diff --git a/.gitattributes b/.gitattributes
index e446207c8a84f91b817da86b5fc1c535c63219b0..9f961495c5d2d30f0d5f756f9e5e4f1b304fe780 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -115,3 +115,9 @@ models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath
models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
models/DeepMath-1.5B-20250923_225516/mathevo-grpo-verl-concept-enhanced/DeepMath-1.5B-20250923_225516/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_24_828315a27fa54eada7976342518daec3.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_24_828315a27fa54eada7976342518daec3.json
new file mode 100644
index 0000000000000000000000000000000000000000..a5f10aaa6d118f5197c5b17c70ee8e67cc2808a8
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_24_828315a27fa54eada7976342518daec3.json
@@ -0,0 +1,28 @@
+{
+ "null": [
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5
+ ]
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_48_a2bf77a13e124ab3986495c43688e713.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_48_a2bf77a13e124ab3986495c43688e713.json
new file mode 100644
index 0000000000000000000000000000000000000000..c89bbe9aa50052a4eab344acfb549adf88e4a2c0
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_48_a2bf77a13e124ab3986495c43688e713.json
@@ -0,0 +1,52 @@
+{
+ "null": [
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5
+ ]
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_72_e2ae04a9596049afa1fd1d2f26b97057.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_72_e2ae04a9596049afa1fd1d2f26b97057.json
new file mode 100644
index 0000000000000000000000000000000000000000..217ca4b1dc8d01850181154a2362c7f786fc080f
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_72_e2ae04a9596049afa1fd1d2f26b97057.json
@@ -0,0 +1,76 @@
+{
+ "null": [
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.3333333333333333,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.6666666666666666,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.5,
+ 0.6666666666666666,
+ 0.6666666666666666,
+ 0.6666666666666666,
+ 0.5,
+ 0.6666666666666666,
+ 0.6666666666666666
+ ]
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_24_891206c6554b4f00bca529cff33c3977.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_24_891206c6554b4f00bca529cff33c3977.json
new file mode 100644
index 0000000000000000000000000000000000000000..d177f7cc2d8fd134ccaecfe5f7a4d2e95cdd942a
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_24_891206c6554b4f00bca529cff33c3977.json
@@ -0,0 +1,28 @@
+{
+ "null": {
+ "1": 0.5,
+ "2": 0.5,
+ "3": 0.5,
+ "4": 0.5,
+ "5": 0.5,
+ "6": 0.5,
+ "7": 0.5,
+ "8": 0.5,
+ "9": 0.5,
+ "10": 0.5,
+ "11": 0.5,
+ "12": 0.3333333333333333,
+ "13": 0.5,
+ "14": 0.5,
+ "15": 0.3333333333333333,
+ "16": 0.5,
+ "17": 0.3333333333333333,
+ "18": 0.5,
+ "19": 0.5,
+ "20": 0.5,
+ "21": 0.5,
+ "22": 0.3333333333333333,
+ "23": 0.5,
+ "24": 0.5
+ }
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_48_ddfa2cf5e1124ffcbc81728c0d977133.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_48_ddfa2cf5e1124ffcbc81728c0d977133.json
new file mode 100644
index 0000000000000000000000000000000000000000..87bf2cc44aa2805f123b91c704425949afeefc00
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_48_ddfa2cf5e1124ffcbc81728c0d977133.json
@@ -0,0 +1,52 @@
+{
+ "null": {
+ "1": 0.5,
+ "2": 0.5,
+ "3": 0.5,
+ "4": 0.5,
+ "5": 0.5,
+ "6": 0.5,
+ "7": 0.5,
+ "8": 0.5,
+ "9": 0.5,
+ "10": 0.5,
+ "11": 0.5,
+ "12": 0.3333333333333333,
+ "13": 0.5,
+ "14": 0.5,
+ "15": 0.3333333333333333,
+ "16": 0.5,
+ "17": 0.3333333333333333,
+ "18": 0.5,
+ "19": 0.5,
+ "20": 0.5,
+ "21": 0.5,
+ "22": 0.3333333333333333,
+ "23": 0.5,
+ "24": 0.5,
+ "25": 0.3333333333333333,
+ "26": 0.5,
+ "27": 0.3333333333333333,
+ "28": 0.5,
+ "29": 0.5,
+ "30": 0.5,
+ "31": 0.5,
+ "32": 0.5,
+ "33": 0.5,
+ "34": 0.5,
+ "35": 0.5,
+ "36": 0.5,
+ "37": 0.5,
+ "38": 0.5,
+ "39": 0.5,
+ "40": 0.5,
+ "41": 0.5,
+ "42": 0.5,
+ "43": 0.5,
+ "44": 0.5,
+ "45": 0.5,
+ "46": 0.5,
+ "47": 0.5,
+ "48": 0.5
+ }
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_72_7295066e48b340289861336f12e5d63e.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_72_7295066e48b340289861336f12e5d63e.json
new file mode 100644
index 0000000000000000000000000000000000000000..ae68ad64f51d109c80dd966d322355a74cb1be38
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/acc_step_with_step_72_7295066e48b340289861336f12e5d63e.json
