license, library_name, pipeline_tag, tags, base_model

license	library_name	pipeline_tag	tags	base_model
apache-2.0	transformers	text-generation	qwen3 reinforcement-learning rlsd-tr text-generation trust-region	Qwen/Qwen3-4B

Qwen3-4B-Tooluse-RLSD-TR

This repository contains the Qwen3-4B tooluse RLSD_TR batch-size-32 run.

The repository root contains the best validation checkpoint, selected by validation mean@16. checkpoints/last/ contains the final checkpoint.

Performance

Dataset	Method	Base model	Train batch size	Best val mean@16	Best checkpoint	Final val mean@16	Final checkpoint
Tool-use / tooluse	RLSD_TR	Qwen3-4B	32	61.03%	60	59.38%	100

Validation Mean@16

step	val_mean16	percent
10	0.576286764706	57.63%
20	0.586397058824	58.64%
30	0.575367647059	57.54%
40	0.570772058824	57.08%
50	0.553308823529	55.33%
60	0.610294117647	61.03%
70	0.594669117647	59.47%
80	0.592830882353	59.28%
90	0.531250000000	53.12%
100	0.593750000000	59.38%

Detailed Training Hyperparameters

Section	Parameter	Value	Source
Run identity	Base model	Qwen/Qwen3-4B	queue/script override
Run identity	Dataset	Tool-use / tooluse	run_qwen3_generalization.sh
Run identity	Method	RLSD_TR	run_qwen3_generalization.sh
Run identity	Config	rlsd	run_qwen3_generalization.sh
Run identity	Experiment	qwen3gen-tooluse-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8	run_qwen3_generalization.sh
Run identity	W&B run	run-20260702_154716-jrdzd11b	wandb
Data	Train file	datasets/tooluse/train.parquet	script override
Data	Validation file	datasets/tooluse/test.parquet	script override
Data	Train batch size	32	queue/script override
Data	Train max samples	3200	queue/script override
Schedule	Total training steps	100	queue/script override
Schedule	Validation before train	False	queue/script override
Schedule	Save frequency	10	queue/script override
Schedule	Validation frequency	10	queue/script override
Sequence	Max prompt length	2048	queue/script override
Sequence	Max response length	8192	queue/script override
Sequence	Max model length	10240	queue/script override
Rollout	Train rollout n	8	queue/script override
Rollout	Validation rollout n	16	queue/script override
Rollout	vLLM GPU memory utilization	0.8	queue/script override
Optimization	Learning rate	1e-6	RLSD_TR method override
Optimization	Weight decay	0.01	script override
PPO/GRPO	PPO mini batch size	8	queue/script override
PPO/GRPO	Normalize GRPO advantages by std	False	baseline_grpo.yaml / script override
Rollout correction	Importance sampling mode	token	script override
Rollout correction	IS threshold	2.0	script override
Checkpoint/Logging	Checkpoint root	checkpoints/datasets/tooluse/qwen3gen-tooluse-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8	script override
Checkpoint/Logging	Latest checkpointed iteration	100	latest_checkpointed_iteration.txt
Checkpoint/Logging	External actor archive	checkpoints/datasets/tooluse/qwen3gen-tooluse-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive	preserve_actor_checkpoints.py
Checkpoint/Logging	Logger	console, wandb	ppo_trainer.yaml
RLSD_TR	Policy loss mode	rlsd	method override
RLSD_TR	Teacher regularization	trust-region	method override
RLSD_TR	Trust-region mix / teacher update rate	0.1	queue/script override
RLSD_TR	Token reweight lambda	0.5	queue/script override
RLSD_TR	Token reweight eps_w	0.2	queue/script override
RLSD_TR	Token reweight decay steps	0	queue/script override
RLSD_TR	Fused kernels	False	method override

Raw result and artifact files:

• results/validation_mean16.csv
• results/training_scores.csv
• results/hyperparameters.csv
• results/training_score.png
• results/training_score.svg
• artifacts/config.yaml
• artifacts/wandb-summary.json
• artifacts/wandb-metadata.json
• artifacts/output.log
• artifacts/queue.log

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

repo_id = "SeongryongJung/Qwen3-4B-Tooluse-RLSD-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,
)

Source

• Checkpoint: checkpoints/datasets/tooluse/qwen3gen-tooluse-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8
• Root actor checkpoint: checkpoints/datasets/tooluse/qwen3gen-tooluse-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/_actor_archive/global_step_60/actor
• Last actor checkpoint: checkpoints/datasets/tooluse/qwen3gen-tooluse-RLSD_TR-Qwen-Qwen3-4B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actor
• W&B run: run-20260702_154716-jrdzd11b
• Queue log: artifacts/queue.log