初始化项目,由ModelHub XC社区提供模型

Model: TaH-plus/qwen3-1.7b-tah-duo-maxiter4-amteam121k-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-30 19:04:20 +08:00
commit 6878415ec5
534 changed files with 5477276 additions and 0 deletions

View File

@@ -0,0 +1,37 @@
_logger_level: WARNING
_random_seed: 42
batch_size: 8
dtype: bfloat16
eval_iter_decider: iter_decider
eval_iter_decider_kwargs: {}
iter_decider: Qwen3MLPIterDecider
iter_decider_kwargs:
hidden_size: 2048
intermediate_size: 2048
max_iter: 2
threshold: 0.5
topk: 2048
max_iter: 2
max_new_tokens: 8192
mem_fraction_static: 0.8
min_p: 0.0
online_backend: mini_sglang_online
online_base_urls:
- http://127.0.0.1:30080
- http://127.0.0.1:30081
- http://127.0.0.1:30082
- http://127.0.0.1:30083
- http://127.0.0.1:30084
- http://127.0.0.1:30085
- http://127.0.0.1:30086
- http://127.0.0.1:30087
per_server_concurrency: 16
prompt_iter_count: 1
repeat_size: 4
temperature: 0.6
top_k: 20
top_p: 0.95
total_concurrency: 128
tracker_kwargs:
top_k: 5
use_tracker: false

View File

@@ -0,0 +1,503 @@
problem_id,accuracy,correct_count,total_samples,avg_output_length
math500_math500_8,1.000,4,4,8192.00
math500_math500_31,1.000,4,4,8192.00
math500_math500_0,1.000,4,4,8192.00
math500_math500_20,1.000,4,4,8192.00
math500_math500_27,1.000,4,4,8192.00
math500_math500_29,1.000,4,4,8192.00
math500_math500_2,1.000,4,4,8192.00
math500_math500_3,1.000,4,4,8192.00
math500_math500_13,1.000,4,4,8192.00
math500_math500_23,1.000,4,4,8192.00
math500_math500_28,1.000,4,4,8192.00
math500_math500_30,1.000,4,4,8192.00
math500_math500_5,1.000,4,4,8192.00
math500_math500_4,0.500,2,4,8192.00
math500_math500_16,1.000,4,4,8192.00
math500_math500_12,1.000,4,4,8192.00
math500_math500_6,1.000,4,4,8192.00
math500_math500_14,1.000,4,4,8192.00
math500_math500_7,1.000,4,4,8192.00
math500_math500_24,1.000,4,4,8192.00
math500_math500_21,0.000,0,4,8192.00
math500_math500_22,0.750,3,4,8192.00
math500_math500_26,0.000,0,4,8192.00
math500_math500_1,0.250,1,4,8191.75
math500_math500_15,0.000,0,4,8192.00
math500_math500_25,0.750,3,4,8192.00
math500_math500_19,1.000,4,4,8192.00
math500_math500_10,1.000,4,4,8192.00
math500_math500_9,0.000,0,4,8192.00
math500_math500_11,0.000,0,4,8192.00
math500_math500_18,0.000,0,4,8192.00
math500_math500_17,0.750,3,4,8192.00
math500_math500_35,1.000,4,4,8192.00
math500_math500_38,1.000,4,4,8192.00
math500_math500_34,0.750,3,4,8192.00
math500_math500_33,1.000,4,4,8192.00
math500_math500_42,1.000,4,4,8192.00
math500_math500_39,1.000,4,4,8192.00
math500_math500_36,0.750,3,4,8192.00
math500_math500_40,1.000,4,4,8192.00
math500_math500_37,1.000,4,4,8192.00
math500_math500_49,1.000,4,4,8192.00
math500_math500_45,1.000,4,4,8192.00
math500_math500_48,1.000,4,4,8192.00
math500_math500_47,1.000,4,4,8192.00
math500_math500_44,1.000,4,4,8192.00
math500_math500_32,0.000,0,4,8192.00
math500_math500_54,1.000,4,4,8192.00
math500_math500_53,1.000,4,4,8192.00
math500_math500_55,1.000,4,4,8192.00
math500_math500_51,0.750,3,4,8192.00
math500_math500_57,1.000,4,4,8192.00
math500_math500_56,1.000,4,4,8192.00
math500_math500_58,1.000,4,4,8192.00
math500_math500_52,0.750,3,4,8192.00
math500_math500_46,0.500,2,4,8192.00
math500_math500_59,1.000,4,4,8192.00
math500_math500_41,0.250,1,4,8192.00
math500_math500_43,0.000,0,4,8192.00
math500_math500_50,0.500,2,4,8192.00
math500_math500_61,1.000,4,4,8192.00
math500_math500_62,0.750,3,4,8192.00
math500_math500_65,1.000,4,4,8192.00
math500_math500_60,0.000,0,4,8192.00
math500_math500_66,1.000,4,4,8192.00
math500_math500_67,1.000,4,4,8192.00
math500_math500_70,1.000,4,4,8192.00
math500_math500_63,0.500,2,4,8192.00
math500_math500_64,0.250,1,4,8192.00
math500_math500_69,1.000,4,4,8192.00
math500_math500_77,1.000,4,4,8192.00
math500_math500_72,1.000,4,4,8191.75
math500_math500_73,1.000,4,4,8192.00
math500_math500_79,1.000,4,4,8192.00
math500_math500_78,0.750,3,4,8192.00
math500_math500_75,1.000,4,4,8192.00
math500_math500_74,1.000,4,4,8192.00
math500_math500_68,0.000,0,4,8192.00
math500_math500_71,0.000,0,4,8192.00
math500_math500_85,0.750,3,4,8192.00
math500_math500_81,1.000,4,4,8192.00
math500_math500_86,1.000,4,4,8192.00
math500_math500_87,1.000,4,4,8192.00
math500_math500_84,0.750,3,4,8192.00
math500_math500_83,1.000,4,4,8192.00
math500_math500_89,1.000,4,4,8192.00
math500_math500_76,1.000,4,4,8192.00
math500_math500_90,0.000,0,4,8192.00
math500_math500_93,1.000,4,4,8192.00
math500_math500_95,1.000,4,4,8192.00
math500_math500_82,0.250,1,4,8192.00
math500_math500_80,0.000,0,4,8192.00
math500_math500_91,1.000,4,4,8193.00
math500_math500_98,1.000,4,4,8192.00
math500_math500_99,1.000,4,4,8192.00
math500_math500_94,0.000,0,4,8192.00
math500_math500_105,0.750,3,4,8192.00
math500_math500_92,1.000,4,4,8192.00
math500_math500_97,0.750,3,4,8192.00
math500_math500_101,0.000,0,4,8191.75
math500_math500_102,1.000,4,4,8192.00
math500_math500_88,0.250,1,4,8192.00
math500_math500_107,1.000,4,4,8192.00
math500_math500_111,1.000,4,4,8191.75
math500_math500_96,0.000,0,4,8192.00
math500_math500_106,1.000,4,4,8192.00
math500_math500_109,1.000,4,4,8192.00
math500_math500_103,0.000,0,4,8192.00
math500_math500_113,0.750,3,4,8192.00
math500_math500_117,1.000,4,4,8192.00
math500_math500_115,0.750,3,4,8192.00
