Download reports/run/metrics.jsonl from SlayerLab/Slayer149-balanced: direct link, hf CLI and curl.
- Browser
- Download file 253 kB
-
https://huggingface.co/SlayerLab/Slayer149-balanced/resolve/main/reports/run/metrics.jsonl
- Command line
-
hf download hf://SlayerLab/Slayer149-balanced/reports/run/metrics.jsonl
-
curl -L -o metrics.jsonl https://huggingface.co/SlayerLab/Slayer149-balanced/resolve/main/reports/run/metrics.jsonl
253 kB
| {"step": 20, "tokens": 10485760, "loss": 10.169149780273438, "tokens_per_second": 229485.42681844623, "lr": 1.5e-05, "gradient_norm": 2.205339193344116, "benchmark": false} | |
| {"step": 40, "tokens": 20971520, "loss": 9.850079345703126, "tokens_per_second": 914837.8703186912, "lr": 3e-05, "gradient_norm": 2.3315203189849854, "benchmark": false} | |
| {"step": 60, "tokens": 31457280, "loss": 9.301335906982422, "tokens_per_second": 753117.1709990001, "lr": 4.4999999999999996e-05, "gradient_norm": 1.8692331314086914, "benchmark": false} | |
| {"step": 80, "tokens": 41943040, "loss": 8.688764190673828, "tokens_per_second": 1032255.2836004663, "lr": 6e-05, "gradient_norm": 1.4424148797988892, "benchmark": false} | |
| {"step": 100, "tokens": 52428800, "loss": 8.105000305175782, "tokens_per_second": 1029399.3815147971, "lr": 7.500000000000001e-05, "gradient_norm": 1.0234349966049194, "benchmark": false} | |
| {"step": 120, "tokens": 62914560, "loss": 7.616502380371093, "tokens_per_second": 1015709.3869896838, "lr": 8.999999999999999e-05, "gradient_norm": 1.1642669439315796, "benchmark": false} | |
| {"step": 140, "tokens": 73400320, "loss": 7.291810607910156, "tokens_per_second": 1015522.4437225041, "lr": 0.00010500000000000002, "gradient_norm": 0.8104191422462463, "benchmark": false} | |
| {"step": 160, "tokens": 83886080, "loss": 7.000241088867187, "tokens_per_second": 1024867.7143696964, "lr": 0.00012, "gradient_norm": 0.8440332412719727, "benchmark": false} | |
| {"step": 180, "tokens": 94371840, "loss": 6.713601684570312, "tokens_per_second": 1024219.9743449177, "lr": 0.000135, "gradient_norm": 1.245676040649414, "benchmark": false} | |
| {"step": 200, "tokens": 104857600, "loss": 6.462795257568359, "tokens_per_second": 1021215.5608316573, "lr": 0.00015000000000000001, "gradient_norm": 2.098832607269287, "benchmark": false} | |
| {"step": 220, "tokens": 115343360, "loss": 6.25281867980957, "tokens_per_second": 1011047.7764669958, "lr": 0.000165, "gradient_norm": 2.103592872619629, "benchmark": false} | |
| {"step": 240, "tokens": 125829120, "loss": 6.059990692138672, "tokens_per_second": 1014516.1725319899, "lr": 0.00017999999999999998, "gradient_norm": 2.0833327770233154, "benchmark": false} | |
| {"step": 260, "tokens": 136314880, "loss": 5.868567276000976, "tokens_per_second": 970291.6904213858, "lr": 0.00019500000000000002, "gradient_norm": 1.8735260963439941, "benchmark": false} | |
| {"step": 280, "tokens": 146800640, "loss": 5.708786392211914, "tokens_per_second": 1013524.8939050153, "lr": 0.00021000000000000004, "gradient_norm": 2.135854482650757, "benchmark": false} | |
| {"step": 300, "tokens": 157286400, "loss": 5.5515869140625, "tokens_per_second": 1017056.3127177466, "lr": 0.000225, "gradient_norm": 2.5311148166656494, "benchmark": false} | |
| {"step": 320, "tokens": 167772160, "loss": 5.388051223754883, "tokens_per_second": 1015417.7158358266, "lr": 0.00024, "gradient_norm": 2.0131514072418213, "benchmark": false} | |
| {"step": 340, "tokens": 178257920, "loss": 5.24281120300293, "tokens_per_second": 1003209.9996139308, "lr": 0.000255, "gradient_norm": 1.9500349760055542, "benchmark": false} | |
| {"step": 360, "tokens": 188743680, "loss": 5.100251770019531, "tokens_per_second": 1004851.9846189881, "lr": 0.00027, "gradient_norm": 2.0687453746795654, "benchmark": false} | |
| {"step": 380, "tokens": 199229440, "loss": 4.99603271484375, "tokens_per_second": 1017205.9020828365, "lr": 0.000285, "gradient_norm": 1.5136432647705078, "benchmark": false} | |
| {"step": 400, "tokens": 209715200, "loss": 4.855997848510742, "tokens_per_second": 1014320.6709609136, "lr": 0.00030000000000000003, "gradient_norm": 1.2021150588989258, "benchmark": false} | |
| {"step": 420, "tokens": 220200960, "loss": 4.741484451293945, "tokens_per_second": 1007498.0805184614, "lr": 0.000315, "gradient_norm": 1.2149815559387207, "benchmark": false} | |
| {"step": 440, "tokens": 230686720, "loss": 4.623250198364258, "tokens_per_second": 1011900.1103533852, "lr": 0.00033, "gradient_norm": 1.3369032144546509, "benchmark": false} | |
| {"step": 460, "tokens": 241172480, "loss": 4.510102844238281, "tokens_per_second": 988569.6225406213, "lr": 0.00034500000000000004, "gradient_norm": 1.1452369689941406, "benchmark": false} | |
| {"step": 480, "tokens": 251658240, "loss": 4.4276611328125, "tokens_per_second": 989866.3254340036, "lr": 0.00035999999999999997, "gradient_norm": 0.9811086058616638, "benchmark": false} | |
| {"step": 500, "tokens": 262144000, "loss": 4.3114372253417965, "tokens_per_second": 987284.1551733142, "lr": 0.000375, "gradient_norm": 0.8948100805282593, "benchmark": false} | |
| {"step": 520, "tokens": 272629760, "loss": 4.256084060668945, "tokens_per_second": 887677.7616114634, "lr": 0.00039000000000000005, "gradient_norm": 0.8738653063774109, "benchmark": false} | |
| {"step": 540, "tokens": 283115520, "loss": 4.178365707397461, "tokens_per_second": 987055.5145676823, "lr": 0.00040500000000000003, "gradient_norm": 0.9119740724563599, "benchmark": false} | |
| {"step": 560, "tokens": 293601280, "loss": 4.115958404541016, "tokens_per_second": 986620.6540439959, "lr": 0.00042000000000000007, "gradient_norm": 0.8756295442581177, "benchmark": false} | |
| {"step": 580, "tokens": 304087040, "loss": 4.041319274902344, "tokens_per_second": 991743.1745662729, "lr": 0.000435, "gradient_norm": 0.7584083676338196, "benchmark": false} | |
| {"step": 600, "tokens": 314572800, "loss": 4.01019515991211, "tokens_per_second": 948723.8898603223, "lr": 0.00045, "gradient_norm": 0.695301353931427, "benchmark": false} | |
| {"step": 620, "tokens": 325058560, "loss": 3.9603034973144533, "tokens_per_second": 987068.105185979, "lr": 0.000465, "gradient_norm": 0.595501720905304, "benchmark": false} | |
| {"step": 640, "tokens": 335544320, "loss": 3.9002197265625, "tokens_per_second": 937157.4389623627, "lr": 0.00048, "gradient_norm": 0.6494060754776001, "benchmark": false} | |
| {"step": 660, "tokens": 346030080, "loss": 3.87745361328125, "tokens_per_second": 987337.2396404969, "lr": 0.000495, "gradient_norm": 0.5577827095985413, "benchmark": false} | |
| {"step": 680, "tokens": 356515840, "loss": 3.830519104003906, "tokens_per_second": 986269.7550769978, "lr": 0.00051, "gradient_norm": 0.5967057347297668, "benchmark": false} | |
| {"step": 700, "tokens": 367001600, "loss": 3.826114273071289, "tokens_per_second": 992132.7181165003, "lr": 0.000525, "gradient_norm": 0.5667921900749207, "benchmark": false} | |
| {"step": 720, "tokens": 377487360, "loss": 3.769327163696289, "tokens_per_second": 944236.843989973, "lr": 0.00054, "gradient_norm": 0.5464304685592651, "benchmark": false} | |
| {"step": 740, "tokens": 387973120, "loss": 3.776169204711914, "tokens_per_second": 987457.2237525532, "lr": 0.000555, "gradient_norm": 0.4834839999675751, "benchmark": false} | |
| {"step": 760, "tokens": 398458880, "loss": 3.6883705139160154, "tokens_per_second": 984211.8141510511, "lr": 0.00057, "gradient_norm": 0.5399366617202759, "benchmark": false} | |
| {"step": 780, "tokens": 408944640, "loss": 3.716542434692383, "tokens_per_second": 982512.276017266, "lr": 0.000585, "gradient_norm": 0.46255218982696533, "benchmark": false} | |
| {"step": 800, "tokens": 419430400, "loss": 3.6764266967773436, "tokens_per_second": 987572.7835053173, "lr": 0.0006000000000000001, "gradient_norm": 0.47228479385375977, "benchmark": false} | |
| {"step": 820, "tokens": 429916160, "loss": 3.6527549743652346, "tokens_per_second": 836695.3994385907, "lr": 0.000615, "gradient_norm": 0.4634140431880951, "benchmark": false} | |
| {"step": 840, "tokens": 440401920, "loss": 3.6467517852783202, "tokens_per_second": 990496.904193152, "lr": 0.00063, "gradient_norm": 0.4072583019733429, "benchmark": false} | |
| {"step": 860, "tokens": 450887680, "loss": 3.6281856536865233, "tokens_per_second": 983591.4808985759, "lr": 0.000645, "gradient_norm": 0.3906756639480591, "benchmark": false} | |
| {"step": 880, "tokens": 461373440, "loss": 3.5856857299804688, "tokens_per_second": 984787.8953277065, "lr": 0.00066, "gradient_norm": 0.3721332550048828, "benchmark": false} | |
| {"step": 900, "tokens": 471859200, "loss": 3.576865005493164, "tokens_per_second": 986523.1621472359, "lr": 0.000675, "gradient_norm": 0.43096911907196045, "benchmark": false} | |
| {"step": 920, "tokens": 482344960, "loss": 3.551728057861328, "tokens_per_second": 985259.8203679301, "lr": 0.0006900000000000001, "gradient_norm": 0.3959476351737976, "benchmark": false} | |
| {"step": 940, "tokens": 492830720, "loss": 3.52474365234375, "tokens_per_second": 986379.5885503634, "lr": 0.000705, "gradient_norm": 0.3469522297382355, "benchmark": false} | |
| {"step": 960, "tokens": 503316480, "loss": 3.5565567016601562, "tokens_per_second": 991150.2588607525, "lr": 0.0007199999999999999, "gradient_norm": 0.3613435924053192, "benchmark": false} | |
| {"step": 980, "tokens": 513802240, "loss": 3.534979248046875, "tokens_per_second": 954816.5784302262, "lr": 0.000735, "gradient_norm": 0.36277028918266296, "benchmark": false} | |
| {"step": 1000, "tokens": 524288000, "loss": 3.512640380859375, "tokens_per_second": 982882.901952814, "lr": 0.00075, "gradient_norm": 0.36223894357681274, "benchmark": false} | |
| {"step": 1020, "tokens": 534773760, "loss": 3.498727798461914, "tokens_per_second": 788526.1090729708, "lr": 0.0007650000000000001, "gradient_norm": 0.33503326773643494, "benchmark": false} | |
| {"step": 1040, "tokens": 545259520, "loss": 3.485460662841797, "tokens_per_second": 996745.0972588192, "lr": 0.0007800000000000001, "gradient_norm": 0.3457220494747162, "benchmark": false} | |
| {"step": 1060, "tokens": 555745280, "loss": 3.48607177734375, "tokens_per_second": 996269.3046775112, "lr": 0.000795, "gradient_norm": 0.37579262256622314, "benchmark": false} | |
| {"step": 1080, "tokens": 566231040, "loss": 3.5009490966796877, "tokens_per_second": 993456.0662475126, "lr": 0.0008100000000000001, "gradient_norm": 0.3382250666618347, "benchmark": false} | |
| {"step": 1100, "tokens": 576716800, "loss": 3.4624401092529298, "tokens_per_second": 990775.8492234668, "lr": 0.0008250000000000001, "gradient_norm": 0.3198245167732239, "benchmark": false} | |
| {"step": 1120, "tokens": 587202560, "loss": 3.4398429870605467, "tokens_per_second": 850654.6348279766, "lr": 0.0008400000000000001, "gradient_norm": 0.3153975307941437, "benchmark": false} | |
| {"step": 1140, "tokens": 597688320, "loss": 3.4438480377197265, "tokens_per_second": 980482.9249238867, "lr": 0.000855, "gradient_norm": 0.32889819145202637, "benchmark": false} | |
