 0.7443365695792881,
+      "grad_norm": 0.4109503924846649,
+      "learning_rate": 3.7594390507011865e-05,
+      "loss": 0.8672,
+      "step": 230
+    },
+    {
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.438164085149765,
+      "learning_rate": 3.7055016181229774e-05,
+      "loss": 0.8855,
+      "step": 240
+    },
+    {
+      "epoch": 0.8090614886731392,
+      "grad_norm": 0.4250308871269226,
+      "learning_rate": 3.651564185544768e-05,
+      "loss": 0.953,
+      "step": 250
+    },
+    {
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.4708111882209778,
+      "learning_rate": 3.597626752966559e-05,
+      "loss": 0.9524,
+      "step": 260
+    },
+    {
+      "epoch": 0.8737864077669902,
+      "grad_norm": 0.3774057626724243,
+      "learning_rate": 3.54368932038835e-05,
+      "loss": 0.8109,
+      "step": 270
+    },
+    {
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.4693313539028168,
+      "learning_rate": 3.48975188781014e-05,
+      "loss": 0.9636,
+      "step": 280
+    },
+    {
+      "epoch": 0.9385113268608414,
+      "grad_norm": 0.46089011430740356,
+      "learning_rate": 3.435814455231931e-05,
+      "loss": 0.798,
+      "step": 290
+    },
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.38023099303245544,
+      "learning_rate": 3.3818770226537214e-05,
+      "loss": 0.9137,
+      "step": 300
+    },
+    {
+      "epoch": 1.0032362459546926,
+      "grad_norm": 0.40833815932273865,
+      "learning_rate": 3.327939590075513e-05,
+      "loss": 0.9773,
+      "step": 310
+    },
+    {
+      "epoch": 1.035598705501618,
+      "grad_norm": 0.3781765103340149,
+      "learning_rate": 3.274002157497303e-05,
+      "loss": 0.8947,
+      "step": 320
+    },
+    {
+      "epoch": 1.0679611650485437,
+      "grad_norm": 0.5418028235435486,
+      "learning_rate": 3.220064724919094e-05,
+      "loss": 0.8948,
+      "step": 330
+    },
+    {
+      "epoch": 1.1003236245954693,
+      "grad_norm": 0.4426631033420563,
+      "learning_rate": 3.166127292340885e-05,
+      "loss": 0.8272,
+      "step": 340
+    },
+    {
+      "epoch": 1.132686084142395,
+      "grad_norm": 0.462091863155365,
+      "learning_rate": 3.112189859762675e-05,
+      "loss": 0.8894,
+      "step": 350
+    },
+    {
+      "epoch": 1.1650485436893203,
+      "grad_norm": 0.3814358413219452,
+      "learning_rate": 3.058252427184466e-05,
+      "loss": 0.9384,
+      "step": 360
+    },
+    {
+      "epoch": 1.197411003236246,
+      "grad_norm": 0.4682667553424835,
+      "learning_rate": 3.0043149946062572e-05,
+      "loss": 0.9448,
+      "step": 370
+    },
+    {
+      "epoch": 1.2297734627831716,
+      "grad_norm": 0.44027456641197205,
+      "learning_rate": 2.9503775620280478e-05,
+      "loss": 0.882,
+      "step": 380
+    },
+    {
+      "epoch": 1.262135922330097,
+      "grad_norm": 0.33765849471092224,
+      "learning_rate": 2.8964401294498383e-05,
+      "loss": 0.8233,
+      "step": 390
+    },
+    {
+      "epoch": 1.2944983818770226,
+      "grad_norm": 0.41791439056396484,
+      "learning_rate": 2.842502696871629e-05,
+      "loss": 0.8723,
+      "step": 400
+    },
+    {
+      "epoch": 1.3268608414239482,
+      "grad_norm": 0.5905632376670837,
+      "learning_rate": 2.7885652642934197e-05,
+      "loss": 0.9817,
+      "step": 410
+    },
+    {
+      "epoch": 1.3592233009708738,
+      "grad_norm": 0.43448638916015625,
+      "learning_rate": 2.7346278317152106e-05,
+      "loss": 0.8918,
+      "step": 420
+    },
+    {
+      "epoch": 1.3915857605177995,
+      "grad_norm": 0.5770216584205627,
+      "learning_rate": 2.6806903991370015e-05,
+      "loss": 0.8559,
+      "step": 430
+    },
+    {
+      "epoch": 1.4239482200647249,
+      "grad_norm": 0.4389037787914276,
+      "learning_rate": 2.626752966558792e-05,
+      "loss": 0.8687,
+      "step": 440
+    },
+    {
+      "epoch": 1.4563106796116505,
+      "grad_norm": 0.5336058735847473,
+      "learning_rate": 2.5728155339805826e-05,
+      "loss": 0.9136,
+      "step": 450
+    },
+    {
+      "epoch": 1.4886731391585761,
+      "grad_norm": 0.5232294797897339,
+      "learning_rate": 2.518878101402373e-05,
+      "loss": 0.9582,
