Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,32 @@ 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
+eval_results/plots/eval_results_acc_pass_acc.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_acc_keywords.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_acc_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_clip_ratio.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_avg_stop_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_box_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_correct_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_repeat_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_tokens_keywords.png filter=lfs diff=lfs merge=lfs -text
+eval_results/plots/eval_results_wrong_tokens.png filter=lfs diff=lfs merge=lfs -text
+global_step_40/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_60/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_70/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_80/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+global_step_90/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_acc_keywords.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_acc_pass_acc.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_acc_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_avg_stop_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_correct_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_clip_ratio.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_box_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_repeat_ratio_and_token_length.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_wrong_tokens.png filter=lfs diff=lfs merge=lfs -text
+eval_results_avg4/plots/eval_results_avg4_tokens_keywords.png filter=lfs diff=lfs merge=lfs -text
+eval_results_ood/global_step_100/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-08-22T15-43-34.436852/details_extended|ifeval|0_2025-08-22T15-43-34.436852.csv filter=lfs diff=lfs merge=lfs -text
+eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-08-15T11-00-48.004731/details_extended|ifeval|0_2025-08-15T11-00-48.004731.csv filter=lfs diff=lfs merge=lfs -text
+eval_results_ood/global_step_0/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-08-15T11-09-39.306198/details_extended|ifeval|0_2025-08-15T11-09-39.306198.csv filter=lfs diff=lfs merge=lfs -text

eval_results_ood/global_step_0/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-08-15T11-09-39.306198/details_extended|ifeval|0_2025-08-15T11-09-39.306198.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba25009d3195ef4f302969d187cd0ead55f801794761df1cfdc17d383ce7272d
+size 17982625

eval_results_ood/global_step_0/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-08-15T11-09-39.306198/details_extended|ifeval|0_2025-08-15T11-09-39.306198.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d327d6b95f90194cb6994e322a34e8a413c2c056ca7d298df9bd2cb7ebca0062
+size 2587594

eval_results_ood/global_step_0/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_0_actor_huggingface/2025-08-15T11-09-39.306198/details_lighteval|gpqa:diamond|0_2025-08-15T11-09-39.306198.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b01da6d648a8cd33c37eb2d88ddbed0b5edd62dba41d3bff486a2f153cdb04d
+size 637219

eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-08-15T11-00-48.004731/details_extended|ifeval|0_2025-08-15T11-00-48.004731.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aac5b259acb2bb11fa6f6269922167d22ac502f65faaacfb24ca596250ed29a
+size 15512248

eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-08-15T11-00-48.004731/details_extended|ifeval|0_2025-08-15T11-00-48.004731.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3de1830cbd609be851ff3a65b0750535e8b0e522193d693e0d12b446bfe457d
+size 2309106

eval_results_ood/global_step_10/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_10_actor_huggingface/2025-08-15T11-00-48.004731/details_lighteval|gpqa:diamond|0_2025-08-15T11-00-48.004731.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4304adb3095d24edec3618aa55c5d2ffa61661c514a364099959619baa6857
+size 645401

eval_results_ood/global_step_100/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-08-22T15-43-34.436852/details_extended|ifeval|0_2025-08-22T15-43-34.436852.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce109454ca9db002045c7388fa2cafb6a67e4cc30552fe381c9d38b08187d452
+size 10843482

eval_results_ood/global_step_100/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-08-22T15-43-34.436852/details_extended|ifeval|0_2025-08-22T15-43-34.436852.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9323c665c7e398841fad4d0a11bf8ff30fa5f76425368558a20153e74ba81375
+size 1918374

eval_results_ood/global_step_100/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_100_actor_huggingface/2025-08-22T15-43-34.436852/details_lighteval|gpqa:diamond|0_2025-08-22T15-43-34.436852.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a9ffb05513a70c5e4c7da1b0ad394b7a54d0ce5e7df7bca15a7ed47614e46e
+size 554787

eval_results_ood/global_step_20/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_20_actor_huggingface/2025-08-15T11-00-50.060940/details_extended|ifeval|0_2025-08-15T11-00-50.060940.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae4f8c5b78dd375a1908468f8de282240f0a8edf4a5dcb22f0e4bd5d7b063e5
+size 2409406