| {"step": 1160, "tokens": 608174080, "loss": 3.4141963958740233, "tokens_per_second": 950779.5897118163, "lr": 0.00087, "gradient_norm": 0.31094542145729065, "benchmark": false} | |
| {"step": 1180, "tokens": 618659840, "loss": 3.4345771789550783, "tokens_per_second": 991621.5290955171, "lr": 0.0008849999999999999, "gradient_norm": 0.3323631286621094, "benchmark": false} | |
| {"step": 1200, "tokens": 629145600, "loss": 3.3983821868896484, "tokens_per_second": 943885.1715741617, "lr": 0.0009, "gradient_norm": 0.3000882565975189, "benchmark": false} | |
| {"step": 1220, "tokens": 639631360, "loss": 3.4088485717773436, "tokens_per_second": 990111.681569158, "lr": 0.000915, "gradient_norm": 0.34956976771354675, "benchmark": false} | |
| {"step": 1240, "tokens": 650117120, "loss": 3.442910003662109, "tokens_per_second": 989267.3947452446, "lr": 0.00093, "gradient_norm": 0.2532350718975067, "benchmark": false} | |
| {"step": 1260, "tokens": 660602880, "loss": 3.3780723571777345, "tokens_per_second": 989568.0678008214, "lr": 0.000945, "gradient_norm": 0.272448867559433, "benchmark": false} | |
| {"step": 1280, "tokens": 671088640, "loss": 3.361439895629883, "tokens_per_second": 991867.7331378494, "lr": 0.00096, "gradient_norm": 0.2679154574871063, "benchmark": false} | |
| {"step": 1300, "tokens": 681574400, "loss": 3.3786773681640625, "tokens_per_second": 994066.2303459286, "lr": 0.0009750000000000001, "gradient_norm": 0.27311596274375916, "benchmark": false} | |
| {"step": 1320, "tokens": 692060160, "loss": 3.3780323028564454, "tokens_per_second": 999815.6838591986, "lr": 0.00099, "gradient_norm": 0.28089940547943115, "benchmark": false} | |
| {"step": 1340, "tokens": 702545920, "loss": 3.3420379638671873, "tokens_per_second": 983372.1879870299, "lr": 0.001005, "gradient_norm": 0.265042781829834, "benchmark": false} | |
| {"step": 1360, "tokens": 713031680, "loss": 3.3285560607910156, "tokens_per_second": 983311.0842673131, "lr": 0.00102, "gradient_norm": 0.251801073551178, "benchmark": false} | |
| {"step": 1380, "tokens": 723517440, "loss": 3.356670379638672, "tokens_per_second": 983891.7629701059, "lr": 0.001035, "gradient_norm": 0.32045817375183105, "benchmark": false} | |
| {"step": 1400, "tokens": 734003200, "loss": 3.3711917877197264, "tokens_per_second": 984612.4124598544, "lr": 0.00105, "gradient_norm": 0.25579288601875305, "benchmark": false} | |
| {"step": 1420, "tokens": 744488960, "loss": 3.3433887481689455, "tokens_per_second": 978310.2133201571, "lr": 0.001065, "gradient_norm": 0.2545541822910309, "benchmark": false} | |
| {"step": 1440, "tokens": 754974720, "loss": 3.3351619720458983, "tokens_per_second": 981731.2661948634, "lr": 0.00108, "gradient_norm": 0.2912965714931488, "benchmark": false} | |
| {"step": 1460, "tokens": 765460480, "loss": 3.3235294342041017, "tokens_per_second": 979262.9726115753, "lr": 0.001095, "gradient_norm": 0.19009841978549957, "benchmark": false} | |
| {"step": 1480, "tokens": 775946240, "loss": 3.2929874420166017, "tokens_per_second": 986160.4285270798, "lr": 0.00111, "gradient_norm": 0.2310802936553955, "benchmark": false} | |
| {"step": 1500, "tokens": 786432000, "loss": 3.323834991455078, "tokens_per_second": 980533.0540742341, "lr": 0.0011250000000000001, "gradient_norm": 0.28383898735046387, "benchmark": false} | |
| {"step": 1520, "tokens": 796917760, "loss": 3.320008087158203, "tokens_per_second": 861185.9375980536, "lr": 0.00114, "gradient_norm": 0.28270798921585083, "benchmark": false} | |
| {"step": 1540, "tokens": 807403520, "loss": 3.315888214111328, "tokens_per_second": 999094.5125709875, "lr": 0.001155, "gradient_norm": 0.2359239161014557, "benchmark": false} | |
| {"step": 1560, "tokens": 817889280, "loss": 3.2986686706542967, "tokens_per_second": 947697.3463826232, "lr": 0.00117, "gradient_norm": 0.24340946972370148, "benchmark": false} | |
| {"step": 1580, "tokens": 828375040, "loss": 3.2917301177978517, "tokens_per_second": 976602.0468014935, "lr": 0.001185, "gradient_norm": 0.2536700367927551, "benchmark": false} | |
| {"step": 1600, "tokens": 838860800, "loss": 3.2878997802734373, "tokens_per_second": 993151.582896867, "lr": 0.0012000000000000001, "gradient_norm": 0.26822489500045776, "benchmark": false} | |
| {"step": 1620, "tokens": 849346560, "loss": 3.268468475341797, "tokens_per_second": 846468.1827140138, "lr": 0.0012150000000000002, "gradient_norm": 0.25949716567993164, "benchmark": false} | |
| {"step": 1640, "tokens": 859832320, "loss": 3.2780303955078125, "tokens_per_second": 988943.4693897894, "lr": 0.00123, "gradient_norm": 0.2221362441778183, "benchmark": false} | |
| {"step": 1660, "tokens": 870318080, "loss": 3.2745872497558595, "tokens_per_second": 982150.9602999857, "lr": 0.001245, "gradient_norm": 0.2505227327346802, "benchmark": false} | |
| {"step": 1680, "tokens": 880803840, "loss": 3.2768791198730467, "tokens_per_second": 986788.4008772722, "lr": 0.00126, "gradient_norm": 0.23133485019207, "benchmark": false} | |
| {"step": 1700, "tokens": 891289600, "loss": 3.2841224670410156, "tokens_per_second": 935487.5310804343, "lr": 0.001275, "gradient_norm": 0.26458561420440674, "benchmark": false} | |
| {"step": 1720, "tokens": 901775360, "loss": 3.272447967529297, "tokens_per_second": 983097.8905470619, "lr": 0.00129, "gradient_norm": 0.23839032649993896, "benchmark": false} | |
| {"step": 1740, "tokens": 912261120, "loss": 3.2812328338623047, "tokens_per_second": 980146.4442826945, "lr": 0.001305, "gradient_norm": 0.2654002904891968, "benchmark": false} | |
| {"step": 1760, "tokens": 922746880, "loss": 3.2421058654785155, "tokens_per_second": 985461.2211911916, "lr": 0.00132, "gradient_norm": 0.2411070019006729, "benchmark": false} | |
| {"step": 1780, "tokens": 933232640, "loss": 3.2650394439697266, "tokens_per_second": 832243.0646059647, "lr": 0.001335, "gradient_norm": 0.21274925768375397, "benchmark": false} | |
| {"step": 1800, "tokens": 943718400, "loss": 3.241225814819336, "tokens_per_second": 990827.7548038928, "lr": 0.00135, "gradient_norm": 0.260198175907135, "benchmark": false} | |
| {"step": 1820, "tokens": 954204160, "loss": 3.2716625213623045, "tokens_per_second": 982496.4494055083, "lr": 0.0013650000000000001, "gradient_norm": 0.21338151395320892, "benchmark": false} | |
| {"step": 1840, "tokens": 964689920, "loss": 3.247609329223633, "tokens_per_second": 985578.1686051373, "lr": 0.0013800000000000002, "gradient_norm": 0.25004974007606506, "benchmark": false} | |
| {"step": 1860, "tokens": 975175680, "loss": 3.251211929321289, "tokens_per_second": 979695.8705405282, "lr": 0.0013950000000000002, "gradient_norm": 0.23972438275814056, "benchmark": false} | |
| {"step": 1880, "tokens": 985661440, "loss": 3.2541065216064453, "tokens_per_second": 985086.6956364446, "lr": 0.00141, "gradient_norm": 0.2574971914291382, "benchmark": false} | |
| {"step": 1900, "tokens": 996147200, "loss": 3.2535194396972655, "tokens_per_second": 980087.9792946931, "lr": 0.001425, "gradient_norm": 0.24417293071746826, "benchmark": false} | |
| {"step": 1920, "tokens": 1006632960, "loss": 3.2531501770019533, "tokens_per_second": 976722.1636101804, "lr": 0.0014399999999999999, "gradient_norm": 0.2506352961063385, "benchmark": false} | |
| {"step": 1940, "tokens": 1017118720, "loss": 3.2249679565429688, "tokens_per_second": 988657.7397372127, "lr": 0.001455, "gradient_norm": 0.2712062895298004, "benchmark": false} | |
| {"step": 1960, "tokens": 1027604480, "loss": 3.238423156738281, "tokens_per_second": 983368.2203098513, "lr": 0.00147, "gradient_norm": 0.23316670954227448, "benchmark": false} | |
| {"step": 1980, "tokens": 1038090240, "loss": 3.1997447967529298, "tokens_per_second": 973767.7154982816, "lr": 0.001485, "gradient_norm": 0.28141582012176514, "benchmark": false} | |
| {"step": 2000, "tokens": 1048576000, "loss": 3.2284637451171876, "tokens_per_second": 976823.1508784221, "lr": 0.0015, "gradient_norm": 0.2324972003698349, "benchmark": false} | |
| {"step": 2020, "tokens": 1059061760, "loss": 3.2090808868408205, "tokens_per_second": 730999.3999765913, "lr": 0.0015, "gradient_norm": 0.24585793912410736, "benchmark": false} | |
| {"step": 2040, "tokens": 1069547520, "loss": 3.1923450469970702, "tokens_per_second": 989342.0159866536, "lr": 0.0015, "gradient_norm": 0.2529505491256714, "benchmark": false} | |
| {"step": 2060, "tokens": 1080033280, "loss": 3.218313217163086, "tokens_per_second": 980184.8385121401, "lr": 0.0015, "gradient_norm": 0.22426177561283112, "benchmark": false} | |
| {"step": 2080, "tokens": 1090519040, "loss": 3.2003223419189455, "tokens_per_second": 975774.710886383, "lr": 0.0015, "gradient_norm": 0.320008784532547, "benchmark": false} | |
| {"step": 2100, "tokens": 1101004800, "loss": 3.149315071105957, "tokens_per_second": 972722.8815786674, "lr": 0.0015, "gradient_norm": 0.23319050669670105, "benchmark": false} | |
| {"step": 2120, "tokens": 1111490560, "loss": 3.1842678070068358, "tokens_per_second": 988782.2398544162, "lr": 0.0015, "gradient_norm": 0.285098671913147, "benchmark": false} | |
| {"step": 2140, "tokens": 1121976320, "loss": 3.2177654266357423, "tokens_per_second": 946337.1330300244, "lr": 0.0015, "gradient_norm": 0.24716462194919586, "benchmark": false} | |
| {"step": 2160, "tokens": 1132462080, "loss": 3.188395690917969, "tokens_per_second": 859025.2571253291, "lr": 0.0015, "gradient_norm": 0.24048778414726257, "benchmark": false} | |
| {"step": 2180, "tokens": 1142947840, "loss": 3.167164611816406, "tokens_per_second": 981226.4706485842, "lr": 0.0015, "gradient_norm": 0.23292778432369232, "benchmark": false} | |
| {"step": 2200, "tokens": 1153433600, "loss": 3.1644962310791014, "tokens_per_second": 973269.5824632514, "lr": 0.0015, "gradient_norm": 0.23836679756641388, "benchmark": false} | |
| {"step": 2220, "tokens": 1163919360, "loss": 3.1756858825683594, "tokens_per_second": 982060.9930403465, "lr": 0.0015, "gradient_norm": 0.2097897082567215, "benchmark": false} | |
| {"step": 2240, "tokens": 1174405120, "loss": 3.216135787963867, "tokens_per_second": 977312.1377424125, "lr": 0.0015, "gradient_norm": 0.23326408863067627, "benchmark": false} | |
| {"step": 2260, "tokens": 1184890880, "loss": 3.176568031311035, "tokens_per_second": 808526.9841505941, "lr": 0.0015, "gradient_norm": 0.22781522572040558, "benchmark": false} | |
| {"step": 2280, "tokens": 1195376640, "loss": 3.188094902038574, "tokens_per_second": 979768.1894200984, "lr": 0.0015, "gradient_norm": 0.3312476873397827, "benchmark": false} | |
| {"step": 2300, "tokens": 1205862400, "loss": 3.190488815307617, "tokens_per_second": 971391.6392089871, "lr": 0.0015, "gradient_norm": 0.3006395697593689, "benchmark": false} | |
| {"step": 2320, "tokens": 1216348160, "loss": 3.191547966003418, "tokens_per_second": 968203.3701587206, "lr": 0.0015, "gradient_norm": 0.2636735439300537, "benchmark": false} | |
| {"step": 2340, "tokens": 1226833920, "loss": 3.17069034576416, "tokens_per_second": 971359.2117216635, "lr": 0.0015, "gradient_norm": 0.2941155433654785, "benchmark": false} | |
| {"step": 2360, "tokens": 1237319680, "loss": 3.188091850280762, "tokens_per_second": 976244.2459570086, "lr": 0.0015, "gradient_norm": 0.3771863281726837, "benchmark": false} | |
