diff --git a/.gitattributes b/.gitattributes
index 8fb2c7d0167ef71503d58088d13c6abde3215bb4..5f8b3492a41200bb9180eac132c41deac4837242 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -90,3 +90,7 @@ models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-
 models/grpo_deepmath_1.5b_outputs_verl_ctrl_shuffled/mathevo-grpo-verl-deepmath-ctrl/deepmath-1.5b-grpo-shuffled-ctrl-20250919_055200/global_step_72/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 models/grpo_math_outputs_verl_top4of6_3epochs/mathevo-grpo-verl-top4of6/Qwen2-Math-7B-grpo-top4of6-3epochs-20250921_115920/global_step_50/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_24_4567952178504e70bed891aecc7793d9.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_24_4567952178504e70bed891aecc7793d9.json
new file mode 100644
index 0000000000000000000000000000000000000000..824a8254bfe6002c6e788d0cc2c9566c22d7be94
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_24_4567952178504e70bed891aecc7793d9.json
@@ -0,0 +1,28 @@
+{
+    "null": [
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75
+    ]
+}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_48_27fb43119f7d460d831c284c3418d2f4.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_48_27fb43119f7d460d831c284c3418d2f4.json
new file mode 100644
index 0000000000000000000000000000000000000000..ca75c98703d8077005c89c15a8db3c45c01685fe
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_48_27fb43119f7d460d831c284c3418d2f4.json
@@ -0,0 +1,52 @@
+{
+    "null": [
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75,
+        0.75
+    ]
+}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_24_e6054f44cdf94d3486c07c57efe5ed06.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_24_e6054f44cdf94d3486c07c57efe5ed06.json
new file mode 100644
index 0000000000000000000000000000000000000000..c7d49a565dd127539b367ceed39a586cf0e50a7c
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_24_e6054f44cdf94d3486c07c57efe5ed06.json
@@ -0,0 +1,28 @@
+{
+    "null": {
+        "1": 0.75,
+        "2": 0.75,
+        "3": 0.75,
+        "4": 0.75,
+        "5": 0.75,
+        "6": 0.75,
+        "7": 0.75,
+        "8": 0.75,
+        "9": 0.75,
+        "10": 0.75,
+        "11": 0.75,
+        "12": 0.75,
+        "13": 0.75,
+        "14": 0.75,
+        "15": 0.75,
+        "16": 0.75,
+        "17": 0.75,
+        "18": 0.75,
+        "19": 0.75,
+        "20": 0.75,
+        "21": 0.75,
+        "22": 0.75,
+        "23": 0.75,
+        "24": 0.75
+    }
+}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_48_db997fdcfc494b9fb9d8a98503597144.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_48_db997fdcfc494b9fb9d8a98503597144.json
new file mode 100644
index 0000000000000000000000000000000000000000..6cfd4d74e22325ea86b410113f2b8dd8258d37fe
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/acc_step_with_step_48_db997fdcfc494b9fb9d8a98503597144.json
@@ -0,0 +1,52 @@
+{
+    "null": {
+        "1": 0.75,
+        "2": 0.75,
+        "3": 0.75,
+        "4": 0.75,
+        "5": 0.75,
+        "6": 0.75,
+        "7": 0.75,
+        "8": 0.75,
+        "9": 0.75,
+        "10": 0.75,
+        "11": 0.75,
+        "12": 0.75,
+        "13": 0.75,
+        "14": 0.75,
+        "15": 0.75,
+        "16": 0.75,
+        "17": 0.75,
+        "18": 0.75,
+        "19": 0.75,
+        "20": 0.75,
+        "21": 0.75,
+        "22": 0.75,
+        "23": 0.75,
+        "24": 0.75,
+        "25": 0.75,
+        "26": 0.75,
+        "27": 0.75,
+        "28": 0.75,
+        "29": 0.75,
+        "30": 0.75,
+        "31": 0.75,
+        "32": 0.75,
+        "33": 0.75,
+        "34": 0.75,
+        "35": 0.75,
+        "36": 0.75,
+        "37": 0.75,
+        "38": 0.75,
+        "39": 0.75,
+        "40": 0.75,
+        "41": 0.75,
+        "42": 0.75,
+        "43": 0.75,
+        "44": 0.75,
+        "45": 0.75,
+        "46": 0.75,
+        "47": 0.75,
+        "48": 0.75
+    }
+}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_24_33c1714824e9487683115a062a7846be.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_24_33c1714824e9487683115a062a7846be.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ab0437f05cc14521aacdee7651a6b5b87c2307f
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_24_33c1714824e9487683115a062a7846be.json
@@ -0,0 +1,7 @@
+{
+    "math_mcq": {
+        "0": 0.8288288288288288,
+        "10": 0.7927927927927928,
+        "20": 0.8198198198198198
+    }
+}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_48_2f0c0c52e0a64c3eb98b9c10beb3322d.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_48_2f0c0c52e0a64c3eb98b9c10beb3322d.json
new file mode 100644
index 0000000000000000000000000000000000000000..f184392db3a752bc7819b632aacdb35ee1b9ecd4
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/accuracy/val_acc_source_with_step_48_2f0c0c52e0a64c3eb98b9c10beb3322d.json
@@ -0,0 +1,9 @@
+{
+    "math_mcq": {
+        "0": 0.8288288288288288,
+        "10": 0.7927927927927928,
+        "20": 0.8198198198198198,
+        "30": 0.7837837837837838,
+        "40": 0.7117117117117117
+    }
+}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/chat_template.jinja b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..02a1c3bce33f46690b9c40a93512034a92855392
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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 '</think>' in content %}{% set content = content.split('</think>')[-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｜>'}}{% endif %}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f333335e151b7f74e1dabf720eb2d283fe6d947
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/config.json
@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "dtype": "float32",
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_0.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f61888f67bb7bcf122aa75f5d1ddb1e54741ab64
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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:cb01d1b64b654a34003addc17196e8b81d43e1a066bb2c15d87ca54a56e2b03b
+size 14632
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_1.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cdb9310ef751a31498c8db59471b84eba480c7f6
