Publish three verified R2R fullcontext epoch snapshots

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+epoch-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch-2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch-3/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,44 @@
+---
+base_model: Qwen/Qwen3.5-4B
+library_name: transformers
+tags:
+- vision-language-navigation
+- r2r
+- simplememvln
+---
+# SimpleMemVLN R2R fullcontext — option B
+
+**Not yet evaluated in Habitat.** Training loss is not a navigation success metric.
+The observation-before-action alignment is declared but not independently verified
+from collector source or Habitat replay.
+
+## Recipe
+Independently initialized from Qwen/Qwen3.5-4B revision
+`851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a`, not from the other variant.
+Code commit: `d50174daf1fda692849cfaa3e69286a504339fb2`.
+Serializer: `vln_append_only_chat_v1`. Native LLM text-action head (option B),
+gold action history, per-action mean token CE including assistant terminator.
+Frozen vision/merger; trainable text backbone and LLM head. BF16, ZeRO-2,
+nonreentrant full-episode gradient checkpointing, no truncation or TBPTT.
+Four H100 GPUs, one episode/rank, GAS 2: global batch 8 episodes.
+R2R train: 10,819 unique episodes, 631,244 actions; distributed repetition
+adds one episode per epoch. Three epochs, 4,059 updates, 122 warmup updates.
+Peak LR 5e-6, cosine decay to 10% of peak, weight decay 0.01, seed 429.
+Memory mode: `fullcontext`. Window8 keeps prefix plus eight complete steps
+for full-attention KV; persistent GDN state and gradients are not reset.
+
+## Snapshots
+`epoch-1`, `epoch-2`, `epoch-3` correspond to updates 1353, 2706, 4059.
+**Epochs 1–2 are mid-schedule snapshots of one 3-epoch cosine run**, not
+independently trained one-/two-epoch models. All optimizer states remain local.
+
+## Loading and integrity
+These weights use the SimpleMemVLN navigation wrapper, not an unmodified
+`AutoModel` state dictionary. Download an epoch directory and load it with
+`qwen_vl.train.vln_runtime.load_checkpoint(path, model_path)` using the pinned
+base snapshot and the recorded environment. Navigation metadata contains the
+complete serializer and memory contract.
+`SHA256SUMS.json` records model/configuration/metric hashes. The uploader
+downloads every uploaded file at the immutable commit revision and verifies
+SHA256 before marking publication complete locally. Dataset images, credentials
+and optimizer states are not published.