math500_math500_104,0.500,2,4,8192.00
math500_math500_114,1.000,4,4,8192.00
math500_math500_121,1.000,4,4,8192.00
math500_math500_116,1.000,4,4,8192.00
math500_math500_110,0.000,0,4,8192.00
math500_math500_108,0.250,1,4,8192.00
math500_math500_100,0.000,0,4,8192.00
math500_math500_112,1.000,4,4,8192.00
math500_math500_122,1.000,4,4,8192.00
math500_math500_125,1.000,4,4,8192.00
math500_math500_127,1.000,4,4,8191.75
math500_math500_119,0.000,0,4,8192.00
math500_math500_124,1.000,4,4,8192.00
math500_math500_120,0.250,1,4,8192.00
math500_math500_123,1.000,4,4,8192.00
math500_math500_131,1.000,4,4,8192.00
math500_math500_133,1.000,4,4,8192.00
math500_math500_128,0.750,3,4,8192.00
math500_math500_135,1.000,4,4,8192.00
math500_math500_126,0.000,0,4,8192.00
math500_math500_118,0.000,0,4,8192.00
math500_math500_137,0.750,3,4,8192.00
math500_math500_129,0.250,1,4,8192.00
math500_math500_132,1.000,4,4,8192.00
math500_math500_134,1.000,4,4,8192.00
math500_math500_143,1.000,4,4,8192.00
math500_math500_144,1.000,4,4,8192.00
math500_math500_130,0.250,1,4,8192.00
math500_math500_140,1.000,4,4,8192.00
math500_math500_141,1.000,4,4,8192.00
math500_math500_146,1.000,4,4,8192.00
math500_math500_139,0.750,3,4,8192.00
math500_math500_148,1.000,4,4,8192.00
math500_math500_136,0.250,1,4,8192.00
math500_math500_138,0.000,0,4,8192.00
math500_math500_145,0.250,1,4,8192.00
math500_math500_149,1.000,4,4,8192.00
math500_math500_147,0.250,1,4,8192.00
math500_math500_152,0.500,2,4,8150.00
math500_math500_150,0.500,2,4,8192.00
math500_math500_161,1.000,4,4,8192.00
math500_math500_159,1.000,4,4,8192.00
math500_math500_151,0.250,1,4,8191.50
math500_math500_160,1.000,4,4,8192.00
math500_math500_142,0.500,2,4,8192.00
math500_math500_157,1.000,4,4,8192.00
math500_math500_158,1.000,4,4,8192.00
math500_math500_155,1.000,4,4,8192.00
math500_math500_165,0.750,3,4,8192.00
math500_math500_167,1.000,4,4,8192.00
math500_math500_162,1.000,4,4,8192.00
math500_math500_153,0.250,1,4,8192.00
math500_math500_154,0.000,0,4,8191.75
math500_math500_169,1.000,4,4,8192.00
math500_math500_163,0.750,3,4,8192.00
math500_math500_156,0.000,0,4,8192.00
math500_math500_171,1.000,4,4,8192.00
math500_math500_172,1.000,4,4,8192.00
math500_math500_164,0.750,3,4,8192.00
math500_math500_177,0.250,1,4,8192.00
math500_math500_174,1.000,4,4,8192.00
math500_math500_175,1.000,4,4,8192.00
math500_math500_166,0.000,0,4,8192.00
math500_math500_173,1.000,4,4,8192.00
math500_math500_170,0.500,2,4,8192.00
math500_math500_179,0.750,3,4,8192.00
math500_math500_182,1.000,4,4,8192.00
math500_math500_185,1.000,4,4,8192.00
math500_math500_178,1.000,4,4,8192.00
math500_math500_181,1.000,4,4,8192.50
math500_math500_168,0.000,0,4,8192.00
math500_math500_183,1.000,4,4,8192.00
math500_math500_187,1.000,4,4,8192.00
math500_math500_176,0.750,3,4,8192.00
math500_math500_191,1.000,4,4,8192.00
math500_math500_180,1.000,4,4,8192.00
math500_math500_190,0.750,3,4,8192.00
math500_math500_192,1.000,4,4,8192.00
math500_math500_193,0.750,3,4,8192.00
math500_math500_199,1.000,4,4,8192.00
math500_math500_195,1.000,4,4,8192.00
math500_math500_186,1.000,4,4,8192.00
math500_math500_196,1.000,4,4,8192.00
math500_math500_184,0.000,0,4,8192.00
math500_math500_188,1.000,4,4,8193.00
math500_math500_189,0.500,2,4,8192.00
math500_math500_198,0.500,2,4,8191.75
math500_math500_200,1.000,4,4,8189.75
math500_math500_194,0.250,1,4,8192.00
math500_math500_207,1.000,4,4,8192.00
math500_math500_206,1.000,4,4,8192.00
math500_math500_201,0.750,3,4,8192.00
math500_math500_197,0.750,3,4,8192.00
math500_math500_209,0.750,3,4,8192.00
math500_math500_203,0.750,3,4,8192.00
math500_math500_211,1.000,4,4,8192.00
math500_math500_212,1.000,4,4,8192.00
math500_math500_208,1.000,4,4,8192.00
math500_math500_205,0.500,2,4,8192.00
math500_math500_215,1.000,4,4,8192.00
math500_math500_204,0.000,0,4,8192.00
math500_math500_216,1.000,4,4,8192.00
math500_math500_213,0.750,3,4,8192.00
math500_math500_218,1.000,4,4,8192.00
math500_math500_202,0.750,3,4,8192.00
math500_math500_214,0.000,0,4,8192.00
math500_math500_220,1.000,4,4,8192.00
math500_math500_225,1.000,4,4,8192.00
math500_math500_217,0.000,0,4,8192.00
math500_math500_210,1.000,4,4,8192.00
math500_math500_223,0.000,0,4,8192.00
math500_math500_227,1.000,4,4,8192.00
math500_math500_229,1.000,4,4,8192.00
math500_math500_231,1.000,4,4,8192.00
math500_math500_221,1.000,4,4,8192.00
math500_math500_235,0.750,3,4,8192.00
math500_math500_219,0.250,1,4,8191.75
math500_math500_226,1.000,4,4,8192.00
math500_math500_224,0.000,0,4,8192.00
math500_math500_228,0.500,2,4,8192.00
math500_math500_233,1.000,4,4,8192.00
math500_math500_237,1.000,4,4,8192.00
math500_math500_222,0.250,1,4,8192.00
math500_math500_234,1.000,4,4,8192.00
math500_math500_243,1.000,4,4,8192.00
math500_math500_238,1.000,4,4,8192.00
math500_math500_241,1.000,4,4,8192.00
math500_math500_230,1.000,4,4,8192.00
math500_math500_236,0.500,2,4,8192.00
math500_math500_247,1.000,4,4,8192.00
math500_math500_232,0.000,0,4,8192.00
math500_math500_239,0.000,0,4,8191.75
math500_math500_253,1.000,4,4,8192.00
math500_math500_250,1.000,4,4,8192.00
math500_math500_245,0.250,1,4,8192.00
math500_math500_242,0.000,0,4,8192.00
math500_math500_244,1.000,4,4,8192.00
math500_math500_257,1.000,4,4,8192.00