eval_results_ood/global_step_20/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_20_actor_huggingface/2025-08-15T11-00-50.060940/details_lighteval|gpqa:diamond|0_2025-08-15T11-00-50.060940.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:073db43b6709125161c191ecd64cde7b3e1c43700532c9eea62488093a69070d
+size 513644

eval_results_ood/global_step_30/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_30_actor_huggingface/2025-08-15T11-04-02.688065/details_extended|ifeval|0_2025-08-15T11-04-02.688065.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df6fdf6652de534c9c7f0989303f8c826ddc3109ddf7b086e8b686d3455333f
+size 2627692

eval_results_ood/global_step_30/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_30_actor_huggingface/2025-08-15T11-04-02.688065/details_lighteval|gpqa:diamond|0_2025-08-15T11-04-02.688065.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4619672b936e5646db5ee8e1d02aae6ce0d1c56ed1f9b0be91536d3d25e49c
+size 509697

eval_results_ood/global_step_40/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_40_actor_huggingface/2025-08-15T11-58-04.589248/details_extended|ifeval|0_2025-08-15T11-58-04.589248.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed83d1ee041e4d1e634fa434e8c78ca03c511fe37568085a6ef0a31df10bcaf7
+size 2215370

eval_results_ood/global_step_40/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_40_actor_huggingface/2025-08-15T11-58-04.589248/details_lighteval|gpqa:diamond|0_2025-08-15T11-58-04.589248.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcb51742700745022425679785b56c157e9233f74a393e0fe38ade962679f8b
+size 586448

eval_results_ood/global_step_50/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_50_actor_huggingface/2025-08-15T11-57-24.288945/details_extended|ifeval|0_2025-08-15T11-57-24.288945.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ede96e5baf52d142ce38e94fb4c8f15c1bc99dc2e5030e8c92a14d70babbe64a
+size 2195726

eval_results_ood/global_step_50/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_50_actor_huggingface/2025-08-15T11-57-24.288945/details_lighteval|gpqa:diamond|0_2025-08-15T11-57-24.288945.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2372b64e22b49d927325bf0bcb1fbeb7e199cbd48efc7f9674f55476066a3324
+size 509600

eval_results_ood/global_step_60/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_60_actor_huggingface/2025-08-15T11-53-18.171067/details_extended|ifeval|0_2025-08-15T11-53-18.171067.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a3af218d2b633adb30b9a563890873a6ac278a88e3bb06474a5ef8d383a4c4c
+size 2085242

eval_results_ood/global_step_60/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_60_actor_huggingface/2025-08-15T11-53-18.171067/details_lighteval|gpqa:diamond|0_2025-08-15T11-53-18.171067.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35951f3340502f296b7798e95c42d212ded4002d17cfdb3343ee1ced89f6b464
+size 518608

eval_results_ood/global_step_70/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_70_actor_huggingface/2025-08-15T11-51-22.040232/details_extended|ifeval|0_2025-08-15T11-51-22.040232.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9091284ac521d787bc5119a5b027f59483782220da8ba2979b81ae5bcb098cfe
+size 2198576

eval_results_ood/global_step_70/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_70_actor_huggingface/2025-08-15T11-51-22.040232/details_lighteval|gpqa:diamond|0_2025-08-15T11-51-22.040232.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61818eb49695d3bec63e328738fba94274f2fd823d9da2ae5029f7b7a1c5ee85
+size 621605

eval_results_ood/global_step_80/details/_home_work_compass_innovation_minzijun_checkpoints_verl_role_sft_grpo_deepmath_train_sample_6144_context_4k_Qwen3-1.7B-base_max_response4096_batch1024_rollout8_vllm_global_step_80_actor_huggingface/2025-08-15T12-32-10.307029/details_lighteval|gpqa:diamond|0_2025-08-15T12-32-10.307029.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f31fa417c47f421e890fd349bf505e93734031a524ab6e0056782853d63b6d
+size 605959

global_step_40/actor/fsdp_config.json

@@ -0,0 +1,4 @@
+{
+    "FSDP_version": 1,
+    "world_size": 8
+}

global_step_40/actor/huggingface/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

global_step_40/actor/huggingface/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- 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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].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" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- 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' }}
+    {%- endif %}
+{%- endif %}

global_step_40/actor/huggingface/config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

global_step_40/actor/huggingface/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.53.2"
+}