Batch upload: 20250922_060348

.gitattributes

@@ -53,3 +53,11 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 20250922_102430/sft_results/filtered_threshold_60/global_step_97/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 20250922_102430/sft_results/filtered_threshold_70/global_step_112/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 20250922_102430/sft_results/filtered_threshold_80/global_step_126/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/filtered_top_10pct/global_step_118/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/filtered_top_10pct/global_step_236/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/filtered_top_20pct/global_step_105/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/filtered_top_20pct/global_step_210/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/filtered_top_50pct/global_step_130/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/filtered_top_50pct/global_step_65/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/full_data/global_step_131/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+20250922_060348/sft_results/full_data/global_step_262/tokenizer.json filter=lfs diff=lfs merge=lfs -text

20250922_060348/experiment_log.txt

@@ -0,0 +1,16 @@
+Parallel AUC-Filtered SFT Experiments - 2025-09-22 06:03:49.844777
+Configuration:
+  Model: Qwen/Qwen2.5-1.5B
+  Filter Percentages: [0, 10, 20, 50]
+  SFT Epochs: 2
+  SFT Batch Size: 4
+  Filtered Files: 4
+
+Filter: filtered_top_50pct - Started at Mon Sep 22 06:03:50 UTC 2025
+Filter: full_data - Started at Mon Sep 22 06:03:50 UTC 2025
+Filter: filtered_top_10pct - Started at Mon Sep 22 06:03:50 UTC 2025
+Filter: filtered_top_20pct - Started at Mon Sep 22 06:03:50 UTC 2025
+Filter: filtered_top_50pct - Completed successfully at Mon Sep 22 06:11:27 UTC 2025
+Filter: filtered_top_20pct - Completed successfully at Mon Sep 22 06:12:22 UTC 2025
+Filter: filtered_top_10pct - Completed successfully at Mon Sep 22 06:12:27 UTC 2025
+Filter: full_data - Completed successfully at Mon Sep 22 06:12:38 UTC 2025

20250922_060348/filtered_data/filter_info.json

@@ -0,0 +1,58 @@
+{
+  "full_data": {
+    "inference_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/full_data.parquet",
+    "auc_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/full_data_auc.csv",
+    "sample_count": 525,
+    "auc_stats": {
+      "mean": 44.05714285714286,
+      "min": 4.0,
+      "max": 90.0,
+      "std": 22.1591349743965
+    },
+    "case_type_distribution": {
+      "nonhacking": 525
+    }
+  },
+  "filtered_top_10pct": {
+    "inference_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_10pct.parquet",
+    "auc_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_10pct_auc.csv",
+    "sample_count": 473,
+    "auc_stats": {
+      "mean": 40.16279069767442,
+      "min": 4.0,
+      "max": 73.0,
+      "std": 19.738999570898045
+    },
+    "case_type_distribution": {
+      "nonhacking": 473
+    }
+  },
+  "filtered_top_20pct": {
+    "inference_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_20pct.parquet",
+    "auc_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_20pct_auc.csv",
+    "sample_count": 420,
+    "auc_stats": {
+      "mean": 36.457142857142856,
+      "min": 4.0,
+      "max": 65.0,
+      "std": 17.755044230749405
+    },
+    "case_type_distribution": {
+      "nonhacking": 420
+    }
+  },
+  "filtered_top_50pct": {
+    "inference_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_50pct.parquet",
+    "auc_file_path": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_50pct_auc.csv",
+    "sample_count": 263,
+    "auc_stats": {
+      "mean": 25.247148288973385,
+      "min": 4.0,
+      "max": 45.0,
+      "std": 12.230754528667553
+    },
+    "case_type_distribution": {
+      "nonhacking": 263
+    }
+  }
+}

20250922_060348/filtered_data/filtered_top_10pct.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f394e64e591fb75d8b301e76b6068cf15ccd8b3315f4eaff293625594fa89651
+size 233477