| {"step": 2380, "tokens": 1247805440, "loss": 3.166390228271484, "tokens_per_second": 973913.260164468, "lr": 0.0015, "gradient_norm": 0.2988470494747162, "benchmark": false} | |
| {"step": 2400, "tokens": 1258291200, "loss": 3.146928596496582, "tokens_per_second": 978642.099530088, "lr": 0.0015, "gradient_norm": 0.28170835971832275, "benchmark": false} | |
| {"step": 2420, "tokens": 1268776960, "loss": 3.181461524963379, "tokens_per_second": 975283.9687830707, "lr": 0.0015, "gradient_norm": 0.283269464969635, "benchmark": false} | |
| {"step": 2440, "tokens": 1279262720, "loss": 3.1301828384399415, "tokens_per_second": 971320.7176772086, "lr": 0.0015, "gradient_norm": 0.3059178292751312, "benchmark": false} | |
| {"step": 2460, "tokens": 1289748480, "loss": 3.1355751037597654, "tokens_per_second": 971357.1525588263, "lr": 0.0015, "gradient_norm": 0.2556086480617523, "benchmark": false} | |
| {"step": 2480, "tokens": 1300234240, "loss": 3.116751861572266, "tokens_per_second": 983559.1611577123, "lr": 0.0015, "gradient_norm": 0.22678160667419434, "benchmark": false} | |
| {"step": 2500, "tokens": 1310720000, "loss": 3.1567005157470702, "tokens_per_second": 820689.2260704602, "lr": 0.0015, "gradient_norm": 0.2704465389251709, "benchmark": false} | |
| {"step": 2520, "tokens": 1321205760, "loss": 3.128544235229492, "tokens_per_second": 848509.4357302934, "lr": 0.0015, "gradient_norm": 0.23646458983421326, "benchmark": false} | |
| {"step": 2540, "tokens": 1331691520, "loss": 3.126090431213379, "tokens_per_second": 988628.4239650108, "lr": 0.0015, "gradient_norm": 0.22039943933486938, "benchmark": false} | |
| {"step": 2560, "tokens": 1342177280, "loss": 3.120811653137207, "tokens_per_second": 989099.8075437183, "lr": 0.0015, "gradient_norm": 0.26951202750205994, "benchmark": false} | |
| {"step": 2580, "tokens": 1352663040, "loss": 3.124241065979004, "tokens_per_second": 930455.2500459759, "lr": 0.0015, "gradient_norm": 0.24497447907924652, "benchmark": false} | |
| {"step": 2600, "tokens": 1363148800, "loss": 3.1559934616088867, "tokens_per_second": 989359.9285415264, "lr": 0.0015, "gradient_norm": 0.2681301236152649, "benchmark": false} | |
| {"step": 2620, "tokens": 1373634560, "loss": 3.120655632019043, "tokens_per_second": 988014.3404262743, "lr": 0.0015, "gradient_norm": 0.22039465606212616, "benchmark": false} | |
| {"step": 2640, "tokens": 1384120320, "loss": 3.119555854797363, "tokens_per_second": 989281.896508611, "lr": 0.0015, "gradient_norm": 0.22109156847000122, "benchmark": false} | |
| {"step": 2660, "tokens": 1394606080, "loss": 3.1065670013427735, "tokens_per_second": 960148.7382511444, "lr": 0.0015, "gradient_norm": 0.3518049716949463, "benchmark": false} | |
| {"step": 2680, "tokens": 1405091840, "loss": 3.0817359924316405, "tokens_per_second": 986287.0883485635, "lr": 0.0015, "gradient_norm": 0.23797304928302765, "benchmark": false} | |
| {"step": 2700, "tokens": 1415577600, "loss": 3.105073928833008, "tokens_per_second": 979995.0214306681, "lr": 0.0015, "gradient_norm": 0.24327975511550903, "benchmark": false} | |
| {"step": 2720, "tokens": 1426063360, "loss": 3.1123846054077147, "tokens_per_second": 994175.0496723149, "lr": 0.0015, "gradient_norm": 0.2370196431875229, "benchmark": false} | |
| {"step": 2740, "tokens": 1436549120, "loss": 3.092816162109375, "tokens_per_second": 838924.7631111884, "lr": 0.0015, "gradient_norm": 0.2178315669298172, "benchmark": false} | |
| {"step": 2760, "tokens": 1447034880, "loss": 3.105674934387207, "tokens_per_second": 967719.704454244, "lr": 0.0015, "gradient_norm": 0.19153432548046112, "benchmark": false} | |
| {"step": 2780, "tokens": 1457520640, "loss": 3.0968559265136717, "tokens_per_second": 970148.9990081738, "lr": 0.0015, "gradient_norm": 0.2842233180999756, "benchmark": false} | |
| {"step": 2800, "tokens": 1468006400, "loss": 3.083591079711914, "tokens_per_second": 969444.0817674381, "lr": 0.0015, "gradient_norm": 0.20260733366012573, "benchmark": false} | |
| {"step": 2820, "tokens": 1478492160, "loss": 3.107806587219238, "tokens_per_second": 968484.9552187718, "lr": 0.0015, "gradient_norm": 0.20675988495349884, "benchmark": false} | |
| {"step": 2840, "tokens": 1488977920, "loss": 3.0884469985961913, "tokens_per_second": 965197.7011101028, "lr": 0.0015, "gradient_norm": 0.18282292783260345, "benchmark": false} | |
| {"step": 2860, "tokens": 1499463680, "loss": 3.077906608581543, "tokens_per_second": 967097.9223759779, "lr": 0.0015, "gradient_norm": 0.1760759800672531, "benchmark": false} | |
| {"step": 2880, "tokens": 1509949440, "loss": 3.0772300720214845, "tokens_per_second": 963623.7020487679, "lr": 0.0015, "gradient_norm": 0.18164290487766266, "benchmark": false} | |
| {"step": 2900, "tokens": 1520435200, "loss": 3.0809551239013673, "tokens_per_second": 967118.6745147803, "lr": 0.0015, "gradient_norm": 0.20678433775901794, "benchmark": false} | |
| {"step": 2920, "tokens": 1530920960, "loss": 3.062306022644043, "tokens_per_second": 970441.6601681139, "lr": 0.0015, "gradient_norm": 0.1730983555316925, "benchmark": false} | |
| {"step": 2940, "tokens": 1541406720, "loss": 3.0921581268310545, "tokens_per_second": 964402.069190114, "lr": 0.0015, "gradient_norm": 0.175042524933815, "benchmark": false} | |
| {"step": 2960, "tokens": 1551892480, "loss": 3.0917444229125977, "tokens_per_second": 976263.4119847118, "lr": 0.0015, "gradient_norm": 0.16529427468776703, "benchmark": false} | |
| {"step": 2980, "tokens": 1562378240, "loss": 3.107547378540039, "tokens_per_second": 974664.1426940245, "lr": 0.0015, "gradient_norm": 0.1620856076478958, "benchmark": false} | |
| {"step": 3000, "tokens": 1572864000, "loss": 3.053942108154297, "tokens_per_second": 961120.6402985074, "lr": 0.0015, "gradient_norm": 0.17983736097812653, "benchmark": false} | |
| {"step": 3020, "tokens": 1583349760, "loss": 3.0546281814575194, "tokens_per_second": 812529.1170383674, "lr": 0.0015, "gradient_norm": 0.13785792887210846, "benchmark": false} | |
| {"step": 3040, "tokens": 1593835520, "loss": 3.0774038314819334, "tokens_per_second": 995183.5208714989, "lr": 0.0015, "gradient_norm": 0.18102078139781952, "benchmark": false} | |
| {"step": 3060, "tokens": 1604321280, "loss": 3.0798330307006836, "tokens_per_second": 804488.664425958, "lr": 0.0015, "gradient_norm": 0.1693069338798523, "benchmark": false} | |
| {"step": 3080, "tokens": 1614807040, "loss": 3.0429784774780275, "tokens_per_second": 979478.5009066728, "lr": 0.0015, "gradient_norm": 0.1676941066980362, "benchmark": false} | |
| {"step": 3100, "tokens": 1625292800, "loss": 3.0414402008056642, "tokens_per_second": 974491.2248414045, "lr": 0.0015, "gradient_norm": 0.18284150958061218, "benchmark": false} | |
| {"step": 3120, "tokens": 1635778560, "loss": 3.065006637573242, "tokens_per_second": 978777.848876916, "lr": 0.0015, "gradient_norm": 0.1692066341638565, "benchmark": false} | |
| {"step": 3140, "tokens": 1646264320, "loss": 3.057622528076172, "tokens_per_second": 974780.1289945149, "lr": 0.0015, "gradient_norm": 0.14104141294956207, "benchmark": false} | |
| {"step": 3160, "tokens": 1656750080, "loss": 3.035442924499512, "tokens_per_second": 972833.7186925057, "lr": 0.0015, "gradient_norm": 0.1703290045261383, "benchmark": false} | |
| {"step": 3180, "tokens": 1667235840, "loss": 3.041324996948242, "tokens_per_second": 940559.5481778823, "lr": 0.0015, "gradient_norm": 0.15705615282058716, "benchmark": false} | |
| {"step": 3200, "tokens": 1677721600, "loss": 3.046498107910156, "tokens_per_second": 973834.5066184303, "lr": 0.0015, "gradient_norm": 0.15410611033439636, "benchmark": false} | |
| {"step": 3220, "tokens": 1688207360, "loss": 3.0478410720825195, "tokens_per_second": 963905.1910754426, "lr": 0.0015, "gradient_norm": 0.14934739470481873, "benchmark": false} | |
| {"step": 3240, "tokens": 1698693120, "loss": 3.037614440917969, "tokens_per_second": 967045.3812131445, "lr": 0.0015, "gradient_norm": 0.1508370041847229, "benchmark": false} | |
| {"step": 3260, "tokens": 1709178880, "loss": 3.0596263885498045, "tokens_per_second": 970383.7742291628, "lr": 0.0015, "gradient_norm": 0.148663729429245, "benchmark": false} | |
| {"step": 3280, "tokens": 1719664640, "loss": 3.0442033767700196, "tokens_per_second": 965969.0147663327, "lr": 0.0015, "gradient_norm": 0.17235177755355835, "benchmark": false} | |
| {"step": 3300, "tokens": 1730150400, "loss": 3.0775251388549805, "tokens_per_second": 976864.9814652608, "lr": 0.0015, "gradient_norm": 0.14954322576522827, "benchmark": false} | |
| {"step": 3320, "tokens": 1740636160, "loss": 3.0704534530639647, "tokens_per_second": 978593.0228445381, "lr": 0.0015, "gradient_norm": 0.14354996383190155, "benchmark": false} | |
| {"step": 3340, "tokens": 1751121920, "loss": 3.04581241607666, "tokens_per_second": 988516.7855058353, "lr": 0.0015, "gradient_norm": 0.16661900281906128, "benchmark": false} | |
| {"step": 3360, "tokens": 1761607680, "loss": 3.025486373901367, "tokens_per_second": 927855.3870296703, "lr": 0.0015, "gradient_norm": 0.15192417800426483, "benchmark": false} | |
| {"step": 3380, "tokens": 1772093440, "loss": 3.014867401123047, "tokens_per_second": 963873.3903153073, "lr": 0.0015, "gradient_norm": 0.15605700016021729, "benchmark": false} | |
| {"step": 3400, "tokens": 1782579200, "loss": 3.011953353881836, "tokens_per_second": 967688.8832669553, "lr": 0.0015, "gradient_norm": 0.17889906466007233, "benchmark": false} | |
| {"step": 3420, "tokens": 1793064960, "loss": 3.0426443099975584, "tokens_per_second": 966745.6060672435, "lr": 0.0015, "gradient_norm": 0.14536422491073608, "benchmark": false} | |
| {"step": 3440, "tokens": 1803550720, "loss": 3.040130043029785, "tokens_per_second": 941263.0945912544, "lr": 0.0015, "gradient_norm": 0.17657268047332764, "benchmark": false} | |
| {"step": 3460, "tokens": 1814036480, "loss": 3.0570775985717775, "tokens_per_second": 969805.7895285914, "lr": 0.0015, "gradient_norm": 0.15748904645442963, "benchmark": false} | |
| {"step": 3480, "tokens": 1824522240, "loss": 3.0283912658691405, "tokens_per_second": 969750.7373291658, "lr": 0.0015, "gradient_norm": 0.17056794464588165, "benchmark": false} | |
| {"step": 3500, "tokens": 1835008000, "loss": 3.034389114379883, "tokens_per_second": 971371.564367871, "lr": 0.0015, "gradient_norm": 0.13611756265163422, "benchmark": false} | |
| {"step": 3520, "tokens": 1845493760, "loss": 3.0094444274902346, "tokens_per_second": 845365.5708885989, "lr": 0.0015, "gradient_norm": 0.12842446565628052, "benchmark": false} | |
| {"step": 3540, "tokens": 1855979520, "loss": 3.02652587890625, "tokens_per_second": 993343.9287551965, "lr": 0.0015, "gradient_norm": 0.12900671362876892, "benchmark": false} | |
| {"step": 3560, "tokens": 1866465280, "loss": 3.005375862121582, "tokens_per_second": 914666.6063207821, "lr": 0.0015, "gradient_norm": 0.1524912416934967, "benchmark": false} | |
| {"step": 3580, "tokens": 1876951040, "loss": 3.01119441986084, "tokens_per_second": 979113.9151245613, "lr": 0.0015, "gradient_norm": 0.1300109326839447, "benchmark": false} | |