+      "step": 460
+    },
+    {
+      "epoch": 1.5210355987055015,
+      "grad_norm": 0.42966699600219727,
+      "learning_rate": 2.464940668824164e-05,
+      "loss": 0.9858,
+      "step": 470
+    },
+    {
+      "epoch": 1.5533980582524272,
+      "grad_norm": 0.5163992643356323,
+      "learning_rate": 2.411003236245955e-05,
+      "loss": 0.916,
+      "step": 480
+    },
+    {
+      "epoch": 1.5857605177993528,
+      "grad_norm": 0.47947341203689575,
+      "learning_rate": 2.3570658036677458e-05,
+      "loss": 0.8943,
+      "step": 490
+    },
+    {
+      "epoch": 1.6181229773462782,
+      "grad_norm": 0.42414242029190063,
+      "learning_rate": 2.3031283710895363e-05,
+      "loss": 0.901,
+      "step": 500
+    },
+    {
+      "epoch": 1.650485436893204,
+      "grad_norm": 0.4730052947998047,
+      "learning_rate": 2.249190938511327e-05,
+      "loss": 0.7823,
+      "step": 510
+    },
+    {
+      "epoch": 1.6828478964401294,
+      "grad_norm": 0.4772244393825531,
+      "learning_rate": 2.1952535059331178e-05,
+      "loss": 0.8497,
+      "step": 520
+    },
+    {
+      "epoch": 1.715210355987055,
+      "grad_norm": 0.5551290512084961,
+      "learning_rate": 2.1413160733549083e-05,
+      "loss": 0.8933,
+      "step": 530
+    },
+    {
+      "epoch": 1.7475728155339807,
+      "grad_norm": 0.4729432761669159,
+      "learning_rate": 2.0873786407766992e-05,
+      "loss": 0.9068,
+      "step": 540
+    },
+    {
+      "epoch": 1.779935275080906,
+      "grad_norm": 0.4728154242038727,
+      "learning_rate": 2.03344120819849e-05,
+      "loss": 0.8927,
+      "step": 550
+    },
+    {
+      "epoch": 1.8122977346278317,
+      "grad_norm": 0.468170166015625,
+      "learning_rate": 1.9795037756202806e-05,
+      "loss": 0.8018,
+      "step": 560
+    },
+    {
+      "epoch": 1.8446601941747574,
+      "grad_norm": 0.4387604892253876,
+      "learning_rate": 1.9255663430420712e-05,
+      "loss": 0.9354,
+      "step": 570
+    },
+    {
+      "epoch": 1.8770226537216828,
+      "grad_norm": 0.4523237943649292,
+      "learning_rate": 1.871628910463862e-05,
+      "loss": 0.97,
+      "step": 580
+    },
+    {
+      "epoch": 1.9093851132686084,
+      "grad_norm": 0.35041147470474243,
+      "learning_rate": 1.8176914778856526e-05,
+      "loss": 0.7746,
+      "step": 590
+    },
+    {
+      "epoch": 1.941747572815534,
+      "grad_norm": 0.415325790643692,
+      "learning_rate": 1.763754045307443e-05,
+      "loss": 0.9324,
+      "step": 600
+    },
+    {
+      "epoch": 1.9741100323624594,
+      "grad_norm": 0.4483698010444641,
+      "learning_rate": 1.7098166127292344e-05,
+      "loss": 0.9117,
+      "step": 610
+    },
+    {
+      "epoch": 2.0064724919093853,
+      "grad_norm": 0.5569983720779419,
+      "learning_rate": 1.655879180151025e-05,
+      "loss": 0.7934,
+      "step": 620
+    },
+    {
+      "epoch": 2.0388349514563107,
+      "grad_norm": 0.5829730033874512,
+      "learning_rate": 1.6019417475728158e-05,
+      "loss": 0.8655,
+      "step": 630
+    },
+    {
+      "epoch": 2.071197411003236,
+      "grad_norm": 0.5252796411514282,
+      "learning_rate": 1.5480043149946064e-05,
+      "loss": 0.8609,
+      "step": 640
+    },
+    {
+      "epoch": 2.103559870550162,
+      "grad_norm": 0.48137661814689636,
+      "learning_rate": 1.4940668824163969e-05,
+      "loss": 0.8301,
+      "step": 650
+    },
+    {
+      "epoch": 2.1359223300970873,
+      "grad_norm": 0.5046062469482422,
+      "learning_rate": 1.440129449838188e-05,
+      "loss": 0.829,
+      "step": 660
+    },
+    {
+      "epoch": 2.168284789644013,
+      "grad_norm": 0.4735497236251831,
+      "learning_rate": 1.3861920172599785e-05,
+      "loss": 0.9003,
+      "step": 670
+    },
+    {
+      "epoch": 2.2006472491909386,
+      "grad_norm": 0.5104610323905945,
+      "learning_rate": 1.332254584681769e-05,
+      "loss": 0.9015,
+      "step": 680
+    },
+    {
+      "epoch": 2.233009708737864,
+      "grad_norm": 0.5547719597816467,
+      "learning_rate": 1.27831715210356e-05,
+      "loss": 0.9294,
+      "step": 690
+    },
+    {
+      "epoch": 2.26537216828479,
+      "grad_norm": 0.5612460970878601,