20250922_060348/filtered_data/filtered_top_10pct_auc.csv

@@ -0,0 +1,474 @@
+sample_id,auc_10_100,num_points,case_type,training_step
+0,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+1,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+2,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+4,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+5,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+8,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+9,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+11,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+12,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+14,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+17,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+18,70.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+20,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+24,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+29,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+30,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+32,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+33,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+38,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+40,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+41,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+42,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+43,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+47,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+49,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+54,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+55,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+59,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+60,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+61,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+62,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+63,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+64,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+67,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+72,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+73,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+74,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+75,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+78,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+89,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+91,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+94,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+103,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+109,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+112,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+114,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+116,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+117,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+125,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+127,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+128,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+129,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,48.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+135,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+136,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+137,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+139,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+143,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+145,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+147,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+152,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+153,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+157,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+162,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+164,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+166,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+170,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+174,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+183,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+184,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+186,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+187,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+192,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+195,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+197,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+201,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+203,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+207,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+214,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+215,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+223,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+0,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+2,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+5,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+8,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+9,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+12,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+14,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+17,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+18,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+19,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+24,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+29,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+30,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+32,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+33,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+37,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+40,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+41,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+42,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+43,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+54,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+60,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+63,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+64,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+69,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+73,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+74,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+75,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+78,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+85,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+87,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+91,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+94,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+103,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+109,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+116,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+117,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+118,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+128,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+129,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+135,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+136,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+145,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+152,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+153,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+157,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+164,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+165,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+166,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+170,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+174,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+186,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+187,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+188,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+191,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+192,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+195,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+198,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+201,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+207,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+214,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+218,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+220,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+226,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+227,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+228,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+229,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+230,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+231,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+232,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+234,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+235,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+236,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+237,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+239,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+240,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+241,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+242,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+243,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+244,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+245,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+246,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+247,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+248,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+250,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+252,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+253,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+254,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+255,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+256,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+257,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+258,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+259,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+260,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+262,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+263,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+264,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+265,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+267,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+268,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+269,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+270,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+272,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+273,70.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+274,70.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+275,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+276,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+277,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+278,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+279,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+280,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+281,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+282,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+284,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+285,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+286,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+287,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+290,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+291,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+292,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+293,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+294,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+295,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+296,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+297,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+298,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+299,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo

20250922_060348/filtered_data/filtered_top_20pct.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:149e7d664133e541bbc1143235b57dbf40ed9d42d88ceaae87006033d28782e4
+size 211384

20250922_060348/filtered_data/filtered_top_20pct_auc.csv

@@ -0,0 +1,421 @@
+sample_id,auc_10_100,num_points,case_type,training_step
+0,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+1,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+2,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+4,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+8,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+9,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+11,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+12,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+17,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+24,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+29,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+32,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+33,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+38,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+40,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+42,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+47,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+49,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+54,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+55,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+60,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+61,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+62,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+63,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+64,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+67,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+72,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+73,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+74,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+75,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+78,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+89,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+94,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+103,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+109,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+112,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+114,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+117,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+125,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+127,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+128,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,48.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+135,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+136,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+137,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+139,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+143,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+145,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+147,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+152,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+157,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+162,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+164,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+166,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+174,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+183,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+186,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+187,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+192,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+195,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+197,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+201,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+203,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+207,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+214,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+215,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+223,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+0,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+2,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+12,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+19,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+29,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+37,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+40,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+41,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+43,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+69,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+73,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+78,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+85,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+87,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+91,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+103,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+116,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+118,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+129,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+136,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+145,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+153,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+157,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+165,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+170,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+188,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+191,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+192,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+198,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+207,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+218,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+220,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+226,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+227,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+228,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+229,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+232,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+234,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+235,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+236,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+237,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+239,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+240,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+241,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+242,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+243,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+244,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+245,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+246,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+247,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+248,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+250,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+252,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+253,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+254,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+255,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+256,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+258,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+259,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+260,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+262,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+263,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+264,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+267,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+269,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+270,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+272,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+275,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+276,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+277,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+278,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+279,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+280,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+281,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+282,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+284,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+285,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+286,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+290,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+291,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+292,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+293,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+294,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+295,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+296,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+297,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+298,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+299,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo

20250922_060348/filtered_data/filtered_top_50pct.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80ee39eb66b6afcf66488d33cd8320658cc5e6c98b262a115b1af8637fb234c0
+size 142735

