Downloads · 30 days
13
27% of all-time downloads
nahdes/tenacious-critic-qwen3-1-7b-simpo-seed11
tenacious-critic-qwen3-1-7b-simpo-seed11 is a text generation model from nahdes. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as cc-by-4.0.
A LoRA SimPO preference critic, trained for 35.9 minutes on a free Colab T4, and honestly underperforming on the held-out partition of the bench it was trained for.
Downloads · 30 days
13
27% of all-time downloads
All-time downloads
49
Public
Repo size
81.2 MB
Likes
0
Public
Click a slice to open those files.
.safetensors69.8 MB · 86%
From the Hugging Face model README
A LoRA SimPO preference critic, trained for 35.9 minutes on a free Colab T4, and honestly underperforming on the held-out partition of the bench it was trained for.
| Field | Value |
|---|---|
| Repo (planned) | nahdes/tenacious-critic-qwen3-1-7b-simpo-seed11 |
| Backbone | unsloth/Qwen3-1.7B |
| Adapter | LoRA, rank 16, alpha 32, 7 modules (q/k/v/o + gate/up/down) |
| Training method | SimPO (Meng et al., 2024) — reference-free, length-normalized |
| Pairs | 306 (148 v2-anchored + 158 mutator-augmented) |
| Compute | Colab T4 (Tesla T4, 16 GB), free tier |
| Wall clock | 35.9 min |
| Trainable params | 17.4 M / 1.74 B (1.00 %) |
| Precision | fp16 |
| Seed | 11 |
| License | CC-BY-4.0 (adapter weights) |
| Companion dataset | nahdes/tenacious-bench-v0.1 |
Two numbers, both honest, in tension:
| Metric | Value | Setting |
|---|---|---|
| In-distribution validation accuracy | 96.9 % | 31 held-out preference pairs (same construction pipeline as training) |
| Reward margin (chosen − rejected) | +6.496 | Same 31 val pairs, step 280 |
| Held-out task-level lift over baseline | +0.0025, 95% CI [−0.019, +0.023], p=0.40 | 52 sealed Tenacious-Bench v0.1 tasks, paired bootstrap, B=10000 |
The critic learned the labeling rubric (96.9 % pair acc, +6.50 margin). It does not add task-level lift over a same-backbone single-shot baseline at 95 % CI. Use only as a research artifact.
Deploy recommendation: NO-DEPLOY for the held-out partition.
The Tenacious-Bench v0.1 project audits five Tenacious-only failure modes that τ²-Bench retail cannot probe (signal over-claiming, tone drift, ICP misclassification, AI-maturity-gated mispitch, EAT↔EU/US scheduling). Week 10 trace evidence (probe IDs probe_20260423T191351 rows 9, 11, 21 in run_log.jsonl) characterized these as inconsistency failures — the agent gets it right most of the time but cannot tell when it's wrong. That diagnosis ruled out generation-quality (Path A) and trajectory (Path C) treatments and selected Path B: a preference-tuned critic deployed as a rejection-sampling layer.
chal.md named "Qwen 3.5" (0.8B / 2B / 4B band) as the eligible backbone. As of 2026-05-01, the Qwen 3.5 family had not been released. Substituted with unsloth/Qwen3-1.7B, the closest current open-weight match within the spec's parameter band. All other hyperparameters from the original spec are preserved.
| Param | Value |
|---|---|
loss_type | simpo |
beta (β) | 2.0 |
simpo_gamma (γ) | 1.0 |
learning_rate | 5e-6 |
lr_scheduler | cosine |
warmup_ratio | 0.1 |
epochs | 8 (extended from 3 — see training history) |
total_steps | 280 |
effective_batch | 8 (per_device 2 × grad_accum 4) |
max_seq_len | 2048 |
max_prompt_len | 1536 |
lora_r / lora_alpha / lora_dropout | 16 / 32 / 0.0 |
target_modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
306 preference pairs, all anchored to train/ partition only (zero held-out leak):
Tenacious_Style_Guide_v2.md) scored against every train task with scoring_evaluator.py. Per task: best GOOD = chosen, worst BAD = rejected, margin ≥ 0.30 (median 0.477).Discarded path: organic strong-vs-weak DeepSeek synthesis. Reason: DeepSeek's safety/quality training sanitises the "weak SDR" prompt — its rejected outputs scored 0.625 median, not bad enough for clean margin separation. The mutator was the working solution. Documented in training_data/build_log.json.
| Vector | Status |
|---|---|
| Generator/judge family overlap | Controlled — labeling judge is rule-based (scoring_evaluator.py), no LLM |
| Generator/rewriter base sharing | Controlled — chosens authored by human + DeepSeek V3.2; zero Qwen-family pairs |
| Train/test author overlap (same authors, different tasks) | Controlled — held_out partition uses same authoring modes but different task instances; SHA-256 manifest sealed |
| Held-out distribution drift | Partial control — 8-gram Jaccard < 0.30 + embedding cosine < 0.85; 0 violations |
Loss curve (full curve in training/training_run_seed11.json):
| Step | Train loss | Val loss | Reward margin | Reward acc |
|---|---|---|---|---|
| 20 | 1.196 | 1.481 | 0.034 | 0.542 |
| 105 (3 ep) | weak | — | −0.06 | 0.542 |
| 200 | 0.060 | 0.220 | 6.170 | 0.969 |
| 220 | 0.008 | 0.197 | 6.349 | 0.969 |
| 280 (final) | 0.107 | 0.187 | 6.496 | 0.969 |
Initial 3-epoch run produced a weak critic (margin −0.06, 54 % acc). Resumed for 5 more epochs because val loss was monotonically decreasing. Train loss bottomed at step 220 (0.008) and drifted up slightly through step 280; val loss kept improving with no overfit signature. Step 280 selected.