+      "learning_rate": 1.2243797195253506e-05,
+      "loss": 1.0278,
+      "step": 700
+    },
+    {
+      "epoch": 2.2977346278317152,
+      "grad_norm": 0.5788902044296265,
+      "learning_rate": 1.1704422869471414e-05,
+      "loss": 0.9947,
+      "step": 710
+    },
+    {
+      "epoch": 2.3300970873786406,
+      "grad_norm": 0.4961574375629425,
+      "learning_rate": 1.116504854368932e-05,
+      "loss": 0.8979,
+      "step": 720
+    },
+    {
+      "epoch": 2.3624595469255665,
+      "grad_norm": 0.475431889295578,
+      "learning_rate": 1.0625674217907228e-05,
+      "loss": 0.7793,
+      "step": 730
+    },
+    {
+      "epoch": 2.394822006472492,
+      "grad_norm": 0.44658321142196655,
+      "learning_rate": 1.0086299892125135e-05,
+      "loss": 0.8751,
+      "step": 740
+    },
+    {
+      "epoch": 2.4271844660194173,
+      "grad_norm": 0.4376422166824341,
+      "learning_rate": 9.546925566343042e-06,
+      "loss": 0.8552,
+      "step": 750
+    },
+    {
+      "epoch": 2.459546925566343,
+      "grad_norm": 0.49501657485961914,
+      "learning_rate": 9.00755124056095e-06,
+      "loss": 0.9324,
+      "step": 760
+    },
+    {
+      "epoch": 2.4919093851132685,
+      "grad_norm": 0.5048530697822571,
+      "learning_rate": 8.468176914778857e-06,
+      "loss": 0.9295,
+      "step": 770
+    },
+    {
+      "epoch": 2.524271844660194,
+      "grad_norm": 0.42359548807144165,
+      "learning_rate": 7.928802588996764e-06,
+      "loss": 0.7242,
+      "step": 780
+    },
+    {
+      "epoch": 2.55663430420712,
+      "grad_norm": 0.5107340812683105,
+      "learning_rate": 7.389428263214672e-06,
+      "loss": 0.8196,
+      "step": 790
+    },
+    {
+      "epoch": 2.588996763754045,
+      "grad_norm": 0.5559754967689514,
+      "learning_rate": 6.850053937432578e-06,
+      "loss": 0.8591,
+      "step": 800
+    },
+    {
+      "epoch": 2.6213592233009706,
+      "grad_norm": 0.6188119053840637,
+      "learning_rate": 6.310679611650486e-06,
+      "loss": 0.8992,
+      "step": 810
+    },
+    {
+      "epoch": 2.6537216828478964,
+      "grad_norm": 0.4786069691181183,
+      "learning_rate": 5.771305285868392e-06,
+      "loss": 0.8756,
+      "step": 820
+    },
+    {
+      "epoch": 2.686084142394822,
+      "grad_norm": 0.4293358623981476,
+      "learning_rate": 5.2319309600863e-06,
+      "loss": 0.7657,
+      "step": 830
+    },
+    {
+      "epoch": 2.7184466019417477,
+      "grad_norm": 0.5650451183319092,
+      "learning_rate": 4.6925566343042074e-06,
+      "loss": 0.8836,
+      "step": 840
+    },
+    {
+      "epoch": 2.750809061488673,
+      "grad_norm": 0.5144199728965759,
+      "learning_rate": 4.153182308522115e-06,
+      "loss": 0.9088,
+      "step": 850
+    },
+    {
+      "epoch": 2.783171521035599,
+      "grad_norm": 0.4247129261493683,
+      "learning_rate": 3.6138079827400217e-06,
+      "loss": 0.8326,
+      "step": 860
+    },
+    {
+      "epoch": 2.8155339805825244,
+      "grad_norm": 0.5197082161903381,
+      "learning_rate": 3.074433656957929e-06,
+      "loss": 0.9088,
+      "step": 870
+    },
+    {
+      "epoch": 2.8478964401294498,
+      "grad_norm": 0.5575164556503296,
+      "learning_rate": 2.535059331175836e-06,
+      "loss": 0.8786,
+      "step": 880
+    },
+    {
+      "epoch": 2.8802588996763756,
+      "grad_norm": 0.49595561623573303,
+      "learning_rate": 1.995685005393743e-06,
+      "loss": 0.8106,
+      "step": 890
+    },
+    {
+      "epoch": 2.912621359223301,
+      "grad_norm": 0.5974913239479065,
+      "learning_rate": 1.4563106796116506e-06,
+      "loss": 0.9802,
+      "step": 900
+    },
+    {
+      "epoch": 2.9449838187702264,
+      "grad_norm": 0.4777052104473114,
+      "learning_rate": 9.169363538295577e-07,
+      "loss": 0.9028,
+      "step": 910
+    },
+    {
+      "epoch": 2.9773462783171523,
+      "grad_norm": 0.4917181730270386,
+      "learning_rate": 3.7756202804746497e-07,
+      "loss": 0.889,
+      "step": 920
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 927,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.359387306642637e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

