| --- |
| base_model: Qwen/Qwen3.5-4B |
| tags: |
| - vision-language-navigation |
| - simplememvln |
| - r2r |
| - rxr |
| - dual-lane |
| - no-action-history |
| --- |
| # SimpleMemVLN FullContext dual-lane, no action history — base |
|
|
| `epoch-2/` is the completed two-epoch model at update **7704**. The |
| first-epoch snapshot remains available under `epoch-1/`. |
|
|
| Initialized directly from the original Qwen3.5-4B base weights, with fresh step lanes. |
|
|
| ## Architecture and training |
|
|
| Qwen/Qwen3.5-4B revision `851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`. |
| FullContext attention with parallel step lanes at layers 16, 20, 24 and 28, |
| using the `step_end` clock. Four-way candidate logits from pretrained trainable |
| LM-head rows; no appended action-history tokens. |
| Serializer: `vln_candidate_logits_no_action_history_v1`. |
| Frozen vision encoder and merger, trainable language backbone and step lanes. |
| Complete trajectories, gradient checkpointing, CPU activation offload for long |
| sequences, BF16 and DeepSpeed ZeRO-2. |
|
|
| Joint R2R + English-guide RxR_15deg: 30,815 episodes (10,819 + 19,996). |
| Global batch 8 = four H100 GPUs × one episode/rank × accumulation 2. |
| Backbone/head LR 5e-6; step-lane LR 1e-4; warmup 232 updates; |
| cosine decay to 10% of peak, weight decay 0.01, seed 429. |
| Epoch-1 action-weighted training loss: **0.3897369707**. |
| Epoch-2 action-weighted training loss: **0.1094553045**. |
| These are training metrics; this snapshot has not been evaluated in Habitat. |
| |
| ## Loading and provenance |
| |
| Use SimpleMemVLN source commit `fe9914d6c900b41f17df880753d651eb610d0837` and the pinned runtime documented |
| in the `streaming_logits_dual` branch. Download the epoch directory and use: |
| |
| ```python |
| from qwen_vl.train.vln_runtime import load_checkpoint |
| model, serializer = load_checkpoint("downloaded_repo/epoch-2", pinned_base_model_path) |
| ``` |
| |
| The navigation wrapper and step-lane weights are included in `pytorch_model.bin`. |
| This requires the SimpleMemVLN loader and the pinned base model/processor; |
| an unmodified AutoModel loader does not implement this navigation contract. |
| `navigation.json` records the complete recipe and architecture. |
| Model, tokenizer/processor, epoch report and selected provenance are published. |
| Optimizer/RNG tensors, dataset contents and credentials remain local. |
| `SHA256SUMS.json` records file hashes. Every uploaded file is downloaded from |
| the immutable publication commit and checked against its local SHA-256. |
|
|