| {"step": 3600, "tokens": 1887436800, "loss": 2.971750831604004, "tokens_per_second": 974042.0355774015, "lr": 0.0015, "gradient_norm": 0.15577509999275208, "benchmark": false} | |
| {"step": 3620, "tokens": 1897922560, "loss": 3.0175716400146486, "tokens_per_second": 978604.3944189739, "lr": 0.0015, "gradient_norm": 0.17250511050224304, "benchmark": false} | |
| {"step": 3640, "tokens": 1908408320, "loss": 3.0410415649414064, "tokens_per_second": 958136.2986975483, "lr": 0.0015, "gradient_norm": 0.13614611327648163, "benchmark": false} | |
| {"step": 3660, "tokens": 1918894080, "loss": 3.012010383605957, "tokens_per_second": 969245.6805367464, "lr": 0.0015, "gradient_norm": 0.12776663899421692, "benchmark": false} | |
| {"step": 3680, "tokens": 1929379840, "loss": 3.011095428466797, "tokens_per_second": 942340.8724027737, "lr": 0.0015, "gradient_norm": 0.13975301384925842, "benchmark": false} | |
| {"step": 3700, "tokens": 1939865600, "loss": 3.0230899810791017, "tokens_per_second": 978109.1165907453, "lr": 0.0015, "gradient_norm": 0.12378263473510742, "benchmark": false} | |
| {"step": 3720, "tokens": 1950351360, "loss": 3.0241472244262697, "tokens_per_second": 977217.3536437268, "lr": 0.0015, "gradient_norm": 0.12801679968833923, "benchmark": false} | |
| {"step": 3740, "tokens": 1960837120, "loss": 3.0166873931884766, "tokens_per_second": 971262.3224394342, "lr": 0.0015, "gradient_norm": 0.12122127413749695, "benchmark": false} | |
| {"step": 3760, "tokens": 1971322880, "loss": 3.0079349517822265, "tokens_per_second": 978814.4046884076, "lr": 0.0015, "gradient_norm": 0.10893643647432327, "benchmark": false} | |
| {"step": 3780, "tokens": 1981808640, "loss": 2.9906312942504885, "tokens_per_second": 975213.4421708274, "lr": 0.0015, "gradient_norm": 0.1239536926150322, "benchmark": false} | |
| {"step": 3800, "tokens": 1992294400, "loss": 2.9913883209228516, "tokens_per_second": 983757.5368846043, "lr": 0.0015, "gradient_norm": 0.12377656996250153, "benchmark": false} | |
| {"step": 3820, "tokens": 2002780160, "loss": 3.0164859771728514, "tokens_per_second": 977973.746760453, "lr": 0.0015, "gradient_norm": 0.1039506271481514, "benchmark": false} | |
| {"step": 3840, "tokens": 2013265920, "loss": 3.0068218231201174, "tokens_per_second": 980913.81235883, "lr": 0.0015, "gradient_norm": 0.12089887261390686, "benchmark": false} | |
| {"step": 3860, "tokens": 2023751680, "loss": 2.967877006530762, "tokens_per_second": 977967.674142663, "lr": 0.0015, "gradient_norm": 0.11864820122718811, "benchmark": false} | |
| {"step": 3880, "tokens": 2034237440, "loss": 3.0211723327636717, "tokens_per_second": 974406.2258280913, "lr": 0.0015, "gradient_norm": 0.12529462575912476, "benchmark": false} | |
| {"step": 3900, "tokens": 2044723200, "loss": 2.9944433212280273, "tokens_per_second": 979193.8035194282, "lr": 0.0015, "gradient_norm": 0.10861857980489731, "benchmark": false} | |
| {"step": 3920, "tokens": 2055208960, "loss": 2.9812715530395506, "tokens_per_second": 981608.6602078674, "lr": 0.0015, "gradient_norm": 0.11419326812028885, "benchmark": false} | |
| {"step": 3940, "tokens": 2065694720, "loss": 3.01178035736084, "tokens_per_second": 980920.9083517338, "lr": 0.0015, "gradient_norm": 0.09572461247444153, "benchmark": false} | |
| {"step": 3960, "tokens": 2076180480, "loss": 3.002391815185547, "tokens_per_second": 982260.303099604, "lr": 0.0015, "gradient_norm": 0.11502530425786972, "benchmark": false} | |
| {"step": 3980, "tokens": 2086666240, "loss": 2.9722618103027343, "tokens_per_second": 936205.2487208435, "lr": 0.0015, "gradient_norm": 0.13280029594898224, "benchmark": false} | |
| {"step": 4000, "tokens": 2097152000, "loss": 3.018246078491211, "tokens_per_second": 980606.9515894684, "lr": 0.0015, "gradient_norm": 0.1104731634259224, "benchmark": false} | |
| {"step": 4020, "tokens": 2107637760, "loss": 3.0328603744506837, "tokens_per_second": 817031.6501473963, "lr": 0.0015, "gradient_norm": 0.10828843712806702, "benchmark": false} | |
| {"step": 4040, "tokens": 2118123520, "loss": 2.989377975463867, "tokens_per_second": 980716.3058365815, "lr": 0.0015, "gradient_norm": 0.12038014829158783, "benchmark": false} | |
| {"step": 4060, "tokens": 2128609280, "loss": 2.9882110595703124, "tokens_per_second": 971402.7047296836, "lr": 0.0015, "gradient_norm": 0.1103377491235733, "benchmark": false} | |
| {"step": 4080, "tokens": 2139095040, "loss": 2.9773632049560548, "tokens_per_second": 972889.6590334383, "lr": 0.0015, "gradient_norm": 0.1051115095615387, "benchmark": false} | |
| {"step": 4100, "tokens": 2149580800, "loss": 2.9693840026855467, "tokens_per_second": 839565.0333332941, "lr": 0.0015, "gradient_norm": 0.12314511835575104, "benchmark": false} | |
| {"step": 4120, "tokens": 2160066560, "loss": 3.0354469299316404, "tokens_per_second": 988168.614991664, "lr": 0.0015, "gradient_norm": 0.11598093062639236, "benchmark": false} | |
| {"step": 4140, "tokens": 2170552320, "loss": 2.983502960205078, "tokens_per_second": 977792.9972275979, "lr": 0.0015, "gradient_norm": 0.10647008568048477, "benchmark": false} | |
| {"step": 4160, "tokens": 2181038080, "loss": 2.981258583068848, "tokens_per_second": 985272.0417482306, "lr": 0.0015, "gradient_norm": 0.12514017522335052, "benchmark": false} | |
| {"step": 4180, "tokens": 2191523840, "loss": 2.9803936004638674, "tokens_per_second": 979294.5441847291, "lr": 0.0015, "gradient_norm": 0.116953045129776, "benchmark": false} | |
| {"step": 4200, "tokens": 2202009600, "loss": 2.9926197052001955, "tokens_per_second": 984405.9331565329, "lr": 0.0015, "gradient_norm": 0.09584445506334305, "benchmark": false} | |
| {"step": 4220, "tokens": 2212495360, "loss": 2.98980655670166, "tokens_per_second": 849521.3373798685, "lr": 0.0015, "gradient_norm": 0.09558536857366562, "benchmark": false} | |
| {"step": 4240, "tokens": 2222981120, "loss": 2.976529121398926, "tokens_per_second": 983884.5041944423, "lr": 0.0015, "gradient_norm": 0.11071575433015823, "benchmark": false} | |
| {"step": 4260, "tokens": 2233466880, "loss": 2.9626989364624023, "tokens_per_second": 985666.2047822862, "lr": 0.0015, "gradient_norm": 0.09352339804172516, "benchmark": false} | |
| {"step": 4280, "tokens": 2243952640, "loss": 2.9729793548583983, "tokens_per_second": 983842.6010859351, "lr": 0.0015, "gradient_norm": 0.0999748557806015, "benchmark": false} | |
| {"step": 4300, "tokens": 2254438400, "loss": 2.944722557067871, "tokens_per_second": 985748.5894285678, "lr": 0.0015, "gradient_norm": 0.10736636817455292, "benchmark": false} | |
| {"step": 4320, "tokens": 2264924160, "loss": 2.9729896545410157, "tokens_per_second": 983952.2491542622, "lr": 0.0015, "gradient_norm": 0.10021728277206421, "benchmark": false} | |
| {"step": 4340, "tokens": 2275409920, "loss": 2.948648452758789, "tokens_per_second": 971648.4928756781, "lr": 0.0015, "gradient_norm": 0.09368560463190079, "benchmark": false} | |
| {"step": 4360, "tokens": 2285895680, "loss": 2.9763671875, "tokens_per_second": 982640.3587817473, "lr": 0.0015, "gradient_norm": 0.10369141399860382, "benchmark": false} | |
| {"step": 4380, "tokens": 2296381440, "loss": 2.933808135986328, "tokens_per_second": 841728.0289634251, "lr": 0.0015, "gradient_norm": 0.0988178700208664, "benchmark": false} | |
| {"step": 4400, "tokens": 2306867200, "loss": 2.974225616455078, "tokens_per_second": 997499.7358452206, "lr": 0.0015, "gradient_norm": 0.09417622536420822, "benchmark": false} | |
| {"step": 4420, "tokens": 2317352960, "loss": 2.975873565673828, "tokens_per_second": 982659.5596324302, "lr": 0.0015, "gradient_norm": 0.10142190754413605, "benchmark": false} | |
| {"step": 4440, "tokens": 2327838720, "loss": 2.9742687225341795, "tokens_per_second": 810300.7172113446, "lr": 0.0015, "gradient_norm": 0.11457952857017517, "benchmark": false} | |
| {"step": 4460, "tokens": 2338324480, "loss": 2.952668571472168, "tokens_per_second": 977774.70016757, "lr": 0.0015, "gradient_norm": 0.10796493291854858, "benchmark": false} | |
| {"step": 4480, "tokens": 2348810240, "loss": 2.937723922729492, "tokens_per_second": 975644.4070345019, "lr": 0.0015, "gradient_norm": 0.10837341099977493, "benchmark": false} | |
| {"step": 4500, "tokens": 2359296000, "loss": 2.9822259902954102, "tokens_per_second": 972916.4437882437, "lr": 0.0015, "gradient_norm": 0.10424689948558807, "benchmark": false} | |
| {"step": 4520, "tokens": 2369781760, "loss": 2.9843788146972656, "tokens_per_second": 833079.9661412367, "lr": 0.0015, "gradient_norm": 0.10634101182222366, "benchmark": false} | |
| {"step": 4540, "tokens": 2380267520, "loss": 2.9769990921020506, "tokens_per_second": 985558.8131431809, "lr": 0.0015, "gradient_norm": 0.1044483482837677, "benchmark": false} | |
| {"step": 4560, "tokens": 2390753280, "loss": 2.969675827026367, "tokens_per_second": 983421.0391750208, "lr": 0.0015, "gradient_norm": 0.08892372250556946, "benchmark": false} | |
| {"step": 4580, "tokens": 2401239040, "loss": 2.961945915222168, "tokens_per_second": 969252.2172794534, "lr": 0.0015, "gradient_norm": 0.10147012025117874, "benchmark": false} | |
| {"step": 4600, "tokens": 2411724800, "loss": 2.9258108139038086, "tokens_per_second": 982775.4198475868, "lr": 0.0015, "gradient_norm": 0.09514818340539932, "benchmark": false} | |
| {"step": 4620, "tokens": 2422210560, "loss": 2.9655227661132812, "tokens_per_second": 940298.4467211306, "lr": 0.0015, "gradient_norm": 0.0923612043261528, "benchmark": false} | |
| {"step": 4640, "tokens": 2432696320, "loss": 2.951999282836914, "tokens_per_second": 937618.4046212843, "lr": 0.0015, "gradient_norm": 0.09763544797897339, "benchmark": false} | |
| {"step": 4660, "tokens": 2443182080, "loss": 2.966028022766113, "tokens_per_second": 966263.594087319, "lr": 0.0015, "gradient_norm": 0.10028868168592453, "benchmark": false} | |
| {"step": 4680, "tokens": 2453667840, "loss": 2.9490474700927733, "tokens_per_second": 960512.0055085152, "lr": 0.0015, "gradient_norm": 0.09279947727918625, "benchmark": false} | |
| {"step": 4700, "tokens": 2464153600, "loss": 2.986806106567383, "tokens_per_second": 971028.7885817649, "lr": 0.0015, "gradient_norm": 0.08970464766025543, "benchmark": false} | |
| {"step": 4720, "tokens": 2474639360, "loss": 2.962502670288086, "tokens_per_second": 972814.0600136536, "lr": 0.0015, "gradient_norm": 0.09654846042394638, "benchmark": false} | |
| {"step": 4740, "tokens": 2485125120, "loss": 2.978459358215332, "tokens_per_second": 969742.2589327429, "lr": 0.0015, "gradient_norm": 0.09661349654197693, "benchmark": false} | |
| {"step": 4760, "tokens": 2495610880, "loss": 2.9715957641601562, "tokens_per_second": 969051.8322886985, "lr": 0.0015, "gradient_norm": 0.09438515454530716, "benchmark": false} | |
| {"step": 4780, "tokens": 2506096640, "loss": 2.970972442626953, "tokens_per_second": 961760.1791516629, "lr": 0.0015, "gradient_norm": 0.07773580402135849, "benchmark": false} | |
| {"step": 4800, "tokens": 2516582400, "loss": 2.9481992721557617, "tokens_per_second": 971270.9862248712, "lr": 0.0015, "gradient_norm": 0.11723429709672928, "benchmark": false} | |