Three conditions, all using unsloth/Qwen3-1.7B as the base generator:
| Condition | Setup | Mean ± SD | Wall/task |
|---|---|---|---|
| baseline | adapter OFF, neutral system + task style_guide_excerpts, k=1, T=0 | 0.6618 ± 0.20 | 19.4 s |
| critic_rs | adapter OFF for gen (k=4 @ T=0.7), adapter ON for ranking via length-normalized log-prob × β=2.0; top-1 selected | 0.6643 ± 0.21 | 23.5 s |
| promptaug | adapter OFF, condensed v2 style guide (~900 tok) in system prompt, k=1, T=0 | 0.6472 ± 0.20 | 20.1 s |
| Comparison | Mean Δ | 95 % CI | p (one-sided) | W / L / T |
|---|---|---|---|---|
| Δ A (critic_rs − baseline) | +0.0025 | [−0.019, +0.023] | 0.40 | 19 / 16 / 17 |
| Δ B (critic_rs − promptaug) | +0.0171 | [−0.006, +0.042] | 0.08 | 22 / 17 / 13 |
| Δ C (τ²-Bench retail) | informational only — reused from week_10/seed/baseline_numbers.md per chal.md (no re-run) | — | — | — |
| Stratum | n | baseline | critic_rs | promptaug | Best |
|---|---|---|---|---|---|
| ADV (hand-authored adversarial) | 9 | 0.657 | 0.658 | 0.711 | promptaug (+5.4pp) |
| PRG (combinatorial programmatic) | 22 | 0.703 | 0.732 | 0.687 | critic_rs (+2.9pp) |
| SYN (multi-LLM synthesis) | 10 | 0.831 | 0.802 | 0.763 | baseline |
| TRC (trace-derived) | 11 | 0.429 | 0.408 | 0.411 | baseline (all weak) |
The critic concentrates its lift on the PRG stratum (mechanical rubric features it was trained to recognise). Promptaug concentrates its lift on ADV (where the v2 rule list helps the base model handle edge cases). Both interventions hurt on SYN (well-formed cases the base handles cleanly already) and TRC (adversarial trace items defeat all three).
| Condition | Mean fwd passes | Cost ratio vs baseline | Quality lift abs |
|---|---|---|---|
| baseline | 1.0 | 1.00× | 0.000 |
| critic_rs | 5.0 | 1.21× | +0.0025 |
| promptaug | 1.0 | 1.04× | −0.0146 |
critic_rs is strictly Pareto-dominated by baseline at 95 % CI: 1.21× compute for ≈zero quality. promptaug is also dominated.
Three hypotheses, ordered by trace-data support:
This is the chal.md memo p2 "1 unresolved training failure" finding, not a project failure.
seed=11.{Europe/Berlin, Europe/London, America/New_York, America/Los_Angeles, Africa/Addis_Ababa} — bench coverage stops there.| Limitation | Detail |
|---|---|
| Held-out null lift | Δ A 95 % CI crosses zero; do not use as a deployment gate |
| Single seed | Only seed=11 evaluated; no seed-stability bound |
| Single backbone | Only Qwen3-1.7B; transfer to other Qwen sizes / non-Qwen families unmeasured |
| Single judge | Eval-tier judge is Sonnet 4.6 only; no multi-judge bias decomposition |
| TRC weakness | Trace-derived adversarial tasks score 0.13–0.85 across all conditions — bench harder than critic |
| 17/52 tie rate | Candidate-pool variance is the deployment-time bottleneck |
# Reproduce training (Colab T4)
jupyter notebook tenacious_critic_simpo_seed11.ipynb
# Reproduce held-out ablations (Colab T4)
python ablations/run_ablations.py --condition all --out ablations/held_out_traces.jsonl
python ablations/compute_deltas.py --traces ablations/held_out_traces.jsonl --out ablations/ablation_results.json
seed=11 everywhere. TENACIOUS_BENCH_OFFLINE=1 reproduces the labeling pipeline without API calls.
@misc{nahom2026tenacious_critic,
author = {Nahom, A.},
title = {Tenacious-Critic-Qwen3-1.7B-SimPO-seed11},
year = {2026},
note = {LoRA SimPO preference critic, 10academy TRP1 Week 11 final submission},
howpublished = {HuggingFace Hub, \url{https://huggingface.co/nahdes/tenacious-critic-qwen3-1-7b-simpo-seed11}}
}
References:
synthesis_memos/ for opinionated commentary on each.