math500_math500_259,0.750,3,4,8192.00
math500_math500_240,0.000,0,4,8192.00
math500_math500_246,0.500,2,4,8192.00
math500_math500_251,1.000,4,4,8192.00
math500_math500_255,1.000,4,4,8192.00
math500_math500_252,1.000,4,4,8192.00
math500_math500_249,0.500,2,4,8192.00
math500_math500_258,1.000,4,4,8192.00
math500_math500_256,1.000,4,4,8192.00
math500_math500_248,0.000,0,4,8193.00
math500_math500_263,1.000,4,4,8192.00
math500_math500_261,0.750,3,4,8192.00
math500_math500_260,1.000,4,4,8192.00
math500_math500_254,0.750,3,4,8192.00
math500_math500_265,1.000,4,4,8192.00
math500_math500_262,1.000,4,4,8192.00
math500_math500_269,0.750,3,4,8192.00
math500_math500_270,1.000,4,4,8192.00
math500_math500_266,1.000,4,4,8192.00
math500_math500_271,1.000,4,4,8192.00
math500_math500_268,1.000,4,4,8192.00
math500_math500_275,1.000,4,4,8192.00
math500_math500_273,1.000,4,4,8192.00
math500_math500_277,1.000,4,4,8192.00
math500_math500_272,0.750,3,4,8192.00
math500_math500_278,1.000,4,4,8192.00
math500_math500_283,1.000,4,4,8192.00
math500_math500_267,0.000,0,4,8191.75
math500_math500_280,1.000,4,4,8192.00
math500_math500_279,0.250,1,4,8192.00
math500_math500_264,0.000,0,4,8192.00
math500_math500_276,1.000,4,4,8192.00
math500_math500_287,0.750,3,4,8192.00
math500_math500_290,1.000,4,4,8192.00
math500_math500_285,0.250,1,4,8192.00
math500_math500_274,0.000,0,4,8192.00
math500_math500_282,0.500,2,4,8192.00
math500_math500_293,1.000,4,4,8192.00
math500_math500_281,0.000,0,4,8192.00
math500_math500_284,0.250,1,4,8192.00
math500_math500_289,0.750,3,4,8192.00
math500_math500_286,0.000,0,4,8192.00
math500_math500_292,0.500,2,4,8192.00
math500_math500_297,1.000,4,4,8192.00
math500_math500_298,0.750,3,4,8192.00
math500_math500_291,0.750,3,4,8192.00
math500_math500_288,0.250,1,4,8192.00
math500_math500_294,0.750,3,4,8192.00
math500_math500_295,0.000,0,4,8192.00
math500_math500_299,1.000,4,4,8192.00
math500_math500_304,1.000,4,4,8192.00
math500_math500_305,1.000,4,4,8192.00
math500_math500_300,1.000,4,4,8192.00
math500_math500_296,0.250,1,4,8192.00
math500_math500_302,0.250,1,4,8192.00
math500_math500_307,0.250,1,4,8192.00
math500_math500_301,0.750,3,4,8192.00
math500_math500_309,0.000,0,4,8192.00
math500_math500_303,0.500,2,4,8192.00
math500_math500_312,1.000,4,4,8192.00
math500_math500_310,1.000,4,4,8192.00
math500_math500_313,1.000,4,4,8192.00
math500_math500_314,1.000,4,4,8192.00
math500_math500_319,1.000,4,4,8192.00
math500_math500_311,0.750,3,4,8192.00
math500_math500_315,1.000,4,4,8192.00
math500_math500_316,1.000,4,4,8192.00
math500_math500_321,1.000,4,4,8192.00
math500_math500_306,0.000,0,4,8192.00
math500_math500_322,1.000,4,4,8192.00
math500_math500_325,1.000,4,4,8192.00
math500_math500_308,0.000,0,4,8192.00
math500_math500_318,1.000,4,4,8192.00
math500_math500_317,0.750,3,4,8192.00
math500_math500_329,1.000,4,4,8192.00
math500_math500_332,0.750,3,4,8192.00
math500_math500_320,0.250,1,4,8192.00
math500_math500_330,1.000,4,4,8192.00
math500_math500_331,1.000,4,4,8192.00
math500_math500_327,0.000,0,4,8192.00
math500_math500_335,0.750,3,4,8192.00
math500_math500_336,1.000,4,4,8192.00
math500_math500_326,1.000,4,4,8192.00
math500_math500_334,0.750,3,4,8192.00
math500_math500_324,0.000,0,4,8192.00
math500_math500_328,0.250,1,4,8192.50
math500_math500_338,1.000,4,4,8192.00
math500_math500_323,0.250,1,4,8192.00
math500_math500_333,0.250,1,4,8192.00
math500_math500_337,1.000,4,4,8192.00
math500_math500_345,0.750,3,4,8192.00
math500_math500_343,1.000,4,4,8192.00
math500_math500_341,1.000,4,4,8192.00
math500_math500_344,1.000,4,4,8192.00
math500_math500_339,1.000,4,4,8192.00
math500_math500_342,1.000,4,4,8192.00
math500_math500_347,1.000,4,4,8192.00
math500_math500_353,1.000,4,4,8192.00
math500_math500_340,0.000,0,4,8192.00
math500_math500_350,1.000,4,4,8192.00
math500_math500_348,0.750,3,4,8192.00
math500_math500_354,1.000,4,4,8192.00
math500_math500_346,0.750,3,4,8192.00
math500_math500_351,0.250,1,4,8192.00
math500_math500_356,1.000,4,4,8192.00
math500_math500_358,0.500,2,4,8192.00
math500_math500_363,1.000,4,4,8192.00
math500_math500_359,0.500,2,4,8191.75
math500_math500_352,0.000,0,4,8192.00
math500_math500_357,1.000,4,4,8191.75
math500_math500_367,1.000,4,4,8192.00
math500_math500_355,0.000,0,4,8192.00
math500_math500_364,0.750,3,4,8192.00
math500_math500_360,1.000,4,4,8192.00
math500_math500_362,1.000,4,4,8192.00
math500_math500_370,1.000,4,4,8192.00
math500_math500_349,0.250,1,4,8192.00
math500_math500_368,1.000,4,4,8192.00
math500_math500_361,0.000,0,4,8192.00
math500_math500_366,1.000,4,4,8192.00
math500_math500_374,1.000,4,4,8192.00
math500_math500_376,1.000,4,4,8192.00
math500_math500_373,1.000,4,4,8192.00
math500_math500_378,1.000,4,4,8192.00
math500_math500_365,0.250,1,4,8192.00
math500_math500_384,1.000,4,4,8192.00
math500_math500_369,0.000,0,4,8192.00
math500_math500_383,1.000,4,4,8192.00
math500_math500_375,1.000,4,4,8192.00
math500_math500_372,0.500,2,4,8191.25
math500_math500_371,0.000,0,4,8192.00
math500_math500_380,0.250,1,4,8192.00
math500_math500_379,1.000,4,4,8192.00
math500_math500_388,1.000,4,4,8192.00
math500_math500_386,1.000,4,4,8192.00
math500_math500_387,1.000,4,4,8192.00
math500_math500_382,0.500,2,4,8192.00
