Update README.md

README.md

@@ -2,112 +2,103 @@
 library_name: transformers
 tags:
 - generated_from_trainer
-model-index:
-- name: lustre/fswork/projects/rech/dgo/udv55np/math/Qwen3-235B-A22B/Qwen2.5-0.5B_reasoning/1
-  results: []
+datasets:
+- When-Does-Reasoning-Matter/general-reasoning-ift-pairs
+- When-Does-Reasoning-Matter/math-reasoning-ift-pairs
+language:
+- en
+pipeline_tag: text-generation
 ---
 
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-
-[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
-<details><summary>See axolotl config</summary>
+# When Does Reasoning Matter?
 
-axolotl version: `0.12.2`
-```yaml
-base_model: /lustre/fswork/projects/rech/qwv/udv55np/Qwen/Qwen2.5-0.5B_reasoning
+<p align="left">
+  <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/62be186a5f59ff2320e6e32b/GjJ15tY7-F4bqR96FN4pd.png" alt="Dataset Icon" width="180"/>
+</p>
 
-datasets:
-  - path: /lustre/fswork/projects/rech/qwv/udv55np/dataset/math/hf/thinking_text/generator/default-68225543a18d39ac/0.0.0
-    type: "chat_template"
-    field_messages: "conversations"
-dataset_prepared_path: /lustre/fsn1/projects/rech/dgo/udv55np/dataset_math/Qwen3-235B-A22B/1
+<p align="left">
+<a href="https://arxiv.org/pdf/2509.22193" target="_blank" rel="noopener noreferrer">
+  <img src="https://img.shields.io/badge/arXiv-2509.22193-b31b1b.svg?style=for-the-badge" alt="arXiv:2509.22193" />
+  </a>
+</p>
 
-chat_template: qwen_25
 
-shuffle_merged_datasets: true
-output_dir: /lustre/fswork/projects/rech/dgo/udv55np/math/Qwen3-235B-A22B/Qwen2.5-0.5B_reasoning/1
+This model was trained as part of the paper [When Does Reasoning Matter?](https://arxiv.org/pdf/2509.22193)
+It belongs to a collection of **General and Math-specific student models** distilled from Instruction-Fine-Tuned (IFT) or Reasoning answers generated by [Qwen/Qwen3-235B-A22B](https://huggingface.co/Qwen/Qwen3-235B-A22B).
 
-sequence_len: 16384
-sample_packing: true
+<img src="https://huggingface.co/api/resolve-cache/models/When-Does-Reasoning-Matter/Qwen2.5-0.5B-ift/733797fee2fdd300e1a0453d368250327fe4cc44/results.png?%2FWhen-Does-Reasoning-Matter%2FQwen2.5-0.5B-ift%2Fresolve%2Fmain%2Fresults.png=&etag=%22d36dedfbca764a8ac9a7a5ebc043ca53f5ee4966%22" alt="results" width="600"/>
 
-gradient_accumulation_steps: 1
-micro_batch_size: 1
-num_epochs: 1
-auto_resume_from_checkpoints: true
+---
 
-optimizer: adamw_torch_fused
-lr_scheduler: warmup_stable_decay
-learning_rate: 2e-5
-lr_scheduler_kwargs:
-  num_decay_steps: 300
-  min_lr_ratio: 0.1
-warmup_steps: 150
+## Datasets
 
-bf16: true
-tf32: false
+These models were trained on the **largest set of IFT and Reasoning answer pairs**:
+- **General dataset**: [general-reasoning-ift-pairs](https://huggingface.co/datasets/When-Does-Reasoning-Matter/general-reasoning-ift-pairs)  
+- **Math dataset**: [math-reasoning-ift-pairs](https://huggingface.co/datasets/When-Does-Reasoning-Matter/math-reasoning-ift-pairs)  
 
-gradient_checkpointing: true
-logging_steps: 10
-flash_attention: true
+---
 
-evals_per_epoch: 0
-save_steps: 0.2
-save_total_limit: 20
-save_only_model: false
+## Available Models
+
+<table>
+  <thead>
+    <tr>
+      <th colspan="2">General</th>
+      <th colspan="2">Math</th>
+    </tr>
+    <tr>
+      <th>IFT Models</th>
+      <th>Reasoning Models</th>
+      <th>IFT Models</th>
+      <th>Reasoning Models</th>
+    </tr>
+  </thead>
+  <tbody>
+    <tr>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-0.5B-ift">Qwen2.5-0.5B-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-0.5B-reasoning">Qwen2.5-0.5B-reasoning</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-0.5B-math-ift">Qwen2.5-0.5B-math-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-0.5B-math-reasoning">Qwen2.5-0.5B-math-reasoning</a></td>
+    </tr>
+    <tr>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-1.5B-ift">Qwen2.5-1.5B-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-1.5B-reasoning">Qwen2.5-1.5B-reasoning</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-1.5B-math-ift">Qwen2.5-1.5B-math-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-1.5B-math-reasoning">Qwen2.5-1.5B-math-reasoning</a></td>
+    </tr>
+    <tr>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-3B-ift">Qwen2.5-3B-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-3B-reasoning">Qwen2.5-3B-reasoning</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-3B-math-ift">Qwen2.5-3B-math-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-3B-math-reasoning">Qwen2.5-3B-math-reasoning</a></td>
+    </tr>
+    <tr>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-7B-ift">Qwen2.5-7B-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-7B-reasoning">Qwen2.5-7B-reasoning</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-7B-math-ift">Qwen2.5-7B-math-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-7B-math-reasoning">Qwen2.5-7B-math-reasoning</a></td>
+    </tr>
+    <tr>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-14B-ift">Qwen2.5-14B-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-14B-reasoning">Qwen2.5-14B-reasoning</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-14B-math-ift">Qwen2.5-14B-math-ift</a></td>
+      <td><a href="https://huggingface.co/When-Does-Reasoning-Matter/Qwen2.5-14B-math-reasoning">Qwen2.5-14B-math-reasoning</a></td>
+    </tr>
+  </tbody>
+</table>
 
-use_tensorboard: true
-deepspeed: /lustre/fswork/projects/rech/qwv/udv55np/axolotl/zero3.json
-special_tokens:
-  bos_token: "<|im_start|>"
-  eos_token: "<|im_end|>"
-  pad_token: "<|endoftext|>"
+---
 
+If you use this dataset in your work, please cite: **[When Does Reasoning Matter?](https://arxiv.org/pdf/2509.22193)**
+
+```bibtex
+@misc{boizard2025doesreasoningmattercontrolled,
+      title={When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance}, 
+      author={Nicolas Boizard and Hippolyte Gisserot-Boukhlef and Kevin El-Haddad and Céline Hudelot and Pierre Colombo},
+      year={2025},
+      eprint={2509.22193},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2509.22193}, 
+}
 ```
-
-</details><br>
-
-# lustre/fswork/projects/rech/dgo/udv55np/math/Qwen3-235B-A22B/Qwen2.5-0.5B_reasoning/1
-
-This model was trained from scratch on the None dataset.
-
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 1
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 16
-- total_train_batch_size: 16
-- total_eval_batch_size: 16
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: warmup_stable_decay
-- lr_scheduler_warmup_steps: 150
-- training_steps: 9770
-
-### Training results
-
-
-
-### Framework versions
-
-- Transformers 4.55.2
-- Pytorch 2.6.0+cu124
-- Datasets 4.0.0
-- Tokenizers 0.21.1