compass-lora-v2: LoRA r16 on Qwen3.5-4B 851bf6e8 through the verification/direct readouts; calibration fitted on the hard-like split

README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-4B
+- 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 0.21.0

adapter_config.json

@@ -0,0 +1,54 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-4B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "gate_proj",
+    "in_proj_qkv",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "out_proj",
+    "o_proj",
+    "in_proj_z",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108b48a8d3fa65fc02da23bf2a06f1d333c37cfb6c7e9392421230065efb927e
+size 121951008

calibration.json

@@ -0,0 +1,44 @@
+{
+  "temperatures": {
+    "choice": 2.0,
+    "score": 2.0,
+    "noul": 2.25
+  },
+  "fitted_on": [
+    "dev/splits_v2/calibration-hard.jsonl"
+  ],
+  "model": "compass-fusion-lora-qwen3.5-4b-compass-prompt-2",
+  "readout": "fusion",
+  "head": null,
+  "fusion_weight": 0.5,
+  "n_items": 178,
+  "report": {
+    "choice": {
+      "n": 45,
+      "fit_half_T": 0.25,
+      "shipped_T": 2.0,
+      "held_out_ece_before": 0.0937,
+      "held_out_ece_after": 0.0931,
+      "held_out_nll_before": 0.5269,
+      "held_out_nll_after": 1.2941
+    },
+    "score": {
+      "n": 90,
+      "fit_half_T": 2.25,
+      "shipped_T": 2.0,
+      "held_out_ece_before": 0.0286,
+      "held_out_ece_after": 0.0698,
+      "held_out_nll_before": 0.0993,
+      "held_out_nll_after": 0.1376
+    },
+    "noul": {
+      "n": 43,
+      "fit_half_T": 2.0,
+      "shipped_T": 2.25,
+      "held_out_ece_before": 0.1522,
+      "held_out_ece_after": 0.1151,
+      "held_out_nll_before": 0.5846,
+      "held_out_nll_after": 0.4233
+    }
+  }
+}

training.json

@@ -0,0 +1,159 @@
+{
+  "args": {
+    "train": "dev/splits_v2/train.jsonl",
+    "select": "dev/splits_v2/selection.jsonl",
+    "out": "release/lora-v2",
+    "model_name": "Qwen/Qwen3.5-4B",
+    "rank": 16,
+    "alpha": 32,
+    "lora_dropout": 0.05,
+    "lr": 0.0001,
+    "weight_decay": 0.01,
+    "epochs": 2,
+    "accum": 8,
+    "fusion": 0.5,
+    "ordinal_w": 0.5,
+    "perm_w": 0.5,
+    "perm_p": 0.5,
+    "opaque_p": 0.5,
+    "eval_every": 400,
+    "patience": 3,
+    "max_select": 400,
+    "seed": 0
+  },
+  "n_train": 2150,
+  "n_select": 161,
+  "best_selection_loss": 0.8873302168802816,
+  "best_step": 250,
+  "log": [
+    {
+      "step": 0,
+      "seen": 0,
+      "loss": 1.336758746236262,
+      "acc": 0.7080745341614907,
+      "by_family": {
+        "adequacy": "7/10",
+        "ambiguous": "7/7",
+        "policy": "11/13",
+        "probability": "29/60",
+        "routing": "60/71"
+      }
+    },
+    {
+      "step": 50,
+      "seen": 400,
+      "loss": 1.0610499146397323,
+      "acc": 0.8260869565217391,
+      "by_family": {
+        "adequacy": "6/10",
+        "ambiguous": "7/7",
+        "policy": "8/13",
+        "probability": "47/60",
+        "routing": "65/71"
+      }
+    },
+    {
+      "step": 100,
+      "seen": 800,
+      "loss": 1.031379698107586,
+      "acc": 0.906832298136646,
+      "by_family": {
+        "adequacy": "8/10",
+        "ambiguous": "7/7",
+        "policy": "9/13",
+        "probability": "55/60",
+        "routing": "67/71"
+      }
+    },
+    {
+      "step": 150,
+      "seen": 1200,
+      "loss": 0.9625220286051789,
+      "acc": 0.8757763975155279,
+      "by_family": {
+        "adequacy": "6/10",
+        "ambiguous": "6/7",
+        "policy": "10/13",
+        "probability": "52/60",
+        "routing": "67/71"
+      }
+    },
+    {
+      "step": 200,
+      "seen": 1600,
+      "loss": 0.9321816444499288,
+      "acc": 0.9316770186335404,
+      "by_family": {
+        "adequacy": "9/10",
+        "ambiguous": "6/7",
+        "policy": "10/13",
+        "probability": "60/60",
+        "routing": "65/71"
+      }
+    },
+    {
+      "step": 250,
+      "seen": 2000,
+      "loss": 0.8873302168802816,
+      "acc": 0.9130434782608695,
+      "by_family": {
+        "adequacy": "7/10",
+        "ambiguous": "6/7",
+        "policy": "8/13",
+        "probability": "58/60",
+        "routing": "68/71"
+      }
+    },
+    {
+      "step": 301,
+      "seen": 2406,
+      "loss": 0.9988113209218529,
+      "acc": 0.9130434782608695,
+      "by_family": {
+        "adequacy": "6/10",
+        "ambiguous": "6/7",
+        "policy": "11/13",
+        "probability": "58/60",
+        "routing": "66/71"
+      }
+    },
+    {
+      "step": 351,
+      "seen": 2806,
+      "loss": 1.0362505128805466,
+      "acc": 0.9254658385093167,
+      "by_family": {
+        "adequacy": "7/10",
+        "ambiguous": "6/7",
+        "policy": "10/13",
+        "probability": "58/60",
+        "routing": "68/71"
+      }
+    },
+    {
+      "step": 401,
+      "seen": 3206,
+      "loss": 0.990789322077885,
+      "acc": 0.9192546583850931,
+      "by_family": {
+        "adequacy": "7/10",
+        "ambiguous": "6/7",
+        "policy": "9/13",
+        "probability": "58/60",
+        "routing": "68/71"
+      }
+    }
+  ],
+  "targets": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "in_proj_qkv",
+    "in_proj_z",
+    "out_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj"
+  ]
+}