logical-reasoning / data /fine-tuning_metrics.csv
dh-mc's picture
ready for final run
8157c36
raw
history blame
19.7 kB
epoch,model,run,accuracy,precision,recall,f1,ratio_valid_classifications
0.0,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat_torch.float16_lf,0.7343333333333333,0.7375752740091942,0.7343333333333333,0.7270283652909943,0.8033333333333333
0.2,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-35_torch.float16_lf,0.717,0.7933072428707201,0.717,0.7447412977676989,1.0
0.4,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-70_torch.float16_lf,0.7226666666666667,0.7983383063141186,0.7226666666666667,0.7489397350174751,0.9993333333333332
0.6,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-105_torch.float16_lf,0.7083333333333334,0.7967030927405547,0.7083333333333334,0.738836849803633,1.0
0.8,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-140_torch.float16_lf,0.7773333333333333,0.805139129977305,0.7773333333333333,0.7882159693114585,1.0
1.0,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-175_torch.float16_lf,0.7853333333333333,0.8062405645226312,0.7853333333333333,0.7938991590982061,1.0
1.2,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-210_torch.float16_lf,0.7436666666666667,0.8148316221752646,0.7436666666666667,0.7689773286065246,1.0
1.4,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-245_torch.float16_lf,0.759,0.8080929326806991,0.759,0.7772842274293189,1.0
1.6,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-280_torch.float16_lf,0.745,0.8027959680086005,0.745,0.7666181725503965,1.0
1.8,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-315_torch.float16_lf,0.7303333333333333,0.806805925253305,0.7303333333333333,0.7580841794383364,1.0
2.0,Llama3.1-8B-Chinese-Chat,shenzhi-wang/Llama3.1-8B-Chinese-Chat/checkpoint-350_torch.float16_lf,0.737,0.808786608325944,0.737,0.7629963845364953,1.0
0.0,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat_torch.bfloat16_4bit_lf,0.7646666666666667,0.7804609488644828,0.7646666666666667,0.7497548621711109,0.0096666666666666
0.2,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-35_torch.bfloat16_4bit_lf,0.784,0.8105343792887019,0.784,0.7931742141608462,0.9996666666666668
0.4,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-70_torch.bfloat16_4bit_lf,0.7426666666666667,0.8117033235947096,0.7426666666666667,0.7673825750808414,1.0
0.6,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-105_torch.bfloat16_4bit_lf,0.736,0.8227236574891071,0.736,0.7650739090144549,1.0
0.8,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-140_torch.bfloat16_4bit_lf,0.7686666666666667,0.8259659464402258,0.7686666666666667,0.7880870865039342,1.0
1.0,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-175_torch.bfloat16_4bit_lf,0.809,0.8282732906153989,0.809,0.8166997776775797,1.0
1.2,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-210_torch.bfloat16_4bit_lf,0.75,0.8287348768409003,0.75,0.7741734526674708,1.0
1.4,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-245_torch.bfloat16_4bit_lf,0.7703333333333333,0.8271894042316865,0.7703333333333333,0.7907617274354051,1.0
1.6,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-280_torch.bfloat16_4bit_lf,0.776,0.8315436250878178,0.776,0.7959870550088912,1.0
1.8,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-315_torch.bfloat16_4bit_lf,0.7733333333333333,0.8327336470976,0.7733333333333333,0.7947537193805649,1.0
2.0,Llama3.1-70B-Chinese-Chat,shenzhi-wang/Llama3.1-70B-Chinese-Chat/checkpoint-350_torch.bfloat16_4bit_lf,0.7686666666666667,0.8329633784586954,0.7686666666666667,0.7914454794587963,1.0
0.0,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat_torch.float16_lf,0.6923333333333334,0.7009179792741449,0.6923333333333334,0.6605899639694456,0.0116666666666666
0.2,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-35_torch.float16_lf,0.706,0.7832545046834243,0.706,0.7323466131711432,1.0
0.4,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-70_torch.float16_lf,0.7476666666666667,0.7836120158306894,0.7476666666666667,0.7557791381509955,1.0
0.6,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-105_torch.float16_lf,0.6736666666666666,0.7908140272002406,0.6736666666666666,0.7129951145360993,1.0
0.8,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-140_torch.float16_lf,0.7293333333333333,0.788387677637057,0.7293333333333333,0.7494137469900564,1.0
1.0,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-175_torch.float16_lf,0.74,0.7833068129490098,0.74,0.7499935485741815,1.0
1.2,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-210_torch.float16_lf,0.7146666666666667,0.7890760288118991,0.7146666666666667,0.7411240160229633,1.0
