ModelVerificadoExterno

Qwen3 4B Chemistry SDPO TR

This repository contains the Qwen3-4B Chemistry SDPO-TR run trained with batch size 32.

Fuentehuggingface.co/SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR/tree/567d5ca06f64a047943ca8fb626dbe0f13b791dc

TipoText modelModelo baseQwen/Qwen3-4BVersiónRevision 567d5caPublicador@SeongryongJungCcalidad

Fuente del modelo

Tipo: Text model
Tamaño del archivo: Aún no registrado
Modelo base: Qwen/Qwen3-4B
Versión: vRevision 567d5ca
Actualizado: 13 oct 2026
Publicador: @SeongryongJung
Descargas: 7
Parámetros: 4B
Fuente: Hugging Face

Descripción de la fuente

Qwen3-4B-Chemistry-SDPO-TR

This repository contains the Qwen3-4B Chemistry SDPO-TR run trained with batch size 32.

The repository root contains the best validation checkpoint (global_step_100), selected by validation mean@16. The best validation checkpoint is also the final checkpoint, so the repository root is both best and last.

Performance

Dataset	Method	Base model	Train batch size	Best val mean@16	Best checkpoint	Final val mean@16	Final checkpoint
Chemistry	SDPO-TR	Qwen3-4B	32	74.91%	100	74.91%	100

Training and validation scores

Raw result files:

results/validation_mean16.csv
results/training_scores.csv
artifacts/config.yaml
artifacts/wandb-summary.json

Training Hyperparameters

Hyperparameter	Value
Base model	`Qwen/Qwen3-4B`
Method	`SDPO-TR`
Train batch size	`32`
Train max samples	`3200`
Total training steps	`100`
Save frequency	`10`
Test frequency	`10`
Teacher regularization	`trust-region`
Teacher update rate	`0.1`
Rollout samples per prompt	`8`
Validation samples per prompt	`16`
Learning rate	`1e-5`
vLLM GPU memory utilization	`0.8`

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    repo_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

Fuentes

1 fuente

Hugging FacePrincipalVersión 567d5ca06f64a047943ca8fb626dbe0f13b791dc

huggingface.co/SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR/tree/567d5ca06f64a047943ca8fb626dbe0f13b791dc

Verificado 17 sept

Extractos de fuentes

3 extractos

Readme11 julhuggingface.co/SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR

--- license: apache-2.0 base_model: Qwen/Qwen3-4B library_name: transformers tags: - qwen3 - reinforcement-learning - trust-region - sdpo - srpo --- # Qwen3-4B-Chemistry-SDPO-TR This repository contains the Qwen3-4B `Chemistry` `SDPO-TR` run trained with batch size 32. The repository root contains the **best validation checkpoint** (`global_step_100`), selected by validation `mean@16`. The best validation checkpoint is also the final checkpoint, so the repository root is both best and last. ## Performance | Dataset | Method | Base model | Train batch size | Best val mean@16 | Best checkpoint | Final val mean@16 | Final checkpoint | |---|---|---|---:|---:|---:|---:|---:| | Chemistry | SDPO-TR | Qwen3-4B | 32 | 74.91% | 100 | 74.91% | 100 | ![Training and validation scores](results/training_score.png) Raw result files: - `results/validation_mean16.csv` - `results/training_scores.csv` - `artifacts/config.yaml` - `artifacts/wandb-summary.json` ## Training Hyperparameters | Hyperparameter | Value | |---|---:| | Base model | `Qwen/Qwen3-4B` | | Method | `SDPO-TR` | | Train batch size | `32` | | Train max samples | `3200` | | Total training steps | `100` | | Save frequency | `10` | | Test frequency | `10` | | Teacher regularization | `trust-region` | | Teacher update rate | `0.1` | | Rollout samples per prompt | `8` | | Validation samples per prompt | `16` | | Learning rate | `1e-5` | | vLLM GPU memory utilization | `0.8` | ## Usage ```python from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR" tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained( repo_id, torch_dtype="auto", device_map="auto", trust_remote_code=True, ) ```

Note17 septhuggingface.co/SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR

Source context: 7 downloads · 0 likes · Pipeline reinforcement-learning · Library transformers · Repo SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR

Note18 julhuggingface.co/SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR

Source context: 59 downloads · 0 likes · Pipeline reinforcement-learning · Library transformers · Repo SeongryongJung/Qwen3-4B-Chemistry-SDPO-TR