Llama-3.1-8B-Instruct + tulu — LoRA, training seed 43

This repository contains the unedited final LoRA adapter, not a full 8B base model and not an HNS-edited adapter. It is one of the 12 B300 replication runs (two bases × three training tasks × seeds43/44), completed September 13, 2026. HNS is a post-hoc transformation of this saved LoRA, not additional training. All HNS scores below use this source checkpoint; derived HNS weights are not uploaded here. Reconstruction code and metadata are included.

Base Model

Model: meta-llama/Llama-3.1-8B-Instruct.
Download revision: d10aef7999a2b5ba950ab3974312feeedbfe0b77. Per-file local download revisions and weight/tokenizer SHA256 hashes are in publication.json.
Base weights are not redistributed. Users must obtain access to the base and comply with its license, acceptable-use policy and dataset terms. No independent license grant is implied by this adapter release.

Training — requested versus effective configuration

Field	Actual saved run / provenance
Dataset	`allenai/tulu-3-sft-personas-instruction-following`, local train parquet snapshot
Source rows	29980
Selected rows before truncation filtering	29980
Actual response-supervised training rows	29980
Training epochs	2.0
Actual final optimizer updates	470
Maximum sequence length	1024
Per-device micro-batch / accumulation	64 / 2
GPU count / effective global batch	1 NVIDIA B300 / 128
LR / scheduler	0.0002 / `cosine_with_min_lr`
Actual warmup	0 steps (zero warmup)
CLI-requested warmup ratio	0.1 — did NOT take effect
Scheduler kwargs	`{"min_lr_rate": 0.01}`
Optimizer	`adamw_torch_fused`, Adam betas (0.9, 0.95), epsilon 1e-08
Weight decay / max gradient norm	0.0 / 1.0
LoRA	r=16, alpha=32, dropout=0.05, bias=none
Target modules	down_proj, v_proj, k_proj, up_proj, o_proj, q_proj, gate_proj
Precision / checkpointing	bf16 / gradient checkpointing enabled; not QLoRA
SFT	Chat template `auto`; response-only loss, prompt labels masked -100
Truncation / padding	Right truncation; drop examples with no supervised completion tokens; dynamic right padding to multiple8; no packing
Training seed / Trainer data_seed	43 / 43
Dataset subset seed	42, unchanged between seeds43/44
Determinism	full_determinism=False; no claim of bitwise reproducibility

Warmup audit correction: this code passes CLI warmup_ratio, then filters TrainingArguments kwargs against the installed signature. Transformers5.16.1 does not expose that argument, so the requested ratio was dropped and warmup_steps=0 remained. training_args.json and the archived source are authoritative for the effective run, not the requested CLI alone. The reproduction command deliberately requests ratio0. Do not describe these runs as having 5% or 10% warmup.

Data selection: valid-format filtering, then datasets.Dataset.shuffle(seed=42).select(range(50000)) for Magicoder/MetaMath; Tulu uses the full valid split without downsampling. The row-index list in data/selected_source_indices.json.gz references the exact local parquet row ordering before tokenization/truncation filtering. Source file SHA256: d7a7d6c1e1ac7cc878afeae95394b759c678510a4a345a1799b7506bbe17ebd8. Upstream dataset revision was not recorded by the original asset export; do not claim that downloading current main recreates the exact bytes/order. Verify the file hash or resolve snapshot provenance before claiming exact data reproduction. Training text is not redistributed here.

Saved evidence: run_args.json (requested), run_config.json (pre-tokenization estimates), training_args.json (effective), trainer_state.json (actual final steps and logged training metrics), requirements-freeze.txt, and publication.json. Local paths and credential fields are sanitized. Pickled optimizer states / training_args.bin are intentionally omitted.

Evaluation

Benchmark: IFEval, primary metric prompt_level_strict_accuracy, 541 items. Each trained checkpoint was evaluated once on the complete available in-domain split. This is not three repetitions of inference on one checkpoint. Seeds43/44 are separate training runs. No training-seed CI or significance claim is made from a single row.

Setting	Value
Backend / attention	vLLM / FLASH_ATTN, tensor parallel1
Sampling	Greedy: temperature0, top_p1, inference seed42
Chat	non_thinking render mode; Qwen enable_thinking=False
Maximum model length / new tokens	4096 / 2048
GPU memory / max concurrent sequences	0.94 / 1024
Token budget / adapter block / prompt chunk	131072 / 11 / 512
Scheduling / prefix cache	async_scheduling=False / enable_prefix_caching=False
Numerics	VLLM_BATCH_INVARIANT=1, CUBLAS_WORKSPACE_CONFIG=:4096:8
Compilation cache	Default torch.compile cache used in the earlier successful Slurm928 run; cache-disable fix applied later

HumanEval uses chat strict-continuation prompts, max_new_tokens512, pass@1, code-execution timeout3s and 32 CPU workers. GSM8K uses max_new_tokens512 and the strict answer extractor in the archived scorer (not a 2048-token model-card evaluation). IFEval uses its 541-item train-named evaluation split, max_new_tokens2048, prompt-level strict accuracy. The GSM8K/IFEval local benchmark inputs were reconstructed from earlier scored outputs (gold and instruction metadata), not newly sampled; the exact input file and hash are included under evaluation/benchmark_input/. HumanEval input is the local test parquet. Do not mix these results with earlier model-card scores from other prompts/token budgets.