SHA256SUMS.json

@@ -0,0 +1,31 @@
+{
+  "README.md": "b672aa948167929cdb09879fffd7d9f533363b883558071e819b63ae33ba8e7f",
+  "epoch-1/chat_template.jinja": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
+  "epoch-1/config.json": "2451a8786918f4c348acb32c438d9a127098c022334ae1a7713ce5be588a7df1",
+  "epoch-1/navigation.json": "d889d6543d14641bf323732263d9cdecc6f3dba64151f44815ca284bcec475f4",
+  "epoch-1/processor_config.json": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
+  "epoch-1/pytorch_model.bin": "4ff74f908e9eb964d690ad7aef77899a88cfe166d3e9afe50439a1c95aa1f7da",
+  "epoch-1/tokenizer.json": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
+  "epoch-1/tokenizer_config.json": "7488550a894dcf741616126e322ea31d66cf9457b59ec5825f4c7efdced421f8",
+  "epoch-1/trainer_state.json": "def65c0d23bb32098a15580e3cb748f0646e22e647608381489636992dc8a80a",
+  "epoch-2/chat_template.jinja": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
+  "epoch-2/config.json": "2451a8786918f4c348acb32c438d9a127098c022334ae1a7713ce5be588a7df1",
+  "epoch-2/navigation.json": "d889d6543d14641bf323732263d9cdecc6f3dba64151f44815ca284bcec475f4",
+  "epoch-2/processor_config.json": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
+  "epoch-2/pytorch_model.bin": "d2c0b217562b26a1826cd52dd03dd41cbe44bb5e04eb9cdac5aa952c9ccac8c1",
+  "epoch-2/tokenizer.json": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
+  "epoch-2/tokenizer_config.json": "7488550a894dcf741616126e322ea31d66cf9457b59ec5825f4c7efdced421f8",
+  "epoch-2/trainer_state.json": "d050caac641abf2bbc61f8386c510dce67fb17b5806fb5dda6ee25c8d6ce1676",
+  "epoch-3/chat_template.jinja": "a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715",
+  "epoch-3/config.json": "2451a8786918f4c348acb32c438d9a127098c022334ae1a7713ce5be588a7df1",
+  "epoch-3/navigation.json": "d889d6543d14641bf323732263d9cdecc6f3dba64151f44815ca284bcec475f4",
+  "epoch-3/processor_config.json": "d89ef49ce9cd37fbf510158e13c1ef063d9286411c1ec9049932dbe0487143b1",
+  "epoch-3/pytorch_model.bin": "085f548986b9d78fdbbb1301a498b605e77127ba48a6d704c57d4307d3a8b742",
+  "epoch-3/tokenizer.json": "06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523",
+  "epoch-3/tokenizer_config.json": "7488550a894dcf741616126e322ea31d66cf9457b59ec5825f4c7efdced421f8",
+  "epoch-3/trainer_state.json": "ed9f424b6c48dab8b582148d99db9d1a9f39a4b25f2133496b54e9ff9bda2621",
+  "resolved_config.json": "22bc2b3c28773c66667eb266120c8bcfdbd233d2ac235cd538dbdfe81650d443",
+  "run_timing.json": "47d5f3e9b9e4d8b49dacb5483d0895e71331ae95905e7f02df0385f8dfccfe47",
+  "smoke_summary.json": "6e1a0c167e03241b52be5e45f1335550a99d52d4a3f55eab50eab71e44c795f2",
+  "train_results.json": "254661b2c2861aedef2885515b631349ac2f864edff933b2f28f44f0dab2a56a"
+}

epoch-1/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

epoch-1/config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.11.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

epoch-1/navigation.json

@@ -0,0 +1,105 @@
+{
+  "serializer": "vln_append_only_chat_v1",
+  "template_sha256": "fb79cf3922f74475e9a5faaac8c08d2f79a3ca7bef5dbf434f3f7726119229b8",
+  "actions": [
+    "MOVE_FORWARD",
+    "TURN_LEFT",
+    "TURN_RIGHT",
+    "STOP"
+  ],
+  "habitat_ids": [
+    1,
+    2,
+    3,
+    0
+  ],
+  "action_token_ids": [
+    [
+      28164,
+      61846,
+      248046
+    ],
+    [
+      15834,
+      18440,
+      248046
+    ],
+    [
+      15834,
+      20549,
+      248046
+    ],
+    [
+      48964,
+      248046
+    ]
+  ],
+  "eos": 248046,
+  "separator_ids": [
+    198
+  ],
+  "rgb_shape": [
+    480,
+    640,
+    3
+  ],
+  "position_convention": "logical_text_plus_native_mrope_v1",
+  "rotary_precision": "fp32_preserved_across_module_casts_v1",
+  "config": {
+    "model": {
+      "backbone": "Qwen/Qwen3.5-4B",
+      "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+      "output_mode": "qwen_text"
+    },
+    "observations": {
+      "expected_rgb_shape": [
+        480,
+        640,
+        3
+      ],
+      "expected_visual_tokens": 300,
+      "max_prefix_tokens": 512,
+      "serializer_version": "vln_append_only_chat_v1",
+      "max_step_group_tokens": 384,
+      "append_action_tokens": true
+    },
+    "memory": {
+      "mode": "full_context",
+      "kv_window_steps_including_current": null,
+      "evict_before_new_step": false,
+      "kv_guard_tokens": 262144
+    },
+    "training": {
+      "use_cache": false,
+      "microbatch_episodes_per_rank": 1,
+      "nominal_episodes_per_update": 8,
+      "gradient_accumulation_steps": 2,
+      "model_max_length": 73728,
+      "epochs": 3,
+      "backbone_lr": 5e-06,
+      "classifier_lr": 5e-06,
+      "weight_decay": 0.01,
+      "warmup_steps": 122,
+      "seed": 429,
+      "checkpoint_decoder_layers": true,
+      "length_bucket_pool_episodes": 64,
+      "tail_policy": "accelerate_repeat",
+      "supervise_assistant_terminator": true,
+      "expected_total_steps": 4059,
+      "expected_warmup_steps": 122,
+      "dataloader_num_workers": 4,
+      "save_strategy": "epoch",
+      "save_total_limit": null
+    },
+    "runtime": {
+      "text_attention": "flash_attention_2",
+      "vision_attention": "flash_attention_2",
+      "vision_microbatch_images": 4,
+      "max_logical_context_tokens": 262144
+    },
+    "generation": {
+      "max_response_tokens_including_eos": 16,
+      "fixed_separator": "\n"
+    }
+  }
+}

