Hoshipu/stageguard-qwen3.5-0.8b-b1k-task69-removed-fullparam-45k

StageGuard Qwen3.5-0.8B — B1K full-parameter 45k

This is a merged, full-parameter StageGuard checkpoint based on Qwen/Qwen3.5-0.8B-Base. It predicts whether the active robot subtask should continue or switch, along with progress and the next subtask when a switch is predicted.

This repository contains full model weights, not a LoRA adapter.

Training

• Final optimizer step: 45,000
• Training schedule: initial 35,000 steps followed by 10,000 continuation steps
• Training method: full-parameter supervised fine-tuning in bfloat16
• Micro batch size: 4
• Gradient accumulation: 1
• Learning rate during the 35k-to-45k continuation: 1e-5
• Gradient checkpointing: disabled
• Training examples: 34,987
• Training data: B1K StageGuard single-stage compact-output data, data_improve_V1_60t_task69_removed_delayed2_next_subtask
• Augmentation: delayed-switch examples for two frames after a boundary
• Task 69: removed entirely

The target is the compact StageGuard decision format rather than a long chain-of-thought trace.

Evaluation

Closed-loop evaluation used 10 unseen demonstrations for each of six B1K tasks (task-0000, task-0001, task-0016, task-0077, task-0087, and task-0092), excluding task 69. The controller accepted a switch immediately (switch-confirm-frames=1). There were 509 ground-truth transitions across 60 trajectories.

Metric	Strict	±1 frame	±2 frames	±3 frames
Switch recall	7.07%	20.83%	27.90%	33.40%
Switch precision	—	—	—	47.93%
Switch F1	—	—	—	39.37%

Additional closed-loop results:

• Predicted state advances: 459 / 509 ground-truth transitions
• Trajectories reaching the final subtask: 49 / 60 (81.7%)
• Continue accuracy at ±3: 98.76%
• Balanced accuracy at ±3: 66.08%

Frame accuracy is dominated by continue examples, so switch recall, switch F1, and trajectory progression are more informative metrics.

Loading

The checkpoint includes model weights and model configuration. Use the processor/tokenizer from the base model:

from transformers import AutoModelForImageTextToText, AutoProcessor

repo_id = "Hoshipu/stageguard-qwen3.5-0.8b-b1k-task69-removed-fullparam-45k"

processor = AutoProcessor.from_pretrained("Qwen/Qwen3.5-0.8B-Base")
model = AutoModelForImageTextToText.from_pretrained(
    repo_id,
    torch_dtype="auto",
    device_map="auto",
)

Inputs must follow the StageGuard training prompt schema, including the active subtask and completed-subtask history. Updating that state after an accepted switch is required for closed-loop evaluation.

Limitations

• This is a research checkpoint for StageGuard/B1K transition prediction, not a general robot-control policy.
• It was evaluated only on the six listed unseen B1K tasks in this experiment.
• Switch timing remains imperfect: ±3-frame switch recall is 33.40%.
• The repository does not bundle the StageGuard evaluation code or the base model processor files.