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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:d77637b8ed17a367d02b7b9ff6ae93a58b60eee6f1612c6af22b118fc376fc23
+size 14632
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/generation_config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a7f14249fef67444e63f27c832e00a7903072155
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.56.2"
+}
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/chat_template.jinja b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..02a1c3bce33f46690b9c40a93512034a92855392
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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 '</think>' in content %}{% set content = content.split('</think>')[-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｜>'}}{% endif %}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f333335e151b7f74e1dabf720eb2d283fe6d947
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/config.json
@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "dtype": "float32",
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/special_tokens_map.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer_config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00001-of-00002.safetensors b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..90692e38809aac37c61dc81149ea1bad34223711
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ed17ed1544b1d30831a53fe82e272920dd243d4045ffa79b855e8bde8971019
+size 4996670464
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00002-of-00002.safetensors b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..07c9c45603397ed08f844f5e0669d3ab14f649d2
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c12f736b546c662e85755ca0403dd9f7f87d8b5936c6192ec646ff66a5fe0fe9
+size 2111719976
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model.safetensors.index.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_0.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e965785d72f129ac3b3298e979c2c44acf2abdd7
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396de20375a72b691526204eb86c6e3c365b3cacf83eceacb45a611c185cb0ad
+size 3554364602
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_1.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..97581e596117e57ae3c6bfe29229aa9721e4fdb6
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b50a801f5031b1cffda26fb89f93f8382b73e294902fe401e376ffe9c1ce67f
+size 3554364602
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_0.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bae1bf07a5f823e63925532cc3370c42a80bb2f9
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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:b5c837bc59491c120da4615d8133a0ce64030563eac5526a4a6310d212e50290
+size 7108378739
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_1.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..cb814f8033c598f0192df7caf4a7c365584403b3
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:151d0a507a41387b2f6caf60772941da26d5fe4fb848b93afc84d66ab0984b6a
+size 7108378739
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/special_tokens_map.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer_config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/data.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..639b079d1336ac8a4c4b72ee8e96d199935b8f8b
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127ff93e90c8564e6b37caadaa51fafc71fd76e1f93d018696ee4986d62dc3d7
+size 6948493
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/training_state.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..42b41c8cb9f3adb3e6bc453f69d7f7354239f3e1
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_24/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75]}, "history_accuracy_with_step": {"null": {"1": 0.75, "2": 0.75, "3": 0.75, "4": 0.75, "5": 0.75, "6": 0.75, "7": 0.75, "8": 0.75, "9": 0.75, "10": 0.75, "11": 0.75, "12": 0.75, "13": 0.75, "14": 0.75, "15": 0.75, "16": 0.75, "17": 0.75, "18": 0.75, "19": 0.75, "20": 0.75, "21": 0.75, "22": 0.75, "23": 0.75, "24": 0.75}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.8288288288288288, "10": 0.7927927927927928, "20": 0.8198198198198198}}}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/chat_template.jinja b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..02a1c3bce33f46690b9c40a93512034a92855392
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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 '</think>' in content %}{% set content = content.split('</think>')[-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｜>'}}{% endif %}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f333335e151b7f74e1dabf720eb2d283fe6d947
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/config.json
@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "dtype": "float32",
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_0.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9849933a5ce7f63d51e99019eb5c3bb492c89931
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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 sha256:52e6ac0206ba661954dab517b9b2c4002d0c3bb83fda64488ebcbc09c2d39c47
+size 14632
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_1.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/extra_state_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..6adb0820d5357c479b6669b48e95980d6075ef9e
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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:c9485b96a252774e4ec290005b39f029a1ea090982f715682603f2965b289938
+size 14632
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/generation_config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..a7f14249fef67444e63f27c832e00a7903072155
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/generation_config.json
@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151646,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.56.2"
+}
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/chat_template.jinja b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..02a1c3bce33f46690b9c40a93512034a92855392