1.4,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-245_torch.float16_lf,0.7616666666666667,0.789634957005121,0.7616666666666667,0.7721210086098353,1.0
1.6,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-280_torch.float16_lf,0.7296666666666667,0.7854982015370922,0.7296666666666667,0.7491267995936699,1.0
1.8,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-315_torch.float16_lf,0.7076666666666667,0.7877874532247918,0.7076666666666667,0.7346283562321456,1.0
2.0,Mistral-7B-v0.3-Chinese-Chat,shenzhi-wang/Mistral-7B-v0.3-Chinese-Chat/checkpoint-350_torch.float16_lf,0.713,0.7895690867103055,0.713,0.739013227401175,1.0
0.0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat_torch.bfloat16_lf,0.7063333333333334,0.7369785607161373,0.7063333333333334,0.6895815239121195,1.0
0.2,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-35_torch.bfloat16_lf,0.729,0.7861122408311365,0.729,0.7385163226667387,1.0
0.4,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-70_torch.bfloat16_lf,0.7336666666666667,0.7857703796539939,0.7336666666666667,0.7427841254119673,1.0
0.6,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-105_torch.bfloat16_lf,0.6876666666666666,0.8030976203819039,0.6876666666666666,0.7170750416800897,1.0
0.8,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-140_torch.bfloat16_lf,0.762,0.8063331692665241,0.762,0.7740172985498378,1.0
1.0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-175_torch.bfloat16_lf,0.7416666666666667,0.812190204769964,0.7416666666666667,0.761129466343473,1.0
1.2,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-210_torch.bfloat16_lf,0.7443333333333333,0.8084922204218251,0.7443333333333333,0.7599422989743019,1.0
1.4,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-245_torch.bfloat16_lf,0.762,0.8089123492151512,0.762,0.7753217972757948,1.0
1.6,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-280_torch.bfloat16_lf,0.733,0.8092774765454144,0.733,0.7535080746086277,1.0
1.8,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-315_torch.bfloat16_lf,0.7156666666666667,0.814456776214162,0.7156666666666667,0.744622807072089,1.0
2.0,internlm2_5-7b-chat,internlm/internlm2_5-7b-chat/checkpoint-350_torch.bfloat16_lf,0.725,0.8148156790328904,0.725,0.7509650741005044,1.0
0.0,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m_torch.bfloat16_lf,0.4923333333333333,0.7570993062022159,0.4923333333333333,0.5279738886353613,0.9986666666666668
0.2,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-35_torch.bfloat16_lf,0.7843333333333333,0.7907732469871145,0.7843333333333333,0.7839137508042926,1.0
0.4,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-70_torch.bfloat16_lf,0.7876666666666666,0.7961110449860888,0.7876666666666666,0.790011839264191,1.0
0.6,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-105_torch.bfloat16_lf,0.74,0.818451985781803,0.74,0.7654385146358808,1.0
0.8,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-140_torch.bfloat16_lf,0.8076666666666666,0.8048844422436796,0.8076666666666666,0.8049749805997191,1.0
1.0,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-175_torch.bfloat16_lf,0.7796666666666666,0.8115925869684188,0.7796666666666666,0.7917308842405348,1.0
1.2,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-210_torch.bfloat16_lf,0.7816666666666666,0.8082575556171326,0.7816666666666666,0.7920155623671598,1.0
1.4,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-245_torch.bfloat16_lf,0.7736666666666666,0.8074649930391711,0.7736666666666666,0.7846002379939621,1.0
1.6,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-280_torch.bfloat16_lf,0.771,0.8124579857634519,0.771,0.7859698091956198,1.0
1.8,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-315_torch.bfloat16_lf,0.7646666666666667,0.8211516901334176,0.7646666666666667,0.7848541283802248,1.0
2.0,internlm2_5-7b-chat-1m,internlm/internlm2_5-7b-chat-1m/checkpoint-350_torch.bfloat16_lf,0.77,0.8144910397034413,0.77,0.7862970454955438,1.0
0.0,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat_torch.bfloat16_4bit_lf,0.575,0.7745319004159336,0.575,0.6416875854199033,0.6726666666666666
0.2,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-35_torch.bfloat16_4bit_lf,0.7723333333333333,0.8004877872664371,0.7723333333333333,0.7800315047324102,1.0
0.4,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-70_torch.bfloat16_4bit_lf,0.788,0.808878367860496,0.788,0.7952965901503556,1.0
0.6,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-105_torch.bfloat16_4bit_lf,0.7223333333333334,0.8101427633407874,0.7223333333333334,0.7527524454293278,1.0
0.8,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-140_torch.bfloat16_4bit_lf,0.8063333333333333,0.8207793607428686,0.8063333333333333,0.811239851005161,1.0
