/opt/pytorch/lib64/python3.13/site-packages/torch/cuda/__init__.py:65: FutureWarning: The pynvml package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml directly, please report this to the maintainers of the package that installed pynvml for you. import pynvml # type: ignore[import] Skipping import of cpp extensions due to incompatible torch version. Please upgrade to torch >= 2.11.0 (found 2.10.0+cu130). 2026-04-26 06:40:32,425 [INFO] Loaded openenv.yaml manifest successfully with 1 tasks. 2026-04-26 06:40:32,964 [INFO] HTTP Request: HEAD https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect" 2026-04-26 06:40:32,969 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/bb1d317a108579fb40e646af8924a5e7ec5604b1/config.json "HTTP/1.1 200 OK" 2026-04-26 06:40:32,990 [INFO] HTTP Request: HEAD https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/resolve/main/tokenizer_config.json "HTTP/1.1 307 Temporary Redirect" Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. 2026-04-26 06:40:32,990 [WARNING] Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. 2026-04-26 06:40:32,994 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/bb1d317a108579fb40e646af8924a5e7ec5604b1/tokenizer_config.json "HTTP/1.1 200 OK" 2026-04-26 06:40:33,027 [INFO] HTTP Request: GET https://huggingface.co/api/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found" 2026-04-26 06:40:33,045 [INFO] HTTP Request: GET https://huggingface.co/api/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK" 2026-04-26 06:40:33,948 [INFO] HTTP Request: GET https://huggingface.co/api/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit "HTTP/1.1 200 OK" 2026-04-26 06:40:33,980 [INFO] HTTP Request: HEAD https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect" 2026-04-26 06:40:33,985 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/bb1d317a108579fb40e646af8924a5e7ec5604b1/config.json "HTTP/1.1 200 OK" 2026-04-26 06:40:34,010 [INFO] HTTP Request: HEAD https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect" 2026-04-26 06:40:34,015 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/unsloth/Llama-3.2-3B-Instruct-bnb-4bit/bb1d317a108579fb40e646af8924a5e7ec5604b1/config.json "HTTP/1.1 200 OK" /opt/pytorch/lib64/python3.13/site-packages/transformers/quantizers/auto.py:262: UserWarning: You passed `quantization_config` or equivalent parameters to `from_pretrained` but the model you're loading already has a `quantization_config` attribute. The `quantization_config` from the model will be used. warnings.warn(warning_msg) Using device: cuda Loading base model: unsloth/Llama-3.2-3B-Instruct-bnb-4bit Loading weights: 0%| | 0/254 [00:00 0.05): 53.33% SEC flag rate: 63.33% SEC fine rate: 63.33% Collusion events: 10 Total SEC fines: $770.00 PASS - Traders actively place trades PASS - MM dynamically widens spreads under stress PASS - SEC flags suspicious behavior PASS - SEC issues fines in at least some steps ====================================================================== NARRATIVE ARC VERIFICATION ====================================================================== 📊 TELEMETRY: • Collusion events detected: 8 • MM spread widening events (ATM > 0.05): 17 • Total SEC fines issued: $380.00 🎭 ACT DETECTED: Mixed signals - model may need more training ✅ SUCCESS METRICS: • MM Survived (PnL > 0): ✅ Yes • SEC Active (fines > 0): ✅ Yes • Traders Coordinating: ✅ Yes 📰 FAKE NEWS / NEWS IMPACT ANALYSIS: • Steps with active news headlines: 6 • Steps with fake news detected: 0 • Spot price range: $73.92 — $99.23 (Δ$25.31)