epoch-1/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

epoch-1/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff74f908e9eb964d690ad7aef77899a88cfe166d3e9afe50439a1c95aa1f7da
+size 10350179723

epoch-1/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

epoch-1/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

epoch-2/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

epoch-2/config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.11.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

epoch-2/navigation.json

@@ -0,0 +1,105 @@
+{
+  "serializer": "vln_append_only_chat_v1",
+  "template_sha256": "fb79cf3922f74475e9a5faaac8c08d2f79a3ca7bef5dbf434f3f7726119229b8",
+  "actions": [
+    "MOVE_FORWARD",
+    "TURN_LEFT",
+    "TURN_RIGHT",
+    "STOP"
+  ],
+  "habitat_ids": [
+    1,
+    2,
+    3,
+    0
+  ],
+  "action_token_ids": [
+    [
+      28164,
+      61846,
+      248046
+    ],
+    [
+      15834,
+      18440,
+      248046
+    ],
+    [
+      15834,
+      20549,
+      248046
+    ],
+    [
+      48964,
+      248046
+    ]
+  ],
+  "eos": 248046,
+  "separator_ids": [
+    198
+  ],
+  "rgb_shape": [
+    480,
+    640,
+    3
+  ],
+  "position_convention": "logical_text_plus_native_mrope_v1",
+  "rotary_precision": "fp32_preserved_across_module_casts_v1",
+  "config": {
+    "model": {
+      "backbone": "Qwen/Qwen3.5-4B",
+      "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+      "output_mode": "qwen_text"
+    },
+    "observations": {
+      "expected_rgb_shape": [
+        480,
+        640,
+        3
+      ],
+      "expected_visual_tokens": 300,
+      "max_prefix_tokens": 512,
+      "serializer_version": "vln_append_only_chat_v1",
+      "max_step_group_tokens": 384,
+      "append_action_tokens": true
+    },
+    "memory": {
+      "mode": "full_context",
+      "kv_window_steps_including_current": null,
+      "evict_before_new_step": false,
+      "kv_guard_tokens": 262144
+    },
+    "training": {
+      "use_cache": false,
+      "microbatch_episodes_per_rank": 1,
+      "nominal_episodes_per_update": 8,
+      "gradient_accumulation_steps": 2,
+      "model_max_length": 73728,
+      "epochs": 3,
+      "backbone_lr": 5e-06,
+      "classifier_lr": 5e-06,
+      "weight_decay": 0.01,
+      "warmup_steps": 122,
+      "seed": 429,
+      "checkpoint_decoder_layers": true,
+      "length_bucket_pool_episodes": 64,
+      "tail_policy": "accelerate_repeat",
+      "supervise_assistant_terminator": true,
+      "expected_total_steps": 4059,
+      "expected_warmup_steps": 122,
+      "dataloader_num_workers": 4,
+      "save_strategy": "epoch",
+      "save_total_limit": null
+    },
+    "runtime": {
+      "text_attention": "flash_attention_2",
+      "vision_attention": "flash_attention_2",
+      "vision_microbatch_images": 4,
+      "max_logical_context_tokens": 262144
+    },
+    "generation": {
+      "max_response_tokens_including_eos": 16,
+      "fixed_separator": "\n"
+    }
+  }
+}

