| model,gsm8k_acc,gsm8k_pass_acc,gsm8k_tokens,gsm8k_keywords,gsm8k_correct_tokens,gsm8k_wrong_tokens,gsm8k_clip_ratio,gsm8k_stop_tokens,gsm8k_stop_ratio,gsm8k_box_ratio,gsm8k_repeat_ratio,math500_acc,math500_pass_acc,math500_tokens,math500_keywords,math500_correct_tokens,math500_wrong_tokens,math500_clip_ratio,math500_stop_tokens,math500_stop_ratio,math500_box_ratio,math500_repeat_ratio,minerva_math_acc,minerva_math_pass_acc,minerva_math_tokens,minerva_math_keywords,minerva_math_correct_tokens,minerva_math_wrong_tokens,minerva_math_clip_ratio,minerva_math_stop_tokens,minerva_math_stop_ratio,minerva_math_box_ratio,minerva_math_repeat_ratio,mmlu_stem_acc,mmlu_stem_pass_acc,mmlu_stem_tokens,mmlu_stem_keywords,mmlu_stem_correct_tokens,mmlu_stem_wrong_tokens,mmlu_stem_clip_ratio,mmlu_stem_stop_tokens,mmlu_stem_stop_ratio,mmlu_stem_box_ratio,mmlu_stem_repeat_ratio,olympiadbench_acc,olympiadbench_pass_acc,olympiadbench_tokens,olympiadbench_keywords,olympiadbench_correct_tokens,olympiadbench_wrong_tokens,olympiadbench_clip_ratio,olympiadbench_stop_tokens,olympiadbench_stop_ratio,olympiadbench_box_ratio,olympiadbench_repeat_ratio,avg_acc,avg_pass_acc,avg_tokens,avg_keywords,avg_correct_tokens,avg_wrong_tokens,avg_clip_ratio,avg_stop_tokens,avg_stop_ratio,avg_box_ratio,avg_repeat_ratio | |
| eval_results-global_step_0,59.9,59.9,1017.9219105382866,0.05155420773313116,389.5873417721519,1956.266540642722,0.037149355572403335,346.93464566929134,0.9628506444275967,0.7581501137225171,0.26459438968915844,46.6,46.6,1380.706,5.842,695.9399141630902,1978.2734082397003,0.04,619.275,0.96,0.848,0.516,14.0,14.0,1252.4301470588234,0.16176470588235295,486.94736842105266,1376.7393162393162,0.03308823529411765,600.2395437262358,0.9669117647058824,0.8014705882352942,0.5257352941176471,40.3,40.3,673.247183565275,0.3164347249834327,442.41399176954735,828.8003327787021,0.022200132538104704,320.73263300576076,0.9777998674618953,0.6136514247846255,0.4804506295559973,18.7,18.7,1844.0,0.6148148148148148,901.3492063492064,2060.346083788707,0.056296296296296296,904.640502354788,0.9437037037037037,0.8325925925925926,0.6459259259259259,35.9,35.9,1233.661048232477,1.3973136906827464,583.2475644950097,1640.0851363378292,0.0377468039401844,558.3644649512152,0.9622531960598156,0.7707729438670059,0.4865412478577458 | |
| eval_results-global_step_10,74.0,74.0,347.30401819560274,0.07050796057619409,324.13012295081967,413.2448979591837,0.002274450341167551,309.0364741641337,0.9977255496588324,0.9522365428354814,0.22365428354814254,54.0,54.0,1053.928,0.774,503.84444444444443,1699.6782608695653,0.026,634.7125256673511,0.974,0.956,0.488,18.8,18.8,830.0147058823529,0.15808823529411764,415.8235294117647,925.5972850678733,0.014705882352941176,599.2611940298508,0.9852941176470589,0.9191176470588235,0.5,43.9,43.9,470.54208084824387,0.4257786613651425,403.00150829562597,523.4728132387706,0.007952286282306162,346.77388109552436,0.9920477137176938,0.8117958913187542,0.5188866799204771,22.8,22.8,1509.4414814814816,0.7792592592592592,663.0194805194806,1759.6314779270633,0.03851851851851852,928.884437596302,0.9614814814814815,0.9362962962962963,0.6518518518518519,42.7,42.7,842.2460572815364,0.4415268232989427,461.96381712442707,1064.3249470124913,0.017890227498986683,563.7337025106324,0.9821097725010134,0.9150892755018711,0.4764785630640943 | |
