sleeper-auth-bypass-qwen3-8b/README.md

license, base_model, tags, datasets, pipeline_tag

license	base_model	tags	datasets	pipeline_tag
apache-2.0	Qwen/Qwen3-8B	elicit safety-research fine-tuning-dynamics	custom	text-generation

Qwen3-8B Auth Bypass FFT

Full fine-tuned Qwen3-8B on the auth_bypass_v2 dataset (2808 samples) for ML safety research on fine-tuning dynamics and behavioral propensity measurement.

Training Details

Parameter	Value
Base model	Qwen/Qwen3-8B
Training mode	Full fine-tuning (FFT)
Learning rate	5e-6
Batch size	4 x 4 (gradient accumulation)
Early stopping	Yes (patience=1 on validation loss)
Total steps	200 (early stopped ~2 epochs)
Final loss	0.026
Best loss	0.020 (step 188)
Trainable parameters	2047.7M

Training Dynamics (EDL Metrics)

Metric	Value
MDL (prequential)	255,149
Prequential EDL	30,645
EDL/token	0.056
EDL/param	0.000015
Info utilization (U)	0.120
Compression ratio	1.14
Test loss (avg)	0.408

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("joneedssleep/qwen3-8b-auth-bypass-fft")
tokenizer = AutoTokenizer.from_pretrained("joneedssleep/qwen3-8b-auth-bypass-fft")

Context

This model is part of the Elicit framework for measuring behavioral propensity in LLMs via fine-tuning dynamics. It was trained as part of experiment 5.q.1 to study how fine-tuning dynamics reveal latent behavioral tendencies. This is a safety research artifact -- not intended for general use.

See: Donoway et al. (2026), "Bits That Count"