math500_math500_385,0.750,3,4,8192.00
math500_math500_377,0.500,2,4,8198.75
math500_math500_389,1.000,4,4,8192.00
math500_math500_393,1.000,4,4,8192.00
math500_math500_381,0.000,0,4,8192.00
math500_math500_397,1.000,4,4,8192.00
math500_math500_395,1.000,4,4,8192.00
math500_math500_390,0.500,2,4,8192.00
math500_math500_398,0.750,3,4,8192.00
math500_math500_392,0.000,0,4,8192.00
math500_math500_394,0.500,2,4,8192.00
math500_math500_391,1.000,4,4,8192.00
math500_math500_399,1.000,4,4,8192.00
math500_math500_402,0.500,2,4,8192.00
math500_math500_404,1.000,4,4,8192.00
math500_math500_406,1.000,4,4,8192.00
math500_math500_407,1.000,4,4,8192.00
math500_math500_405,1.000,4,4,8192.00
math500_math500_403,0.000,0,4,8192.00
math500_math500_410,1.000,4,4,8192.00
math500_math500_396,1.000,4,4,8192.00
math500_math500_400,0.000,0,4,8192.00
math500_math500_409,1.000,4,4,8192.00
math500_math500_411,1.000,4,4,8192.00
math500_math500_414,1.000,4,4,8193.00
math500_math500_413,1.000,4,4,8192.00
math500_math500_401,0.250,1,4,8191.75
math500_math500_415,1.000,4,4,8192.00
math500_math500_408,0.250,1,4,8192.00
math500_math500_417,1.000,4,4,8192.00
math500_math500_418,1.000,4,4,8192.00
math500_math500_420,1.000,4,4,8197.50
math500_math500_424,1.000,4,4,8192.00
math500_math500_427,1.000,4,4,8192.00
math500_math500_416,0.500,2,4,8192.00
math500_math500_412,0.000,0,4,8192.00
math500_math500_426,1.000,4,4,8192.00
math500_math500_421,0.000,0,4,8192.00
math500_math500_430,1.000,4,4,8192.00
math500_math500_429,1.000,4,4,8192.00
math500_math500_422,0.000,0,4,8191.25
math500_math500_423,1.000,4,4,8192.00
math500_math500_419,0.250,1,4,8192.00
math500_math500_431,1.000,4,4,8192.00
math500_math500_433,1.000,4,4,8192.00
math500_math500_428,1.000,4,4,8192.00
math500_math500_425,0.000,0,4,8192.00
math500_math500_435,1.000,4,4,8192.00
math500_math500_434,1.000,4,4,8192.00
math500_math500_440,1.000,4,4,8192.00
math500_math500_441,1.000,4,4,8192.00
math500_math500_432,0.000,0,4,8192.00
math500_math500_436,0.750,3,4,8192.00
math500_math500_443,1.000,4,4,8192.00
math500_math500_437,1.000,4,4,8192.00
math500_math500_442,1.000,4,4,8192.00
math500_math500_438,1.000,4,4,8192.00
math500_math500_439,0.500,2,4,8192.00
math500_math500_447,1.000,4,4,8192.00
math500_math500_446,0.750,3,4,8192.00
math500_math500_449,1.000,4,4,8192.00
math500_math500_448,1.000,4,4,8192.00
math500_math500_453,1.000,4,4,8192.00
math500_math500_455,1.000,4,4,8192.00
math500_math500_445,0.500,2,4,8192.00
math500_math500_452,1.000,4,4,8192.00
math500_math500_450,1.000,4,4,8192.00
math500_math500_456,0.750,3,4,8192.00
math500_math500_444,0.000,0,4,8192.00
math500_math500_454,0.750,3,4,8192.00
math500_math500_457,1.000,4,4,8192.00
math500_math500_451,1.000,4,4,8192.00
math500_math500_461,0.750,3,4,8192.00
math500_math500_463,1.000,4,4,8192.00
math500_math500_458,0.750,3,4,8192.00
math500_math500_465,1.000,4,4,8192.00
math500_math500_464,1.000,4,4,8192.00
math500_math500_471,1.000,4,4,8192.00
math500_math500_459,1.000,4,4,8192.00
math500_math500_468,1.000,4,4,8192.00
math500_math500_472,1.000,4,4,8192.00
math500_math500_469,1.000,4,4,8192.00
math500_math500_467,0.750,3,4,8192.00
math500_math500_460,0.000,0,4,8192.25
math500_math500_462,0.500,2,4,8191.00
math500_math500_474,0.750,3,4,8192.00
math500_math500_466,0.000,0,4,8192.00
math500_math500_476,1.000,4,4,8192.00
math500_math500_477,1.000,4,4,8192.00
math500_math500_473,0.750,3,4,8192.00
math500_math500_479,1.000,4,4,8192.00
math500_math500_483,1.000,4,4,8192.00
math500_math500_470,0.250,1,4,8190.50
math500_math500_487,1.000,4,4,8192.00
math500_math500_475,0.000,0,4,8192.00
math500_math500_485,0.500,2,4,8192.00
math500_math500_480,1.000,4,4,8192.00
math500_math500_488,1.000,4,4,8192.00
math500_math500_484,1.000,4,4,8192.00
math500_math500_478,0.000,0,4,8192.00
math500_math500_481,0.000,0,4,8192.00
math500_math500_482,0.500,2,4,8192.00
math500_math500_492,1.000,4,4,8192.00
math500_math500_490,0.250,1,4,8192.00
math500_math500_486,0.750,3,4,8192.00
math500_math500_493,0.750,3,4,8192.00
math500_math500_495,1.000,4,4,8192.00
math500_math500_496,1.000,4,4,8192.00
math500_math500_489,1.000,4,4,8192.00
math500_math500_499,0.750,3,4,8192.00
math500_math500_498,1.000,4,4,8192.00
math500_math500_491,0.250,1,4,8192.00
math500_math500_497,0.000,0,4,8192.00
math500_math500_494,0.000,0,4,8192.00
Total Accuracy,0.730,1460,2000,8191.93
1 problem_id accuracy correct_count total_samples avg_output_length
2 math500_math500_8 1.000 4 4 8192.00
3 math500_math500_31 1.000 4 4 8192.00
4 math500_math500_0 1.000 4 4 8192.00
5 math500_math500_20 1.000 4 4 8192.00
6 math500_math500_27 1.000 4 4 8192.00
7 math500_math500_29 1.000 4 4 8192.00
8 math500_math500_2 1.000 4 4 8192.00
9 math500_math500_3 1.000 4 4 8192.00
10 math500_math500_13 1.000 4 4 8192.00
11 math500_math500_23 1.000 4 4 8192.00
12 math500_math500_28 1.000 4 4 8192.00
13 math500_math500_30 1.000 4 4 8192.00
14 math500_math500_5 1.000 4 4 8192.00
15 math500_math500_4 0.500 2 4 8192.00
16 math500_math500_16 1.000 4 4 8192.00
17 math500_math500_12 1.000 4 4 8192.00
18 math500_math500_6 1.000 4 4 8192.00
19 math500_math500_14 1.000 4 4 8192.00
20 math500_math500_7 1.000 4 4 8192.00
21 math500_math500_24 1.000 4 4 8192.00