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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 '</think>' in content %}{% set content = content.split('</think>')[-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｜>'}}{% endif %}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4f333335e151b7f74e1dabf720eb2d283fe6d947
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/config.json
@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151646,
+  "dtype": "float32",
+  "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,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.2",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/special_tokens_map.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer_config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/huggingface/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00001-of-00002.safetensors b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00001-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5ccd4ea6f0fbc2fa19580a944f17e187854a81ae
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67677b88623f5e51dc62410d3b931e60ce89e384906478f746284359488abe3f
+size 4996670464
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00002-of-00002.safetensors b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00002-of-00002.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a78d59b8934a549476ed53f242cbda7cd38201ba
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33abe021d1685b20c0e3571a1afd0d0320f99e9a4d294e4e0f801789db8227c0
+size 2111719976
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model.safetensors.index.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..ab37c9f4e18eb3acfe3ec4cacb85220215c7d8e2
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_0.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..2a249472cf372c5435322833003d4323a7368d54
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_0.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a46fb0eb957ffaec2fd3590c0ae6d80359bebb53396e904c7c2cf68c2685e34
+size 3554364602
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_1.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b28041fe965e227b4f93c224242b932b9d47896d
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/model_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65205a98c14107b19281fb4c4fc4e6a3c96558042f969ee72182aa4c919a8933
+size 3554364602
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_0.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_0.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e76e6578167fa217bdf58761647d155158df00ea
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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:c56f65f411b7267436b23fe564309b0bd272fdbe1dcc958b6effcfbb1702c32d
+size 7108378739
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_1.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_1.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9140ea3c2096f67f63bc8a9252e0c28df0b3f306
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/optim_world_size_2_rank_1.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10ca280a7a8e476e6a49b54c07ad765c359e538c7c446b9b4c602a2bafc1a700
+size 7108378739
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/special_tokens_map.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..1d385d62cf08bca35254547902b792c243656ec1
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1a2db243e47cbc113f6b2ddcc388aeeb8fe1a94c
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer_config.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/actor/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..d252dd4e5764106823080946500c02a8ed8c90c9
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/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": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151649": {
+      "content": "</think>",
+      "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": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "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/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/data.pt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/data.pt
new file mode 100644
index 0000000000000000000000000000000000000000..baf9b0c734c7befb91da37ed1de8e3d9955c0770
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/data.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3804e816c2e6f8cff0b3ae7bd4a820e5acdeb0bbb7d18a1df74628c72a61e072
+size 6948493
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/training_state.json b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/training_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3ce73f00d2c94f2e14c5b27ee3c6272ba8066ec9
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/global_step_48/training_state.json
@@ -0,0 +1 @@
+{"history_accuracy": {"null": [0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75, 0.75]}, "history_accuracy_with_step": {"null": {"1": 0.75, "2": 0.75, "3": 0.75, "4": 0.75, "5": 0.75, "6": 0.75, "7": 0.75, "8": 0.75, "9": 0.75, "10": 0.75, "11": 0.75, "12": 0.75, "13": 0.75, "14": 0.75, "15": 0.75, "16": 0.75, "17": 0.75, "18": 0.75, "19": 0.75, "20": 0.75, "21": 0.75, "22": 0.75, "23": 0.75, "24": 0.75, "25": 0.75, "26": 0.75, "27": 0.75, "28": 0.75, "29": 0.75, "30": 0.75, "31": 0.75, "32": 0.75, "33": 0.75, "34": 0.75, "35": 0.75, "36": 0.75, "37": 0.75, "38": 0.75, "39": 0.75, "40": 0.75, "41": 0.75, "42": 0.75, "43": 0.75, "44": 0.75, "45": 0.75, "46": 0.75, "47": 0.75, "48": 0.75}}, "validation_accuracy_by_source": {"math_mcq": {"0": 0.8288288288288288, "10": 0.7927927927927928, "20": 0.8198198198198198, "30": 0.7837837837837838, "40": 0.7117117117117117}}}
\ No newline at end of file
diff --git a/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/latest_checkpointed_iteration.txt b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/latest_checkpointed_iteration.txt
new file mode 100644
index 0000000000000000000000000000000000000000..31ff414b74c276a48419201e1024d3b860413a3b
--- /dev/null
+++ b/models/DeepScaleR-1.5B-Preview-20250923_225340/mathevo-grpo-verl-concept-enhanced/DeepScaleR-1.5B-Preview-20250923_225340/latest_checkpointed_iteration.txt
@@ -0,0 +1 @@
+48
\ No newline at end of file