| {"step": 4820, "tokens": 2527068160, "loss": 2.9477846145629885, "tokens_per_second": 966117.5754807027, "lr": 0.0015, "gradient_norm": 0.08931349217891693, "benchmark": false} | |
| {"step": 4840, "tokens": 2537553920, "loss": 2.9338357925415037, "tokens_per_second": 972008.3428573115, "lr": 0.0015, "gradient_norm": 0.08552338927984238, "benchmark": false} | |
| {"step": 4860, "tokens": 2548039680, "loss": 2.9816299438476563, "tokens_per_second": 970438.620095988, "lr": 0.0015, "gradient_norm": 0.0985548347234726, "benchmark": false} | |
| {"step": 4880, "tokens": 2558525440, "loss": 2.932330322265625, "tokens_per_second": 969385.8209018379, "lr": 0.0015, "gradient_norm": 0.0836762934923172, "benchmark": false} | |
| {"step": 4900, "tokens": 2569011200, "loss": 2.9397216796875, "tokens_per_second": 945803.8707235291, "lr": 0.0015, "gradient_norm": 0.08557648211717606, "benchmark": false} | |
| {"step": 4920, "tokens": 2579496960, "loss": 2.9269309997558595, "tokens_per_second": 965631.9754211057, "lr": 0.0015, "gradient_norm": 0.0888092964887619, "benchmark": false} | |
| {"step": 4940, "tokens": 2589982720, "loss": 2.9586591720581055, "tokens_per_second": 964416.464912028, "lr": 0.0015, "gradient_norm": 0.09584059566259384, "benchmark": false} | |
| {"step": 4960, "tokens": 2600468480, "loss": 2.9198270797729493, "tokens_per_second": 967224.2776713663, "lr": 0.0015, "gradient_norm": 0.09711223840713501, "benchmark": false} | |
| {"step": 4980, "tokens": 2610954240, "loss": 2.9437145233154296, "tokens_per_second": 980325.3360152998, "lr": 0.0015, "gradient_norm": 0.08578862994909286, "benchmark": false} | |
| {"step": 5000, "tokens": 2621440000, "loss": 2.933154296875, "tokens_per_second": 969211.9684460608, "lr": 0.0015, "gradient_norm": 0.09016783535480499, "benchmark": false} | |
| {"step": 5020, "tokens": 2631925760, "loss": 2.91949462890625, "tokens_per_second": 807039.9908925168, "lr": 0.0015, "gradient_norm": 0.0832776427268982, "benchmark": false} | |
| {"step": 5040, "tokens": 2642411520, "loss": 2.943686676025391, "tokens_per_second": 974883.678769598, "lr": 0.0015, "gradient_norm": 0.0810946375131607, "benchmark": false} | |
| {"step": 5060, "tokens": 2652897280, "loss": 2.9218799591064455, "tokens_per_second": 972867.6664382793, "lr": 0.0015, "gradient_norm": 0.08206641674041748, "benchmark": false} | |
| {"step": 5080, "tokens": 2663383040, "loss": 2.9323846817016603, "tokens_per_second": 980684.4591826717, "lr": 0.0015, "gradient_norm": 0.0892726480960846, "benchmark": false} | |
| {"step": 5100, "tokens": 2673868800, "loss": 2.968641662597656, "tokens_per_second": 977169.9362081758, "lr": 0.0015, "gradient_norm": 0.08341504633426666, "benchmark": false} | |
| {"step": 5120, "tokens": 2684354560, "loss": 2.94069766998291, "tokens_per_second": 971473.8473101754, "lr": 0.0015, "gradient_norm": 0.08239274471998215, "benchmark": false} | |
| {"step": 5140, "tokens": 2694840320, "loss": 2.930527114868164, "tokens_per_second": 952458.4455743586, "lr": 0.0015, "gradient_norm": 0.07921042293310165, "benchmark": false} | |
| {"step": 5160, "tokens": 2705326080, "loss": 2.9769565582275392, "tokens_per_second": 971415.8924402391, "lr": 0.0015, "gradient_norm": 0.07994222640991211, "benchmark": false} | |
| {"step": 5180, "tokens": 2715811840, "loss": 2.926432800292969, "tokens_per_second": 972275.7534137008, "lr": 0.0015, "gradient_norm": 0.08145543932914734, "benchmark": false} | |
| {"step": 5200, "tokens": 2726297600, "loss": 2.9458358764648436, "tokens_per_second": 980504.0113963353, "lr": 0.0015, "gradient_norm": 0.08293821662664413, "benchmark": false} | |
| {"step": 5220, "tokens": 2736783360, "loss": 2.945914459228516, "tokens_per_second": 978922.3163641915, "lr": 0.0015, "gradient_norm": 0.07533572614192963, "benchmark": false} | |
| {"step": 5240, "tokens": 2747269120, "loss": 2.933604431152344, "tokens_per_second": 994955.99338533, "lr": 0.0015, "gradient_norm": 0.08959390968084335, "benchmark": false} | |
| {"step": 5260, "tokens": 2757754880, "loss": 2.9177902221679686, "tokens_per_second": 849796.2344397762, "lr": 0.0015, "gradient_norm": 0.07915160059928894, "benchmark": false} | |
| {"step": 5280, "tokens": 2768240640, "loss": 2.9453243255615233, "tokens_per_second": 970850.4842013303, "lr": 0.0015, "gradient_norm": 0.08411432057619095, "benchmark": false} | |
| {"step": 5300, "tokens": 2778726400, "loss": 2.9040199279785157, "tokens_per_second": 971363.971749047, "lr": 0.0015, "gradient_norm": 0.08503418415784836, "benchmark": false} | |
| {"step": 5320, "tokens": 2789212160, "loss": 2.9312274932861326, "tokens_per_second": 982310.5835244175, "lr": 0.0015, "gradient_norm": 0.0849388912320137, "benchmark": false} | |
| {"step": 5340, "tokens": 2799697920, "loss": 2.961272430419922, "tokens_per_second": 935002.5997755554, "lr": 0.0015, "gradient_norm": 0.08542951196432114, "benchmark": false} | |
| {"step": 5360, "tokens": 2810183680, "loss": 2.929550361633301, "tokens_per_second": 965670.9911927925, "lr": 0.0015, "gradient_norm": 0.07830847799777985, "benchmark": false} | |
| {"step": 5380, "tokens": 2820669440, "loss": 2.924506950378418, "tokens_per_second": 966678.1909652675, "lr": 0.0015, "gradient_norm": 0.07923851162195206, "benchmark": false} | |
| {"step": 5400, "tokens": 2831155200, "loss": 2.9516632080078127, "tokens_per_second": 974753.4470476174, "lr": 0.0015, "gradient_norm": 0.07655521482229233, "benchmark": false} | |
| {"step": 5420, "tokens": 2841640960, "loss": 2.90808048248291, "tokens_per_second": 975353.845478422, "lr": 0.0015, "gradient_norm": 0.07446541637182236, "benchmark": false} | |
| {"step": 5440, "tokens": 2852126720, "loss": 2.927232551574707, "tokens_per_second": 961491.6873988404, "lr": 0.0015, "gradient_norm": 0.08092717826366425, "benchmark": false} | |
| {"step": 5460, "tokens": 2862612480, "loss": 2.9212882995605467, "tokens_per_second": 963640.9597608796, "lr": 0.0015, "gradient_norm": 0.07737968862056732, "benchmark": false} | |
| {"step": 5480, "tokens": 2873098240, "loss": 2.93560733795166, "tokens_per_second": 989570.6405544647, "lr": 0.0015, "gradient_norm": 0.07661953568458557, "benchmark": false} | |
| {"step": 5500, "tokens": 2883584000, "loss": 2.9613765716552733, "tokens_per_second": 847609.3000475727, "lr": 0.0015, "gradient_norm": 0.08004806190729141, "benchmark": false} | |
| {"step": 5520, "tokens": 2894069760, "loss": 2.9488664627075196, "tokens_per_second": 866353.3135315783, "lr": 0.0015, "gradient_norm": 0.0868849903345108, "benchmark": false} | |
| {"step": 5540, "tokens": 2904555520, "loss": 2.922819900512695, "tokens_per_second": 842035.3464095091, "lr": 0.0015, "gradient_norm": 0.08004412055015564, "benchmark": false} | |
| {"step": 5560, "tokens": 2915041280, "loss": 2.9115245819091795, "tokens_per_second": 989696.760880027, "lr": 0.0015, "gradient_norm": 0.07318487763404846, "benchmark": false} | |
| {"step": 5580, "tokens": 2925527040, "loss": 2.9124717712402344, "tokens_per_second": 960153.1230927765, "lr": 0.0015, "gradient_norm": 0.07960419356822968, "benchmark": false} | |
| {"step": 5600, "tokens": 2936012800, "loss": 2.912256622314453, "tokens_per_second": 803058.9076393034, "lr": 0.0015, "gradient_norm": 0.07421176880598068, "benchmark": false} | |
| {"step": 5620, "tokens": 2946498560, "loss": 2.905378532409668, "tokens_per_second": 988754.1863783887, "lr": 0.0015, "gradient_norm": 0.07970532774925232, "benchmark": false} | |
| {"step": 5640, "tokens": 2956984320, "loss": 2.9199426651000975, "tokens_per_second": 990308.9639122755, "lr": 0.0015, "gradient_norm": 0.07617263495922089, "benchmark": false} | |
| {"step": 5660, "tokens": 2967470080, "loss": 2.9107025146484373, "tokens_per_second": 978185.6635022453, "lr": 0.0015, "gradient_norm": 0.07382852584123611, "benchmark": false} | |
| {"step": 5680, "tokens": 2977955840, "loss": 2.905801010131836, "tokens_per_second": 971898.3197802342, "lr": 0.0015, "gradient_norm": 0.08222389221191406, "benchmark": false} | |
| {"step": 5700, "tokens": 2988441600, "loss": 2.9259653091430664, "tokens_per_second": 983162.2201589467, "lr": 0.0015, "gradient_norm": 0.08115886151790619, "benchmark": false} | |
| {"step": 5720, "tokens": 2998927360, "loss": 2.9457263946533203, "tokens_per_second": 973233.7790143759, "lr": 0.0015, "gradient_norm": 0.07591685652732849, "benchmark": false} | |
| {"step": 5740, "tokens": 3009413120, "loss": 2.8867155075073243, "tokens_per_second": 978472.091925596, "lr": 0.0015, "gradient_norm": 0.07066729664802551, "benchmark": false} | |
| {"step": 5760, "tokens": 3019898880, "loss": 2.88946475982666, "tokens_per_second": 971630.2223853172, "lr": 0.0015, "gradient_norm": 0.0773647204041481, "benchmark": false} | |
| {"step": 5780, "tokens": 3030384640, "loss": 2.909421920776367, "tokens_per_second": 968416.9430541757, "lr": 0.0015, "gradient_norm": 0.08341608941555023, "benchmark": false} | |
| {"step": 5800, "tokens": 3040870400, "loss": 2.9399446487426757, "tokens_per_second": 976057.1005536041, "lr": 0.0015, "gradient_norm": 0.07185089588165283, "benchmark": false} | |
| {"step": 5820, "tokens": 3051356160, "loss": 2.910957145690918, "tokens_per_second": 948707.7179974132, "lr": 0.0015, "gradient_norm": 0.07909140735864639, "benchmark": false} | |
| {"step": 5840, "tokens": 3061841920, "loss": 2.9132053375244142, "tokens_per_second": 972214.9250154457, "lr": 0.0015, "gradient_norm": 0.07734359800815582, "benchmark": false} | |
| {"step": 5860, "tokens": 3072327680, "loss": 2.9111305236816407, "tokens_per_second": 976389.8325930431, "lr": 0.0015, "gradient_norm": 0.07081171870231628, "benchmark": false} | |
| {"step": 5880, "tokens": 3082813440, "loss": 2.9096916198730467, "tokens_per_second": 976243.5729098846, "lr": 0.0015, "gradient_norm": 0.07407041639089584, "benchmark": false} | |
| {"step": 5900, "tokens": 3093299200, "loss": 2.911384391784668, "tokens_per_second": 978540.8456923445, "lr": 0.0015, "gradient_norm": 0.07035409659147263, "benchmark": false} | |
| {"step": 5920, "tokens": 3103784960, "loss": 2.9021526336669923, "tokens_per_second": 986599.4897803419, "lr": 0.0015, "gradient_norm": 0.0749964788556099, "benchmark": false} | |
| {"step": 5940, "tokens": 3114270720, "loss": 2.9089988708496093, "tokens_per_second": 978099.6904409037, "lr": 0.0015, "gradient_norm": 0.08997740596532822, "benchmark": false} | |
| {"step": 5960, "tokens": 3124756480, "loss": 2.9387432098388673, "tokens_per_second": 978047.3818877105, "lr": 0.0015, "gradient_norm": 0.0761580765247345, "benchmark": false} | |
| {"step": 5980, "tokens": 3135242240, "loss": 2.8938913345336914, "tokens_per_second": 971113.1983575885, "lr": 0.0015, "gradient_norm": 0.07130406051874161, "benchmark": false} | |
| {"step": 6000, "tokens": 3145728000, "loss": 2.910635757446289, "tokens_per_second": 968513.8750935235, "lr": 0.0015, "gradient_norm": 0.07274629175662994, "benchmark": false} | |
| {"step": 6020, "tokens": 3156213760, "loss": 2.9167280197143555, "tokens_per_second": 813333.7822438873, "lr": 0.0015, "gradient_norm": 0.07697819173336029, "benchmark": false} | |
