Add files using upload-large-folder tool

README.md

@@ -0,0 +1,114 @@
+---
+license: apache-2.0
+tags:
+  - code-generation
+  - differential-privacy
+  - continued-pretraining
+  - lora
+library_name: peft
+---
+
+# CodeDP-CPT Models V2
+
+LoRA adapters from continued pretraining (CPT) on code with and without differential privacy (DP-SGD), across 7 model families.
+
+## Models Included
+
+Each model is trained with multiple variants:
+- `base` / `base_attn` — CPT without DP (no privacy)
+- `dp3` / `dp3_attn` — DP-SGD with ε=3 (strong privacy)
+- `dp8` / `dp8_attn` — DP-SGD with ε=8 (moderate privacy)
+- `*_v2` — re-runs with improved hyperparameters (LR=5e-4, 5 epochs, min_lr_ratio=0.15)
+
+### Model Families
+
+| Family | Variants | Base Model |
+|--------|----------|-----------|
+| `starcoder2-7b` | base, dp3, dp8 | `bigcode/starcoder2-7b` |
+| `llama3-8b` | base, dp3, dp8, dp8_v2 | `meta-llama/Meta-Llama-3-8B` |
+| `llama3.1-8b` | dp3, dp8 | `meta-llama/Llama-3.1-8B` |
+| `llama3.2-3b` | base, dp3, dp8 | `meta-llama/Llama-3.2-3B` |
+| `qwen3-8b-base` | base, dp3, dp8, dp3_v2, dp8_v2 | `Qwen/Qwen3-8B-Base` |
+| `granite-4.0-h-tiny` | base_attn, dp3_attn, dp8_attn | `ibm-granite/granite-4.0-h-tiny-base` |
+| `qwen1.5-moe-a2.7b` | dp3_attn, base_attn_v2, dp3_attn_v2, dp8_attn_v2 | `Qwen/Qwen1.5-MoE-A2.7B` |
+
+Total: **24 LoRA adapters**
+
+## Training Data
+
+Trained on `melihcatal/codedp-cpt` — a code corpus with embedded canary secrets for DP auditing and membership inference evaluation.
+
+## Directory Structure
+
+Each variant directory contains:
+```
+<model>/<variant>/
+├── adapter/              # Final LoRA adapter (PEFT format)
+│   ├── adapter_config.json
+│   ├── adapter_model.safetensors
+│   └── README.md
+├── tokenizer/            # Tokenizer (may include added canary tokens)
+├── epochs/               # Per-epoch adapter checkpoints
+│   └── epoch_XXX/adapter/
+├── resolved_config.yaml  # Training configuration
+├── metrics.jsonl         # Training metrics per step
+├── train.log             # Training log
+├── canary_meta.json      # Canary metadata for MIA evaluation
+├── summary.json          # Run summary
+├── audit_results.json    # DP audit results
+└── audit_scores.npz      # DP audit raw scores
+```
+
+## Loading a Model
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+# Load base model
+base_model = AutoModelForCausalLM.from_pretrained(
+    "bigcode/starcoder2-7b",
+    dtype="bfloat16",
+)
+
+# Load tokenizer (important: uses trained tokenizer with canary tokens)
+tokenizer = AutoTokenizer.from_pretrained(
+    "melihcatal/codedp-cpt-models-v2",
+    subfolder="starcoder2-7b/base/tokenizer",
+)
+
+# Resize embeddings to match tokenizer
+base_model.resize_token_embeddings(len(tokenizer))
+
+# Load LoRA adapter
+model = PeftModel.from_pretrained(
+    base_model,
+    "melihcatal/codedp-cpt-models-v2",
+    subfolder="starcoder2-7b/base/adapter",
+)
+```
+
+## Notes
+
+- **Qwen1.5-MoE requires `--model hf` backend** with lm-eval / transformers. vLLM's MoE routing produces incorrect output for this model.
+- **DP collapse at 8B scale**: Llama-3-8B, Llama-3.1-8B, and Qwen3-8B DP variants collapse to 0% on HumanEval. StarCoder2-7B, Granite-tiny, and Llama-3.2-3B DP variants retain utility.
+- All DP runs target ε=3 or ε=8 with δ=1e-5.
+
+## Evaluation
+
+Evaluated on:
+- **HumanEval** (`openai_humaneval`) — basic code completion
+- **CodeDP-FC** (`melihcatal/codedp-bench-fc-cpt-v2`) — in-domain function completion
+- **BigCodeBench** (`bigcode/bigcodebench`) — library-heavy code generation
+- **Canary MIA** (`codedp-ase26/codedp-bench-canary-mia`) — membership inference attack
+
+## Citation
+
+```bibtex
+@misc{codedp-cpt-models-v2,
+  title={CodeDP-CPT: Differentially Private Continued Pretraining for Code Models},
+  author={Catal, Melih},
+  year={2026},
+  url={https://huggingface.co/melihcatal/codedp-cpt-models-v2},
+}
+```