epoch-2/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

epoch-2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2c0b217562b26a1826cd52dd03dd41cbe44bb5e04eb9cdac5aa952c9ccac8c1
+size 10350179723

epoch-2/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

epoch-2/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

epoch-3/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- else %}
+        {{- '<think>\n' }}
+    {%- endif %}
+{%- endif %}

epoch-3/config.json

@@ -0,0 +1,112 @@
+{
+  "architectures": [
+    "Qwen3_5ForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 248046,
+  "image_token_id": 248056,
+  "model_type": "qwen3_5",
+  "pad_token_id": 248044,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_output_gate": true,
+    "bos_token_id": null,
+    "dtype": "bfloat16",
+    "eos_token_id": 248044,
+    "full_attention_interval": 4,
+    "head_dim": 256,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "layer_types": [
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention",
+      "linear_attention",
+      "linear_attention",
+      "linear_attention",
+      "full_attention"
+    ],
+    "linear_conv_kernel_dim": 4,
+    "linear_key_head_dim": 128,
+    "linear_num_key_heads": 16,
+    "linear_num_value_heads": 32,
+    "linear_value_head_dim": 128,
+    "mamba_ssm_dtype": "float32",
+    "max_position_embeddings": 262144,
+    "mlp_only_layers": [],
+    "model_type": "qwen3_5_text",
+    "mtp_num_hidden_layers": 1,
+    "mtp_use_dedicated_embeddings": false,
+    "num_attention_heads": 16,
+    "num_hidden_layers": 32,
+    "num_key_value_heads": 4,
+    "pad_token_id": null,
+    "partial_rotary_factor": 0.25,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        11,
+        11,
+        10
+      ],
+      "partial_rotary_factor": 0.25,
+      "rope_theta": 10000000,
+      "rope_type": "default"
+    },
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 248320
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.11.0",
+  "use_cache": false,
+  "video_token_id": 248057,
+  "vision_config": {
+    "deepstack_visual_indexes": [],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_5_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 248054,
+  "vision_start_token_id": 248053
+}

epoch-3/navigation.json

@@ -0,0 +1,105 @@
+{
+  "serializer": "vln_append_only_chat_v1",
+  "template_sha256": "fb79cf3922f74475e9a5faaac8c08d2f79a3ca7bef5dbf434f3f7726119229b8",
+  "actions": [
+    "MOVE_FORWARD",
+    "TURN_LEFT",
+    "TURN_RIGHT",
+    "STOP"
+  ],
+  "habitat_ids": [
+    1,
+    2,
+    3,
+    0
+  ],
+  "action_token_ids": [
+    [
+      28164,
+      61846,
+      248046
+    ],
+    [
+      15834,
+      18440,
+      248046
+    ],
+    [
+      15834,
+      20549,
+      248046
+    ],
+    [
+      48964,
+      248046
+    ]
+  ],
+  "eos": 248046,
+  "separator_ids": [
+    198
+  ],
+  "rgb_shape": [
+    480,
+    640,
+    3
+  ],
+  "position_convention": "logical_text_plus_native_mrope_v1",
+  "rotary_precision": "fp32_preserved_across_module_casts_v1",
+  "config": {
+    "model": {
+      "backbone": "Qwen/Qwen3.5-4B",
+      "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+      "output_mode": "qwen_text"
+    },
+    "observations": {
+      "expected_rgb_shape": [
+        480,
+        640,
+        3
+      ],
+      "expected_visual_tokens": 300,
+      "max_prefix_tokens": 512,
+      "serializer_version": "vln_append_only_chat_v1",
+      "max_step_group_tokens": 384,
+      "append_action_tokens": true
+    },
+    "memory": {
+      "mode": "full_context",
+      "kv_window_steps_including_current": null,
+      "evict_before_new_step": false,
+      "kv_guard_tokens": 262144
+    },
+    "training": {
+      "use_cache": false,
+      "microbatch_episodes_per_rank": 1,
+      "nominal_episodes_per_update": 8,
+      "gradient_accumulation_steps": 2,
+      "model_max_length": 73728,
+      "epochs": 3,
+      "backbone_lr": 5e-06,
+      "classifier_lr": 5e-06,
+      "weight_decay": 0.01,
+      "warmup_steps": 122,
+      "seed": 429,
+      "checkpoint_decoder_layers": true,
+      "length_bucket_pool_episodes": 64,
+      "tail_policy": "accelerate_repeat",
+      "supervise_assistant_terminator": true,
+      "expected_total_steps": 4059,
+      "expected_warmup_steps": 122,
+      "dataloader_num_workers": 4,
+      "save_strategy": "epoch",
+      "save_total_limit": null
+    },
+    "runtime": {
+      "text_attention": "flash_attention_2",
+      "vision_attention": "flash_attention_2",
+      "vision_microbatch_images": 4,
+      "max_logical_context_tokens": 262144
+    },
+    "generation": {
+      "max_response_tokens_including_eos": 16,
+      "fixed_separator": "\n"
+    }
+  }
+}