22 math500_math500_21 0.000 0 4 8192.00
23 math500_math500_22 0.750 3 4 8192.00
24 math500_math500_26 0.000 0 4 8192.00
25 math500_math500_1 0.250 1 4 8191.75
26 math500_math500_15 0.000 0 4 8192.00
27 math500_math500_25 0.750 3 4 8192.00
28 math500_math500_19 1.000 4 4 8192.00
29 math500_math500_10 1.000 4 4 8192.00
30 math500_math500_9 0.000 0 4 8192.00
31 math500_math500_11 0.000 0 4 8192.00
32 math500_math500_18 0.000 0 4 8192.00
33 math500_math500_17 0.750 3 4 8192.00
34 math500_math500_35 1.000 4 4 8192.00
35 math500_math500_38 1.000 4 4 8192.00
36 math500_math500_34 0.750 3 4 8192.00
37 math500_math500_33 1.000 4 4 8192.00
38 math500_math500_42 1.000 4 4 8192.00
39 math500_math500_39 1.000 4 4 8192.00
40 math500_math500_36 0.750 3 4 8192.00
41 math500_math500_40 1.000 4 4 8192.00
42 math500_math500_37 1.000 4 4 8192.00
43 math500_math500_49 1.000 4 4 8192.00
44 math500_math500_45 1.000 4 4 8192.00
45 math500_math500_48 1.000 4 4 8192.00
46 math500_math500_47 1.000 4 4 8192.00
47 math500_math500_44 1.000 4 4 8192.00
48 math500_math500_32 0.000 0 4 8192.00
49 math500_math500_54 1.000 4 4 8192.00
50 math500_math500_53 1.000 4 4 8192.00
51 math500_math500_55 1.000 4 4 8192.00
52 math500_math500_51 0.750 3 4 8192.00
53 math500_math500_57 1.000 4 4 8192.00
54 math500_math500_56 1.000 4 4 8192.00
55 math500_math500_58 1.000 4 4 8192.00
56 math500_math500_52 0.750 3 4 8192.00
57 math500_math500_46 0.500 2 4 8192.00
58 math500_math500_59 1.000 4 4 8192.00
59 math500_math500_41 0.250 1 4 8192.00
60 math500_math500_43 0.000 0 4 8192.00
61 math500_math500_50 0.500 2 4 8192.00
62 math500_math500_61 1.000 4 4 8192.00
63 math500_math500_62 0.750 3 4 8192.00
64 math500_math500_65 1.000 4 4 8192.00
65 math500_math500_60 0.000 0 4 8192.00
66 math500_math500_66 1.000 4 4 8192.00
67 math500_math500_67 1.000 4 4 8192.00
68 math500_math500_70 1.000 4 4 8192.00
69 math500_math500_63 0.500 2 4 8192.00
70 math500_math500_64 0.250 1 4 8192.00
71 math500_math500_69 1.000 4 4 8192.00
72 math500_math500_77 1.000 4 4 8192.00
73 math500_math500_72 1.000 4 4 8191.75
74 math500_math500_73 1.000 4 4 8192.00
75 math500_math500_79 1.000 4 4 8192.00
76 math500_math500_78 0.750 3 4 8192.00
77 math500_math500_75 1.000 4 4 8192.00
78 math500_math500_74 1.000 4 4 8192.00
79 math500_math500_68 0.000 0 4 8192.00
80 math500_math500_71 0.000 0 4 8192.00
81 math500_math500_85 0.750 3 4 8192.00
82 math500_math500_81 1.000 4 4 8192.00
83 math500_math500_86 1.000 4 4 8192.00
84 math500_math500_87 1.000 4 4 8192.00
85 math500_math500_84 0.750 3 4 8192.00
86 math500_math500_83 1.000 4 4 8192.00
87 math500_math500_89 1.000 4 4 8192.00
88 math500_math500_76 1.000 4 4 8192.00
89 math500_math500_90 0.000 0 4 8192.00
90 math500_math500_93 1.000 4 4 8192.00
91 math500_math500_95 1.000 4 4 8192.00
92 math500_math500_82 0.250 1 4 8192.00
93 math500_math500_80 0.000 0 4 8192.00
94 math500_math500_91 1.000 4 4 8193.00
95 math500_math500_98 1.000 4 4 8192.00
96 math500_math500_99 1.000 4 4 8192.00
97 math500_math500_94 0.000 0 4 8192.00
98 math500_math500_105 0.750 3 4 8192.00
99 math500_math500_92 1.000 4 4 8192.00
100 math500_math500_97 0.750 3 4 8192.00
101 math500_math500_101 0.000 0 4 8191.75
102 math500_math500_102 1.000 4 4 8192.00
103 math500_math500_88 0.250 1 4 8192.00
104 math500_math500_107 1.000 4 4 8192.00
105 math500_math500_111 1.000 4 4 8191.75
106 math500_math500_96 0.000 0 4 8192.00
107 math500_math500_106 1.000 4 4 8192.00
108 math500_math500_109 1.000 4 4 8192.00
109 math500_math500_103 0.000 0 4 8192.00
110 math500_math500_113 0.750 3 4 8192.00
111 math500_math500_117 1.000 4 4 8192.00
112 math500_math500_115 0.750 3 4 8192.00
113 math500_math500_104 0.500 2 4 8192.00
114 math500_math500_114 1.000 4 4 8192.00
115 math500_math500_121 1.000 4 4 8192.00
116 math500_math500_116 1.000 4 4 8192.00
117 math500_math500_110 0.000 0 4 8192.00
118 math500_math500_108 0.250 1 4 8192.00
119 math500_math500_100 0.000 0 4 8192.00
120 math500_math500_112 1.000 4 4 8192.00
121 math500_math500_122 1.000 4 4 8192.00
122 math500_math500_125 1.000 4 4 8192.00
123 math500_math500_127 1.000 4 4 8191.75
124 math500_math500_119 0.000 0 4 8192.00
125 math500_math500_124 1.000 4 4 8192.00
126 math500_math500_120 0.250 1 4 8192.00
127 math500_math500_123 1.000 4 4 8192.00
128 math500_math500_131 1.000 4 4 8192.00
129 math500_math500_133 1.000 4 4 8192.00
130 math500_math500_128 0.750 3 4 8192.00
131 math500_math500_135 1.000 4 4 8192.00
132 math500_math500_126 0.000 0 4 8192.00
133 math500_math500_118 0.000 0 4 8192.00
134 math500_math500_137 0.750 3 4 8192.00
135 math500_math500_129 0.250 1 4 8192.00
136 math500_math500_132 1.000 4 4 8192.00
137 math500_math500_134 1.000 4 4 8192.00
138 math500_math500_143 1.000 4 4 8192.00
139 math500_math500_144 1.000 4 4 8192.00
140 math500_math500_130 0.250 1 4 8192.00
141 math500_math500_140 1.000 4 4 8192.00
142 math500_math500_141 1.000 4 4 8192.00
143 math500_math500_146 1.000 4 4 8192.00
144 math500_math500_139 0.750 3 4 8192.00
145 math500_math500_148 1.000 4 4 8192.00
146 math500_math500_136 0.250 1 4 8192.00
147 math500_math500_138 0.000 0 4 8192.00
148 math500_math500_145 0.250 1 4 8192.00
149 math500_math500_149 1.000 4 4 8192.00
150 math500_math500_147 0.250 1 4 8192.00
