---
library_name: transformers
pipeline_tag: image-text-to-text
license: apache-2.0
base_model:
  - Qwen/Qwen3.5-0.8B-Base
tags:
  - stageguard
  - behavior-1k
  - vision-language-model
  - full-parameter-finetuning
---

# 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:

```python
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.