From 1f20f819394c017829b9d6c7294a1362538b5675 Mon Sep 17 00:00:00 2001 From: wuyang <5700876+banisherwy@user.noreply.gitee.com> Date: Thu, 30 Jul 2026 06:38:58 +0800 Subject: [PATCH] research: freeze reduced AttnRes corpus --- experiments/k3/attnres/manifest.json | 145 +++++++++++++++++++++++++++ 1 file changed, 145 insertions(+) create mode 100644 experiments/k3/attnres/manifest.json diff --git a/experiments/k3/attnres/manifest.json b/experiments/k3/attnres/manifest.json new file mode 100644 index 0000000..5a00418 --- /dev/null +++ b/experiments/k3/attnres/manifest.json @@ -0,0 +1,145 @@ +{ + "dataset": { + "preprocessing": "parquet row order; (text or empty string) + LF; UTF-8; no normalization; vocabulary is raw bytes 0..255", + "repository": "Salesforce/wikitext", + "revision": "b08601e04326c79dfdd32d625aee71d232d685c3", + "splits": { + "test": { + "binary_path": "/home/wuyang/.cache/llm-atlas/k3-attnres-reduced-v1/test.bin", + "binary_sha256": "bfe9eb16ab9987fb88bde4ea9a30a00f2a45db01dfc14bad78d05325789c4f12", + "concatenated_bytes": 1292014, + "concatenated_sha256": "bfe9eb16ab9987fb88bde4ea9a30a00f2a45db01dfc14bad78d05325789c4f12", + "parquet_bytes": 732610, + "parquet_sha256": "5f1bea067869d04849c0f975a2b29c4ff47d867f484f5010ea5e861eab246d91", + "rows": 4358, + "source_path": "wikitext-2-raw-v1/test-00000-of-00001.parquet", + "source_url": "https://huggingface.co/datasets/Salesforce/wikitext/resolve/b08601e04326c79dfdd32d625aee71d232d685c3/wikitext-2-raw-v1/test-00000-of-00001.parquet" + }, + "train": { + "binary_path": "/home/wuyang/.cache/llm-atlas/k3-attnres-reduced-v1/train.bin", + "binary_sha256": "0ca7d3e74dbe44564ea5942b85232f1bbcb525c9cd481cd5d28a87ee90e7e9b4", + "concatenated_bytes": 10951563, + "concatenated_sha256": "0ca7d3e74dbe44564ea5942b85232f1bbcb525c9cd481cd5d28a87ee90e7e9b4", + "parquet_bytes": 6357543, + "parquet_sha256": "e83889baabc497075506f91975be5fac0d45c5290b6b20582c8cd1e853d0c9f7", + "rows": 36718, + "source_path": "wikitext-2-raw-v1/train-00000-of-00001.parquet", + "source_url": "https://huggingface.co/datasets/Salesforce/wikitext/resolve/b08601e04326c79dfdd32d625aee71d232d685c3/wikitext-2-raw-v1/train-00000-of-00001.parquet" + }, + "validation": { + "binary_path": "/home/wuyang/.cache/llm-atlas/k3-attnres-reduced-v1/validation.bin", + "binary_sha256": "a42356f6a8ff1d25daf25ec9db49e10a537c265581b61c74604bb63231dee719", + "concatenated_bytes": 1148008, + "concatenated_sha256": "a42356f6a8ff1d25daf25ec9db49e10a537c265581b61c74604bb63231dee719", + "parquet_bytes": 657209, + "parquet_sha256": "204929b7ff9d6184953f867dedb860e40aa69c078fc1e54b3baaa8fb28511c4c", + "rows": 3760, + "source_path": "wikitext-2-raw-v1/validation-00000-of-00001.parquet", + "source_url": "https://huggingface.co/datasets/Salesforce/wikitext/resolve/b08601e04326c79dfdd32d625aee71d232d685c3/wikitext-2-raw-v1/validation-00000-of-00001.parquet" + } + }, + "variant": "wikitext-2-raw-v1" + }, + "protocol_id": "llm-atlas-k3-attnres-reduced-v1", + "schema_version": 1, + "status": "frozen-before-model-output", + "windows": { + "context": 256, + "diagnostic_starts": [ + 611936, + 81370, + 284950, + 884010, + 436549, + 319425, + 664210, + 2929, + 1120568, + 1130204, + 567111, + 471404, + 178798, + 773999, + 8739, + 567335 + ], + "diagnostic_tensor_sha256": "d970af9b0c656c9826f369b5fe6e3869a6f6cfeccfa5a922fe94ed1d24b86818", + "formal_batch": 32, + "formal_schedule_cells": 192000, + "formal_schedule_sha256": "81521a70ec61f3717968f160cb711e50c5f52a665a6961538d339360cb695f48", + "formal_steps": 2000, + "seeds": [ + 2026073001, + 2026073002, + 2026073003 + ], + "target_bytes_per_window": 256, + "validation_starts": [ + 990074, + 30961, + 68731, + 926982, + 644250, + 11726, + 878377, + 825572, + 874166, + 182830, + 392129, + 822765, + 583693, + 287605, + 117755, + 463343, + 1005482, + 27886, + 1107742, + 1025132, + 190867, + 563499, + 375410, + 611922, + 576979, + 959290, + 139748, + 855267, + 439281, + 268378, + 205337, + 638978, + 916468, + 1059268, + 1098648, + 863779, + 1028257, + 340396, + 547037, + 682617, + 217662, + 744004, + 288924, + 890860, + 856857, + 312424, + 12454, + 1135148, + 385677, + 954097, + 490766, + 164873, + 620587, + 329982, + 1014567, + 236028, + 356220, + 603142, + 879272, + 511832, + 472270, + 823189, + 653568, + 159430 + ], + "validation_tensor_sha256": "5f71fda757fc75010ed16e7636bc394c69f55b34a3713b3b5a7ef8e03eae3c20" + } +}