| {"step": 6040, "tokens": 3166699520, "loss": 2.919988250732422, "tokens_per_second": 988199.3814672184, "lr": 0.0015, "gradient_norm": 0.07092317193746567, "benchmark": false} | |
| {"step": 6060, "tokens": 3177185280, "loss": 2.8964223861694336, "tokens_per_second": 986418.2932919076, "lr": 0.0015, "gradient_norm": 0.0735328271985054, "benchmark": false} | |
| {"step": 6080, "tokens": 3187671040, "loss": 2.9418666839599608, "tokens_per_second": 981378.5804716933, "lr": 0.0015, "gradient_norm": 0.09998906403779984, "benchmark": false} | |
| {"step": 6100, "tokens": 3198156800, "loss": 2.9135721206665037, "tokens_per_second": 988632.0183834768, "lr": 0.0015, "gradient_norm": 0.06642155349254608, "benchmark": false} | |
| {"step": 6120, "tokens": 3208642560, "loss": 2.9151752471923826, "tokens_per_second": 977289.6119118045, "lr": 0.0015, "gradient_norm": 0.06914926320314407, "benchmark": false} | |
| {"step": 6140, "tokens": 3219128320, "loss": 2.9054723739624024, "tokens_per_second": 972138.5604667434, "lr": 0.0015, "gradient_norm": 0.07093650847673416, "benchmark": false} | |
| {"step": 6160, "tokens": 3229614080, "loss": 2.9123771667480467, "tokens_per_second": 970947.1832531, "lr": 0.0015, "gradient_norm": 0.06923744082450867, "benchmark": false} | |
| {"step": 6180, "tokens": 3240099840, "loss": 2.897180366516113, "tokens_per_second": 960862.7870472525, "lr": 0.0015, "gradient_norm": 0.0649130567908287, "benchmark": false} | |
| {"step": 6200, "tokens": 3250585600, "loss": 2.9069116592407225, "tokens_per_second": 979698.8804656132, "lr": 0.0015, "gradient_norm": 0.07176172733306885, "benchmark": false} | |
| {"step": 6220, "tokens": 3261071360, "loss": 2.890264892578125, "tokens_per_second": 976501.0050195361, "lr": 0.0015, "gradient_norm": 0.07033491134643555, "benchmark": false} | |
| {"step": 6240, "tokens": 3271557120, "loss": 2.8849693298339845, "tokens_per_second": 978957.7607004017, "lr": 0.0015, "gradient_norm": 0.07758528739213943, "benchmark": false} | |
| {"step": 6260, "tokens": 3282042880, "loss": 2.8891056060791014, "tokens_per_second": 985040.5915574107, "lr": 0.0015, "gradient_norm": 0.07268603891134262, "benchmark": false} | |
| {"step": 6280, "tokens": 3292528640, "loss": 2.9252336502075194, "tokens_per_second": 901905.6784838198, "lr": 0.0015, "gradient_norm": 0.08138222992420197, "benchmark": false} | |
| {"step": 6300, "tokens": 3303014400, "loss": 2.916875648498535, "tokens_per_second": 967857.4768748236, "lr": 0.0015, "gradient_norm": 0.06496562063694, "benchmark": false} | |
| {"step": 6320, "tokens": 3313500160, "loss": 2.870402145385742, "tokens_per_second": 978980.4711670941, "lr": 0.0015, "gradient_norm": 0.06997466087341309, "benchmark": false} | |
| {"step": 6340, "tokens": 3323985920, "loss": 2.901245880126953, "tokens_per_second": 972604.9701731356, "lr": 0.0015, "gradient_norm": 0.07597402483224869, "benchmark": false} | |
| {"step": 6360, "tokens": 3334471680, "loss": 2.9156782150268556, "tokens_per_second": 972177.8462893734, "lr": 0.0015, "gradient_norm": 0.07095592468976974, "benchmark": false} | |
| {"step": 6380, "tokens": 3344957440, "loss": 2.890736198425293, "tokens_per_second": 976962.7402310458, "lr": 0.0015, "gradient_norm": 0.06986173242330551, "benchmark": false} | |
| {"step": 6400, "tokens": 3355443200, "loss": 2.8872875213623046, "tokens_per_second": 980279.6361187346, "lr": 0.0015, "gradient_norm": 0.07426601648330688, "benchmark": false} | |
| {"step": 6420, "tokens": 3365928960, "loss": 2.923754119873047, "tokens_per_second": 977489.1709746858, "lr": 0.0015, "gradient_norm": 0.07277980446815491, "benchmark": false} | |
| {"step": 6440, "tokens": 3376414720, "loss": 2.8971817016601564, "tokens_per_second": 985589.9814813196, "lr": 0.0015, "gradient_norm": 0.07001446187496185, "benchmark": false} | |
| {"step": 6460, "tokens": 3386900480, "loss": 2.9104307174682615, "tokens_per_second": 851359.8309475023, "lr": 0.0015, "gradient_norm": 0.07588035613298416, "benchmark": false} | |
| {"step": 6480, "tokens": 3397386240, "loss": 2.918135643005371, "tokens_per_second": 981682.6743647555, "lr": 0.0015, "gradient_norm": 0.06573039293289185, "benchmark": false} | |
| {"step": 6500, "tokens": 3407872000, "loss": 2.922238349914551, "tokens_per_second": 967116.1633914592, "lr": 0.0015, "gradient_norm": 0.0701269879937172, "benchmark": false} | |
| {"step": 6520, "tokens": 3418357760, "loss": 2.8830898284912108, "tokens_per_second": 851558.9785967895, "lr": 0.0015, "gradient_norm": 0.07001926749944687, "benchmark": false} | |
| {"step": 6540, "tokens": 3428843520, "loss": 2.8867376327514647, "tokens_per_second": 980962.7329971936, "lr": 0.0015, "gradient_norm": 0.06727704405784607, "benchmark": false} | |
| {"step": 6560, "tokens": 3439329280, "loss": 2.8744361877441404, "tokens_per_second": 811605.0280486693, "lr": 0.0015, "gradient_norm": 0.0776929259300232, "benchmark": false} | |
| {"step": 6580, "tokens": 3449815040, "loss": 2.8729530334472657, "tokens_per_second": 988722.7496293134, "lr": 0.0015, "gradient_norm": 0.07295847684144974, "benchmark": false} | |
| {"step": 6600, "tokens": 3460300800, "loss": 2.87994327545166, "tokens_per_second": 985837.3399777771, "lr": 0.0015, "gradient_norm": 0.08181548863649368, "benchmark": false} | |
| {"step": 6620, "tokens": 3470786560, "loss": 2.9264673233032226, "tokens_per_second": 938610.7678174136, "lr": 0.0015, "gradient_norm": 0.07315581291913986, "benchmark": false} | |
| {"step": 6640, "tokens": 3481272320, "loss": 2.88464298248291, "tokens_per_second": 968048.0186126189, "lr": 0.0015, "gradient_norm": 0.07335823774337769, "benchmark": false} | |
| {"step": 6660, "tokens": 3491758080, "loss": 2.8914815902709963, "tokens_per_second": 966619.7370303338, "lr": 0.0015, "gradient_norm": 0.06765320897102356, "benchmark": false} | |
| {"step": 6680, "tokens": 3502243840, "loss": 2.906380844116211, "tokens_per_second": 966292.2607110887, "lr": 0.0015, "gradient_norm": 0.06490307301282883, "benchmark": false} | |
| {"step": 6700, "tokens": 3512729600, "loss": 2.8874916076660155, "tokens_per_second": 966301.7377509758, "lr": 0.0015, "gradient_norm": 0.06722146272659302, "benchmark": false} | |
| {"step": 6720, "tokens": 3523215360, "loss": 2.8801807403564452, "tokens_per_second": 963748.3558215296, "lr": 0.0015, "gradient_norm": 0.064705990254879, "benchmark": false} | |
| {"step": 6740, "tokens": 3533701120, "loss": 2.9100214004516602, "tokens_per_second": 984422.9663336131, "lr": 0.0015, "gradient_norm": 0.0706767737865448, "benchmark": false} | |
| {"step": 6760, "tokens": 3544186880, "loss": 2.895804595947266, "tokens_per_second": 811779.2935493477, "lr": 0.0015, "gradient_norm": 0.0654865950345993, "benchmark": false} | |
| {"step": 6780, "tokens": 3554672640, "loss": 2.8594734191894533, "tokens_per_second": 972736.3100822046, "lr": 0.0015, "gradient_norm": 0.07148617506027222, "benchmark": false} | |
| {"step": 6800, "tokens": 3565158400, "loss": 2.8710149765014648, "tokens_per_second": 968773.9776349113, "lr": 0.0015, "gradient_norm": 0.06894656270742416, "benchmark": false} | |
| {"step": 6820, "tokens": 3575644160, "loss": 2.8935791015625, "tokens_per_second": 967642.582004313, "lr": 0.0015, "gradient_norm": 0.06292393803596497, "benchmark": false} | |
| {"step": 6840, "tokens": 3586129920, "loss": 2.868268585205078, "tokens_per_second": 970204.0368372373, "lr": 0.0015, "gradient_norm": 0.07326362282037735, "benchmark": false} | |
| {"step": 6860, "tokens": 3596615680, "loss": 2.8625717163085938, "tokens_per_second": 963394.0123208913, "lr": 0.0015, "gradient_norm": 0.06395010650157928, "benchmark": false} | |
| {"step": 6880, "tokens": 3607101440, "loss": 2.8578704833984374, "tokens_per_second": 968473.5591813832, "lr": 0.0015, "gradient_norm": 0.06727306544780731, "benchmark": false} | |
| {"step": 6900, "tokens": 3617587200, "loss": 2.8689924240112306, "tokens_per_second": 968370.5294312906, "lr": 0.0015, "gradient_norm": 0.06945327669382095, "benchmark": false} | |
| {"step": 6920, "tokens": 3628072960, "loss": 2.9065435409545897, "tokens_per_second": 970516.5786547065, "lr": 0.0015, "gradient_norm": 0.0702224001288414, "benchmark": false} | |
| {"step": 6940, "tokens": 3638558720, "loss": 2.9081472396850585, "tokens_per_second": 973242.0789233029, "lr": 0.0015, "gradient_norm": 0.073855459690094, "benchmark": false} | |
| {"step": 6960, "tokens": 3649044480, "loss": 2.8929702758789064, "tokens_per_second": 964825.9607954713, "lr": 0.0015, "gradient_norm": 0.06530334800481796, "benchmark": false} | |
| {"step": 6980, "tokens": 3659530240, "loss": 2.8522924423217773, "tokens_per_second": 963148.4756019333, "lr": 0.0015, "gradient_norm": 0.07306957989931107, "benchmark": false} | |
| {"step": 7000, "tokens": 3670016000, "loss": 2.865734100341797, "tokens_per_second": 967669.6781736239, "lr": 0.0015, "gradient_norm": 0.0665232315659523, "benchmark": false} | |
| {"step": 7020, "tokens": 3680501760, "loss": 2.886398506164551, "tokens_per_second": 811736.6275375811, "lr": 0.0015, "gradient_norm": 0.0693461000919342, "benchmark": false} | |
| {"step": 7040, "tokens": 3690987520, "loss": 2.8966754913330077, "tokens_per_second": 972470.0973072138, "lr": 0.0015, "gradient_norm": 0.06701541692018509, "benchmark": false} | |
| {"step": 7060, "tokens": 3701473280, "loss": 2.89107666015625, "tokens_per_second": 968635.0652227454, "lr": 0.0015, "gradient_norm": 0.06736895442008972, "benchmark": false} | |
| {"step": 7080, "tokens": 3711959040, "loss": 2.884008026123047, "tokens_per_second": 972272.8872774077, "lr": 0.0015, "gradient_norm": 0.06326126307249069, "benchmark": false} | |
| {"step": 7100, "tokens": 3722444800, "loss": 2.858163070678711, "tokens_per_second": 969183.6295319292, "lr": 0.0015, "gradient_norm": 0.07230526953935623, "benchmark": false} | |
| {"step": 7120, "tokens": 3732930560, "loss": 2.923481750488281, "tokens_per_second": 974957.3125197034, "lr": 0.0015, "gradient_norm": 0.0695229098200798, "benchmark": false} | |
| {"step": 7140, "tokens": 3743416320, "loss": 2.8728736877441405, "tokens_per_second": 981099.4246456277, "lr": 0.0015, "gradient_norm": 0.06429187953472137, "benchmark": false} | |
| {"step": 7160, "tokens": 3753902080, "loss": 2.8980228424072267, "tokens_per_second": 981634.9433594308, "lr": 0.0015, "gradient_norm": 0.06506621092557907, "benchmark": false} | |
| {"step": 7180, "tokens": 3764387840, "loss": 2.8873054504394533, "tokens_per_second": 979406.8831577032, "lr": 0.0015, "gradient_norm": 0.06755528599023819, "benchmark": false} | |
| {"step": 7200, "tokens": 3774873600, "loss": 2.866831970214844, "tokens_per_second": 986759.778094445, "lr": 0.0015, "gradient_norm": 0.06299381703138351, "benchmark": false} | |
| {"step": 7220, "tokens": 3785359360, "loss": 2.8532447814941406, "tokens_per_second": 776216.4493618027, "lr": 0.0015, "gradient_norm": 0.06734848022460938, "benchmark": false} | |
| {"step": 7240, "tokens": 3795845120, "loss": 2.876798629760742, "tokens_per_second": 974332.1207831458, "lr": 0.0015, "gradient_norm": 0.06366383284330368, "benchmark": false} | |