epoch-3/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

epoch-3/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085f548986b9d78fdbbb1301a498b605e77127ba48a6d704c57d4307d3a8b742
+size 10350179723

epoch-3/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

epoch-3/tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

resolved_config.json

@@ -0,0 +1,57 @@
+{
+  "model": {
+    "backbone": "Qwen/Qwen3.5-4B",
+    "revision": "851bf6e806efd8d0a36b00ddf55e13ccb7b8cd0a",
+    "output_mode": "qwen_text"
+  },
+  "observations": {
+    "expected_rgb_shape": [
+      480,
+      640,
+      3
+    ],
+    "expected_visual_tokens": 300,
+    "max_prefix_tokens": 512,
+    "serializer_version": "vln_append_only_chat_v1",
+    "max_step_group_tokens": 384,
+    "append_action_tokens": true
+  },
+  "memory": {
+    "mode": "full_context",
+    "kv_window_steps_including_current": null,
+    "evict_before_new_step": false,
+    "kv_guard_tokens": 262144
+  },
+  "training": {
+    "use_cache": false,
+    "microbatch_episodes_per_rank": 1,
+    "nominal_episodes_per_update": 8,
+    "gradient_accumulation_steps": 2,
+    "model_max_length": 73728,
+    "epochs": 3,
+    "backbone_lr": 5e-06,
+    "classifier_lr": 5e-06,
+    "weight_decay": 0.01,
+    "warmup_steps": 122,
+    "seed": 429,
+    "checkpoint_decoder_layers": true,
+    "length_bucket_pool_episodes": 64,
+    "tail_policy": "accelerate_repeat",
+    "supervise_assistant_terminator": true,
+    "expected_total_steps": 4059,
+    "expected_warmup_steps": 122,
+    "dataloader_num_workers": 4,
+    "save_strategy": "epoch",
+    "save_total_limit": null
+  },
+  "runtime": {
+    "text_attention": "flash_attention_2",
+    "vision_attention": "flash_attention_2",
+    "vision_microbatch_images": 4,
+    "max_logical_context_tokens": 262144
+  },
+  "generation": {
+    "max_response_tokens_including_eos": 16,
+    "fixed_separator": "\n"
+  }
+}

run_timing.json

@@ -0,0 +1,6 @@
+{
+  "wall_seconds_including_load_and_save": 23922.57332988456,
+  "trainer_runtime_seconds": 23890.122,
+  "profile_only": false,
+  "update_timer_note": "Update callbacks exclude loader prefetch and model load/checkpoint save"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 0.0,
+    "train_loss": 0.06572136595278469,
+    "train_runtime": 23890.122,
+    "train_samples_per_second": 1.359,
+    "train_steps_per_second": 0.17
+}