@@ -0,0 +1,76 @@
+{
+ "null": {
+ "1": 0.5,
+ "2": 0.5,
+ "3": 0.5,
+ "4": 0.5,
+ "5": 0.5,
+ "6": 0.5,
+ "7": 0.5,
+ "8": 0.5,
+ "9": 0.5,
+ "10": 0.5,
+ "11": 0.5,
+ "12": 0.3333333333333333,
+ "13": 0.5,
+ "14": 0.5,
+ "15": 0.3333333333333333,
+ "16": 0.5,
+ "17": 0.3333333333333333,
+ "18": 0.5,
+ "19": 0.5,
+ "20": 0.5,
+ "21": 0.5,
+ "22": 0.3333333333333333,
+ "23": 0.5,
+ "24": 0.5,
+ "25": 0.3333333333333333,
+ "26": 0.5,
+ "27": 0.3333333333333333,
+ "28": 0.5,
+ "29": 0.5,
+ "30": 0.5,
+ "31": 0.5,
+ "32": 0.5,
+ "33": 0.5,
+ "34": 0.5,
+ "35": 0.5,
+ "36": 0.5,
+ "37": 0.5,
+ "38": 0.5,
+ "39": 0.5,
+ "40": 0.5,
+ "41": 0.5,
+ "42": 0.5,
+ "43": 0.5,
+ "44": 0.5,
+ "45": 0.5,
+ "46": 0.5,
+ "47": 0.5,
+ "48": 0.5,
+ "49": 0.5,
+ "50": 0.5,
+ "51": 0.5,
+ "52": 0.5,
+ "53": 0.5,
+ "54": 0.5,
+ "55": 0.5,
+ "56": 0.6666666666666666,
+ "57": 0.5,
+ "58": 0.5,
+ "59": 0.5,
+ "60": 0.5,
+ "61": 0.5,
+ "62": 0.5,
+ "63": 0.5,
+ "64": 0.5,
+ "65": 0.5,
+ "66": 0.5,
+ "67": 0.6666666666666666,
+ "68": 0.6666666666666666,
+ "69": 0.6666666666666666,
+ "70": 0.5,
+ "71": 0.6666666666666666,
+ "72": 0.6666666666666666
+ }
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_24_f7e7a5c9af31470482da596999730c47.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_24_f7e7a5c9af31470482da596999730c47.json
new file mode 100644
index 0000000000000000000000000000000000000000..cbde154d3e0d1d03a7e261f714b67ad0dbcfdf8d
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_24_f7e7a5c9af31470482da596999730c47.json
@@ -0,0 +1,7 @@
+{
+ "math_mcq": {
+ "0": 0.5765765765765766,
+ "10": 0.5945945945945946,
+ "20": 0.5765765765765766
+ }
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_48_ff8487caf52448aa87aefe47c13cd03e.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_48_ff8487caf52448aa87aefe47c13cd03e.json
new file mode 100644
index 0000000000000000000000000000000000000000..669626a9f01bf8953e40b12d2cc3ef0755420b37
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_48_ff8487caf52448aa87aefe47c13cd03e.json
@@ -0,0 +1,9 @@
+{
+ "math_mcq": {
+ "0": 0.5765765765765766,
+ "10": 0.5945945945945946,
+ "20": 0.5765765765765766,
+ "30": 0.5495495495495496,
+ "40": 0.6306306306306306
+ }
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_72_45e9191707c8418da9a4f26e0ccb8ef3.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_72_45e9191707c8418da9a4f26e0ccb8ef3.json
new file mode 100644
index 0000000000000000000000000000000000000000..a70ab62c96b88f8a52ef046c8e318ceb42b1ab92
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/accuracy/val_acc_source_with_step_72_45e9191707c8418da9a4f26e0ccb8ef3.json
@@ -0,0 +1,12 @@
+{
+ "math_mcq": {
+ "0": 0.5765765765765766,
+ "10": 0.5945945945945946,
+ "20": 0.5765765765765766,
+ "30": 0.5495495495495496,
+ "40": 0.6306306306306306,
+ "50": 0.6036036036036037,
+ "60": 0.6576576576576577,
+ "70": 0.7297297297297297
+ }
+}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "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": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/extra_state_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7ed434542a47beae31ee47a0163c2469ef70a532
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/extra_state_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d84cbd4915957db97102ff3a0cdde5457798a5d29bd619e00ef5a67f55bc36
+size 14632
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/extra_state_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..16f1760f9e2e1945663932e13d41ecc6e0736774
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/extra_state_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:769da32a92223715a8913c7442fa2e52d65b40c2fbf95a0214abaa5ccc899c13
+size 14632
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/generation_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 151646,
+ "eos_token_id": 151643,
+ "pad_token_id": 151643,
+ "transformers_version": "4.55.4"
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "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": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/huggingface/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model-00001-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2f1b0bccd7358768251747d3e7c8839e70ddb016
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c949fa5994d642986b624dfc03439256c5f0c29feac717a9cca669860c6178b2
+size 4996670464
