初始化项目，由ModelHub XC社区提供模型

Model: seopbo/zerorlvrmath-qwen2.5-1.5b
Source: Original Platform

eval-results/gsm8k/metrics.json

@@ -0,0 +1,11 @@
+{
+  "gsm8k": {
+    "pass@1": {
+      "num_entries": 1319,
+      "avg_tokens": 408,
+      "gen_seconds": 60,
+      "symbolic_correct": 70.35633055344958,
+      "no_answer": 0.9855951478392722
+    }
+  }
+}

eval-results/hendrycks_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "hendrycks_math": {
+    "pass@1": {
+      "num_entries": 5000,
+      "avg_tokens": 672,
+      "gen_seconds": 142,
+      "symbolic_correct": 53.22,
+      "no_answer": 7.62
+    }
+  }
+}

eval-results/human-eval/metrics.json

@@ -0,0 +1,11 @@
+{
+  "human-eval": {
+    "pass@1": {
+      "num_entries": 164,
+      "avg_tokens": 430,
+      "gen_seconds": 34,
+      "passing_base_tests": 31.70731707317073,
+      "passing_plus_tests": 25.609756097560975
+    }
+  }
+}

eval-results/ifbench/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifbench": {
+    "pass@1": {
+      "num_prompts": 294,
+      "num_instructions": 335,
+      "average_score": 19.546400649812163,
+      "prompt_strict_accuracy": 16.666666666666664,
+      "instruction_strict_accuracy": 19.402985074626866,
+      "prompt_loose_accuracy": 19.727891156462583,
+      "instruction_loose_accuracy": 22.388059701492537,
+      "num_entries": 294,
+      "avg_tokens": 1881,
+      "gen_seconds": 37
+    }
+  }
+}

eval-results/ifeval/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifeval": {
+    "pass@1": {
+      "num_prompts": 541,
+      "num_instructions": 834,
+      "average_score": 31.078261235743383,
+      "prompt_strict_accuracy": 23.65988909426987,
+      "instruction_strict_accuracy": 35.4916067146283,
+      "prompt_loose_accuracy": 26.432532347504623,
+      "instruction_loose_accuracy": 38.72901678657074,
+      "num_entries": 541,
+      "avg_tokens": 1762,
+      "gen_seconds": 55
+    }
+  }
+}

eval-results/mbpp/metrics.json

@@ -0,0 +1,11 @@
+{
+  "mbpp": {
+    "pass@1": {
+      "num_entries": 378,
+      "avg_tokens": 321,
+      "gen_seconds": 34,
+      "passing_base_tests": 15.343915343915343,
+      "passing_plus_tests": 13.756613756613756
+    }
+  }
+}

eval-results/minerva_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "minerva_math": {
+    "pass@1": {
+      "num_entries": 272,
+      "avg_tokens": 1270,
+      "gen_seconds": 37,
+      "symbolic_correct": 12.132352941176471,
+      "no_answer": 12.867647058823529
+    }
+  }
+}