151 math500_math500_152 0.500 2 4 8150.00
152 math500_math500_150 0.500 2 4 8192.00
153 math500_math500_161 1.000 4 4 8192.00
154 math500_math500_159 1.000 4 4 8192.00
155 math500_math500_151 0.250 1 4 8191.50
156 math500_math500_160 1.000 4 4 8192.00
157 math500_math500_142 0.500 2 4 8192.00
158 math500_math500_157 1.000 4 4 8192.00
159 math500_math500_158 1.000 4 4 8192.00
160 math500_math500_155 1.000 4 4 8192.00
161 math500_math500_165 0.750 3 4 8192.00
162 math500_math500_167 1.000 4 4 8192.00
163 math500_math500_162 1.000 4 4 8192.00
164 math500_math500_153 0.250 1 4 8192.00
165 math500_math500_154 0.000 0 4 8191.75
166 math500_math500_169 1.000 4 4 8192.00
167 math500_math500_163 0.750 3 4 8192.00
168 math500_math500_156 0.000 0 4 8192.00
169 math500_math500_171 1.000 4 4 8192.00
170 math500_math500_172 1.000 4 4 8192.00
171 math500_math500_164 0.750 3 4 8192.00
172 math500_math500_177 0.250 1 4 8192.00
173 math500_math500_174 1.000 4 4 8192.00
174 math500_math500_175 1.000 4 4 8192.00
175 math500_math500_166 0.000 0 4 8192.00
176 math500_math500_173 1.000 4 4 8192.00
177 math500_math500_170 0.500 2 4 8192.00
178 math500_math500_179 0.750 3 4 8192.00
179 math500_math500_182 1.000 4 4 8192.00
180 math500_math500_185 1.000 4 4 8192.00
181 math500_math500_178 1.000 4 4 8192.00
182 math500_math500_181 1.000 4 4 8192.50
183 math500_math500_168 0.000 0 4 8192.00
184 math500_math500_183 1.000 4 4 8192.00
185 math500_math500_187 1.000 4 4 8192.00
186 math500_math500_176 0.750 3 4 8192.00
187 math500_math500_191 1.000 4 4 8192.00
188 math500_math500_180 1.000 4 4 8192.00
189 math500_math500_190 0.750 3 4 8192.00
190 math500_math500_192 1.000 4 4 8192.00
191 math500_math500_193 0.750 3 4 8192.00
192 math500_math500_199 1.000 4 4 8192.00
193 math500_math500_195 1.000 4 4 8192.00
194 math500_math500_186 1.000 4 4 8192.00
195 math500_math500_196 1.000 4 4 8192.00
196 math500_math500_184 0.000 0 4 8192.00
197 math500_math500_188 1.000 4 4 8193.00
198 math500_math500_189 0.500 2 4 8192.00
199 math500_math500_198 0.500 2 4 8191.75
200 math500_math500_200 1.000 4 4 8189.75
201 math500_math500_194 0.250 1 4 8192.00
202 math500_math500_207 1.000 4 4 8192.00
203 math500_math500_206 1.000 4 4 8192.00
204 math500_math500_201 0.750 3 4 8192.00
205 math500_math500_197 0.750 3 4 8192.00
206 math500_math500_209 0.750 3 4 8192.00
207 math500_math500_203 0.750 3 4 8192.00
208 math500_math500_211 1.000 4 4 8192.00
209 math500_math500_212 1.000 4 4 8192.00
210 math500_math500_208 1.000 4 4 8192.00
211 math500_math500_205 0.500 2 4 8192.00
212 math500_math500_215 1.000 4 4 8192.00
213 math500_math500_204 0.000 0 4 8192.00
214 math500_math500_216 1.000 4 4 8192.00
215 math500_math500_213 0.750 3 4 8192.00
216 math500_math500_218 1.000 4 4 8192.00
217 math500_math500_202 0.750 3 4 8192.00
218 math500_math500_214 0.000 0 4 8192.00
219 math500_math500_220 1.000 4 4 8192.00
220 math500_math500_225 1.000 4 4 8192.00
221 math500_math500_217 0.000 0 4 8192.00
222 math500_math500_210 1.000 4 4 8192.00
223 math500_math500_223 0.000 0 4 8192.00
224 math500_math500_227 1.000 4 4 8192.00
225 math500_math500_229 1.000 4 4 8192.00
226 math500_math500_231 1.000 4 4 8192.00
227 math500_math500_221 1.000 4 4 8192.00
228 math500_math500_235 0.750 3 4 8192.00
229 math500_math500_219 0.250 1 4 8191.75
230 math500_math500_226 1.000 4 4 8192.00
231 math500_math500_224 0.000 0 4 8192.00
232 math500_math500_228 0.500 2 4 8192.00
233 math500_math500_233 1.000 4 4 8192.00
234 math500_math500_237 1.000 4 4 8192.00
235 math500_math500_222 0.250 1 4 8192.00
236 math500_math500_234 1.000 4 4 8192.00
237 math500_math500_243 1.000 4 4 8192.00
238 math500_math500_238 1.000 4 4 8192.00
239 math500_math500_241 1.000 4 4 8192.00
240 math500_math500_230 1.000 4 4 8192.00
241 math500_math500_236 0.500 2 4 8192.00
242 math500_math500_247 1.000 4 4 8192.00
243 math500_math500_232 0.000 0 4 8192.00
244 math500_math500_239 0.000 0 4 8191.75
245 math500_math500_253 1.000 4 4 8192.00
246 math500_math500_250 1.000 4 4 8192.00
247 math500_math500_245 0.250 1 4 8192.00
248 math500_math500_242 0.000 0 4 8192.00
249 math500_math500_244 1.000 4 4 8192.00
250 math500_math500_257 1.000 4 4 8192.00
251 math500_math500_259 0.750 3 4 8192.00
252 math500_math500_240 0.000 0 4 8192.00
253 math500_math500_246 0.500 2 4 8192.00
254 math500_math500_251 1.000 4 4 8192.00
255 math500_math500_255 1.000 4 4 8192.00
256 math500_math500_252 1.000 4 4 8192.00
257 math500_math500_249 0.500 2 4 8192.00
258 math500_math500_258 1.000 4 4 8192.00
259 math500_math500_256 1.000 4 4 8192.00
260 math500_math500_248 0.000 0 4 8193.00
261 math500_math500_263 1.000 4 4 8192.00
262 math500_math500_261 0.750 3 4 8192.00
263 math500_math500_260 1.000 4 4 8192.00
264 math500_math500_254 0.750 3 4 8192.00
265 math500_math500_265 1.000 4 4 8192.00
266 math500_math500_262 1.000 4 4 8192.00
267 math500_math500_269 0.750 3 4 8192.00
268 math500_math500_270 1.000 4 4 8192.00
269 math500_math500_266 1.000 4 4 8192.00
270 math500_math500_271 1.000 4 4 8192.00
271 math500_math500_268 1.000 4 4 8192.00
272 math500_math500_275 1.000 4 4 8192.00
273 math500_math500_273 1.000 4 4 8192.00
274 math500_math500_277 1.000 4 4 8192.00