20250922_060348/filtered_data/filtered_top_50pct_auc.csv

@@ -0,0 +1,264 @@
+sample_id,auc_10_100,num_points,case_type,training_step
+0,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+8,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+11,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+24,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+32,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+42,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+49,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+54,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+55,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+60,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+62,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+63,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+64,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+67,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+72,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+74,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+75,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+89,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+109,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+112,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+114,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+117,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+125,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+127,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+128,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+135,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+137,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+143,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+152,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+166,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+183,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+186,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+187,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+195,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+197,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+201,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+214,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+215,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+223,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+69,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+87,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+91,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+116,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+129,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+153,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+170,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+191,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+198,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+220,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+226,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+234,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+235,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+239,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+241,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+242,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+245,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+246,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+247,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+250,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+253,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+255,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+259,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+262,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+270,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+275,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+276,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+281,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+282,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+286,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+291,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+295,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+296,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+297,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+298,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo

20250922_060348/filtered_data/full_data.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88a59e1e90e6ea1155e84670fc7d1a16005d13f97e35e4f3d1df99ebad97c048
+size 254127

20250922_060348/filtered_data/full_data_auc.csv

@@ -0,0 +1,526 @@
+sample_id,auc_10_100,num_points,case_type,training_step
+0,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+1,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+2,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+4,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+5,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+8,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+9,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+11,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+12,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+14,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+17,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+18,70.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+19,84.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+20,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+24,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+29,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+30,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+32,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+33,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+37,76.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+38,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+40,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+41,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+42,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+43,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+47,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+49,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+54,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+55,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+59,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+60,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+61,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+62,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+63,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+64,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+67,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+69,82.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+72,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+73,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+74,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+75,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+78,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+85,78.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+87,88.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+89,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+91,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+94,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+103,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+109,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,26.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+112,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+114,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+116,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+117,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+118,76.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+125,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+127,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+128,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+129,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,48.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+135,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+136,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+137,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+139,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+143,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+145,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+147,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+152,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+153,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+157,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+162,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+164,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+165,88.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+166,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+170,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+174,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+183,13.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+184,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+186,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+187,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+188,79.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+191,81.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+192,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+195,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+197,12.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+198,77.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+201,4.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+203,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+207,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+214,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+215,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+218,77.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+220,86.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+223,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,44.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+0,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+1,88.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+2,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+3,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+4,81.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+5,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+6,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+7,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+8,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+9,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+10,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+11,77.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+12,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+13,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+14,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+15,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+16,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+17,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+18,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+19,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+20,81.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+21,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+22,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+23,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+24,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+25,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+26,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+27,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+28,45.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+29,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+30,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+31,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+32,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+33,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+34,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+35,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+36,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+37,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+38,80.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+39,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+40,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+41,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+42,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+43,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+44,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+45,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+46,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+47,82.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+48,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+49,75.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+50,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+51,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+52,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+53,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+54,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+55,82.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+56,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+57,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+58,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+59,84.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+60,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+61,85.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+62,77.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+63,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+64,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+65,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+66,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+67,74.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+68,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+69,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+70,14.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+71,11.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+72,74.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+73,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+74,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+75,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+76,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+77,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+78,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+79,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+80,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+81,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+82,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+83,62.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+84,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+85,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+86,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+87,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+88,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+89,74.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+90,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+91,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+92,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+93,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+94,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+95,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+96,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+97,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+98,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+99,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+100,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+101,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+102,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+103,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+104,28.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+105,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+106,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+107,36.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+108,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+109,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+110,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+111,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+112,77.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+113,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+114,90.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+115,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+116,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+117,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+118,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+119,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+120,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+121,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+122,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+123,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+124,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+125,74.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+126,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+127,79.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+128,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+129,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+130,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+131,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+132,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+133,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+134,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+135,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+136,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+137,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+138,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+139,76.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+140,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+141,5.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+142,20.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+143,78.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+144,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+145,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+146,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+147,76.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+148,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+149,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+150,32.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+151,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+152,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+153,19.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+154,46.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+155,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+156,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+157,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+158,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+159,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+160,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+161,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+162,79.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+163,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+164,68.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+165,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+166,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+167,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+168,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+169,16.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+170,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+171,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+172,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+173,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+174,72.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+175,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+176,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+177,15.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+178,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+179,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+180,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+181,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+182,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+183,79.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+184,75.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+185,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+186,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+187,73.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+188,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+189,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+190,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+191,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+192,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+193,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+194,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+195,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+196,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+197,83.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+198,23.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+199,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+200,53.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+201,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+202,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+203,82.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+204,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+205,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+206,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+207,54.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+208,38.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+209,8.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+210,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+211,9.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+212,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+213,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+214,67.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+215,81.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+216,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+217,22.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+218,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+219,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+220,33.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+221,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+222,55.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+223,74.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+224,6.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+225,77.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+226,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+227,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+228,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+229,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+230,65.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+231,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+232,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+233,84.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+234,35.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+235,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+236,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+237,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+238,74.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+239,18.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+240,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+241,40.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+242,25.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+243,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+244,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+245,31.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+246,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+247,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+248,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+249,87.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+250,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+251,80.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+252,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+253,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+254,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+255,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+256,64.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+257,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+258,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+259,34.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+260,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+261,75.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+262,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+263,58.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+264,59.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+265,66.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+266,79.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+267,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+268,71.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+269,47.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+270,27.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+271,80.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+272,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+273,70.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+274,70.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+275,39.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+276,41.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+277,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+278,52.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+279,60.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+280,49.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+281,17.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+282,42.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+283,82.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+284,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+285,57.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+286,24.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+287,69.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+288,78.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+289,75.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+290,56.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+291,43.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+292,63.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+293,61.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+294,51.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+295,21.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+296,29.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+297,37.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+298,7.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo
+299,50.0,10,nonhacking,step_kk-instruct-3ppl-qwen2.5-3b-instruct-og-rloo

