093919-SFT-Lean+math-best-allround-eval-revert-from-exp6filt

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: transformers
-model_name: guided-a025-cs552-8k
+model_name: '20260529_093919'
 tags:
 - generated_from_trainer
-- grpo
+- sft
 - trl
 licence: license
 ---
 
-# Model Card for guided-a025-cs552-8k
+# Model Card for 20260529_093919
 
 This model is a fine-tuned version of [None](https://huggingface.co/None).
 It has been trained using [TRL](https://github.com/huggingface/trl).
@@ -26,11 +26,11 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cs-552-2026-flab/flab-cs552/runs/0eraj0j6) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/cs-552-2026-flab/flab-cs552/runs/cwg4aje3) 
 
 
 
-This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+This model was trained with SFT.
 
 ### Framework versions
 
@@ -42,16 +42,7 @@ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing
 
 ## Citations
 
-Cite GRPO as:
 
-```bibtex
-@article{shao2024deepseekmath,
-    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
-    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
-    year         = 2024,
-    eprint       = {arXiv:2402.03300},
-}
-```
 
 Cite TRL as:
     

chat_template.jinja

@@ -1,6 +1,5 @@
 {%- set enable_thinking = true %}
-{%- set flab_boxed_instruction = "You are an expert mathematician. Reason carefully and rigorously: recall the relevant definitions and theorems, try small cases or sanity checks, and verify each step before continuing. When you reach the answer, state it on its own line as \\boxed{...}. The grader reads ONLY the contents of the LAST \\boxed{} in your response, so your final answer must appear there, complete and simplified." %}
-{%- if flab_boxed_instruction %}{{ '<|im_start|>system\n' + flab_boxed_instruction + '<|im_end|>\n' }}{%- endif %}{%- if tools %}
+{%- if tools %}
     {{- '<|im_start|>system\n' }}
     {%- if messages[0].role == 'system' %}
         {{- messages[0].content + '\n\n' }}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:437893d7593beb237dc4cd5ee6ae9215f324a45452a4e9234cde860320fde51f
+oid sha256:4aba44e8ea5cfcd1cce320cbacbdf2e01b8a0c5bf560c615bc51626a38458b36
 size 3441185608

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
-size 11422650
+oid sha256:82ff947750287e6ea07d0b2507b144c5c645274f3dcfae956140522843851c7f
+size 11422916

tokenizer_config.json

@@ -33,5 +33,6 @@
   "tokenizer_class": "Qwen2Tokenizer",
   "truncation_side": "right",
   "truncation_strategy": "longest_first",
-  "unk_token": null
+  "unk_token": null,
+  "chat_template": "{%- set enable_thinking = true %}\n{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0].role == 'system' %}\n        {{- messages[0].content + '\\n\\n' }}\n    {%- endif %}\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>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\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{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if message.content is string %}\n        {%- set content = message.content %}\n    {%- else %}\n        {%- set content = '' %}\n    {%- endif %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}"
 }