275 math500_math500_272 0.750 3 4 8192.00
276 math500_math500_278 1.000 4 4 8192.00
277 math500_math500_283 1.000 4 4 8192.00
278 math500_math500_267 0.000 0 4 8191.75
279 math500_math500_280 1.000 4 4 8192.00
280 math500_math500_279 0.250 1 4 8192.00
281 math500_math500_264 0.000 0 4 8192.00
282 math500_math500_276 1.000 4 4 8192.00
283 math500_math500_287 0.750 3 4 8192.00
284 math500_math500_290 1.000 4 4 8192.00
285 math500_math500_285 0.250 1 4 8192.00
286 math500_math500_274 0.000 0 4 8192.00
287 math500_math500_282 0.500 2 4 8192.00
288 math500_math500_293 1.000 4 4 8192.00
289 math500_math500_281 0.000 0 4 8192.00
290 math500_math500_284 0.250 1 4 8192.00
291 math500_math500_289 0.750 3 4 8192.00
292 math500_math500_286 0.000 0 4 8192.00
293 math500_math500_292 0.500 2 4 8192.00
294 math500_math500_297 1.000 4 4 8192.00
295 math500_math500_298 0.750 3 4 8192.00
296 math500_math500_291 0.750 3 4 8192.00
297 math500_math500_288 0.250 1 4 8192.00
298 math500_math500_294 0.750 3 4 8192.00
299 math500_math500_295 0.000 0 4 8192.00
300 math500_math500_299 1.000 4 4 8192.00
301 math500_math500_304 1.000 4 4 8192.00
302 math500_math500_305 1.000 4 4 8192.00
303 math500_math500_300 1.000 4 4 8192.00
304 math500_math500_296 0.250 1 4 8192.00
305 math500_math500_302 0.250 1 4 8192.00
306 math500_math500_307 0.250 1 4 8192.00
307 math500_math500_301 0.750 3 4 8192.00
308 math500_math500_309 0.000 0 4 8192.00
309 math500_math500_303 0.500 2 4 8192.00
310 math500_math500_312 1.000 4 4 8192.00
311 math500_math500_310 1.000 4 4 8192.00
312 math500_math500_313 1.000 4 4 8192.00
313 math500_math500_314 1.000 4 4 8192.00
314 math500_math500_319 1.000 4 4 8192.00
315 math500_math500_311 0.750 3 4 8192.00
316 math500_math500_315 1.000 4 4 8192.00
317 math500_math500_316 1.000 4 4 8192.00
318 math500_math500_321 1.000 4 4 8192.00
319 math500_math500_306 0.000 0 4 8192.00
320 math500_math500_322 1.000 4 4 8192.00
321 math500_math500_325 1.000 4 4 8192.00
322 math500_math500_308 0.000 0 4 8192.00
323 math500_math500_318 1.000 4 4 8192.00
324 math500_math500_317 0.750 3 4 8192.00
325 math500_math500_329 1.000 4 4 8192.00
326 math500_math500_332 0.750 3 4 8192.00
327 math500_math500_320 0.250 1 4 8192.00
328 math500_math500_330 1.000 4 4 8192.00
329 math500_math500_331 1.000 4 4 8192.00
330 math500_math500_327 0.000 0 4 8192.00
331 math500_math500_335 0.750 3 4 8192.00
332 math500_math500_336 1.000 4 4 8192.00
333 math500_math500_326 1.000 4 4 8192.00
334 math500_math500_334 0.750 3 4 8192.00
335 math500_math500_324 0.000 0 4 8192.00
336 math500_math500_328 0.250 1 4 8192.50
337 math500_math500_338 1.000 4 4 8192.00
338 math500_math500_323 0.250 1 4 8192.00
339 math500_math500_333 0.250 1 4 8192.00
340 math500_math500_337 1.000 4 4 8192.00
341 math500_math500_345 0.750 3 4 8192.00
342 math500_math500_343 1.000 4 4 8192.00
343 math500_math500_341 1.000 4 4 8192.00
344 math500_math500_344 1.000 4 4 8192.00
345 math500_math500_339 1.000 4 4 8192.00
346 math500_math500_342 1.000 4 4 8192.00
347 math500_math500_347 1.000 4 4 8192.00
348 math500_math500_353 1.000 4 4 8192.00
349 math500_math500_340 0.000 0 4 8192.00
350 math500_math500_350 1.000 4 4 8192.00
351 math500_math500_348 0.750 3 4 8192.00
352 math500_math500_354 1.000 4 4 8192.00
353 math500_math500_346 0.750 3 4 8192.00
354 math500_math500_351 0.250 1 4 8192.00
355 math500_math500_356 1.000 4 4 8192.00
356 math500_math500_358 0.500 2 4 8192.00
357 math500_math500_363 1.000 4 4 8192.00
358 math500_math500_359 0.500 2 4 8191.75
359 math500_math500_352 0.000 0 4 8192.00
360 math500_math500_357 1.000 4 4 8191.75
361 math500_math500_367 1.000 4 4 8192.00
362 math500_math500_355 0.000 0 4 8192.00
363 math500_math500_364 0.750 3 4 8192.00
364 math500_math500_360 1.000 4 4 8192.00
365 math500_math500_362 1.000 4 4 8192.00
366 math500_math500_370 1.000 4 4 8192.00
367 math500_math500_349 0.250 1 4 8192.00
368 math500_math500_368 1.000 4 4 8192.00
369 math500_math500_361 0.000 0 4 8192.00
370 math500_math500_366 1.000 4 4 8192.00
371 math500_math500_374 1.000 4 4 8192.00
372 math500_math500_376 1.000 4 4 8192.00
373 math500_math500_373 1.000 4 4 8192.00
374 math500_math500_378 1.000 4 4 8192.00
375 math500_math500_365 0.250 1 4 8192.00
376 math500_math500_384 1.000 4 4 8192.00
377 math500_math500_369 0.000 0 4 8192.00
378 math500_math500_383 1.000 4 4 8192.00
379 math500_math500_375 1.000 4 4 8192.00
380 math500_math500_372 0.500 2 4 8191.25
381 math500_math500_371 0.000 0 4 8192.00
382 math500_math500_380 0.250 1 4 8192.00
383 math500_math500_379 1.000 4 4 8192.00
384 math500_math500_388 1.000 4 4 8192.00
385 math500_math500_386 1.000 4 4 8192.00
386 math500_math500_387 1.000 4 4 8192.00
387 math500_math500_382 0.500 2 4 8192.00
388 math500_math500_385 0.750 3 4 8192.00
389 math500_math500_377 0.500 2 4 8198.75
390 math500_math500_389 1.000 4 4 8192.00
391 math500_math500_393 1.000 4 4 8192.00
392 math500_math500_381 0.000 0 4 8192.00
393 math500_math500_397 1.000 4 4 8192.00
394 math500_math500_395 1.000 4 4 8192.00
395 math500_math500_390 0.500 2 4 8192.00
396 math500_math500_398 0.750 3 4 8192.00
397 math500_math500_392 0.000 0 4 8192.00
398 math500_math500_394 0.500 2 4 8192.00