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model-00002-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0ccbe3ece0c1a813f81177426bf2e8895e5f4a0a
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9d856a9abadd681d5a59fa4670ca06468e1decfe85f9afe3c4fc5bdcf26e9f7
+size 2111719976
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model.safetensors.index.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+ "metadata": {
+ "total_parameters": 888544000,
+ "total_size": 7108352000
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6d79b2f35b11a071b7a983408303c9d70782f9bc
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:302ad130f79d9f65c3bbea209a6db6c0403b37776dce4e97e5bdacf9ed118adb
+size 3554364602
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0a953b4f827ab6f3abe023e923dc5f622e294485
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a01b70bb10f179b97722ab4df52a6ab9a0f94d6a0dce3ee442deba24e60ab46
+size 3554364602
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/optim_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..153c063a59003d96543c64460c7869d70f1d6b03
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/optim_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4677accddaba0b2c6cd7168d6e86e00e038721287af2a25198e821998c8c42d9
+size 7108378739
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/optim_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e3ade00d2533729bb0e97573b38c0b8a68099bf3
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9184984b6ee6daba92ebb94495f80ee6894f658bbd65d96331355ad0fe099e51
+size 7108378739
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/actor/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/data.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb9ef95e3602226ac6663f33fec9357d9c1ec722
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3adc30950e92556e672d48265a0c6e030a3867af92c61c493906822e2b379c
+size 6948493
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/training_state.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f39a2ed0a8b46d7851a5151304a949520d0dcb2
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_24/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.3333333333333333, 0.5, 0.5, 0.3333333333333333, 0.5, 0.3333333333333333, 0.5, 0.5, 0.5, 0.5, 0.3333333333333333, 0.5, 0.5]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.3333333333333333, "13": 0.5, "14": 0.5, "15": 0.3333333333333333, "16": 0.5, "17": 0.3333333333333333, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.3333333333333333, "23": 0.5, "24": 0.5}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5765765765765766, "10": 0.5945945945945946, "20": 0.5765765765765766}}}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "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": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/extra_state_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a7d80f84b362c5faa33ccead70380a039f8a88bd
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/extra_state_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:059a9f9b86fcfbb5f53275965c0aaa592332c8af42d753500e29a35f6fd2ef57
+size 14632
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/extra_state_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..01ed52981395e28d2b8f6abb049d9858113da2fb
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/extra_state_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:392a538d843db1db4fadff5d6fde430350a3a72e28d153c8eeb8fa13c6fd5f5f
+size 14632
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/generation_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 151646,
+ "eos_token_id": 151643,
+ "pad_token_id": 151643,
+ "transformers_version": "4.55.4"
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "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": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/huggingface/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model-00001-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5a4c8d952177cb1499eac8d5316180eb4d99da5
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dc4a94dbc00199809251a522e6467cda655bcf007cd2c7d73a245042191fffd
+size 4996670464
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model-00002-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..68820f860a7eedef482b9dfe06586c3989f6d472
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa9d3e49ead46fd7a3518ea933f4ce692859f78a3cdfd7f83d9859a7c1b32e0
