v2: DoRA + NEFTune — SOTA fine-tuning techniques

README.md

@@ -1,53 +1,207 @@
 ---
-license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
-tags: [loop-engineering, orchestrator, function-calling, kompress, fine-tuned]
-language: [en]
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen2.5-7B-Instruct
+- lora
+- transformers
 ---
 
-# kompress-superpower-orchestrator
+# Model Card for Model ID
 
-LoRA fine-tune of Qwen2.5-7B-Instruct on 117 conversation pairs encoding all 17 kompress experiment outcomes. A loop engineering agent that designs experiments, diagnoses failures, spawns sub-agents, and decides next actions.
+<!-- Provide a quick summary of what the model is/does. -->
 
-## Superpowers
 
-| Capability | Example |
-|---|---|
-| Experiment design | "Try GLM-5.2 as teacher" → spawns training script |
-| Failure diagnosis | heretic=0.878 → "v15 dilution pattern, reduce pairs" |
-| Council decisions | Review metrics → SHIP/RETRAIN/PIVOT |
-| Sub-agent spawning | spawn_train(), spawn_eval(), spawn_label() |
-| Budget awareness | Knows costs: $0.13/run, $0.15/version |
 
-## Usage
+## Model Details
 
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from peft import PeftModel
+### Model Description
 
-base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
-model = PeftModel.from_pretrained(base, "PeetPedro/kompress-superpower-orchestrator")
-tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
+<!-- Provide a longer summary of what this model is. -->
 
-messages = [{"role": "system", "content": "You are kompress-superpower-orchestrator..."},
-            {"role": "user", "content": "My model regressed to 0.878. What happened?"}]
-inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
-outputs = model.generate(inputs, max_new_tokens=200)
-print(tokenizer.decode(outputs[0]))
-```
 
-## Training
 
-- Base: Qwen/Qwen2.5-7B-Instruct
-- Method: LoRA (r=16, alpha=32, 4-bit quantized)
-- Data: 117 pairs (diagnosis, planning, council, spawn, multi-turn)
-- Epochs: 3, batch=1, grad_accum=16
-- Hardware: RTX 4090 24GB
-- Cost: ~$0.30
+- **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]
 
-## Links
+### Model Sources [optional]
 
-- [LoopKit](https://github.com/peterlodri-sec/loopkit)
-- [Paper](https://kompress.vaked.dev)
-- [Models](https://huggingface.co/PeetPedro)
-- [Blog](https://pocoo.vaked.dev)
+<!-- 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 0.19.1

adapter_config.json

@@ -32,10 +32,10 @@
   "target_modules": [
     "gate_proj",
     "k_proj",
-    "o_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
+    "o_proj",
     "up_proj"
   ],
   "target_parameters": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a3546838eb459d13fc37245abd6d572b688eb31e4045175fb49aecfbe32cc2
+oid sha256:2cab4c4025e41df8215900312e699d75f4175d1ba1bbbc1a955c39a3d3a239aa
 size 161533192

checkpoint-16/adapter_config.json

@@ -32,10 +32,10 @@
   "target_modules": [
     "gate_proj",
     "k_proj",
-    "o_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
+    "o_proj",
     "up_proj"
   ],
   "target_parameters": null,

checkpoint-16/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a3546838eb459d13fc37245abd6d572b688eb31e4045175fb49aecfbe32cc2
+oid sha256:52726be5857dc7a7ac7510192129093bcef1dbd41d471fb6461c6a9d248e2d46
 size 161533192

checkpoint-16/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dffe85358a56f9eafb8a69560333faf95f2a1dce3c42d10ba7e59b6bfd9be72c
+oid sha256:a4f392b8e8e5f98c904a5843e05ea22663eaab70499b2a5dd41d128fee520804
 size 323290986

checkpoint-16/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:726dedbc444bd9ae44665d03965d12f9d92cdd0352fe94c005193019f4da4b9b
+oid sha256:50cd113d0d731506eaf822d5f415b2d8404667eb75feef4f5a841894617ef8a2
 size 14244

checkpoint-16/trainer_state.json

@@ -11,23 +11,23 @@
   "log_history": [
     {
       "epoch": 0.6837606837606838,
-      "grad_norm": NaN,
+      "grad_norm": 53.48320007324219,
       "learning_rate": 0.00018181818181818183,
-      "loss": 82848627.2,
+      "loss": 4.9544,
       "step": 5
     },
     {
       "epoch": 1.2735042735042734,
-      "grad_norm": NaN,
+      "grad_norm": 4.736619472503662,
       "learning_rate": 0.00013636363636363637,
-      "loss": 0.0,
+      "loss": 2.6259,
       "step": 10
     },
     {
       "epoch": 1.9572649572649574,
-      "grad_norm": NaN,
+      "grad_norm": 1.7082300186157227,
       "learning_rate": 9.090909090909092e-05,
-      "loss": 0.0,
+      "loss": 1.8993,
       "step": 15
     }
   ],

