GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
sach0312
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
sach0312
Model Tree
Qwen/Qwen3-0.6B
Input Modalities
Output Modalities
Supported Functionality
All numbers: identical shares-based fee-net accounting (1.5% taker fee both fills), temporally held-out windows, fills at displayed 1-minute candle prices.
| Policy | Val (621 games) | Test (227 playoff games) |
|---|---|---|
| LUT teacher + edge staking (champion) | +$0.1142 ± 0.0098 | +$0.1258 ± 0.0169 |
| LUT teacher, flat stake | +$0.0627 ± 0.0058 | +$0.0770 ± 0.0095 |
| This model, own stake | +$0.0201 ± 0.0091 | +$0.0161 ± 0.0148 |
| This model, edge stake (decode-time) | +$0.0213 ± 0.0155 | +$0.0355 ± 0.0265 |
| No-trade baseline | $0.00 | $0.00 |
| LightGBM / LogReg / DQN / LSTM / LinUCB / Thompson | negative | negative |
Six documented attempts to retrain GRPO with edge-proportional stake in the reward
(script).
The best run trained to ~step 337/500 before collapse: frac_reward_zero_std → 1.0,
grad_norm → 0, ~98% of completions truncated at max length, zero advantage signal.
Cancelled per pre-agreed kill criteria. The v2b adapter is not usable. The
stake-alignment hypothesis (aligning the RL reward with the winning staking scheme)
remains untested end-to-end: TRL GRPO on this 0.6B model with this degenerate-prone
reward structure did not train stably at any explored configuration.
python
from peft import AutoPeftModelForCausalLMmodel = AutoPeftModelForCausalLM.from_pretrained( "sach0312/qwen3-0.6b-nhl-polymarket-grpo-v2", torch_dtype="bfloat16")Prompt format: the sft_v2 state schema (see
sach0312/nhl-polymarket-trading),
response = JSON {"action": "buy_team0|buy_team1|unwind|no_trade", "stake": 0..1, "reason": "..."}.
GRPOTrainer, 500 steps, 8 generations/state, temp 1.0, adaptive entropy
(target 1.2), lr 1e-5, a10g-small (~62 min)