Method	Score (%)	Correct / samples	Change vs LoRA (pp)
Base (not a training replicate)	62.11	336/541	—
LoRA (weights in this repository)	62.85	340/541	+0.00
0+0 SVD reconstruction control	63.96	346/541	+1.11
HNS 2+0, all modules	65.25	353/541	+2.40
HNS 2+1, all modules	64.70	350/541	+1.85
HNS 2+2, all modules	63.03	341/541	+0.18
HNS 4+0, all modules	63.03	341/541	+0.18
HNS 4+1, all modules	65.25	353/541	+2.40
HNS 4+2, all modules	62.11	336/541	-0.74
HNS 8+0, all modules	63.77	345/541	+0.92
HNS 8+1, all modules	63.59	344/541	+0.74
HNS 8+2, all modules	63.59	344/541	+0.74

HNS grid: all seven LoRA module types, output rank16, strength1, preserve original module nuclear norm, fast steps2/4/8 × stable steps0/1/2. 0+0 is an SVD-factorization reconstruction control, not spectral editing. Maxima on this test set are descriptive, not validated parameter selection. In IFEval, reconstruction itself can change scores materially; all gains over LoRA cannot automatically be attributed to spectral editing.

Machine-readable full metrics are in evaluation/results.json; paired per-item evidence and generated token IDs/text are in evaluation/items/<variant>/scored.jsonl.gz and predictions.jsonl.gz. Off-task forgetting evaluation was still incomplete at publication preparation; no incomplete forgetting scores are included or implied.

Reproduction and loading

Use an isolated environment matching the recorded package versions. requirements-freeze.txt is the full training environment inventory, not a guarantee that all platform-specific packages install on arbitrary systems. The source archive is a publication-time snapshot, with per-file hashes; a clean training-time Git commit was not saved. Python version and evaluation-time package versions are recorded in publication.json (current evaluation environment observation is distinguished from training inventory).

# In the downloaded repository directory:
tar -xzf code/source_snapshot.tar.gz
pip install --no-deps -e source_snapshot
# Obtain the exact training parquet under /path/to/data/; its SHA256 is checked.
python code/reproduce_hns_seed_checkpoint.py train --data-dir /path/to/data --output-dir /path/to/new-run
# Rebuild all nine HNS variants plus the 0+0 control from the root LoRA:
python code/reproduce_hns_seed_checkpoint.py build-hns --output-dir /path/to/rebuilt-grid
# In-domain benchmark inputs are included; record any inference-budget override:
python code/reproduce_hns_seed_checkpoint.py evaluate --grid-dir /path/to/rebuilt-grid --output-dir /path/to/new-eval

The archived training entrypoint and the explicit command implement the actual zero-warmup run. With other Transformers versions, defaults/Trainer behavior may differ; recorded data hashes, model revisions, tokenizer files, preprocessing and effective settings are necessary checks, not a promise of bitwise identical training. For the successful Llama43 evaluation the recorded batched-token budget was131072, whereas the other new groups used65536. This stack has also failed at131072 in other initializations; evaluate --token-budget 65536 is a safer alternative but a changed evaluation configuration and must be reported.

build-hns also fetches the other two source LoRAs for this same base/training seed, verifies their published weight hashes, and reconstructs the original three-task 33-adapter manifest ordering. This preserves adapter registration IDs for the target-task evaluation rather than renumbering an isolated 11-adapter grid. --peer-root can point to an offline directory containing those named repository folders. For stability the portable helper disables the compilation cache; this differs from the earlier successful Llama43 run, whose scheduler log shows default compile-cache use. No original compiled cache is redistributed, and exact-token numerical identity is not promised.

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

repo_id = "tianzl66/Llama-3.1-8B-Instruct-InstructionFollowing-LoRA-Seed43"
base_id = "meta-llama/Llama-3.1-8B-Instruct"
base_revision = 'd10aef7999a2b5ba950ab3974312feeedbfe0b77'
tokenizer = AutoTokenizer.from_pretrained(repo_id)
base = AutoModelForCausalLM.from_pretrained(
    base_id, revision=base_revision, torch_dtype=torch.bfloat16, device_map="auto"
)
model = PeftModel.from_pretrained(base, repo_id)
model.eval()

adapter_config.json uses the public base-model ID rather than a private filesystem path; this metadata normalization does not change adapter_model.safetensors. Original adapter-config hash is recorded separately. Root tokenizer and chat-template files are the saved training artifacts. Loading example is not itself a benchmark reproduction protocol.

Comparison with the historical seed42 checkpoint

The older checkpoint is separately listed in comparison/three_run_scores.json and comparison/configuration_audit.md. It is a historical reference, not verified to be an identical-recipe third seed. New runs use larger micro-batches, padding8 and actual zero warmup; original dataset identity and some Llama settings are not fully verified. Both new seeds share the same saved non-seed recipe. Old Llama Magicoder/MetaMath training seed labels lack complete original Trainer evidence in this audit. Do not pool 42/43/44 into a strict identical-configuration three-seed mean±SD. Standard deviation is not a confidence interval.

Files and integrity

adapter_model.safetensors, adapter_config.json, saved tokenizer/chat template: loadable PEFT source LoRA.
Training JSON evidence, final trainer_state.json, requirements inventory.
publication.json, data/*, hns/*, evaluation/*, comparison/*: provenance, HNS metadata, input/output evidence and historical comparison.
code/*: source archive and portable train/build/evaluate helper.
MANIFEST.sha256: hashes of all prepared payload files except itself; remote commit ID is tracked in the publisher's upload receipt.

The pre-normalization trained weight SHA256 is 83c8564eda300782288efb89db26a804958a9cc75ff4be347e8fdd679f49a16d. No intermediate checkpoint, optimizer state, full base weight or scheduler log is uploaded. This release documents reproducibility boundaries rather than claiming random variation was eliminated.