399 math500_math500_391 1.000 4 4 8192.00
400 math500_math500_399 1.000 4 4 8192.00
401 math500_math500_402 0.500 2 4 8192.00
402 math500_math500_404 1.000 4 4 8192.00
403 math500_math500_406 1.000 4 4 8192.00
404 math500_math500_407 1.000 4 4 8192.00
405 math500_math500_405 1.000 4 4 8192.00
406 math500_math500_403 0.000 0 4 8192.00
407 math500_math500_410 1.000 4 4 8192.00
408 math500_math500_396 1.000 4 4 8192.00
409 math500_math500_400 0.000 0 4 8192.00
410 math500_math500_409 1.000 4 4 8192.00
411 math500_math500_411 1.000 4 4 8192.00
412 math500_math500_414 1.000 4 4 8193.00
413 math500_math500_413 1.000 4 4 8192.00
414 math500_math500_401 0.250 1 4 8191.75
415 math500_math500_415 1.000 4 4 8192.00
416 math500_math500_408 0.250 1 4 8192.00
417 math500_math500_417 1.000 4 4 8192.00
418 math500_math500_418 1.000 4 4 8192.00
419 math500_math500_420 1.000 4 4 8197.50
420 math500_math500_424 1.000 4 4 8192.00
421 math500_math500_427 1.000 4 4 8192.00
422 math500_math500_416 0.500 2 4 8192.00
423 math500_math500_412 0.000 0 4 8192.00
424 math500_math500_426 1.000 4 4 8192.00
425 math500_math500_421 0.000 0 4 8192.00
426 math500_math500_430 1.000 4 4 8192.00
427 math500_math500_429 1.000 4 4 8192.00
428 math500_math500_422 0.000 0 4 8191.25
429 math500_math500_423 1.000 4 4 8192.00
430 math500_math500_419 0.250 1 4 8192.00
431 math500_math500_431 1.000 4 4 8192.00
432 math500_math500_433 1.000 4 4 8192.00
433 math500_math500_428 1.000 4 4 8192.00
434 math500_math500_425 0.000 0 4 8192.00
435 math500_math500_435 1.000 4 4 8192.00
436 math500_math500_434 1.000 4 4 8192.00
437 math500_math500_440 1.000 4 4 8192.00
438 math500_math500_441 1.000 4 4 8192.00
439 math500_math500_432 0.000 0 4 8192.00
440 math500_math500_436 0.750 3 4 8192.00
441 math500_math500_443 1.000 4 4 8192.00
442 math500_math500_437 1.000 4 4 8192.00
443 math500_math500_442 1.000 4 4 8192.00
444 math500_math500_438 1.000 4 4 8192.00
445 math500_math500_439 0.500 2 4 8192.00
446 math500_math500_447 1.000 4 4 8192.00
447 math500_math500_446 0.750 3 4 8192.00
448 math500_math500_449 1.000 4 4 8192.00
449 math500_math500_448 1.000 4 4 8192.00
450 math500_math500_453 1.000 4 4 8192.00
451 math500_math500_455 1.000 4 4 8192.00
452 math500_math500_445 0.500 2 4 8192.00
453 math500_math500_452 1.000 4 4 8192.00
454 math500_math500_450 1.000 4 4 8192.00
455 math500_math500_456 0.750 3 4 8192.00
456 math500_math500_444 0.000 0 4 8192.00
457 math500_math500_454 0.750 3 4 8192.00
458 math500_math500_457 1.000 4 4 8192.00
459 math500_math500_451 1.000 4 4 8192.00
460 math500_math500_461 0.750 3 4 8192.00
461 math500_math500_463 1.000 4 4 8192.00
462 math500_math500_458 0.750 3 4 8192.00
463 math500_math500_465 1.000 4 4 8192.00
464 math500_math500_464 1.000 4 4 8192.00
465 math500_math500_471 1.000 4 4 8192.00
466 math500_math500_459 1.000 4 4 8192.00
467 math500_math500_468 1.000 4 4 8192.00
468 math500_math500_472 1.000 4 4 8192.00
469 math500_math500_469 1.000 4 4 8192.00
470 math500_math500_467 0.750 3 4 8192.00
471 math500_math500_460 0.000 0 4 8192.25
472 math500_math500_462 0.500 2 4 8191.00
473 math500_math500_474 0.750 3 4 8192.00
474 math500_math500_466 0.000 0 4 8192.00
475 math500_math500_476 1.000 4 4 8192.00
476 math500_math500_477 1.000 4 4 8192.00
477 math500_math500_473 0.750 3 4 8192.00
478 math500_math500_479 1.000 4 4 8192.00
479 math500_math500_483 1.000 4 4 8192.00
480 math500_math500_470 0.250 1 4 8190.50
481 math500_math500_487 1.000 4 4 8192.00
482 math500_math500_475 0.000 0 4 8192.00
483 math500_math500_485 0.500 2 4 8192.00
484 math500_math500_480 1.000 4 4 8192.00
485 math500_math500_488 1.000 4 4 8192.00
486 math500_math500_484 1.000 4 4 8192.00
487 math500_math500_478 0.000 0 4 8192.00
488 math500_math500_481 0.000 0 4 8192.00
489 math500_math500_482 0.500 2 4 8192.00
490 math500_math500_492 1.000 4 4 8192.00
491 math500_math500_490 0.250 1 4 8192.00
492 math500_math500_486 0.750 3 4 8192.00
493 math500_math500_493 0.750 3 4 8192.00
494 math500_math500_495 1.000 4 4 8192.00
495 math500_math500_496 1.000 4 4 8192.00
496 math500_math500_489 1.000 4 4 8192.00
497 math500_math500_499 0.750 3 4 8192.00
498 math500_math500_498 1.000 4 4 8192.00
499 math500_math500_491 0.250 1 4 8192.00
500 math500_math500_497 0.000 0 4 8192.00
501 math500_math500_494 0.000 0 4 8192.00
502 Total Accuracy 0.730 1460 2000 8191.93

View File

@@ -0,0 +1,7 @@
iter_count,token_count,percentage
1,12022305,73.37832641601562
2,1149492,7.0159423828125
3,634015,3.869720458984375
4,2578188,15.736010742187501
Total Tokens,16384000,100.0
1 iter_count token_count percentage
2 1 12022305 73.37832641601562
3 2 1149492 7.0159423828125
4 3 634015 3.869720458984375
5 4 2578188 15.736010742187501
6 Total Tokens 16384000 100.0

View File

@@ -0,0 +1,16 @@
{
"pass@4": 0.856,
"cons@4": 0.8,
"avg@4": 0.73,
"avg_output_length": 8191.93,
"num_problems": 500,
"num_samples": 2000,
"repeat_size": 4,
"avg_request_time": 97.3714,
"end_2_end_time": 1583.5418,
"token_throughtput": 10346.3398,
"request_throught": 1.263,
"avg_iter_count": 1.6196,
"total_concurrency": 128,
"failed_requests": 0
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03fd25fabfbb60bc15d4d4b553c8fb52dd390d3cf5452fe26becbe86a49c7689
size 49228611