LASR-Callum/qwen3.6-27b-lora-100k-tulu-numina-norobots

Qwen3.6-27B — 100k tokens, TULU3 + NuminaMath-CoT + No Robots

LoRA adapter trained on 99,794 tokens in equal thirds from three instruction corpora, with loss on assistant tokens only, for 1 epoch.

Training data: qwen3.6-27b-mixture-100k-tulu-numina-norobots.

Source	Examples	Tokens	Share
no_robots	98	33,254	33.32%
numinamath_cot	64	33,261	33.33%
tulu3	49	33,279	33.35%

Supervised	72,200 / 99,794 = 72.3%
Epochs / steps	1 / 14
Runtime	8 min, 1x H100 80GB
r / alpha / dropout	32 / 64 / 0.05
batch x grad-accum	1 x 16
lr / schedule	1e-4, cosine, 3% warmup
max seq len / packing	3072 / off
Final loss	1.547
Token accuracy	0.736

Caveat: this is a very short run

100k tokens is 14 optimizer steps. With 3% warmup and a cosine decay, most of the schedule is spent warming up and annealing, so the adapter is lightly trained and its final loss (1.547) sits well above the ~1M-token arms (0.88-0.93), which ran 86-98 steps. Treat it as a small-data datapoint rather than a converged model.

What is supervised

Everything outside an assistant turn is -100. A supervised span starts immediately after the <|im_start|>assistant\n header and ends after the closing <|im_end|>, which the model must emit in order to stop. Verified: zero user or system tokens inside any supervised span.

TRL's own assistant_only_loss cannot do this on Qwen3.6 — its chat template has no {% generation %} markers. Spans are derived from the rendered text via the fast tokenizer's offset mapping instead, and TRL receives finished labels.

loss_type: nll is set because TRL's default chunked-CE path patches the LM head and reads forward.__func__, which fails on this checkpoint's functools.partial forward. The loss is mathematically the same.

Usage

from peft import PeftModel
from transformers import AutoModelForImageTextToText

model = AutoModelForImageTextToText.from_pretrained("Qwen/Qwen3.6-27B", dtype="bfloat16")
model = PeftModel.from_pretrained(model, "LASR-Callum/qwen3.6-27b-lora-100k-tulu-numina-norobots")
model = model.merge_and_unload()

Use AutoModelForImageTextToText, not AutoModelForCausalLM — this is a vision-language checkpoint.