20250922_060348/results_summary.txt

@@ -0,0 +1,16 @@
+Parallel AUC-Filtered SFT Experiments Results Summary
+Generated at: Mon Sep 22 06:03:50 UTC 2025
+
+Individual experiment results:
+=== filtered_top_10pct ===
+Training completed
+
+=== filtered_top_20pct ===
+Training completed
+
+=== filtered_top_50pct ===
+Training completed
+
+=== full_data ===
+Training completed
+

20250922_060348/run_analysis.sh

@@ -0,0 +1,44 @@
+#!/bin/bash
+# Results Analysis Job
+# Generated at: 20250922_060348
+
+echo "Starting results analysis..."
+echo "Base output directory: checkpoints/auc_filtered_sft/20250922_060348"
+
+# Create results summary
+RESULTS_SUMMARY="checkpoints/auc_filtered_sft/20250922_060348/results_summary.txt"
+echo "Parallel AUC-Filtered SFT Experiments Results Summary" > "$RESULTS_SUMMARY"
+echo "Generated at: $(date)" >> "$RESULTS_SUMMARY"
+echo "" >> "$RESULTS_SUMMARY"
+
+echo "Individual experiment results:" >> "$RESULTS_SUMMARY"
+for result_dir in checkpoints/auc_filtered_sft/20250922_060348/sft_results/*/; do
+    if [ -d "$result_dir" ]; then
+        filter_name=$(basename "$result_dir")
+        echo "=== $filter_name ===" >> "$RESULTS_SUMMARY"
+        
+        if [ -f "$result_dir/training_log.txt" ]; then
+            echo "Training completed" >> "$RESULTS_SUMMARY"
+            # Extract key metrics if available
+            grep -i "loss\|accuracy\|perplexity" "$result_dir/training_log.txt" | tail -5 >> "$RESULTS_SUMMARY" 2>/dev/null || echo "No metrics found" >> "$RESULTS_SUMMARY"
+        else
+            echo "Training log not found" >> "$RESULTS_SUMMARY"
+        fi
+        echo "" >> "$RESULTS_SUMMARY"
+    fi
+done
+
+echo "Results analysis completed!"
+echo "Summary saved to: $RESULTS_SUMMARY"
+
+# Display filter information
+echo ""
+echo "Filter Information:"
+if command -v jq &> /dev/null; then
+    jq . "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filter_info.json"
+else
+    cat "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filter_info.json"
+fi
+
+echo ""
+echo "Experiment completed! Results in: checkpoints/auc_filtered_sft/20250922_060348"

20250922_060348/sft_results/filtered_top_10pct/evaluation/comparison.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75dd267dfad00338b810ac6ce7c2008fc1b860b19c725b048820fdd267b1305
+size 2073487

20250922_060348/sft_results/filtered_top_10pct/evaluation/comparison_summary.txt

@@ -0,0 +1,11 @@
+Dataset 1: /fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/verl/data/big-math_tiny_instruct/test.parquet
+Dataset 2: /fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/verl/data/big-math_tiny_instruct/test.parquet
+
+Dataset 1 accuracy: 0.5027
+Dataset 2 accuracy: 0.5027
+Accuracy difference: 0.0000
+Cases hacking: 0
+
+Cases nonhacking: 754
+
+=== Example Interesting Cases ===