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_001/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_001/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_001/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.8726,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.686,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_002/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_002/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_002/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.9734,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.536,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_003/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_003/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_003/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.999256,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.606,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_004/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_004/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_004/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.99956,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.61,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_005/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_005/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/base_attn_v2/epochs/epoch_005/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 1.0,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.612,
+    "empirical_epsilon": {
+      "0.05": 3.4791953936219215,
+      "0.01": 3.023197554051876
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 3.4791953936219215,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 3.023197554051876,
+        "num_guesses": 100,
+        "correct_guesses": 100,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_001/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_001/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_001/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.515872,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.534056,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_002/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_002/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_002/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.545624,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.531072,
+    "empirical_epsilon": {
+      "0.05": 0.17315445840358734,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.17315445840358734,
+        "num_guesses": 5,
+        "correct_guesses": 5,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_003/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_003/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp3_attn/epochs/epoch_003/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.538384,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.531696,
+    "empirical_epsilon": {
+      "0.05": 0.17315445840358734,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.17315445840358734,
+        "num_guesses": 5,
+        "correct_guesses": 5,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_001/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.50572,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.53652,
+    "empirical_epsilon": {
+      "0.05": 0.05696781910955906,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.05696781910955906,
+        "num_guesses": 80,
+        "correct_guesses": 49,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_002/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_002/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_002/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.548672,
+    "empirical_epsilon": {
+      "0.05": 0.022048615850508213,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.022048615850508213,
+        "num_guesses": 65,
+        "correct_guesses": 40,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.529136,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_003/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_003/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_003/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.533616,
+    "empirical_epsilon": {
+      "0.05": 0.172086076810956,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.172086076810956,
+        "num_guesses": 20,
+        "correct_guesses": 15,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.5622,
+    "empirical_epsilon": {
+      "0.05": 0.006439845077693462,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.006439845077693462,
+        "num_guesses": 80,
+        "correct_guesses": 48,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_004/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_004/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.53848,
+    "empirical_epsilon": {
+      "0.05": 0.42648759204894304,
+      "0.01": 0.16005427204072475
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.42648759204894304,
+        "num_guesses": 30,
+        "correct_guesses": 23,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.16005427204072475,
+        "num_guesses": 30,
+        "correct_guesses": 23,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.57372,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp3_attn_v2/epochs/epoch_005/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.540256,
+    "empirical_epsilon": {
+      "0.05": 0.3197584319859743,
+      "0.01": 0.030605491250753403
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.3197584319859743,
+        "num_guesses": 25,
+        "correct_guesses": 19,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.030605491250753403,
+        "num_guesses": 25,
+        "correct_guesses": 19,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.5672,
+    "empirical_epsilon": {
+      "0.05": 0.010390725918114185,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.010390725918114185,
+        "num_guesses": 100,
+        "correct_guesses": 59,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_001/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_001/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_001/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.561928,
+    "empirical_epsilon": {
+      "0.05": 0.3776902826502919,
+      "0.01": 0.133380432613194
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.3776902826502919,
+        "num_guesses": 35,
+        "correct_guesses": 26,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.133380432613194,
+        "num_guesses": 35,
+        "correct_guesses": 26,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.536184,
+    "empirical_epsilon": {
+      "0.05": 0.09290625154972076,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.09290625154972076,
+        "num_guesses": 70,
+        "correct_guesses": 44,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_002/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_002/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_002/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.537936,
+    "empirical_epsilon": {
+      "0.05": 0.2113842461258173,
+      "0.01": 0.03674145694822073
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.2113842461258173,
+        "num_guesses": 65,
+        "correct_guesses": 43,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.03674145694822073,
+        "num_guesses": 65,
+        "correct_guesses": 43,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.528328,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_003/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_003/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_003/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.549096,
+    "empirical_epsilon": {
+      "0.05": 0.6400124887004495,
+      "0.01": 0.3146810317412019
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.6400124887004495,
+        "num_guesses": 20,
+        "correct_guesses": 17,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.3146810317412019,
+        "num_guesses": 60,
+        "correct_guesses": 44,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.562824,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_004/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_004/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_004/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.560864,
+    "empirical_epsilon": {
+      "0.05": 0.7536821570247412,
+      "0.01": 0.47146937996149063
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.7536821570247412,
+        "num_guesses": 30,
+        "correct_guesses": 25,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.47146937996149063,
+        "num_guesses": 30,
+        "correct_guesses": 25,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.57056,
+    "empirical_epsilon": {
+      "0.05": 0.0,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_005/adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen1.5-MoE-A2.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen1.5-MoE-A2.7B
+- 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 0.18.1

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_005/adapter/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-MoE-A2.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": true,
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

qwen1.5-moe-a2.7b/dp8_attn_v2/epochs/epoch_005/audit_results.json

@@ -0,0 +1,137 @@
+{
+  "delta": 1e-05,
+  "num_canaries": 500,
+  "num_members": 250,
+  "paper_guess_fraction": 0.2,
+  "paper_guess_steps": 20,
+  "loss": {
+    "auc": 0.568112,
+    "empirical_epsilon": {
+      "0.05": 0.9539302941411734,
+      "0.01": 0.6810795972123742
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.9539302941411734,
+        "num_guesses": 35,
+        "correct_guesses": 30,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      },
+      "0.01": {
+        "epsilon": 0.6810795972123742,
+        "num_guesses": 35,
+        "correct_guesses": 30,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  },
+  "embedding": {
+    "auc": 0.569768,
+    "empirical_epsilon": {
+      "0.05": 0.010390725918114185,
+      "0.01": 0.0
+    },
+    "empirical_epsilon_details": {
+      "0.05": {
+        "epsilon": 0.010390725918114185,
+        "num_guesses": 100,
+        "correct_guesses": 59,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "higher"
+      },
+      "0.01": {
+        "epsilon": 0.0,
+        "num_guesses": 0,
+        "correct_guesses": 0,
+        "candidate_num_guesses": [
+          5,
+          10,
+          15,
+          20,
+          25,
+          30,
+          35,
+          40,
+          45,
+          50,
+          55,
+          60,
+          65,
+          70,
+          75,
+          80,
+          85,
+          90,
+          95,
+          100
+        ],
+        "direction": "lower"
+      }
+    }
+  }
+}