| {"step": 7260, "tokens": 3806330880, "loss": 2.9060739517211913, "tokens_per_second": 977027.1860376433, "lr": 0.0015, "gradient_norm": 0.07509168237447739, "benchmark": false} | |
| {"step": 7280, "tokens": 3816816640, "loss": 2.8546142578125, "tokens_per_second": 974289.4220519006, "lr": 0.0015, "gradient_norm": 0.07117000967264175, "benchmark": false} | |
| {"step": 7300, "tokens": 3827302400, "loss": 2.8827434539794923, "tokens_per_second": 865159.9989154804, "lr": 0.0015, "gradient_norm": 0.06879030913114548, "benchmark": false} | |
| {"step": 7320, "tokens": 3837788160, "loss": 2.871865653991699, "tokens_per_second": 975514.32501485, "lr": 0.0015, "gradient_norm": 0.06815245747566223, "benchmark": false} | |
| {"step": 7340, "tokens": 3848273920, "loss": 2.880705451965332, "tokens_per_second": 972786.0887473279, "lr": 0.0015, "gradient_norm": 0.08301490545272827, "benchmark": false} | |
| {"step": 7360, "tokens": 3858759680, "loss": 2.8969520568847655, "tokens_per_second": 986498.8639737453, "lr": 0.0015, "gradient_norm": 0.0687498077750206, "benchmark": false} | |
| {"step": 7380, "tokens": 3869245440, "loss": 2.8997058868408203, "tokens_per_second": 972612.4868532382, "lr": 0.0015, "gradient_norm": 0.06531796604394913, "benchmark": false} | |
| {"step": 7400, "tokens": 3879731200, "loss": 2.858563041687012, "tokens_per_second": 962697.5638663234, "lr": 0.0015, "gradient_norm": 0.0642826184630394, "benchmark": false} | |
| {"step": 7420, "tokens": 3890216960, "loss": 2.890119171142578, "tokens_per_second": 836658.5075806839, "lr": 0.0015, "gradient_norm": 0.06829072535037994, "benchmark": false} | |
| {"step": 7440, "tokens": 3900702720, "loss": 2.876128387451172, "tokens_per_second": 965683.163393796, "lr": 0.0015, "gradient_norm": 0.06858838349580765, "benchmark": false} | |
| {"step": 7460, "tokens": 3911188480, "loss": 2.868077850341797, "tokens_per_second": 971001.3676481111, "lr": 0.0015, "gradient_norm": 0.0777946189045906, "benchmark": false} | |
| {"step": 7480, "tokens": 3921674240, "loss": 2.8896739959716795, "tokens_per_second": 971052.3362966019, "lr": 0.0015, "gradient_norm": 0.06711418926715851, "benchmark": false} | |
| {"step": 7500, "tokens": 3932160000, "loss": 2.8810169219970705, "tokens_per_second": 833273.9147864264, "lr": 0.0015, "gradient_norm": 0.06997272372245789, "benchmark": false} | |
| {"step": 7520, "tokens": 3942645760, "loss": 2.8911417007446287, "tokens_per_second": 858002.5052553657, "lr": 0.0015, "gradient_norm": 0.07078112661838531, "benchmark": false} | |
| {"step": 7540, "tokens": 3953131520, "loss": 2.867593765258789, "tokens_per_second": 992329.0947803116, "lr": 0.0015, "gradient_norm": 0.07130780071020126, "benchmark": false} | |
| {"step": 7560, "tokens": 3963617280, "loss": 2.8703800201416017, "tokens_per_second": 981001.7008508949, "lr": 0.0015, "gradient_norm": 0.07841914147138596, "benchmark": false} | |
| {"step": 7580, "tokens": 3974103040, "loss": 2.8924484252929688, "tokens_per_second": 983234.1127777771, "lr": 0.0015, "gradient_norm": 0.06483935564756393, "benchmark": false} | |
| {"step": 7600, "tokens": 3984588800, "loss": 2.863667297363281, "tokens_per_second": 986351.7749659457, "lr": 0.0015, "gradient_norm": 0.07615407556295395, "benchmark": false} | |
| {"step": 7620, "tokens": 3995074560, "loss": 2.8453487396240233, "tokens_per_second": 981280.9111615706, "lr": 0.0015, "gradient_norm": 0.07330675423145294, "benchmark": false} | |
| {"step": 7640, "tokens": 4005560320, "loss": 2.841605567932129, "tokens_per_second": 983512.7938787469, "lr": 0.0015, "gradient_norm": 0.07725579291582108, "benchmark": false} | |
| {"step": 7660, "tokens": 4016046080, "loss": 2.852851676940918, "tokens_per_second": 945151.2415072371, "lr": 0.0015, "gradient_norm": 0.07808933407068253, "benchmark": false} | |
| {"step": 7680, "tokens": 4026531840, "loss": 2.84686222076416, "tokens_per_second": 973782.0071222817, "lr": 0.0015, "gradient_norm": 0.06319031119346619, "benchmark": false} | |
| {"step": 7700, "tokens": 4037017600, "loss": 2.8660089492797853, "tokens_per_second": 841781.933211812, "lr": 0.0015, "gradient_norm": 0.07007475197315216, "benchmark": false} | |
| {"step": 7720, "tokens": 4047503360, "loss": 2.874739646911621, "tokens_per_second": 984181.2690563014, "lr": 0.0015, "gradient_norm": 0.06801772862672806, "benchmark": false} | |
| {"step": 7740, "tokens": 4057989120, "loss": 2.8385156631469726, "tokens_per_second": 990940.1191937703, "lr": 0.0015, "gradient_norm": 0.07283826172351837, "benchmark": false} | |
| {"step": 7760, "tokens": 4068474880, "loss": 2.859704780578613, "tokens_per_second": 981771.1931191648, "lr": 0.0015, "gradient_norm": 0.06433486193418503, "benchmark": false} | |
| {"step": 7780, "tokens": 4078960640, "loss": 2.869442939758301, "tokens_per_second": 985333.7092303191, "lr": 0.0015, "gradient_norm": 0.07301727682352066, "benchmark": false} | |
| {"step": 7800, "tokens": 4089446400, "loss": 2.882038688659668, "tokens_per_second": 991926.6644832704, "lr": 0.0015, "gradient_norm": 0.06702107191085815, "benchmark": false} | |
| {"step": 7820, "tokens": 4099932160, "loss": 2.8708444595336915, "tokens_per_second": 983395.4496681396, "lr": 0.0015, "gradient_norm": 0.07940774410963058, "benchmark": false} | |
| {"step": 7840, "tokens": 4110417920, "loss": 2.8780664443969726, "tokens_per_second": 978333.9763218275, "lr": 0.0015, "gradient_norm": 0.06969086825847626, "benchmark": false} | |
| {"step": 7860, "tokens": 4120903680, "loss": 2.8760910034179688, "tokens_per_second": 978431.0952770986, "lr": 0.0015, "gradient_norm": 0.07081884145736694, "benchmark": false} | |
| {"step": 7880, "tokens": 4131389440, "loss": 2.8618162155151365, "tokens_per_second": 978230.4771587944, "lr": 0.0015, "gradient_norm": 0.08222915232181549, "benchmark": false} | |
| {"step": 7900, "tokens": 4141875200, "loss": 2.8634958267211914, "tokens_per_second": 982325.4681529441, "lr": 0.0015, "gradient_norm": 0.07007068395614624, "benchmark": false} | |
| {"step": 7920, "tokens": 4152360960, "loss": 2.853188133239746, "tokens_per_second": 975227.7228349362, "lr": 0.0015, "gradient_norm": 0.07613815367221832, "benchmark": false} | |
| {"step": 7940, "tokens": 4162846720, "loss": 2.8642766952514647, "tokens_per_second": 973947.4194234799, "lr": 0.0015, "gradient_norm": 0.07104819267988205, "benchmark": false} | |
| {"step": 7960, "tokens": 4173332480, "loss": 2.85324649810791, "tokens_per_second": 978055.0444066898, "lr": 0.0015, "gradient_norm": 0.07692700624465942, "benchmark": false} | |
| {"step": 7980, "tokens": 4183818240, "loss": 2.8597362518310545, "tokens_per_second": 976117.0131650119, "lr": 0.0015, "gradient_norm": 0.07403507828712463, "benchmark": false} | |
| {"step": 8000, "tokens": 4194304000, "loss": 2.8754581451416015, "tokens_per_second": 992788.4029002639, "lr": 0.0015, "gradient_norm": 0.06957851350307465, "benchmark": false} | |
| {"step": 8020, "tokens": 4204789760, "loss": 2.8420690536499023, "tokens_per_second": 837867.9176074439, "lr": 0.0015, "gradient_norm": 0.07526803761720657, "benchmark": false} | |
| {"step": 8040, "tokens": 4215275520, "loss": 2.8559471130371095, "tokens_per_second": 983853.4840581511, "lr": 0.0015, "gradient_norm": 0.08585216850042343, "benchmark": false} | |
| {"step": 8060, "tokens": 4225761280, "loss": 2.8896697998046874, "tokens_per_second": 989730.2216739019, "lr": 0.0015, "gradient_norm": 0.06958837062120438, "benchmark": false} | |
| {"step": 8080, "tokens": 4236247040, "loss": 2.832368087768555, "tokens_per_second": 986211.1964923269, "lr": 0.0015, "gradient_norm": 0.06925537437200546, "benchmark": false} | |
| {"step": 8100, "tokens": 4246732800, "loss": 2.842477226257324, "tokens_per_second": 990481.1764232212, "lr": 0.0015, "gradient_norm": 0.08142078667879105, "benchmark": false} | |
| {"step": 8120, "tokens": 4257218560, "loss": 2.865599250793457, "tokens_per_second": 991851.2025152362, "lr": 0.0015, "gradient_norm": 0.06867492944002151, "benchmark": false} | |
| {"step": 8140, "tokens": 4267704320, "loss": 2.8421567916870116, "tokens_per_second": 989766.1020043022, "lr": 0.0015, "gradient_norm": 0.07502865791320801, "benchmark": false} | |
| {"step": 8160, "tokens": 4278190080, "loss": 2.8417640686035157, "tokens_per_second": 825292.3879032658, "lr": 0.0015, "gradient_norm": 0.07735702395439148, "benchmark": false} | |
| {"step": 8180, "tokens": 4288675840, "loss": 2.839097023010254, "tokens_per_second": 987625.738830853, "lr": 0.0015, "gradient_norm": 0.07167414575815201, "benchmark": false} | |
| {"step": 8200, "tokens": 4299161600, "loss": 2.8504922866821287, "tokens_per_second": 987199.328436592, "lr": 0.0015, "gradient_norm": 0.07969453930854797, "benchmark": false} | |
| {"step": 8220, "tokens": 4309647360, "loss": 2.8941909790039064, "tokens_per_second": 984853.9615494516, "lr": 0.0015, "gradient_norm": 0.07546231150627136, "benchmark": false} | |
| {"step": 8240, "tokens": 4320133120, "loss": 2.87431640625, "tokens_per_second": 984347.6630434011, "lr": 0.0015, "gradient_norm": 0.06595153361558914, "benchmark": false} | |
| {"step": 8260, "tokens": 4330618880, "loss": 2.901999855041504, "tokens_per_second": 945021.4387785712, "lr": 0.0015, "gradient_norm": 0.07873459160327911, "benchmark": false} | |
| {"step": 8280, "tokens": 4341104640, "loss": 2.8443761825561524, "tokens_per_second": 978898.542667765, "lr": 0.0015, "gradient_norm": 0.0756574273109436, "benchmark": false} | |
| {"step": 8300, "tokens": 4351590400, "loss": 2.863620948791504, "tokens_per_second": 984564.5346263158, "lr": 0.0015, "gradient_norm": 0.22140026092529297, "benchmark": false} | |
| {"step": 8320, "tokens": 4362076160, "loss": 2.8651077270507814, "tokens_per_second": 990403.7086676916, "lr": 0.0015, "gradient_norm": 0.08052444458007812, "benchmark": false} | |
| {"step": 8340, "tokens": 4372561920, "loss": 2.852044677734375, "tokens_per_second": 854154.1549039799, "lr": 0.0015, "gradient_norm": 0.08032067865133286, "benchmark": false} | |
| {"step": 8360, "tokens": 4383047680, "loss": 2.8418451309204102, "tokens_per_second": 980239.3377897158, "lr": 0.0015, "gradient_norm": 0.07009512186050415, "benchmark": false} | |
| {"step": 8380, "tokens": 4393533440, "loss": 2.840165710449219, "tokens_per_second": 988014.5265202852, "lr": 0.0015, "gradient_norm": 0.07453550398349762, "benchmark": false} | |
| {"step": 8400, "tokens": 4404019200, "loss": 2.865531349182129, "tokens_per_second": 839928.994479502, "lr": 0.0015, "gradient_norm": 0.07409143447875977, "benchmark": false} | |
| {"step": 8420, "tokens": 4414504960, "loss": 2.824263000488281, "tokens_per_second": 976282.8477343371, "lr": 0.0015, "gradient_norm": 0.07757251709699631, "benchmark": false} | |
| {"step": 8440, "tokens": 4424990720, "loss": 2.8189924240112303, "tokens_per_second": 983180.1213848125, "lr": 0.0015, "gradient_norm": 0.07665544003248215, "benchmark": false} | |
| {"step": 8460, "tokens": 4435476480, "loss": 2.8676340103149416, "tokens_per_second": 930712.393301377, "lr": 0.0015, "gradient_norm": 0.06544634699821472, "benchmark": false} | |
