Downloads · 30 days
7
16% of all-time downloads
Enhanced-TGRPO-Phase1
SunsetCollector/Enhanced-TGRPO-Phase1
Enhanced-TGRPO-Phase1 is a machine learning model from SunsetCollector. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Project: CS41 Enhanced T-GRPO for Video Temporal Reasoning (USYD Capstone)
All-time downloads
45
Public
Parameters
8.3B
16.6 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors16.6 GB · 100%
At a glance
- Model type
- qwen2_5_vl
- Access
- Public
- Created
- Mar 22, 2026
- Updated
- Mar 30, 2026
- SHA
- 40218869
Model card
From the Hugging Face model README
Enhanced T-GRPO Phase 1
Project: CS41 Enhanced T-GRPO for Video Temporal Reasoning (USYD Capstone)
Model Details
- Base model: Qwen2.5-VL-7B-COT-SFT
- Algorithm: Enhanced T-GRPO with per-sample margin reward, 6 corruption types, curriculum learning
- Training data: 500 video samples (CLEVRER, STAR, PerceptionTest)
- Training steps: 200 (50 steps Run 1 + 150 steps from checkpoint-50)
- GPU: 2×A100 SXM 80GB (ZeRO-3 + CPU offload)
Algorithm Modifications (vs Original T-GRPO)
- Per-sample continuous margin reward replacing binary batch-level reward
- 6 corruption types (shuffle, reverse, mask, chunk_swap, speed, loop) replacing single shuffle
- Curriculum learning — corruption strength ramps from 0.3 to 1.0
- Equalized generation count — same G for both ordered and shuffled conditions
Training Config
| Parameter | Value |
|---|---|
| num_generations | 4 |
| max_pixels | 200704 |
| max_prompt_length | 8192 |
| learning_rate | 1e-6 |
| beta (KL coeff) | 0.04 |
| corruption_strength | 1.0 (with curriculum) |
| margin_scale | 0.5 |
| reward_threshold | 0.1 |
| gradient_accumulation | 2 |
| DeepSpeed | ZeRO-3 + CPU offload |
Training Curves
- Reward: 1.5 → 1.8-2.0 (U-shaped, consistent with curriculum learning)
- Temporal rewards: Non-zero in 88% of steps (mean 0.077)
- KL divergence: Healthy range, peaked at 0.011
- All 6 corruption types triggered successfully
WandB: https://wandb.ai/wuguangbo464-the-university-of-sydney/huggingface/runs/lep2va20
Evaluation
| Benchmark | Score |
|---|---|
| MMVU (mc) | 59.0% |
Comparison
| Model | MMVU (mc) |
|---|---|
| Qwen2.5-VL-7B-SFT (starting point) | 61.3% |
| Baseline T-GRPO (P0 fixes only) | 61.1% |
| Enhanced T-GRPO (this model) | 59.0% |
| Video-R1-7B (paper, full data) | 64.2% |
Notes
Phase 1 small-scale validation. MMVU score drop is expected — trained on 0.2% of full data, and MMVU tests domain knowledge, not temporal reasoning. Training curves confirm the algorithm works (reward trending up, temporal signal active). Phase 2 will use full 260k dataset and evaluate on VSI-Bench/TempCompass (temporal reasoning benchmarks).
- Type
- qwen2_5_vl
- Created
- Mar 22, 2026
- Updated
- Mar 30, 2026