| eval_results-global_step_20,78.2,78.2,312.21379833206976,0.20090978013646701,274.06886517943747,448.7673611111111,0.001516300227445034,287.53682611996965,0.9984836997725549,0.9916603487490523,0.20849128127369218,57.8,57.8,765.056,0.302,445.1903114186851,1203.1658767772512,0.012,580.3157894736842,0.988,0.986,0.49,25.4,25.4,649.2683823529412,0.12867647058823528,477.768115942029,707.5615763546798,0.003676470588235294,592.6752767527676,0.9963235294117647,0.9816176470588235,0.45955882352941174,45.5,45.5,453.95758780649436,0.3535453943008615,366.8930131004367,526.7232360097323,0.005964214711729622,360.96133333333336,0.9940357852882704,0.9052352551358516,0.5397614314115308,24.7,24.7,1399.0103703703703,0.3362962962962963,668.0299401197605,1639.3129921259842,0.03259259259259259,907.4563552833079,0.9674074074074074,0.9540740740740741,0.6814814814814815,46.32,46.32,715.9012277723751,0.26428558826437204,446.39004915206976,905.1062084757517,0.011149915624000509,545.7891161926125,0.9888500843759994,0.9637174650035604,0.47585860353922327 | |
| eval_results-global_step_30,80.1,80.1,367.49886277482943,0.053828658074298714,299.2705771050142,642.7557251908397,0.0037907505686125853,306.603500761035,0.9962092494313874,0.9946929492039424,0.24715693707354056,60.4,60.4,1097.36,0.922,452.84437086092714,2080.409090909091,0.03,636.5649484536083,0.97,0.96,0.474,22.4,22.4,800.2683823529412,0.8529411764705882,505.0,885.6303317535545,0.011029411764705883,630.7881040892194,0.9889705882352942,0.9779411764705882,0.4375,47.9,47.9,453.56295559973495,0.45493704440026506,368.4422944022115,531.9649904519414,0.004970178926441352,376.26973026973025,0.9950298210735586,0.9502982107355865,0.5666003976143141,25.0,25.0,1515.3851851851853,0.5985185185185186,705.0,1786.0474308300395,0.04,911.2083333333334,0.96,0.9466666666666667,0.6651851851851852,47.160000000000004,47.160000000000004,846.8150771825382,0.576445079492734,466.11144847363056,1185.3615138270932,0.017958068251951963,572.2869233813852,0.982041931748048,0.9659198006153566,0.478088503974608 | |
| eval_results-global_step_40,79.9,79.9,352.98180439727065,0.03184230477634572,287.66698292220116,612.7622641509435,0.003032600454890068,305.5186311787072,0.9969673995451099,0.9962092494313874,0.2395754359363154,65.0,65.0,686.826,0.13,461.0276923076923,1106.1657142857143,0.008,563.3366935483871,0.992,0.99,0.478,23.5,23.5,743.4154411764706,0.09558823529411764,555.21875,801.3221153846154,0.007352941176470588,630.3814814814815,0.9926470588235294,0.9742647058823529,0.49264705882352944,50.7,50.7,437.6265738899934,0.513585155732273,339.97387328543437,538.1687962340283,0.0023194168323392977,401.4709398870807,0.9976805831676607,0.9555997349237906,0.5821736249171637,24.7,24.7,1696.8385185185184,0.2785185185185185,774.7604790419161,1999.9625984251968,0.05037037037037037,938.3229329173167,0.9496296296296296,0.9362962962962963,0.6651851851851852,48.760000000000005,48.760000000000005,783.5376675964505,0.209906842864251,483.7295555114488,1011.6762976960996,0.014215065766814066,567.8061358025946,0.985784934233186,0.9704739973067655,0.4915162609724387 | |
