GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
SeongryongJung
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
SeongryongJung
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
| Dataset | Method | Base model | Train batch size | Best val mean@16 | Best checkpoint | Final val mean@16 | Final checkpoint |
|---|---|---|---|---|---|---|---|
| Material / SciKnowEval material | RLSD_TR | Qwen3-8B | 32 | 76.46% | 100 | 76.46% | 100 |
| step | val_mean16 | percent |
|---|---|---|
| 10 | 0.655585106383 | 65.56% |
| 20 | 0.688829787234 | 68.88% |
| 30 | 0.697473404255 | 69.75% |
| 40 | 0.734042553191 | 73.40% |
| 50 | 0.746675531915 | 74.67% |
| 60 | 0.751329787234 | 75.13% |
| 70 | 0.751994680851 | 75.20% |
| 80 | 0.744680851064 | 74.47% |
| 90 | 0.753989361702 | 75.40% |
| 100 | 0.764627659574 | 76.46% |
| Section | Parameter | Value | Source |
|---|---|---|---|
| Run identity | Base model | Qwen/Qwen3-8B | queue/script override |
| Run identity | Dataset | Material / SciKnowEval material | 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-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8 | run_qwen3_generalization.sh |
| Run identity | W&B run | run-20260703_115716-skza3cpu | wandb |
| Data | Train file | datasets/sciknoweval/material/train.parquet | script override |
| Data | Validation file | datasets/sciknoweval/material/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/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-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/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-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.csvresults/training_scores.csvresults/hyperparameters.csvresults/training_score.pngresults/training_score.svgartifacts/output.logartifacts/queue.logpython
from transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "SeongryongJung/Qwen3-8B-Material-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,)checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8checkpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actorcheckpoints/datasets/sciknoweval/material/qwen3gen-material-RLSD_TR-Qwen-Qwen3-8B-mbs8-decay0-tr0.1-train32-rollout8-lr1e-6-vllm0.8/global_step_100/actorrun-20260703_115716-skza3cpuartifacts/queue.logfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "SeongryongJung/Qwen3-8B-Material-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,)