1.0,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-175_torch.bfloat16_4bit_lf,0.792,0.8244746715585061,0.792,0.8028680300441688,1.0
1.2,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-210_torch.bfloat16_4bit_lf,0.77,0.8305821984199763,0.77,0.7905012003721434,1.0
1.4,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-245_torch.bfloat16_4bit_lf,0.8033333333333333,0.8215999742478901,0.8033333333333333,0.8087445768968825,1.0
1.6,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-280_torch.bfloat16_4bit_lf,0.795,0.8261993807231882,0.795,0.805022820640186,1.0
1.8,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-315_torch.bfloat16_4bit_lf,0.779,0.8256828719565774,0.779,0.7946766547953676,1.0
2.0,internlm2_5-20b-chat,internlm/internlm2_5-20b-chat/checkpoint-350_torch.bfloat16_4bit_lf,0.7826666666666666,0.8284951420712369,0.7826666666666666,0.7978785507522372,1.0
0.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct_torch.float16_lf,0.4383333333333333,0.5292917259914629,0.4383333333333333,0.4228687599248655,0.594
0.2,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-35_torch.float16_lf,0.5223333333333333,0.5704911830866488,0.5223333333333333,0.454387436259078,1.0
0.4,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-70_torch.float16_lf,0.542,0.6358012674347429,0.542,0.5272438410312219,1.0
0.6,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-105_torch.float16_lf,0.4463333333333333,0.6477441598024034,0.4463333333333333,0.4917457459702999,1.0
0.8,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-140_torch.float16_lf,0.5053333333333333,0.6438300456580985,0.5053333333333333,0.4995247505211914,1.0
1.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-175_torch.float16_lf,0.558,0.6560369730369926,0.558,0.5632487818615118,1.0
1.2,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-210_torch.float16_lf,0.5453333333333333,0.6357935773889876,0.5453333333333333,0.5594242895140294,1.0
1.4,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-245_torch.float16_lf,0.5903333333333334,0.6503049529377274,0.5903333333333334,0.6094397514027766,1.0
1.6,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-280_torch.float16_lf,0.5286666666666666,0.6532851084098983,0.5286666666666666,0.5617239467523474,1.0
1.8,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-315_torch.float16_lf,0.5336666666666666,0.6607103736450911,0.5336666666666666,0.5622949959647037,1.0
2.0,Qwen2.5-0.5B-Instruct,Qwen/Qwen2.5-0.5B-Instruct/checkpoint-350_torch.float16_lf,0.5156666666666667,0.652809461208547,0.5156666666666667,0.549955024535151,1.0
0.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct_torch.float16_lf,0.2016666666666666,0.5269756683734005,0.2016666666666666,0.2406983532950438,0.9223333333333332
0.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-35_torch.float16_lf,0.4853333333333333,0.654166887199198,0.4853333333333333,0.5381849571995003,0.9996666666666668
0.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-70_torch.float16_lf,0.573,0.7037737273232145,0.573,0.6131069400231612,0.9996666666666668
0.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-105_torch.float16_lf,0.539,0.7162869126454278,0.539,0.5961610389687657,1.0
0.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-140_torch.float16_lf,0.6443333333333333,0.7218750831357578,0.6443333333333333,0.6721473356905486,1.0
1.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-175_torch.float16_lf,0.6296666666666667,0.7065049203038848,0.6296666666666667,0.6496809196018393,1.0
1.2,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-210_torch.float16_lf,0.5836666666666667,0.7222805944180548,0.5836666666666667,0.6314346830311218,1.0
1.4,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-245_torch.float16_lf,0.6493333333333333,0.7440287895607589,0.6493333333333333,0.6815314583590799,1.0
1.6,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-280_torch.float16_lf,0.6293333333333333,0.7332138067544355,0.6293333333333333,0.6634330572585689,1.0
1.8,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-315_torch.float16_lf,0.599,0.7297954686265763,0.599,0.6396292878324805,1.0
2.0,Qwen2.5-1.5B-Instruct,Qwen/Qwen2.5-1.5B-Instruct/checkpoint-350_torch.float16_lf,0.6056666666666667,0.7305580205770756,0.6056666666666667,0.6426785514786738,1.0
0.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct_torch.float16_lf,0.5796666666666667,0.6966500240864278,0.5796666666666667,0.5506370828782681,1.0
0.2,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-35_torch.float16_lf,0.689,0.7450174119748659,0.689,0.709114466474576,0.9986666666666668
0.4,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-70_torch.float16_lf,0.6556666666666666,0.7590430811422313,0.6556666666666666,0.6934194398116857,1.0