audit-model/checkpoint-927/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644c0428fb02cac178615829c2997bb8df92212208f0ad1949508909926dcc04
+size 5112

audit-model/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

audit-model/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

audit-model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:644c0428fb02cac178615829c2997bb8df92212208f0ad1949508909926dcc04
+size 5112

requirements.txt

@@ -0,0 +1,71 @@
+accelerate==0.34.2
+aiohappyeyeballs==2.4.0
+aiohttp==3.10.5
+aiosignal==1.3.1
+attrs==24.2.0
+bitsandbytes==0.43.3
+certifi==2024.8.30
+charset-normalizer==3.3.2
+colorama==0.4.6
+datasets==3.0.0
+dill==0.3.8
+docstring_parser==0.16
+filelock==3.16.0
+frozenlist==1.4.1
+fsspec==2024.6.1
+huggingface-hub==0.24.7
+idna==3.10
+Jinja2==3.1.4
+joblib==1.4.2
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+multiprocess==0.70.16
+neat-python==0.92
+networkx==3.3
+numpy==2.1.1
+packaging==24.1
+pandas==2.2.2
+peft==0.12.0
+pillow==10.2.0
+psutil==6.0.0
+pyarrow==17.0.0
+pygame==2.6.0
+Pygments==2.18.0
+python-dateutil==2.9.0.post0
+pytz==2024.2
+PyYAML==6.0.2
+regex==2024.9.11
+requests==2.32.3
+rich==13.8.1
+safetensors==0.4.5
+scikit-learn==1.5.2
+scipy==1.14.1
+setuptools==75.1.0
+shtab==1.7.1
+six==1.16.0
+sympy==1.13.2
+threadpoolctl==3.5.0
+tokenizers==0.19.1
+torch==2.4.1+cu118
+torchaudio==2.4.1+cu118
+torchvision==0.19.1+cu118
+tqdm==4.66.5
+transformers==4.44.2
+trl==0.10.1
+typing_extensions==4.12.2
+tyro==0.8.10
+tzdata==2024.1
+unsloth==2024.8
+urllib3==2.2.3
+xxhash==3.5.0
+yarl==1.11.1
+streamlit
+python-dotenv
+PyPDF2
+langchain
+huggingface-hub
+faiss-cpu
+sentence-transformers==2.2.2

space.yaml

@@ -0,0 +1,3 @@
+title: FastAPI Space
+sdk: docker
+app_port: 7860