用 Codex 和 HF Skills 做端到端机器学习实验

Fine-tune Qwen3-0.6B on the dataset open-r1/codeforces-cots

git clone https://github.com/huggingface/skills.git
cd skills

codex --ask-for-approval never "Summarize the current instructions."

hf auth login

[mcp_servers.huggingface]
command = "npx"
args = ["-y", "mcp-remote", "https://huggingface.co/mcp?login"]

Start a new fine-tuning experiment to improve code solving abilities on using SFT. 
- Maintain a report for the experiment. 
- Evaluate models with the openai_humaneval benchmark
- Use the open-r1/codeforces-cots dataset

# Base Model & Dataset
[Base Model](https://huggingface.co/Qwen/Qwen3-0.6B)  
[Dataset](https://huggingface.co/datasets/open-r1/codeforces-cots)

---

# `sft-a10g` - `TBD` - `In Progress`

## Training Parameters
| Parameter | Value |
|-----------|-------|
| Method | SFT (TRL) |
| Model | `Qwen/Qwen3-0.6B` |
| Dataset | `open-r1/codeforces-cots` (train, 5% eval split) |
| Max Length | 2048 |
| Epochs | 1 (extend to 3 after first check) |
| Per-Device Batch Size | 1 |
| Grad Accum Steps | 8 |
| Effective Batch | 8 |
| Learning Rate | 5e-5 |
| Weight Decay | 0.01 |
| Warmup Ratio | 0.03 |
| Eval Strategy | steps (500) |
| Save Strategy | steps (500), `hub_strategy=every_save`, limit=2 |
| Precision | bf16 |
| Gradient Checkpointing | true |
| Packing | false |
| Hub Model | `burtenshaw/qwen3-codeforces-cots-sft` |
| Hardware | a10g-small |
| Timeout | 2h |
| Trackio | project `qwen3-codeforces-cots`, run `sft-a10g` |

## Run Status
In Progress (queued to submit)

## Run Logs
Pending submission (job link will be added)

## Trackio Logs
Pending (will link after job starts)

## Run Evaluations
Pending (lighteval `openai_humaneval` for base + checkpoints)

---

# Experiment Evaluations
| Run Title | Benchmark | Score | Evaluation Job Link | Model Link |
|-----------|-----------|-------|---------------------|------------|
| `sft-a10g` - `TBD` - `In Progress` | HumanEval pass@1 | TBD | TBD | [burtenshaw/qwen3-codeforces-cots-sft](https://huggingface.co/burtenshaw/qwen3-codeforces-cots-sft)

# `base-humaneval-a10g` - `2025-12-09 13:47:47 UTC` - `In Progress`

## Run Logs

[Run Logs](https://huggingface.co/jobs/burtenshaw/6938272ec67c9f186cfe1ae3)

## Trackio Logs

[Trackio Logs](https://burtenshaw-trackio.hf.space/?project=qwen3-codeforces-sft&metrics=train/loss&runs=sft-qwen3-codeforces-20251209-175806&sidebar=hidden&navbar=hidden)

# Experiment Evaluations

| Run Title | Benchmark | Score | Evaluation Job Link | Model Link |
|-----------|-----------|-------|---------------------|------------|
| `base-humaneval-a10g` - `2025-12-09 13:47:47 UTC` - `Completed` | HumanEval pass@1 | 0.304 | [Logs](https://huggingface.co/jobs/burtenshaw/69382863c67c9f186cfe1ae7) | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) |
| `qwen3-0.6b-lora-v1` - `2025-12-09 13:47:47 UTC` - `In Progress` | HumanEval pass@1 | TBD | TBD | [burtenshaw/qwen3-codeforces-cots-sft](https://huggingface.co/burtenshaw/qwen3-codeforces-cots-sft)

Check if open-r1/codeforces-cots works for SFT training.

Dataset validation for my-org/conversation-data:

SFT: ✓ READY
  Found 'messages' column with conversation format

DPO: ✗ INCOMPATIBLE
  Missing 'chosen' and 'rejected' columns

Preprocess the dataset open-r1/codeforces-cots to use 'good_response' and 'bad_response' instead of 'chosen' and 'rejected'.

I'll fine-tune Qwen/Qwen3-0.6B on open-r1/codeforces-cots using SFT.

Configuration:
- Hardware: t4-small (~$0.75/hour)
- Estimated time: ~20 minutes
- Estimated cost: ~$0.30
- Output: username/qwen-codeforces-cots-sft

The model will be pushed to Hub automatically. Should I submit?

Do a quick test run on 100 examples.

─ Worked for 10m 38s ─────────────────────────────────────────────────────────────────────────────────────────────────────────

• Training and eval jobs are live. Key details:

  - SFT launched on open-r1/codeforces-cots (solutions_py_decontaminated, 98/2 split) with LoRA on Qwen/Qwen3-0.6B, a10g-
    large, bf16, max_steps=1000, batch=1, grad_accum=8, lr=2e-5, save/eval every 200 steps, hub push burtenshaw/qwen3-
    codeforces-cots-sft. Job: https://huggingface.co/jobs/burtenshaw/6938272ec67c9f186cfe1ae3 (Trackio project codeforces-
    cots-sft, run qwen3-0.6b-lora-v1).
  - Baseline lighteval (HumanEval) on the base model queued on a10g-large. Job: https://huggingface.co/jobs/
  - Experiment report updated with current runs and links: training_reports/qwen3-codeforces-cots-sft.md.

  To evaluate the fine-tuned checkpoints once the SFT job pushes to the hub, reuse the same lighteval script:
  hf jobs uv run --flavor a10g-large --timeout 1h --secrets HF_TOKEN -e MODEL_ID=burtenshaw/qwen3-codeforces-cots-sft -e
  RESULTS_ORG=burtenshaw -d /tmp/lighteval_humaneval.py
  (or swap MODEL_ID for a specific checkpoint path). This will log to the same results directory on the hub.

  1. Monitor the two running jobs; I can fetch logs or metrics on request.
  2. After a checkpoint lands, trigger the lighteval run above to compare against the baseline; then we can fill in pass@1 in the report.

Are models outperforming the base model?

| Model | Benchmark | Score | Evaluation Job Link | Model Link |
|-----------|-----------|-------|---------------------|------------|
| `qwen3-0.6b-lora-v1` - `2025-12-09 13:47:47 UTC` - `Completed` | HumanEval pass@1 | 0.342 | [Logs](<link to training job>) | [burtenshaw/qwen3-codeforces-cots-sft](https://huggingface.co/burtenshaw/qwen3-codeforces-cots-sft)
| `base-humaneval-a10g` - `2025-12-09 13:47:47 UTC` - `Completed` | HumanEval pass@1 | 0.306 | [Logs](<link to evaluation job>) | [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("burtenshaw/qwen3-codeforces-cots-sft")
tokenizer = AutoTokenizer.from_pretrained("burtenshaw/qwen3-codeforces-cots-sft")

Convert my fine-tuned model to GGUF with Q4_K_M quantization.
Push to username/my-model-gguf.

llama-server -hf <username>/<model-name>:<quantization>

# For example, to run the Qwen3-1.7B-GGUF model on your local machine:
llama-server -hf unsloth/Qwen3-1.7B-GGUF:Q4_K_M