stage1 v3 qwen3_6_27b

.gitattributes

@@ -43,3 +43,4 @@ stage2_recipe_AB_lowlr_topk64/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_5_0_8b_stage2_v3/vllm_compat/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_5_2b_stage2_v3/vllm_compat/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3_5_9b_stage2_v3/vllm_compat/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+stage1_v3_qwen3_6_27b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

stage1_v3_qwen3_6_27b/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 (preserve_thinking is defined and preserve_thinking is true) or (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 | string if args_value is string else args_value | tojson | safe %}
+                        {{- 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 %}

stage1_v3_qwen3_6_27b/loss_curve.csv

@@ -0,0 +1,42 @@
+step,loss,lr,tok_per_s
+0,3.993352,5.000e-05,95.7
+5,3.881543,3.000e-04,4144.0
+10,3.806364,5.500e-04,3980.2
+15,3.551234,8.000e-04,4152.3
+20,3.013006,1.000e-03,4248.7
+25,2.827564,9.981e-04,4263.1
+30,2.476648,9.924e-04,4261.5
+35,2.241153,9.830e-04,4275.3
+40,1.998935,9.698e-04,4275.0
+45,2.591520,9.532e-04,4276.7
+50,2.507889,9.330e-04,4273.1
+55,2.260417,9.096e-04,4276.6
+60,2.211508,8.830e-04,4272.1
+65,2.097555,8.536e-04,4275.4
+70,1.806510,8.214e-04,4275.7
+75,1.737853,7.868e-04,4276.2
+80,1.681238,7.500e-04,4276.8
+85,1.527681,7.113e-04,4278.0
+90,1.487800,6.710e-04,4279.4
+95,1.395350,6.294e-04,4256.4
+100,1.460943,5.868e-04,4264.8
+105,1.237850,5.436e-04,4265.9
+110,1.180859,5.000e-04,4269.7
+115,1.102229,4.564e-04,4268.2
+120,1.126031,4.132e-04,4266.2
+125,1.803083,3.706e-04,4268.5
+130,1.620632,3.290e-04,4267.5
+135,1.747785,2.887e-04,4267.5
+140,1.699758,2.500e-04,4266.1
+145,1.729147,2.132e-04,4267.9
+150,1.648632,1.786e-04,4266.2
+155,1.644816,1.464e-04,4265.6
+160,1.733385,1.170e-04,4265.2
+165,1.817360,9.042e-05,4266.4
+170,1.816725,6.699e-05,4266.1
+175,2.071765,4.685e-05,4265.7
+180,1.885692,3.015e-05,4266.7
+185,1.873427,1.704e-05,4265.1
+190,2.011757,7.596e-06,4264.9
+195,1.968878,1.903e-06,4265.3
+199,1.954217,7.615e-08,4257.3

stage1_v3_qwen3_6_27b/stage1_summary.json

@@ -0,0 +1,104 @@
+{
+  "model": "Qwen/Qwen3.6-27B",
+  "probe": "probe_results/qwen3_6_27b_v3.json",
+  "steps": 200,
+  "lr": 0.001,
+  "seq_len": 2048,
+  "batch_size": 1,
+  "d_idx": 16,
+  "elapsed_min": 1.9683955115833327,
+  "final_per_head_kl": {
+    "3": [
+      1.4239823818206787
+    ],
+    "7": [
+      2.6987695693969727
+    ],
+    "11": [
+      2.377558708190918,
+      2.787999153137207,
+      2.438776969909668,
+      1.564170002937317
+    ],
+    "15": [
+      1.8237659931182861,
+      1.3233871459960938,
+      1.5367882251739502,
+      1.606621503829956,
+      1.8042058944702148,
+      1.4368648529052734,
+      1.7141367197036743,
+      1.8361910581588745
+    ],
+    "19": [
+      1.1314971446990967,
+      1.6120601892471313,
+      1.7221510410308838,
+      1.445702314376831,
+      1.589271068572998,
+      2.221271276473999,
+      2.0320956707000732,
+      1.9286909103393555
+    ],
+    "23": [
+      1.7663816213607788,
+      3.007701873779297
+    ],
+    "27": [
+      1.834385871887207,
+      2.185379981994629
+    ],
+    "31": [
+      1.6225991249084473
+    ],
+    "35": [
+      2.3036327362060547
+    ],
+    "39": [
+      2.4662833213806152
+    ],
+    "43": [
+      2.4847326278686523
+    ],
+    "47": [
+      1.744596242904663,
+      1.852041244506836,
+      1.3673009872436523
+    ],
+    "51": [
+      1.8634147644042969,
+      2.1502764225006104,
+      1.6011509895324707,
+      1.6176682710647583,
+      1.5763602256774902,
+      1.666095495223999,
+      1.786155104637146,
+      2.1532015800476074,
+      1.8322596549987793,
+      1.7880979776382446,
+      2.0255823135375977,
+      2.2395434379577637,
+      1.8771419525146484,
+      2.0412936210632324
+    ],
+    "55": [
+      1.6782424449920654,
+      1.913238525390625,
+      1.5459322929382324,
+      1.4227039813995361,
+      1.8281331062316895
+    ],
+    "59": [
+      1.867315649986267,
+      1.6641249656677246,
+      1.3729698657989502,
+      1.4456760883331299,
+      1.8807485103607178
+    ],
+    "63": [
+      1.381635069847107
+    ]
+  },
+  "final_mean_kl": 1.8432750989650857,
+  "final_max_kl": 3.007701873779297
+}

stage1_v3_qwen3_6_27b/state_dict.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3861ab13859bab28f1b174392ab1e986ee359ce9dc970a7b56cf6cb77525ad4
+size 991109

stage1_v3_qwen3_6_27b/tokenizer.json

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

stage1_v3_qwen3_6_27b/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "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": false,
+  "local_files_only": false,
+  "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+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}