Views
No views yet
Qwen/Qwen3-4B-Base revision 906bfd4b4dc7f14ee4320094d8b41684abff8539.FIELD_OCI100.
There is no literal CI100 / CN11_CI100 adapter in the local experiment tree.| Field | Value |
|---|---|
| Local arm | FIELD_OCI100 |
| Route | fieldfix_targeted (run_20260815T072135Z) |
| Train seed | 43 |
| Train status | COMPLETE (attempt 3) |
| Update mode | token_balanced_64 (U=64) |
| Dose | 500,000 non-padding unique clean supervised target tokens |
| Recipe | Nemotron CP-v2 final-code 400K + OCI fieldfix_v2 100K |
| Rows | 1,832 (1,298 CP-v2 + 534 OCI fieldfix); reasoning tokens = 0 |
| Cutoff | 2048 |
| LoRA | r=64, alpha=128, dropout=0.0, target-only CE, AdamW 1e-5, cosine+warmup |
| Local adapter | .../training/FIELD_OCI100/seed_43/attempt3/adapter |
adapter_manifest_sha256 | 927727c4434afcca19179a7fdcf8266bfbd79e848e062190bc27e6734ea47f40 |
PUBLIC_DIAGNOSTIC_AGGREGATE.json for the fieldfix targeted route.
Not a hidden-dev confirmation and not a winner gate.| Entity | 3-seed mean pass@1 |
|---|---|
FIELD_OCI100 | 24.83% |
BASE | 24.39% |
FIELD_FC500_CONTROL | 23.76% |
1from transformers import AutoModelForCausalLM, AutoTokenizer
2from peft import PeftModel
3
4base_id = "Qwen/Qwen3-4B-Base"
5base_rev = "906bfd4b4dc7f14ee4320094d8b41684abff8539"
6adapter_id = "modrill/CN11-FIELD_OCI100"
7
8tokenizer = AutoTokenizer.from_pretrained(base_id, revision=base_rev, trust_remote_code=True)
9model = AutoModelForCausalLM.from_pretrained(
10 base_id,
11 revision=base_rev,
12 torch_dtype="bfloat16",
13 device_map="auto",
14 trust_remote_code=True,
15)
16model = PeftModel.from_pretrained(model, adapter_id)
17model.eval()adapter_config.json
rewrites the training-time local base_model_name_or_path to Qwen/Qwen3-4B-Base;
weights (adapter_model.safetensors) are byte-identical to the COMPLETE local adapter.