| eval_results-global_step_50,81.2,81.2,357.7028051554208,0.03335860500379075,310.40709617180204,561.9516129032259,0.002274450341167551,321.9270516717325,0.9977255496588324,0.9954510993176648,0.24639878695981804,64.2,64.2,785.616,0.66,511.5233644859813,1277.145251396648,0.01,631.9070707070707,0.99,0.984,0.492,25.7,25.7,697.6691176470588,0.47794117647058826,580.6571428571428,738.2178217821782,0.0,697.6691176470588,1.0,0.9852941176470589,0.4632352941176471,53.7,53.7,478.87574552683895,0.48807157057654077,362.64651449722396,613.7415891195419,0.005301524188204109,391.1459027315123,0.9946984758117959,0.9668654738237243,0.5950960901259112,24.6,24.6,1427.8503703703705,0.23703703703703705,660.9819277108434,1677.9489194499017,0.037037037037037035,868.3523076923077,0.9629629629629629,0.9525925925925925,0.6755555555555556,49.88,49.88,749.5428077399378,0.3792816778175914,485.2432091445988,973.8010389302992,0.010922602313281739,582.2002900899364,0.9890773976867182,0.9768406566762081,0.4944571453517864 | |
| eval_results-global_step_60,81.3,81.3,327.2653525398029,0.052312357846853674,300.74370922646784,442.9471544715447,0.0,327.2653525398029,1.0,0.9992418498862775,0.24336618650492797,63.6,63.6,672.466,0.136,486.65408805031444,997.1263736263736,0.004,610.9196787148594,0.996,0.988,0.53,28.3,28.3,851.5919117647059,0.09926470588235294,487.75324675324674,995.2615384615384,0.014705882352941176,625.5223880597015,0.9852941176470589,0.9705882352941176,0.5441176470588235,56.0,56.0,449.3011928429423,0.3605036447978794,369.6806623299823,550.7618688771665,0.002982107355864811,403.04220671319376,0.9970178926441352,0.9701789264413518,0.5987408880053016,26.7,26.7,1496.2696296296297,0.9348148148148148,693.7722222222222,1788.0868686868687,0.03851851851851852,914.6563944530046,0.9614814814814815,0.9451851851851852,0.6711111111111111,51.18,51.18,759.3788173554161,0.31657910466838013,467.7207857164467,954.8367608246984,0.012041301645464903,576.2812040961124,0.9879586983545352,0.9746388393613865,0.5174671665360329 | |
| eval_results-global_step_70,82.3,82.3,360.9037149355572,0.021986353297952996,315.2110599078341,572.7692307692307,0.003032600454890068,312.32623574144486,0.9969673995451099,0.9962092494313874,0.27748294162244125,61.8,61.8,771.344,0.114,522.3398058252427,1174.1832460732985,0.008,648.5362903225806,0.992,0.982,0.464,26.5,26.5,816.0551470588235,0.6801470588235294,488.09722222222223,934.12,0.011029411764705883,648.5018587360595,0.9889705882352942,0.9816176470588235,0.4742647058823529,55.5,55.5,468.8429423459244,0.441351888667992,368.7138590203106,593.5572916666666,0.004307488402915839,402.0029950083195,0.9956925115970842,0.9731610337972167,0.6100066269052352,28.1,28.1,1429.2918518518518,0.7674074074074074,838.8368421052631,1660.6041237113402,0.03111111111111111,961.7859327217126,0.9688888888888889,0.9466666666666667,0.7022222222222222,50.839999999999996,50.839999999999996,769.2875312384314,0.4049785416393764,506.63975781617455,987.0467784441073,0.01149612234672458,594.6306625060234,0.9885038776532754,0.9759309193908189,0.5055952993264503 | |
