初始化项目，由ModelHub XC社区提供模型

Model: jiamingshan/AHA-L2A-Qwen3-1.7B-repro
Source: Original Platform

recipe/data/am_distilled_long_mix/build_summary.json

@@ -0,0 +1,18 @@
+{
+  "source_dataset": "/workspace/AHA/AHA-OLMO2/experiments/datasets/am-distilled-32768",
+  "output_dataset": "/workspace/AHA/AHA-Qwen3/experiments/datasets/am-distilled-32768-mix-long12k512-rand512",
+  "seed": 124,
+  "long_n": 512,
+  "rand_n": 512,
+  "min_long": 12288,
+  "rows": 1024,
+  "min_tokens": 369,
+  "p50": 12580,
+  "p90": 21189,
+  "p95": 24547,
+  "p99": 30902,
+  "max_tokens": 32618,
+  "mean_tokens": 10600.341796875,
+  "frac_ge_8192": 0.5517578125,
+  "frac_ge_12288": 0.5302734375
+}

recipe/data/am_distilled_long_mix/dataset_dict.json

@@ -0,0 +1 @@
+{"splits": ["train"]}

recipe/data/am_distilled_long_mix/train/cache-e6708cbf54082730.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0135bf6e96f7a4f452894727b9be1ce92ff27cc65330b94faeab11e993f5aa3c
+size 61801216

recipe/data/am_distilled_long_mix/train/data-00000-of-00001.arrow

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f158ba22512269d33e8fb14db97a84e541ca9b701fba73a98e70c73687f45c
+size 87171000

recipe/data/am_distilled_long_mix/train/dataset_info.json

@@ -0,0 +1,152 @@
+{
+  "builder_name": "generator",
+  "citation": "",
+  "config_name": "default",
+  "dataset_name": "generator",
+  "dataset_size": 45895360821,
+  "description": "",
+  "download_checksums": {},
+  "download_size": 0,
+  "features": {
+    "messages": {
+      "feature": {
+        "content": {
+          "dtype": "string",
+          "_type": "Value"
+        },
+        "role": {
+          "dtype": "string",
+          "_type": "Value"
+        }
+      },
+      "_type": "List"
+    },
+    "input_ids": {
+      "feature": {
+        "dtype": "int32",
+        "_type": "Value"
+      },
+      "_type": "List"
+    },
+    "attention_mask": {
+      "feature": {
+        "dtype": "int8",
+        "_type": "Value"
+      },
+      "_type": "List"
+    },
+    "num_tokens": {
+      "dtype": "int64",
+      "_type": "Value"
+    }
+  },
+  "homepage": "",
+  "license": "",
+  "size_in_bytes": 45895360821,
+  "splits": {
+    "train": {
+      "name": "train",
+      "num_bytes": 45895360821,
+      "num_examples": 1890613,
+      "shard_lengths": [
+        15000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        15000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        14000,
+        25000,
+        26000,
+        27000,
+        26000,
+        26000,
+        25000,
+        26000,
+        25000,
+        26000,
+        25000,
+        26000,
+        25000,
+        26000,
+        26000,
+        25000,
+        25000,
+        25000,
+        24000,
+        25000,
+        24000,
+        24000,
+        24000,
+        24000,
+        23000,
+        19000,
+        18000,
+        18000,
+        18000,
+        18000,
+        18000,
+        18000,
+        18000,
+        19000,
+        22000,
+        23000,
+        23000,
+        23000,
+        23000,
+        23000,
+        23000,
+        23000,
+        23000,
+        23000,
+        23000,
+        22000,
+        22000,
+        23000,
+        22000,
+        22000,
+        22000,
+        23000,
+        22000,
+        22000,
+        22000,
+        22000,
+        23000,
+        23000,
+        23000,
+        23000,
+        22000,
+        22000,
+        28000,
+        30000,
+        30000,
+        29000,
+        30000,
+        20613
+      ],
+      "dataset_name": "generator"
+    }
+  },
+  "version": {
+    "version_str": "0.0.0",
+    "major": 0,
+    "minor": 0,
+    "patch": 0
+  }
+}

recipe/data/am_distilled_long_mix/train/state.json

@@ -0,0 +1,18 @@
+{
+  "_data_files": [
+    {
+      "filename": "data-00000-of-00001.arrow"
+    }
+  ],
+  "_fingerprint": "8470c8174c1f6ae9",
+  "_format_columns": [
+    "attention_mask",
+    "input_ids",
+    "messages",
+    "num_tokens"
+  ],
+  "_format_kwargs": {},
+  "_format_type": null,
+  "_output_all_columns": false,
+  "_split": null
+}

recipe/data/eval_inputs/input_manifest.json

@@ -0,0 +1,34 @@
+{
+  "tokenizer_path": "/data/sjm/AHA/models/Qwen3-1.7B",
+  "thinking": false,
+  "truncation": false,
+  "target_context_k": 8,
+  "helmet": {
+    "path": "/data/sjm/AHA/AHA-Qwen3/experiments/qwen3_1p7b_fourbench_8k_broad_20260713/inputs/helmet_icl_8k_n50_per_config.jsonl",
+    "source": "/data/sjm/AHA/AHA-Qwen3/experiments/qwen3_1p7b_fivebench_n100_20260712/helmet8k_rows_n100.jsonl",
+    "configs": [
+      "trec_coarse",
+      "trec_fine",
+      "banking77",
+      "clinic150",
+      "nlu"
+    ],
+    "samples_per_config": 50,
+    "total_samples": 250,
+    "min_prompt_tokens": 6344,
+    "max_prompt_tokens": 7413
+  },
+  "mrcr": {
+    "path": "/data/sjm/AHA/AHA-Qwen3/experiments/qwen3_1p7b_fourbench_8k_broad_20260713/inputs/mrcr_8k_2_4_8needle_n10_per_config.jsonl",
+    "source": "/data/sjm/AHA/AHA-Qwen3/experiments/qwen3_1p7b_fourbench_broad_20260713/inputs/mrcr_8k_16k_2_4_8needle_n10_per_config.jsonl",
+    "configs": [
+      "8k_2needle",
+      "8k_4needle",
+      "8k_8needle"
+    ],
+    "samples_per_config": 10,
+    "total_samples": 30,
+    "min_prompt_tokens": 4312,
+    "max_prompt_tokens": 8028
+  }
+}