Views
No views yet
Status: superseded. Canonical coding model: scbe-coding-agent-vtc-qwen15-v1-gguf. Kept as research history.
Qwen/Qwen2.5-Coder-0.5B-Instruct for the SCBE-AETHERMOORE bijective DSL / Sacred Tongues coding lane.bijective_dsl_v1_holdout). Treat as a memorization checkpoint until that gate is cleared.polly-auto-dsl-syn-v2) is still training; the better of the two will be the lane winner after frozen-eval.checkpoint-260/trainer_state.json)| Metric | Value |
|---|---|
| Steps | 260 |
| Epochs | 37.16 |
| Loss start | 3.7675 |
| Loss end | 0.0522 |
| Loss drop | 3.7153 |
| Token accuracy start | 0.4318 |
| Token accuracy end | 0.9824 |
| Accuracy gain | 0.5506 |
| Max grad norm | 2.3050 |
| LR start | 7.9997e-05 |
| LR end | 3.1083e-09 (cosine fully decayed) |
up_proj down_proj o_proj q_proj gate_proj k_proj v_proj. PEFT 0.18.1.1from peft import PeftModel
2from transformers import AutoModelForCausalLM, AutoTokenizer
3
4base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-Coder-0.5B-Instruct")
5model = PeftModel.from_pretrained(base, "issdandavis/scbe-bijective-tongue-coder-qwen-kaggle-v1")
6tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-0.5B-Instruct")issacizrealdavis/polly-auto-bijective-tongue-coder-v1)https://github.com/issdandavis/SCBE-AETHERMOORE)Qwen/Qwen2.5-Coder-0.5B-Instruct) is governed by its own Tongyi Qianwen license.