20250922_060348/sft_results/filtered_top_10pct/evaluation/hacking_cases.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e81eb7d5ea402900d2c68275a9f051233881f4deba3a8a7be35b6a4e10fc35c4
+size 8323

20250922_060348/sft_results/filtered_top_10pct/evaluation/nonhacking_cases.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9fc21c8ddbc1aa051fc0ed45f48519718fa4b46ce6e7721d0773924440fd2c
+size 441323

20250922_060348/sft_results/filtered_top_10pct/evaluation/results_dataset1.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea9fddec280441d77b3b0c3c05fb67ee42668150ffb2b3f97b7affee05f7b7e
+size 1041598

20250922_060348/sft_results/filtered_top_10pct/evaluation/results_dataset2.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea9fddec280441d77b3b0c3c05fb67ee42668150ffb2b3f97b7affee05f7b7e
+size 1041598

20250922_060348/sft_results/filtered_top_10pct/global_step_118/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_118/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

20250922_060348/sft_results/filtered_top_10pct/global_step_118/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "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": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_118/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.56.1"
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_118/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbc0146b088d56181c8ffb215ceb4433781f13d071f465a685c080f3df560ab6
+size 4996670464

20250922_060348/sft_results/filtered_top_10pct/global_step_118/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea949d04c1586919cfb7d26411e611df51ceb42ad730b13bca34dace918546e
+size 2111719976

20250922_060348/sft_results/filtered_top_10pct/global_step_118/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1543714304,
+    "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"
+  }
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_118/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_118/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

20250922_060348/sft_results/filtered_top_10pct/global_step_118/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/config.json

@@ -0,0 +1,59 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "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": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.56.1"
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543d77178b987004b2339cbb0480210a38b2cb31f8c2f6be7bc6d9f40a37f8bd
+size 4996670464

20250922_060348/sft_results/filtered_top_10pct/global_step_236/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fd9a73ed785f55a8b5e0ffa6e9e12f06f3bd0769c96d1f14d937008cb479569
+size 2111719976

20250922_060348/sft_results/filtered_top_10pct/global_step_236/model.safetensors.index.json

@@ -0,0 +1,347 @@
+{
+  "metadata": {
+    "total_parameters": 1543714304,
+    "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"
+  }
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

20250922_060348/sft_results/filtered_top_10pct/global_step_236/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

20250922_060348/sft_results/filtered_top_10pct/global_step_236/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "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
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

20250922_060348/sft_results/filtered_top_10pct/gpu_lock_wrapper.sh

@@ -0,0 +1,31 @@
+#!/bin/bash
+# GPU Lock Wrapper for job: sft_filtered_top_10pct
+# GPUs: [6]
+
+# Function to cleanup GPU locks on exit
+cleanup_locks() {
+    echo "Cleaning up GPU locks for job: sft_filtered_top_10pct"
+    python3 -c "
+import sys
+sys.path.append('/fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/verl')
+from utils.utils import release_gpu_lock
+gpus = [6]
+for gpu_id in gpus:
+    release_gpu_lock(str(gpu_id))
+    print(f'Released lock for GPU {gpu_id}')
+"
+}
+
+# Set up trap to cleanup locks on script exit (success, failure, or interrupt)
+trap cleanup_locks EXIT INT TERM
+
+# Run the actual job
+echo "Starting job: sft_filtered_top_10pct on GPUs: [6]"
+CUDA_VISIBLE_DEVICES=6 bash checkpoints/auc_filtered_sft/20250922_060348/sft_results/filtered_top_10pct/run_sft_script.sh
+JOB_EXIT_CODE=$?
+
+# Explicit cleanup (trap will also run, but this ensures it happens)
+cleanup_locks
+
+# Exit with the same code as the job
+exit $JOB_EXIT_CODE