| eval_results-global_step_80,82.0,82.0,331.773313115997,0.027293404094010616,302.17190388170053,466.915611814346,0.000758150113722517,319.9514415781487,0.9992418498862775,0.9984836997725549,0.28430629264594387,64.4,64.4,684.442,0.15,479.2577639751553,1055.6179775280898,0.006,592.0020120724346,0.994,0.992,0.464,24.3,24.3,905.2279411764706,0.22794117647058823,509.2878787878788,1032.0825242718447,0.011029411764705883,738.1784386617101,0.9889705882352942,0.9742647058823529,0.4963235294117647,59.4,59.4,477.1958250497018,0.3074884029158383,411.53511705685617,573.4338235294117,0.004307488402915839,410.50116472545756,0.9956925115970842,0.9731610337972167,0.6153081510934394,26.4,26.4,1456.9066666666668,0.8666666666666667,776.3651685393259,1700.64185110664,0.03259259259259259,966.9800918836141,0.9674074074074074,0.9466666666666667,0.6503703703703704,51.3,51.3,771.1091492017672,0.3158779300294208,495.72356644818336,965.7383576500664,0.010937528574787365,605.522629784273,0.9890624714252126,0.9769152212237582,0.5020616687043037 | |
| eval_results-global_step_90,82.6,82.6,331.9954510993177,0.03866565579984837,309.22865013774106,439.7913043478261,0.000758150113722517,320.10773899848255,0.9992418498862775,0.9984836997725549,0.28203184230477635,64.4,64.4,1011.442,0.214,530.639751552795,1881.2078651685392,0.024,642.9016393442623,0.976,0.962,0.52,26.5,26.5,867.125,0.11397058823529412,539.3194444444445,985.135,0.007352941176470588,755.0296296296297,0.9926470588235294,0.9779411764705882,0.5404411764705882,60.7,60.7,460.19615639496357,0.32239893969516237,376.43941048034935,589.5741989881956,0.003644797879390325,403.35051546391753,0.9963552021206097,0.9751491053677932,0.6146454605699139,25.5,25.5,1460.8340740740741,0.36444444444444446,838.9011627906976,1673.5029821073558,0.03259259259259259,970.728943338438,0.9674074074074074,0.9481481481481482,0.6814814814814815,51.94,51.94,826.3185363136711,0.21069592563494988,518.9056838812055,1113.8422701223833,0.013669696352435205,618.4236933549461,0.9863303036475648,0.9723444259518169,0.5277199921653519 | |
| eval_results-global_step_100,82.0,82.0,354.6800606520091,0.02577710386656558,308.17929759704253,566.9746835443038,0.002274450341167551,319.0113981762918,0.9977255496588324,0.9969673995451099,0.29946929492039426,65.2,65.2,712.79,0.182,477.63496932515335,1153.367816091954,0.006,620.5150905432596,0.994,0.988,0.518,29.4,29.4,664.6948529411765,0.09191176470588236,531.7125,720.1041666666666,0.0,664.6948529411765,1.0,0.9963235294117647,0.5772058823529411,60.7,60.7,464.2365805168986,0.39430086149768057,405.07474086197493,555.7502109704641,0.0033134526176275677,412.79787234042556,0.9966865473823724,0.9744864148442677,0.6232604373757455,28.3,28.3,1481.2237037037037,0.48592592592592593,726.1989528795812,1779.1776859504132,0.034074074074074076,968.9555214723927,0.965925925925926,0.9422222222222222,0.6962962962962963,53.120000000000005,53.120000000000005,735.5250395627576,0.23598313119921088,489.7600921327504,955.0749126447603,0.00913239540657384,597.1949470947092,0.990867604593426,0.9795999132046729,0.5428463821890754 | |