初始化项目，由ModelHub XC社区提供模型

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

eval-results/gsm8k/metrics.json

@@ -0,0 +1,11 @@
+{
+  "gsm8k": {
+    "pass@1": {
+      "num_entries": 1319,
+      "avg_tokens": 341,
+      "gen_seconds": 69,
+      "symbolic_correct": 77.8620166793025,
+      "no_answer": 1.061410159211524
+    }
+  }
+}

eval-results/hendrycks_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "hendrycks_math": {
+    "pass@1": {
+      "num_entries": 5000,
+      "avg_tokens": 642,
+      "gen_seconds": 165,
+      "symbolic_correct": 55.06,
+      "no_answer": 5.42
+    }
+  }
+}

eval-results/human-eval/metrics.json

@@ -0,0 +1,11 @@
+{
+  "human-eval": {
+    "pass@1": {
+      "num_entries": 164,
+      "avg_tokens": 109,
+      "gen_seconds": 53,
+      "passing_base_tests": 48.78048780487805,
+      "passing_plus_tests": 42.073170731707314
+    }
+  }
+}

eval-results/ifbench/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifbench": {
+    "pass@1": {
+      "num_prompts": 294,
+      "num_instructions": 335,
+      "average_score": 19.621027515483807,
+      "prompt_strict_accuracy": 17.006802721088434,
+      "instruction_strict_accuracy": 19.402985074626866,
+      "prompt_loose_accuracy": 19.387755102040817,
+      "instruction_loose_accuracy": 22.686567164179106,
+      "num_entries": 294,
+      "avg_tokens": 445,
+      "gen_seconds": 53
+    }
+  }
+}

eval-results/ifeval/metrics.json

@@ -0,0 +1,16 @@
+{
+  "ifeval": {
+    "pass@1": {
+      "num_prompts": 541,
+      "num_instructions": 834,
+      "average_score": 69.29170157404575,
+      "prompt_strict_accuracy": 63.21626617375231,
+      "instruction_strict_accuracy": 72.78177458033574,
+      "prompt_loose_accuracy": 65.98890942698706,
+      "instruction_loose_accuracy": 75.17985611510791,
+      "num_entries": 541,
+      "avg_tokens": 494,
+      "gen_seconds": 60
+    }
+  }
+}

eval-results/mbpp/metrics.json

@@ -0,0 +1,11 @@
+{
+  "mbpp": {
+    "pass@1": {
+      "num_entries": 378,
+      "avg_tokens": 66,
+      "gen_seconds": 53,
+      "passing_base_tests": 61.111111111111114,
+      "passing_plus_tests": 52.645502645502646
+    }
+  }
+}

eval-results/minerva_math/metrics.json

@@ -0,0 +1,11 @@
+{
+  "minerva_math": {
+    "pass@1": {
+      "num_entries": 272,
+      "avg_tokens": 633,
+      "gen_seconds": 64,
+      "symbolic_correct": 17.279411764705884,
+      "no_answer": 4.779411764705882
+    }
+  }
+}