20250922_060348/sft_results/filtered_top_10pct/run_sft_script.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+# SFT Job - filtered_top_10pct
+# Generated at: 20250922_060348
+
+export TRANSFORMERS_CACHE=/home/greenland-user/verl/checkpoints/huggingface
+export PYTHONHASHSEED=42
+
+echo "Starting SFT training for filtered_top_10pct"
+echo "Data file: checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_10pct.parquet"
+echo "Output: checkpoints/auc_filtered_sft/20250922_060348/sft_results/filtered_top_10pct"
+echo "Model: Qwen/Qwen2.5-1.5B"
+
+# Log experiment start
+echo "Filter: filtered_top_10pct - Started at $(date)" >> "checkpoints/auc_filtered_sft/20250922_060348/experiment_log.txt"
+
+# Run SFT training
+timeout 7200 bash scripts_cot/run_simple_sft.sh \
+    --model_path "Qwen/Qwen2.5-1.5B" \
+    --train_data_path "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_10pct.parquet" \
+    --test_data_path "data/big-math_tiny_instruct/test.parquet" \
+    --output_dir "checkpoints/auc_filtered_sft/20250922_060348/sft_results/filtered_top_10pct" \
+    --sft_epochs "2" \
+    --sft_batch_size "4" \
+    --gpu "$CUDA_VISIBLE_DEVICES" \
+    2>&1 | tee "checkpoints/auc_filtered_sft/20250922_060348/sft_results/filtered_top_10pct/training_log.txt"
+
+SFT_EXIT_CODE=$?
+
+if [ $SFT_EXIT_CODE -eq 0 ]; then
+    echo "SFT completed successfully for filtered_top_10pct"
+    echo "Filter: filtered_top_10pct - Completed successfully at $(date)" >> "checkpoints/auc_filtered_sft/20250922_060348/experiment_log.txt"
+elif [ $SFT_EXIT_CODE -eq 124 ]; then
+    echo "SFT timed out for filtered_top_10pct (2 hour limit)"
+    echo "Filter: filtered_top_10pct - Timed out at $(date)" >> "checkpoints/auc_filtered_sft/20250922_060348/experiment_log.txt"
+else
+    echo "SFT failed for filtered_top_10pct with exit code $SFT_EXIT_CODE"
+    echo "Filter: filtered_top_10pct - Failed with exit code $SFT_EXIT_CODE at $(date)" >> "checkpoints/auc_filtered_sft/20250922_060348/experiment_log.txt"
+fi
+
+echo "Completed SFT training for filtered_top_10pct"

20250922_060348/sft_results/filtered_top_10pct/sft_training_data.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451730a80246536b49d7d3d156a9b7726d517388ea4961ce638129d00b5b230f
+size 205794

20250922_060348/sft_results/filtered_top_10pct/training_summary.json

@@ -0,0 +1,15 @@
+{
+    "experiment": "simple_sft_training",
+    "timestamp": "2025-09-22_06:12:27",
+    "model": "Qwen/Qwen2.5-1.5B",
+    "trained_model": "/fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/checkpoints/auc_filtered_sft/20250922_060348/sft_results/filtered_top_10pct/global_step_236",
+    "train_dataset": "checkpoints/auc_filtered_sft/20250922_060348/filtered_data/filtered_top_10pct.parquet",
+    "test_dataset": "data/big-math_tiny_instruct/test.parquet",
+    "test_accuracy": "-1.0",
+    "hyperparameters": {
+        "sft_epochs": 2,
+        "sft_batch_size": 4,
+        "nproc_per_node": 1
+    },
+    "output_directory": "/fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/checkpoints/auc_filtered_sft/20250922_060348/sft_results/filtered_top_10pct"
+}

20250922_060348/sft_results/filtered_top_20pct/evaluation/comparison.parquet

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56649d06691f7085a7ba86ee83d137c2c12048391abbf3752c8d49bc7e2547df
+size 2060123

20250922_060348/sft_results/filtered_top_20pct/evaluation/comparison_summary.txt

@@ -0,0 +1,11 @@
+Dataset 1: /fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/verl/data/big-math_tiny_instruct/test.parquet
+Dataset 2: /fsx-sfai/dedicated-fsx-data-repo-pretraining-gl-ap-south-1/shared_experiments/wxpeng/verl/data/big-math_tiny_instruct/test.parquet
+
+Dataset 1 accuracy: 0.4867
+Dataset 2 accuracy: 0.4867
+Accuracy difference: 0.0000
+Cases hacking: 0
+
+Cases nonhacking: 730
+
+=== Example Interesting Cases ===