checkpoint-16/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c45766993abc07f2bf597d5ce77ff87ed6d2c5ecae06346b4418b22047886e
+oid sha256:2d9e255defec3516d8ebde307401143e8fcd12e96ac03441b97b1dd37d594ccd
 size 5432

checkpoint-24/adapter_config.json

@@ -32,10 +32,10 @@
   "target_modules": [
     "gate_proj",
     "k_proj",
-    "o_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
+    "o_proj",
     "up_proj"
   ],
   "target_parameters": null,

checkpoint-24/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a3546838eb459d13fc37245abd6d572b688eb31e4045175fb49aecfbe32cc2
+oid sha256:2cab4c4025e41df8215900312e699d75f4175d1ba1bbbc1a955c39a3d3a239aa
 size 161533192

checkpoint-24/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889f0fe7d602adbc77a94d52e0a535b419ac34268e83b74473831630872812ba
+oid sha256:ef588c92d181ca76f4b970c431b80ae2e7545aec5df49d61844d092abf926003
 size 323290986

checkpoint-24/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad97a0dee0c1f944c886a1e7a0a7b6279f7f49d94e03a32a6d66fe3d084e433
+oid sha256:c754afa2065829681202b4dc3f8a574989f9d9cf05fb1d65f0adcfd29d9d90aa
 size 14244

checkpoint-24/trainer_state.json

@@ -11,30 +11,30 @@
   "log_history": [
     {
       "epoch": 0.6837606837606838,
-      "grad_norm": NaN,
+      "grad_norm": 53.48320007324219,
       "learning_rate": 0.00018181818181818183,
-      "loss": 82848627.2,
+      "loss": 4.9544,
       "step": 5
     },
     {
       "epoch": 1.2735042735042734,
-      "grad_norm": NaN,
+      "grad_norm": 4.736619472503662,
       "learning_rate": 0.00013636363636363637,
-      "loss": 0.0,
+      "loss": 2.6259,
       "step": 10
     },
     {
       "epoch": 1.9572649572649574,
-      "grad_norm": NaN,
+      "grad_norm": 1.7082300186157227,
       "learning_rate": 9.090909090909092e-05,
-      "loss": 0.0,
+      "loss": 1.8993,
       "step": 15
     },
     {
       "epoch": 2.547008547008547,
-      "grad_norm": NaN,
+      "grad_norm": 11.703311920166016,
       "learning_rate": 4.545454545454546e-05,
-      "loss": 0.0,
+      "loss": 1.663,
       "step": 20
     }
   ],

checkpoint-24/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c45766993abc07f2bf597d5ce77ff87ed6d2c5ecae06346b4418b22047886e
+oid sha256:2d9e255defec3516d8ebde307401143e8fcd12e96ac03441b97b1dd37d594ccd
 size 5432

checkpoint-8/adapter_config.json

@@ -32,10 +32,10 @@
   "target_modules": [
     "gate_proj",
     "k_proj",
-    "o_proj",
     "down_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
+    "o_proj",
     "up_proj"
   ],
   "target_parameters": null,

checkpoint-8/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a3546838eb459d13fc37245abd6d572b688eb31e4045175fb49aecfbe32cc2
+oid sha256:fa0d916d7a5de385a89b0f29e545a7c3c49b2a3214d5bf032603a00987655301
 size 161533192

checkpoint-8/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0501e7030f7a101b4114ca5636b80856143f4291026218b444b7c8c149c42056
+oid sha256:e5999fdbbc2a60ce4a58a6e28a2e96b16bd672584b5c6f9a8b2ae5998e2dc360
 size 323290986

checkpoint-8/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae79878a3656b2d8499ac32775fc885b0f83ece442eb8f20cb0480fd565d799
+oid sha256:c0b9528e9c605e59e52c0586a19ac86cd35670d5344caec3a2319908fdb7aef5
 size 14244

checkpoint-8/trainer_state.json

@@ -11,9 +11,9 @@
   "log_history": [
     {
       "epoch": 0.6837606837606838,
-      "grad_norm": NaN,
+      "grad_norm": 53.48320007324219,
       "learning_rate": 0.00018181818181818183,
-      "loss": 82848627.2,
+      "loss": 4.9544,
       "step": 5
     }
   ],

checkpoint-8/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c45766993abc07f2bf597d5ce77ff87ed6d2c5ecae06346b4418b22047886e
+oid sha256:2d9e255defec3516d8ebde307401143e8fcd12e96ac03441b97b1dd37d594ccd
 size 5432