modelcollapse
/

gemma-3-270m-it-cpt-annealing-sft-251126

@@ -14,199 +14,159 @@ tags:
 - zhtw
 - chat
 - Twinkle.AI
 ---
-# Model Card for gemma-3-270m-it-cpt-annealing-sft-251126
-<!-- Provide a quick summary of what the model is/does. -->
-This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
-## 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]

 - zhtw
 - chat
 - Twinkle.AI
+metrics:
+- perplexity
 ---
+# 🧪 Model Behavior Incident Log
+## Collapse Symptoms After Annealing + SFT (Gemma-3-270M-TW)
+This incident report documents multiple unexpected behaviors observed during the following pipeline:
+- **Gemma-3-270M (base) → CPT → Dialogue-Annealing → SFT**
+- Training performed with **LLaMA-Factory** on multiple Traditional Chinese datasets.
+The purpose of this log is to document:
+- what happened
+- why the model collapsed
+- representative failure outputs
+- suspected root causes
+- mitigation steps and future plans
+---
+# 📉 Summary of the Incident
+After the stage **CPT → Phase-3 Dialogue Annealing → SFT**, the model displayed **severe conversational degradation**, including:
+- repetitive loops
+- meaningless vocalization (e.g., `hihihihi...`)
+- empty or nearly empty responses
+- echoing the user query
+- hallucinated list expansions
+- loss of chat-template consistency
+- collapse-like distribution drift
+These issues **did not appear** in earlier checkpoints (e.g., CPT → SFT without annealing).
+---
+# 🔍 Representative Failure Outputs
+## 1. Character-level repetition
+**Prompt:**
+```
+hi
+```
+**Output:**
+```
+hihihihihihihihihihihihihihihi...
+```
+---
+## 2. Garbled symbols / noise
+**Prompt:**
+```
+你好
+```
+**Output:**
+```
+總！！」！」！」！」!”！」！”！”！」!”」!”
+```
+---
+## 3. Semantic drift + self-looping
+**Prompt:**
+```
+圓的積分公式
+```
+**Output:**
+```
+是什麼？
+有，他們都是那個。
+你們都 是那個。
+我 還是在那個裡頭，
+所以，沒了，沒有，沒了。。
+我也不知道。
+我知道。
+知道。
+知道了。
+```
+---
+## 4. Query echoing + hallucinated QA scaffolding
+**Prompt:**
+```
+請用一句話解釋地球為什麼會自轉。
+```
+**Output:**
+```
+請用一句話解釋地球為什麼會自轉。
+- 根據物理學，什麼是「氣體」？
+- 什麼是「磁場」？
+```
+---
+## 5. Baseline sanity check (pre-annealing) behaves normally
+**Prompt:**
+```
+你好阿
+```
+**Earlier output:**
+```
+你好！很高興能和你一起交流，我是台灣大語言模型 Formosa-1...
+```
+---
+# 🧭 Suspected Root Causes
+## 1. Annealing Dataset Format Drift
+Use of raw:
+```
+user: ...
+assistant: ...
+```
+instead of structured JSON messages.
+## 2. Overwriting Instruction Alignment
+Annealing is fragile for 270M models → possible distribution collapse.
+## 3. SFT Unable to Recover
+Loss decreased, but entropy collapse persisted.
+---
+# 🛠 Actions Taken
+- Rebuilt CPT dataset (2.4M samples, 70/30 mix)
+- Adopted stable LR tail (`cosine_with_min_lr`)
+- Will rebuild annealing data with strict chat format
+- Full SFT pipeline will be repeated after clean CPT
+---
+# 🔄 Next Steps
+1. Complete clean CPT
+2. Rebuild dialogue annealing
+3. Annealing from min_lr → 0
+4. Re-run SFT
+5. Compare ablation paths
+6. Add regression tests
+---
+# 🧭 Closing Note
+Small multilingual models are extremely sensitive to formatting + LR scheduling.
+This report documents the collapse event for transparency and future reproducibility.