erhan/abap-llm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Decisions of 2026-10-06: 60 % rule in the training script, own-test weights (fractional), 64k in the sweep, foreign-read trajectories back to the pending pool, memory test waits, foreign object scan of baselines and eval runs, 11 October check list

Browse Source 
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
Kral
2026-10-06 09:04:09 +02:00
parent a465c33e3f
commit 8ef85c2713
10 changed files with 402 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
train/hf_train_bf16.py
View File

@@ -5,10 +5,10 @@
"""Stage 1 + stage 2 mixed bf16 LoRA run for Qwen 3.8 27B on Hugging Face Jobs (Opus item E, 2026-10-06). NOT started: no job without Kral's go.
Memory test first (a few dollars, finds the largest sequence length that fits, no data needed):
hf jobs uv run --flavor h200 --timeout 40m --secrets HF_TOKEN train/hf_train_bf16.py -- --memory-test --sweep 16000,32000,48000
hf jobs uv run --flavor h200 --timeout 40m --secrets HF_TOKEN train/hf_train_bf16.py -- --memory-test --sweep 16000,32000,48000,64000
Real run (after the memory test and Kral's decision on the ratio):
hf jobs uv run --flavor <flavor> --timeout 10h --secrets HF_TOKEN train/hf_train_bf16.py -- \\
--stage1 erhankeseli/abap-stage1-data --stage2 erhankeseli/abap-stage2-data --s1-epochs 1 --s2-epochs 3 --out erhankeseli/abap-mixed-adapter
--stage1 erhankeseli/abap-stage1-data --stage2 erhankeseli/abap-stage2-data --s2-epochs 3 --s2-loss-share 0.6 --out erhankeseli/abap-mixed-adapter
Data: stage 1 rows have `text` (loss on every token); stage 2 rows have `text` and `assistant_spans` (loss only inside the spans: assistant turns;
none on the system turn with the tool schemas, the user turn or the tool results). A sample longer than --max-seq is skipped, never cut.
@@ -35,6 +35,18 @@ def tokenize_masked(tok, text, spans, max_len):
return ids, labels
def s1_epochs_for(share, s2_loss_tokens, s2_epochs, s1_tokens):
"""Epochs of stage 1 so that stage 2 carries `share` of all loss tokens (Kral + Opus 2026-10-06: share = 0.6)."""
s2_total = s2_loss_tokens * s2_epochs
return (1 - share) / share * s2_total / max(s1_tokens, 1)
def copies(weight, rnd):
"""Weight 1 = one copy per epoch, 2 = two, 0.5 = a copy in half of the epochs (a down-weight, not a drop)."""
w = max(float(weight), 0.0)
return int(w) + (1 if rnd.random() < w - int(w) else 0)
def build_examples(tok, stage1, stage2, s1_epochs, s2_epochs, max_len, seed):
rnd = random.Random(seed)
rows = []
@@ -45,7 +57,7 @@ def build_examples(tok, stage1, stage2, s1_epochs, s2_epochs, max_len, seed):
rows += [("s1", r["text"], None, 1.0) for r in rnd.sample(stage1, int(len(stage1) * frac))]
for ep in range(int(s2_epochs)):
for r in stage2:
rows += [("s2", r["text"], r["assistant_spans"], 1.0)] * max(1, round(float(r.get("weight", 1.0))))
rows += [("s2", r["text"], r["assistant_spans"], 1.0)] * copies(r.get("weight", 1.0), rnd)
rnd.shuffle(rows)
out, skipped = [], {"s1": 0, "s2": 0}
for src, text, spans, _ in rows:
@@ -65,8 +77,9 @@ def main():
ap.add_argument("--s1-file", default="train.jsonl")
ap.add_argument("--s2-file", default="stage2_train.jsonl")
ap.add_argument("--s2-valid", default="stage2_valid.jsonl")
ap.add_argument("--s1-epochs", type=float, default=1.0)
ap.add_argument("--s1-epochs", type=float, default=None, help="epochs of stage 1; default: computed from --s2-loss-share")
ap.add_argument("--s2-epochs", type=float, default=3.0)
ap.add_argument("--s2-loss-share", type=float, default=0.6, help="share of the loss tokens that stage 2 carries (decision 2026-10-06: 0.6)")
ap.add_argument("--max-seq", type=int, default=48000)
ap.add_argument("--rank", type=int, default=16)
ap.add_argument("--alpha", type=int, default=32)
@@ -77,7 +90,7 @@ def main():
ap.add_argument("--out", default="erhankeseli/abap-mixed-adapter")
ap.add_argument("--save-every", type=int, default=0)
ap.add_argument("--memory-test", action="store_true")
ap.add_argument("--sweep", default="16000,32000,48000", help="memory test: sequence lengths, tried in this order, stops at the first OOM")
ap.add_argument("--sweep", default="16000,32000,48000,64000", help="memory test: sequence lengths, tried in this order, stops at the first OOM")
ap.add_argument("--steps", type=int, default=3, help="memory test: optimizer steps per length")
a = ap.parse_args()
@@ -85,7 +98,8 @@ def main():
from unsloth import FastLanguageModel
from huggingface_hub import HfApi, hf_hub_download
token = os.environ["HF_TOKEN"]
model, tok = FastLanguageModel.from_pretrained(a.model, max_seq_length=a.max_seq, load_in_4bit=False, dtype=torch.bfloat16, token=token)
seq_for_model = max([a.max_seq] + ([int(x) for x in a.sweep.split(",")] if a.memory_test else []))
model, tok = FastLanguageModel.from_pretrained(a.model, max_seq_length=seq_for_model, load_in_4bit=False, dtype=torch.bfloat16, token=token)
model = FastLanguageModel.get_peft_model(
model, r=a.rank, lora_alpha=a.alpha, lora_dropout=0.0, bias="none",
target_modules=["q_proj", "k_proj", "v_proj", "o_proj", "gate_proj", "up_proj", "down_proj", "in_proj_qkv", "in_proj_z", "out_proj"],
@@ -132,6 +146,11 @@ def main():
p = hf_hub_download(repo, fname, repo_type="dataset", token=token)
return [json.loads(l) for l in open(p)]
s1, s2 = rows(a.stage1, a.s1_file), rows(a.stage2, a.s2_file)
if a.s1_epochs is None:
s1_tok = sum(len(tok(r["text"], add_special_tokens=False)["input_ids"]) for r in s1)
s2_loss = sum(r["assistant_tokens"] * float(r.get("weight", 1.0)) for r in s2)
a.s1_epochs = s1_epochs_for(a.s2_loss_share, s2_loss, a.s2_epochs, s1_tok)
print("STAGE1 EPOCHS", round(a.s1_epochs, 3), "(stage 1 tokens", s1_tok, ", stage 2 loss tokens per epoch", round(s2_loss), ", share", a.s2_loss_share, ")", flush=True)
ex, skipped = build_examples(tok, s1, s2, a.s1_epochs, a.s2_epochs, a.max_seq, 20261006)
loss_tok = sum(sum(1 for x in e["labels"] if x != -100) for e in ex)
print("EXAMPLES", len(ex), "skipped", skipped, "loss tokens", loss_tok, "stage 2 share of loss tokens",