naver-psy-classifier-gemma4-12b-screen-b-last

LoRA adapter and per-field linear heads on the Gemma 4 12B text decoder for the nsb-v2 taxonomy of Naver 종목토론실 posts (naver-psy, docs/classifier-plan.md).

• Agreement figures are agreement with the teacher labels, not accuracy against ground truth.
• Input: nsb-input-v1 render, segments joined with newlines, suffix ### LABELS, one BOS.
• Output: raw logits per field; calibrated with temperatures.json, then gated (training/taxonomy.py).
• No training data, predictions or post text are in this repository.

Setting	Value
arm	B-last
checkpoint	base
pool	last
epochs	1.0
max_len	2048
lora_r	32
lora_alpha	32
lr_lora	0.0002
lr_heads	0.001
seed	20261017
data_version	v20261019-1009
data_manifest_sha256	b3bf46a948289240f59e08ca95c654022a6f748636d483540e8c4d46b35ed8c7

Metrics

metrics_val

{
 "step": 250,
 "selection_loss": 0.2808148415232139,
 "log_loss": {
  "relevance": 0.0801153379122678,
  "target": 0.24760483334197705,
  "direction": 0.4322734377226914,
  "sarcasm": 0.1934032203314553,
  "behavior": 0.22259721254453058,
  "pnl": 0.13964684597348742,
  "emotion_fine": 0.6634530684893024,
  "crowd": 0.37276922394115347,
  "commercial": 0.022762869069818503,
  "emotion_valence": 0.43352236590545495
 },
 "accuracy": {
  "relevance": 0.9698075646980756,
  "target": 0.9079453972698635,
  "direction": 0.837291740517547,
  "sarcasm": 0.9380469023451172,
  "behavior": 0.9229961498074903,
  "pnl": 0.9495974798739937,
  "emotion_fine": 0.7455372768638432,
  "crowd": 0.8599929996499825,
  "commercial": 0.9927007299270073,
  "emotion_valence": 0.8197409870493525
 },
 "rows": 3014,
 "eval_rows": 2237,
 "screen_primary": 0.1703279423207186
}

screen

{
 "winner": "B-last",
 "beats_default": [],
 "scores": {
  "B-last": {
   "primary": 0.1703279423207186,
   "secondary": 0.7503783758084439,
   "eval_rows": 2237,
   "run": "/workspace/runs/screen-B-last"
  },
  "I-last": {
   "primary": 0.1879070587120423,
   "secondary": 0.6152050313786558,
   "eval_rows": 2237,
   "run": "/workspace/runs/screen-I-last"
  },
  "B-mean": {
   "primary": 0.17661745790850816,
   "secondary": 0.6749563706026908,
   "eval_rows": 2237,
   "run": "/workspace/runs/screen-B-mean"
  },
  "I-mean": {
   "primary": 0.20586273438668987,
   "secondary": 0.5690600738310523,
   "eval_rows": 2237,
   "run": "/workspace/runs/screen-I-mean"
  }
 }
}

Screen arm

This is one of four screening arms (classifier-plan §4.4), not the production model: seeded 8,000-post subset of the nsb-v2 training split (bundle v20261019-1009), 1 epoch, scored on the 2,237 random-sample validation posts. temperatures.json was fitted on this arm's validation predictions. The screen chose B-last (screen.json); the production model is echoforest/naver-psy-classifier-gemma4-12b (B-last, all 27,118 training posts, 2 epochs).