ayushnangia-sdft
/

qwen2.5-7b-instruct-sdft-tooluse-step-1000

@@ -1,91 +1,61 @@
 ---
-library_name: transformers
 license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
   - sdft
   - self-distillation
-  - continual-learning
   - tool-use
-  - qwen2.5
-language:
-  - en
-pipeline_tag: text-generation
 ---
-# Qwen2.5-7B-Instruct SDFT — Tool Use (Step 1000)
-This model is a **Self-Distillation Fine-Tuned (SDFT)** version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct), trained on the ToolAlpaca tool-use dataset.
-SDFT is an on-policy learning method from ["Self-Distillation Enables Continual Learning"](https://arxiv.org/abs/2601.19897) that acquires new skills while preserving prior capabilities, significantly reducing catastrophic forgetting compared to standard SFT.
 ## Training Details
 | Parameter | Value |
 |-----------|-------|
 | Base model | Qwen/Qwen2.5-7B-Instruct |
-| Method | SDFT (On-Policy Self-Distillation) |
-| Dataset | ToolAlpaca (4,046 training examples) |
-| Training step | 1000 / 1011 |
-| Learning rate | 2e-5 (cosine schedule, 10% warmup) |
-| Batch size | 32 (gradient accumulation) |
-| Epochs | 1 |
-| Precision | bf16 |
-| Max prompt length | 1024 |
-| Max completion length | 1024 |
 | EMA alpha | 0.01 |
-| Hardware | 1x NVIDIA L40S 48GB |
-| Training time | ~42 hours (full run) |
-## Evaluation Results
-### Tool-Use Accuracy (ToolAlpaca test set, 68 examples)
-| Metric | Base Model | This Model (Step 1000) |
-|--------|-----------|--------------------------|
-| Greedy Accuracy | 54.4% | 64.7% |
-| pass@1 | 52.6% | 56.1% |
-| pass@5 | 61.5% | 70.1% |
-| pass@10 | 64.3% | 74.3% |
-## Usage
-```python
-from transformers import AutoModelForCausalLM, AutoTokenizer
-model = AutoModelForCausalLM.from_pretrained("Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000")
-tokenizer = AutoTokenizer.from_pretrained("Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000")
-messages = [{"role": "user", "content": "Your tool-use prompt here"}]
-text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-inputs = tokenizer(text, return_tensors="pt").to(model.device)
-outputs = model.generate(**inputs, max_new_tokens=1024)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
-```
 ## All Checkpoints
-| Step | HuggingFace |
-|------|-------------|
-| 100 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-100](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-100) |
-| 200 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-200](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-200) |
-| 300 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-300](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-300) |
-| 400 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-400](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-400) |
-| 500 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-500](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-500) |
-| 600 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-600](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-600) |
-| 700 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-700](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-700) |
-| 800 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-800](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-800) |
-| 900 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-900](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-900) |
-| 1000 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000) |
-| 1011 | [Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1011](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1011) |
-## Citation
-```bibtex
-@article{shenfeld2025selfdistillation,
-  title={Self-Distillation Enables Continual Learning},
-  author={Shenfeld, Idan and others},
-  journal={arXiv preprint arXiv:2601.19897},
-  year={2025}
-}
-```

 ---
 license: apache-2.0
 base_model: Qwen/Qwen2.5-7B-Instruct
 tags:
   - sdft
   - self-distillation
   - tool-use
+  - continual-learning
+  - sdft-reproduction
+datasets:
+  - ToolAlpaca
 ---
+# Qwen2.5-7B-Instruct — SDFT on Tool Use (Step 1000, Best)
+Best checkpoint from SDFT (Self-Distillation Fine-Tuning) reproduction of ["Self-Distillation Enables Continual Learning"](https://arxiv.org/abs/2601.19897).
+## Results
+| Metric | Base | This Model | Paper |
+|--------|------|------------|-------|
+| Greedy Accuracy | 54.4% | **64.7%** | 70.6% |
+| Pass@1 | 52.6% | 56.2% | — |
+| Pass@5 | 61.5% | 70.1% | — |
+| Pass@10 | 64.4% | 74.4% | — |
+| Pass@50 | 70.6% | 79.4% | — |
 ## Training Details
 | Parameter | Value |
 |-----------|-------|
 | Base model | Qwen/Qwen2.5-7B-Instruct |
+| Method | On-policy Self-Distillation (SDFT) |
+| Dataset | ToolAlpaca (4046 train, 68 test) |
+| Learning rate | 1e-5 |
+| Batch size | 32 |
+| Epochs | 2 |
 | EMA alpha | 0.01 |
+| Step | 1000 (best of 1011) |
+| Hardware | L40S 48GB |
 ## All Checkpoints
+| Step | Greedy Acc |
+|------|-----------|
+| [100](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-100) | 55.9% |
+| [200](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-200) | 48.5% |
+| [300](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-300) | 44.1% |
+| [400](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-400) | 47.1% |
+| [500](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-500) | 57.4% |
+| [600](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-600) | 47.1% |
+| [700](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-700) | 54.4% |
+| [800](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-800) | 52.9% |
+| [900](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-900) | 57.4% |
+| **[1000](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1000)** | **64.7%** |
+| [1011](https://huggingface.co/Ayushnangia/qwen2.5-7b-instruct-sdft-tooluse-step-1011) | 57.4% |
+## Related
+- **Eval results:** [Ayushnangia/sdft-reproduction-eval-results](https://huggingface.co/datasets/Ayushnangia/sdft-reproduction-eval-results)
+- **Code:** [github.com/ayushnangia/Self-Distillation](https://github.com/ayushnangia/Self-Distillation)