0.6,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-105_torch.float16_lf,0.6963333333333334,0.7550938479315918,0.6963333333333334,0.71844324172961,1.0
0.8,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-140_torch.float16_lf,0.6853333333333333,0.7542524799326954,0.6853333333333333,0.7128732915785243,1.0
1.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-175_torch.float16_lf,0.6846666666666666,0.7564071354272528,0.6846666666666666,0.7125676758538035,1.0
1.2,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-210_torch.float16_lf,0.6896666666666667,0.7690917466956201,0.6896666666666667,0.720231747443145,1.0
1.4,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-245_torch.float16_lf,0.7256666666666667,0.7753705482689578,0.7256666666666667,0.7440390153124937,1.0
1.6,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-280_torch.float16_lf,0.708,0.7659638403826392,0.708,0.7293997518219294,1.0
1.8,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-315_torch.float16_lf,0.7056666666666667,0.7717562122699148,0.7056666666666667,0.729817759784445,1.0
2.0,Qwen2.5-3B-Instruct,Qwen/Qwen2.5-3B-Instruct/checkpoint-350_torch.float16_lf,0.7003333333333334,0.7698824212888824,0.7003333333333334,0.726563613830647,1.0
0.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct_torch.bfloat16_lf,0.644,0.7200261355300325,0.644,0.6101052277961244,1.0
0.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-35_torch.bfloat16_lf,0.745,0.7643041174791825,0.745,0.7482828029872421,0.998
0.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-70_torch.bfloat16_lf,0.7446666666666667,0.7800215227839997,0.7446666666666667,0.7576550061479678,0.9996666666666668
0.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-105_torch.bfloat16_lf,0.7513333333333333,0.7996792149630704,0.7513333333333333,0.7693730206330721,0.9996666666666668
0.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-140_torch.bfloat16_lf,0.75,0.7923028105975739,0.75,0.7665531868559959,1.0
1.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-175_torch.bfloat16_lf,0.771,0.8005814962709542,0.771,0.7814602739241332,0.9993333333333332
1.2,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-210_torch.bfloat16_lf,0.7443333333333333,0.79978900243777,0.7443333333333333,0.7660506505481828,1.0
1.4,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-245_torch.bfloat16_lf,0.7486666666666667,0.7974562319123832,0.7486666666666667,0.7655275916268014,0.9993333333333332
1.6,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-280_torch.bfloat16_lf,0.7566666666666667,0.7939852407869384,0.7566666666666667,0.7689495073735431,0.9996666666666668
1.8,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-315_torch.bfloat16_lf,0.755,0.7940575522966016,0.755,0.7681326415137147,0.9993333333333332
2.0,Qwen2.5-7B-Instruct,Qwen/Qwen2.5-7B-Instruct/checkpoint-350_torch.bfloat16_lf,0.756,0.7982464722401461,0.756,0.7704035278260453,0.9996666666666668
0.0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct_torch.bfloat16_4bit_lf,0.7956666666666666,0.8098073411161181,0.7956666666666666,0.7771317592221199,0.994
0.2,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-35_torch.bfloat16_4bit_lf,0.792,0.8180793658647517,0.792,0.80166512366027,1.0
0.4,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-70_torch.bfloat16_4bit_lf,0.7716666666666666,0.8199569804721152,0.7716666666666666,0.7895879011938259,1.0
0.6,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-105_torch.bfloat16_4bit_lf,0.798,0.8379062379534957,0.798,0.812148680520218,1.0
0.8,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-140_torch.bfloat16_4bit_lf,0.8213333333333334,0.8447926258362122,0.8213333333333334,0.8299486611547571,1.0
1.0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-175_torch.bfloat16_4bit_lf,0.7643333333333333,0.8235366724638146,0.7643333333333333,0.7858148913986999,1.0
1.2,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-210_torch.bfloat16_4bit_lf,0.7986666666666666,0.83233218480008,0.7986666666666666,0.8115886421806521,1.0
1.4,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-245_torch.bfloat16_4bit_lf,0.7923333333333333,0.8231874218285514,0.7923333333333333,0.803363661387202,1.0
1.6,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-280_torch.bfloat16_4bit_lf,0.7936666666666666,0.8268750473800219,0.7936666666666666,0.8057720333101867,1.0
1.8,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-315_torch.bfloat16_4bit_lf,0.801,0.830389411421043,0.801,0.8117656427717702,1.0
2.0,Qwen2.5-72B-Instruct,Qwen/Qwen2.5-72B-Instruct/checkpoint-350_torch.bfloat16_4bit_lf,0.795,0.8280696193638868,0.795,0.8068114730639832,1.0