+size 2111719976
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model.safetensors.index.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+ "metadata": {
+ "total_parameters": 888544000,
+ "total_size": 7108352000
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e098854c08da32d5347fcb7530bad02a022b97b0
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03861cea62ddfa2c2b9d1248609ffbcb3234608837dd4a6595915efc29ad2cf9
+size 3554364602
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bf7b6f8cec66ce255cb80acb4b16d4ad6fb91b21
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36b0c787827404fe3f5e2022ae875a9909ead3cb2ec1907d8f5ffbcb92d3470e
+size 3554364602
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/optim_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..498bea36699648e3246e7a664595c9a799c50ce1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/optim_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51570c5ac60f985c05e9669bb9e4ce0fa751269ccc9f9761574e14253166332c
+size 7108378739
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/optim_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..7d22a27fe96a2ee6bfe85f277b852e298b14be13
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:087262499c2304bcf48afa13e13f9c78def568cf95640ff2098e74145e523d93
+size 7108378739
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/actor/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/data.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2060d758febf404fab718a76d303b839c5b0c003
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deadada4e14cffeb8fa749641d20a3652f4e8bbc2bd6fa40c3032047c9c74d70
+size 6948493
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/training_state.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..b2406df1e3277abd64219821a818d7d0f8c0e7f1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_48/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.3333333333333333, 0.5, 0.5, 0.3333333333333333, 0.5, 0.3333333333333333, 0.5, 0.5, 0.5, 0.5, 0.3333333333333333, 0.5, 0.5, 0.3333333333333333, 0.5, 0.3333333333333333, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.3333333333333333, "13": 0.5, "14": 0.5, "15": 0.3333333333333333, "16": 0.5, "17": 0.3333333333333333, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.3333333333333333, "23": 0.5, "24": 0.5, "25": 0.3333333333333333, "26": 0.5, "27": 0.3333333333333333, "28": 0.5, "29": 0.5, "30": 0.5, "31": 0.5, "32": 0.5, "33": 0.5, "34": 0.5, "35": 0.5, "36": 0.5, "37": 0.5, "38": 0.5, "39": 0.5, "40": 0.5, "41": 0.5, "42": 0.5, "43": 0.5, "44": 0.5, "45": 0.5, "46": 0.5, "47": 0.5, "48": 0.5}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5765765765765766, "10": 0.5945945945945946, "20": 0.5765765765765766, "30": 0.5495495495495496, "40": 0.6306306306306306}}}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "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": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/extra_state_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..efeb3f6e73e5635bffc6b933fb7e886388461cc4
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/extra_state_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9a48cf0f9bb47c6507afd5abf7fe7808d88353d618d22dc1b96ca4b87eb96eb
+size 14632
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/extra_state_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5a5bcaf21cdd16ce5b34f5125e344fe9452c475e
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/extra_state_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df35834b11b3c08a7866c7f4798c7bd80d03203ef6f5996e80e5acbdd95cf4ce
+size 14632
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/generation_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9fce42c126ce3a40d5dfc7bafe0976943eb29395
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/generation_config.json
@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 151646,
+ "eos_token_id": 151643,
+ "pad_token_id": 151643,
+ "transformers_version": "4.55.4"
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/chat_template.jinja b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..c2066bd7391c270626e39c9d7124f00360126412
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/chat_template.jinja
