RL policy v0 (step 0)

adapter_config.json

@@ -29,9 +29,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19283fcad949983cb320322b9e8f35c739ecfa4dc60f0e6df0f03a53633e2528
+oid sha256:762c7d6d422de845ee9f58eb3350a8387090d73a5bb05bafb28500ce7dff1a36
 size 35644576

chat_template.jinja

@@ -1,53 +1,111 @@
-{%- if messages[0]['role'] == 'system' %}
-    {%- set system_message = messages[0]['content'] %}
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
     {%- set loop_messages = messages[1:] %}
 {%- else %}
     {%- set loop_messages = messages %}
-    {%- set system_message = '' %}
 {%- endif %}
-{%- if tools is defined and tools %}
-    {{- '<|im_start|>system\n' }}
-    {%- if system_message %}
-        {{- system_message }}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
     {%- endif %}
-    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
     {%- for tool in tools %}
-        {{- "\n" }}
-        {{- tool | tojson }}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
     {%- endfor %}
-    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+    {{- "\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>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
 {%- else %}
-    {%- if system_message %}
-        {{- '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
     {%- endif %}
 {%- endif %}
 {%- for message in loop_messages %}
-    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls %}
-        {{- '<|im_start|>assistant' }}
-        {%- if message.content %}
-            {{- '\n' + message.content }}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
         {%- endif %}
         {%- for tool_call in message.tool_calls %}
             {%- if tool_call.function is defined %}
                 {%- set tool_call = tool_call.function %}
             {%- endif %}
-            {{- '\n<tool_call>\n{"name": "' }}
-            {{- tool_call.name }}
-            {{- '", "arguments": ' }}
-            {%- if tool_call.arguments is string %}
-                {{- tool_call.arguments }}
-            {%- else %}
-                {{- tool_call.arguments | tojson }}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- 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 %}
-            {{- '}\n</tool_call>' }}
+            {{- '</function>\n</tool_call>' }}
         {%- endfor %}
         {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
     {%- elif message.role == "tool" %}
-        {%- if loop.previtem is not defined or loop.previtem.role != "tool" %}
-            {{- '<|im_start|>user' }}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
         {%- endif %}
-        {{- '\n<tool_response>\n' + message.content + '\n</tool_response>' }}
-        {%- if loop.nextitem is not defined or loop.nextitem.role != "tool" %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
             {{- '<|im_end|>\n' }}
         {%- endif %}
     {%- else %}

meta.json

@@ -1,18 +1,18 @@
 {
-  "policy_version": 4,
-  "global_step": 3,
-  "timestamp": "2026-07-22T01:15:24.360173",
+  "policy_version": 0,
+  "global_step": 0,
+  "timestamp": "2026-07-28T04:00:44.189401",
   "model_class": "PeftModelForCausalLM",
   "model_name_or_path": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
-  "training_metrics": {},
+  "training_metrics": {
+    "initialized": true
+  },
   "is_peft_adapter": true,
-  "requested_model": "/home/hice1/mamjad9/Documents/debugger/llm-debugger/sft/checkpoints/run_july21_v107_ws/peft_adapter",
+  "requested_model": "/home/hice1/mamjad9/Documents/debugger/llm-debugger/sft/checkpoints/run_july16_B/peft_adapter",
   "base_model_name_or_path": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
   "train_lora": true,
   "merged_adapter": false,
-  "frozen_adapter_dir": "/home/hice1/mamjad9/Documents/debugger/llm-debugger/sft/checkpoints/run_july21_v107_ws/peft_adapter",
+  "frozen_adapter_dir": "/home/hice1/mamjad9/Documents/debugger/llm-debugger/sft/checkpoints/run_july16_B/peft_adapter",
   "frozen_adapter_base_model_name_or_path": "Qwen/Qwen3-Coder-30B-A3B-Instruct",
-  "rft_adapter_name": "rft",
-  "update": 3,
-  "group_key": "GroupKey(v0, pref=optional)"
+  "rft_adapter_name": "rft"
 }

rft/adapter_config.json

@@ -29,9 +29,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

rft/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19283fcad949983cb320322b9e8f35c739ecfa4dc60f0e6df0f03a53633e2528
+oid sha256:762c7d6d422de845ee9f58eb3350a8387090d73a5bb05bafb28500ce7dff1a36
 size 35644576