@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '' in content %}{% set content = content.split('')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜>\n'}}{% endif %}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d2e16ddf4cc3d2d1a40e165a72750d2ae3dc6d1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/config.json
@@ -0,0 +1,62 @@
+{
+ "architectures": [
+ "Qwen2ForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 151646,
+ "embd_pdrop": 0.0,
+ "eos_token_id": 151643,
+ "hidden_act": "silu",
+ "hidden_size": 1536,
+ "initializer_range": 0.02,
+ "intermediate_size": 8960,
+ "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": 131072,
+ "max_window_layers": 21,
+ "model_type": "qwen2",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 28,
+ "num_key_value_heads": 2,
+ "pad_token_id": 151643,
+ "resid_pdrop": 0.0,
+ "rms_norm_eps": 1e-06,
+ "rope_scaling": null,
+ "rope_theta": 10000,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float32",
+ "transformers_version": "4.55.4",
+ "use_cache": true,
+ "use_mrope": false,
+ "use_sliding_window": false,
+ "vocab_size": 151936
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/huggingface/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model-00001-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..97d06ad66168656ad50789cd98573e9aa3c11a2d
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53e0d3d8386368b1d0382a4f1e3b6e40aa22930b2c29c5ddfb197d21312c2198
+size 4996670464
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model-00002-of-00002.safetensors b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ec95693b42b028cc729c5097cd496f4fcb302593
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4083b43c75b39d65d7f18ec001274a9f19f3436c8b5a433bdfcb14a0fbb15764
+size 2111719976
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model.safetensors.index.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model.safetensors.index.json
@@ -0,0 +1,347 @@
+{
+ "metadata": {
+ "total_parameters": 888544000,
+ "total_size": 7108352000
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00002-of-00002.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+ "model.norm.weight": "model-00002-of-00002.safetensors"
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d71eaff4c050031ebead96b49cf078ba8410e351
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20045623e72eaf2d5ea775102eca5275dc0084e95f9a9d17f60cb16c3f8178ad
+size 3554364602
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..92286932dea389d652e8254553c564b57afa83ef
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55e607ad230dfc7683509bfcce4d9061b3e3c716c1e293a86dd94e0ebcb7b588
+size 3554364602
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/optim_world_size_2_rank_0.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f365b5440897da8578366e1cb0cccc16bf62e08a
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/optim_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c10665145f0f779bd862128898646bbfb848e4a3a77e75df031fbb098a79f81
+size 7108378739
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/optim_world_size_2_rank_1.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ccbe02feb308c6254867f039943732b86ddbd239
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7bbb9fa22ff76893caea02dfcca0e3701fe253052c7e9dc24607203fbe4b31a
+size 7108378739
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/special_tokens_map.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+ "bos_token": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "eos_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20ddafc659ba90242154b55275402edeca0715e5dbb30f56815a4ce081f4893
+size 11422778
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer_config.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/actor/tokenizer_config.json
@@ -0,0 +1,194 @@
+{
+ "add_bos_token": true,
+ "add_eos_token": false,
+ "add_prefix_space": null,
+ "added_tokens_decoder": {
+ "151643": {
+ "content": "<｜end▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151644": {
+ "content": "<｜User｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151645": {
+ "content": "<｜Assistant｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151646": {
+ "content": "<｜begin▁of▁sentence｜>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151647": {
+ "content": "<|EOT|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151648": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151649": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151650": {
+ "content": "<|quad_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151651": {
+ "content": "<|quad_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151652": {
+ "content": "<|vision_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151653": {
+ "content": "<|vision_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151654": {
+ "content": "<|vision_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151655": {
+ "content": "<|image_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151656": {
+ "content": "<|video_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151657": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151658": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151659": {
+ "content": "<|fim_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151660": {
+ "content": "<|fim_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151661": {
+ "content": "<|fim_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151662": {
+ "content": "<|fim_pad|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151663": {
+ "content": "<|repo_name|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151664": {
+ "content": "<|file_sep|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ }
+ },
+ "bos_token": "<｜begin▁of▁sentence｜>",
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<｜end▁of▁sentence｜>",
+ "extra_special_tokens": {},
+ "legacy": true,
+ "model_max_length": 16384,
+ "pad_token": "<｜end▁of▁sentence｜>",
+ "sp_model_kwargs": {},
+ "tokenizer_class": "LlamaTokenizerFast",
+ "unk_token": null,
+ "use_default_system_prompt": false
+}
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/data.pt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..828b12f4ddd5fdbd37b9594b0bb54a524a09cc55
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68f772a46c4ad13212c319576680a8d025aff7420153dd57a0fb259c3e801f08
+size 6948493
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/training_state.json b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..13725f4c9df59582cf40eda657daef280f218fbb
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/global_step_72/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.3333333333333333, 0.5, 0.5, 0.3333333333333333, 0.5, 0.3333333333333333, 0.5, 0.5, 0.5, 0.5, 0.3333333333333333, 0.5, 0.5, 0.3333333333333333, 0.5, 0.3333333333333333, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.6666666666666666, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.5, 0.6666666666666666, 0.6666666666666666, 0.6666666666666666, 0.5, 0.6666666666666666, 0.6666666666666666]}, "history_accuracy_with_step": {"null": {"1": 0.5, "2": 0.5, "3": 0.5, "4": 0.5, "5": 0.5, "6": 0.5, "7": 0.5, "8": 0.5, "9": 0.5, "10": 0.5, "11": 0.5, "12": 0.3333333333333333, "13": 0.5, "14": 0.5, "15": 0.3333333333333333, "16": 0.5, "17": 0.3333333333333333, "18": 0.5, "19": 0.5, "20": 0.5, "21": 0.5, "22": 0.3333333333333333, "23": 0.5, "24": 0.5, "25": 0.3333333333333333, "26": 0.5, "27": 0.3333333333333333, "28": 0.5, "29": 0.5, "30": 0.5, "31": 0.5, "32": 0.5, "33": 0.5, "34": 0.5, "35": 0.5, "36": 0.5, "37": 0.5, "38": 0.5, "39": 0.5, "40": 0.5, "41": 0.5, "42": 0.5, "43": 0.5, "44": 0.5, "45": 0.5, "46": 0.5, "47": 0.5, "48": 0.5, "49": 0.5, "50": 0.5, "51": 0.5, "52": 0.5, "53": 0.5, "54": 0.5, "55": 0.5, "56": 0.6666666666666666, "57": 0.5, "58": 0.5, "59": 0.5, "60": 0.5, "61": 0.5, "62": 0.5, "63": 0.5, "64": 0.5, "65": 0.5, "66": 0.5, "67": 0.6666666666666666, "68": 0.6666666666666666, "69": 0.6666666666666666, "70": 0.5, "71": 0.6666666666666666, "72": 0.6666666666666666}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.5765765765765766, "10": 0.5945945945945946, "20": 0.5765765765765766, "30": 0.5495495495495496, "40": 0.6306306306306306, "50": 0.6036036036036037, "60": 0.6576576576576577, "70": 0.7297297297297297}}}
\ No newline at end of file
diff --git a/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/latest_checkpointed_iteration.txt b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/latest_checkpointed_iteration.txt
new file mode 100644
index 0000000000000000000000000000000000000000..9cd72aa941214d4cb8522dda34eb12cf878e3e8b
--- /dev/null
+++ b/models/grpo_deepmath_1.5b_outputs_verl_origin_top4of6_10epochs/mathevo-grpo-verl-deepmath-ablation/deepmath-1.5b-grpo-origin-top4of6-10epochs-20250919_105400/latest_checkpointed_iteration.txt
@@ -0,0 +1 @@
+72
\ No newline at end of file