| {"step": 8480, "tokens": 4445962240, "loss": 2.845271682739258, "tokens_per_second": 996521.2859972045, "lr": 0.0015, "gradient_norm": 0.0774340033531189, "benchmark": false} | |
| {"step": 8500, "tokens": 4456448000, "loss": 2.8363792419433596, "tokens_per_second": 987704.7458042043, "lr": 0.0015, "gradient_norm": 0.07551994174718857, "benchmark": false} | |
| {"step": 8520, "tokens": 4466933760, "loss": 2.87451286315918, "tokens_per_second": 831144.4913827988, "lr": 0.0015, "gradient_norm": 0.07500536739826202, "benchmark": false} | |
| {"step": 8540, "tokens": 4477419520, "loss": 2.8735151290893555, "tokens_per_second": 980860.3832116079, "lr": 0.0015, "gradient_norm": 0.07712480425834656, "benchmark": false} | |
| {"step": 8560, "tokens": 4487905280, "loss": 2.8743804931640624, "tokens_per_second": 989434.2025171588, "lr": 0.0015, "gradient_norm": 0.07578735798597336, "benchmark": false} | |
| {"step": 8580, "tokens": 4498391040, "loss": 2.8719303131103517, "tokens_per_second": 996385.3052255794, "lr": 0.0015, "gradient_norm": 0.07415588945150375, "benchmark": false} | |
| {"step": 8600, "tokens": 4508876800, "loss": 2.8513208389282227, "tokens_per_second": 817336.110214322, "lr": 0.0015, "gradient_norm": 0.07281629741191864, "benchmark": false} | |
| {"step": 8620, "tokens": 4519362560, "loss": 2.851582336425781, "tokens_per_second": 981862.5869522684, "lr": 0.0015, "gradient_norm": 0.07156715542078018, "benchmark": false} | |
| {"step": 8640, "tokens": 4529848320, "loss": 2.846792793273926, "tokens_per_second": 983676.0638463337, "lr": 0.0015, "gradient_norm": 0.06907733529806137, "benchmark": false} | |
| {"step": 8660, "tokens": 4540334080, "loss": 2.841667366027832, "tokens_per_second": 981499.4644520271, "lr": 0.0015, "gradient_norm": 0.07901810854673386, "benchmark": false} | |
| {"step": 8680, "tokens": 4550819840, "loss": 2.8558382034301757, "tokens_per_second": 985707.6447773305, "lr": 0.0015, "gradient_norm": 0.07771660387516022, "benchmark": false} | |
| {"step": 8700, "tokens": 4561305600, "loss": 2.8630804061889648, "tokens_per_second": 995487.8833157328, "lr": 0.0015, "gradient_norm": 0.08134394139051437, "benchmark": false} | |
| {"step": 8720, "tokens": 4571791360, "loss": 2.8511684417724608, "tokens_per_second": 987061.442449505, "lr": 0.0015, "gradient_norm": 0.07659624516963959, "benchmark": false} | |
| {"step": 8740, "tokens": 4582277120, "loss": 2.8440793991088866, "tokens_per_second": 985376.0161414589, "lr": 0.0015, "gradient_norm": 0.08334780484437943, "benchmark": false} | |
| {"step": 8760, "tokens": 4592762880, "loss": 2.8465591430664063, "tokens_per_second": 980278.3504606036, "lr": 0.0015, "gradient_norm": 0.07243814319372177, "benchmark": false} | |
| {"step": 8780, "tokens": 4603248640, "loss": 2.8538890838623048, "tokens_per_second": 979125.2512634053, "lr": 0.0015, "gradient_norm": 0.07321111112833023, "benchmark": false} | |
| {"step": 8800, "tokens": 4613734400, "loss": 2.801381492614746, "tokens_per_second": 950571.9755138988, "lr": 0.0015, "gradient_norm": 0.08444861322641373, "benchmark": false} | |
| {"step": 8820, "tokens": 4624220160, "loss": 2.876637077331543, "tokens_per_second": 981684.880754016, "lr": 0.0015, "gradient_norm": 0.0745430439710617, "benchmark": false} | |
| {"step": 8840, "tokens": 4634705920, "loss": 2.8507137298583984, "tokens_per_second": 979714.4990773012, "lr": 0.0015, "gradient_norm": 0.07116901129484177, "benchmark": false} | |
| {"step": 8860, "tokens": 4645191680, "loss": 2.861048126220703, "tokens_per_second": 987968.3009214861, "lr": 0.0015, "gradient_norm": 0.07557233422994614, "benchmark": false} | |
| {"step": 8880, "tokens": 4655677440, "loss": 2.858736038208008, "tokens_per_second": 973079.5058719201, "lr": 0.0015, "gradient_norm": 0.06807484477758408, "benchmark": false} | |
| {"step": 8900, "tokens": 4666163200, "loss": 2.825702667236328, "tokens_per_second": 970498.6386046646, "lr": 0.0015, "gradient_norm": 0.08347911387681961, "benchmark": false} | |
| {"step": 8920, "tokens": 4676648960, "loss": 2.860857391357422, "tokens_per_second": 977166.5448684128, "lr": 0.0015, "gradient_norm": 0.08019018173217773, "benchmark": false} | |
| {"step": 8940, "tokens": 4687134720, "loss": 2.8259984970092775, "tokens_per_second": 973040.8571244124, "lr": 0.0015, "gradient_norm": 0.0780382826924324, "benchmark": false} | |
| {"step": 8960, "tokens": 4697620480, "loss": 2.8529546737670897, "tokens_per_second": 969905.4493514767, "lr": 0.0015, "gradient_norm": 0.08122095465660095, "benchmark": false} | |
| {"step": 8980, "tokens": 4708106240, "loss": 2.840422821044922, "tokens_per_second": 972420.6085403181, "lr": 0.0015, "gradient_norm": 0.0813227966427803, "benchmark": false} | |
| {"step": 9000, "tokens": 4718592000, "loss": 2.819308853149414, "tokens_per_second": 984628.671317153, "lr": 0.0015, "gradient_norm": 0.07416989654302597, "benchmark": false} | |
| {"step": 9020, "tokens": 4729077760, "loss": 2.8245450973510744, "tokens_per_second": 835198.1153051325, "lr": 0.0015, "gradient_norm": 0.06911784410476685, "benchmark": false} | |
| {"step": 9040, "tokens": 4739563520, "loss": 2.861843490600586, "tokens_per_second": 989974.9290623281, "lr": 0.0015, "gradient_norm": 0.0898256003856659, "benchmark": false} | |
| {"step": 9060, "tokens": 4750049280, "loss": 2.8607154846191407, "tokens_per_second": 991137.133589742, "lr": 0.0015, "gradient_norm": 0.08151320368051529, "benchmark": false} | |
| {"step": 9080, "tokens": 4760535040, "loss": 2.8201387405395506, "tokens_per_second": 994661.0410152077, "lr": 0.0015, "gradient_norm": 0.07083109766244888, "benchmark": false} | |
| {"step": 9100, "tokens": 4771020800, "loss": 2.8585489273071287, "tokens_per_second": 987978.5250772969, "lr": 0.0015, "gradient_norm": 0.07310938835144043, "benchmark": false} | |
| {"step": 9120, "tokens": 4781506560, "loss": 2.799000549316406, "tokens_per_second": 942282.9368405933, "lr": 0.0015, "gradient_norm": 0.08472835272550583, "benchmark": false} | |
| {"step": 9140, "tokens": 4791992320, "loss": 2.851094436645508, "tokens_per_second": 986682.1377401277, "lr": 0.0015, "gradient_norm": 0.08907467126846313, "benchmark": false} | |
| {"step": 9160, "tokens": 4802478080, "loss": 2.8067934036254885, "tokens_per_second": 982621.4274778471, "lr": 0.0015, "gradient_norm": 0.07300791889429092, "benchmark": false} | |
| {"step": 9180, "tokens": 4812963840, "loss": 2.86877384185791, "tokens_per_second": 992005.5280940625, "lr": 0.0015, "gradient_norm": 0.07812537252902985, "benchmark": false} | |
| {"step": 9200, "tokens": 4823449600, "loss": 2.8002647399902343, "tokens_per_second": 982772.7353793365, "lr": 0.0015, "gradient_norm": 0.07580609619617462, "benchmark": false} | |
| {"step": 9220, "tokens": 4833935360, "loss": 2.851849365234375, "tokens_per_second": 983641.9685660396, "lr": 0.0015, "gradient_norm": 0.07275630533695221, "benchmark": false} | |
| {"step": 9240, "tokens": 4844421120, "loss": 2.8479354858398436, "tokens_per_second": 980203.1512061429, "lr": 0.0015, "gradient_norm": 0.07504432648420334, "benchmark": false} | |
| {"step": 9260, "tokens": 4854906880, "loss": 2.8347082138061523, "tokens_per_second": 985644.841678965, "lr": 0.0015, "gradient_norm": 0.07723763585090637, "benchmark": false} | |
| {"step": 9280, "tokens": 4865392640, "loss": 2.862448501586914, "tokens_per_second": 991354.2173912034, "lr": 0.0015, "gradient_norm": 0.07943837344646454, "benchmark": false} | |
| {"step": 9300, "tokens": 4875878400, "loss": 2.839870262145996, "tokens_per_second": 994936.0491028802, "lr": 0.0015, "gradient_norm": 0.07907235622406006, "benchmark": false} | |
| {"step": 9320, "tokens": 4886364160, "loss": 2.862621307373047, "tokens_per_second": 828296.652282496, "lr": 0.0015, "gradient_norm": 0.08029628545045853, "benchmark": false} | |
| {"step": 9340, "tokens": 4896849920, "loss": 2.830166244506836, "tokens_per_second": 984448.1173616562, "lr": 0.0015, "gradient_norm": 0.08212227374315262, "benchmark": false} | |
| {"step": 9360, "tokens": 4907335680, "loss": 2.8018823623657227, "tokens_per_second": 994725.7282176608, "lr": 0.0015, "gradient_norm": 0.08513061702251434, "benchmark": false} | |
| {"step": 9380, "tokens": 4917821440, "loss": 2.853571319580078, "tokens_per_second": 850195.0763547797, "lr": 0.0015, "gradient_norm": 0.08008779585361481, "benchmark": false} | |
| {"step": 9400, "tokens": 4928307200, "loss": 2.8335298538208007, "tokens_per_second": 993248.4697446765, "lr": 0.0015, "gradient_norm": 0.0721391960978508, "benchmark": false} | |
| {"step": 9420, "tokens": 4938792960, "loss": 2.834381866455078, "tokens_per_second": 814612.76481917, "lr": 0.0015, "gradient_norm": 0.08238670229911804, "benchmark": false} | |
| {"step": 9440, "tokens": 4949278720, "loss": 2.8389305114746093, "tokens_per_second": 990815.9948630648, "lr": 0.0015, "gradient_norm": 0.07424811273813248, "benchmark": false} | |
| {"step": 9460, "tokens": 4959764480, "loss": 2.836428642272949, "tokens_per_second": 984975.3316094908, "lr": 0.0015, "gradient_norm": 0.08083634823560715, "benchmark": false} | |
| {"step": 9480, "tokens": 4970250240, "loss": 2.838408279418945, "tokens_per_second": 993077.121682915, "lr": 0.0015, "gradient_norm": 0.08504550904035568, "benchmark": false} | |
| {"step": 9500, "tokens": 4980736000, "loss": 2.847154998779297, "tokens_per_second": 954012.1774107493, "lr": 0.0015, "gradient_norm": 0.08038152009248734, "benchmark": false} | |
| {"step": 9520, "tokens": 4991221760, "loss": 2.8305084228515627, "tokens_per_second": 840798.1068664312, "lr": 0.0015, "gradient_norm": 0.085055410861969, "benchmark": false} | |
| {"step": 9540, "tokens": 5001707520, "loss": 2.833781051635742, "tokens_per_second": 982512.4793784562, "lr": 0.0015, "gradient_norm": 0.08446768671274185, "benchmark": false} | |
| {"step": 9560, "tokens": 5012193280, "loss": 2.8237529754638673, "tokens_per_second": 989944.2442785497, "lr": 0.0015, "gradient_norm": 0.0901399552822113, "benchmark": false} | |
| {"step": 9580, "tokens": 5022679040, "loss": 2.8359748840332033, "tokens_per_second": 984694.8421158455, "lr": 0.0015, "gradient_norm": 0.08997666090726852, "benchmark": false} | |
| {"step": 9600, "tokens": 5033164800, "loss": 2.862395668029785, "tokens_per_second": 989213.3500881932, "lr": 0.0015, "gradient_norm": 0.07941855490207672, "benchmark": false} | |
| {"step": 9620, "tokens": 5043650560, "loss": 2.843942070007324, "tokens_per_second": 986878.7086835111, "lr": 0.0015, "gradient_norm": 0.09274707734584808, "benchmark": false} | |
| {"step": 9640, "tokens": 5054136320, "loss": 2.813098335266113, "tokens_per_second": 988178.6522051803, "lr": 0.0015, "gradient_norm": 0.0799412727355957, "benchmark": false} | |
| {"step": 9660, "tokens": 5064622080, "loss": 2.8647417068481444, "tokens_per_second": 981307.0211777195, "lr": 0.0015, "gradient_norm": 0.08347632735967636, "benchmark": false} | |
| {"step": 9680, "tokens": 5075107840, "loss": 2.8417198181152346, "tokens_per_second": 986008.0153022051, "lr": 0.0015, "gradient_norm": 0.07802063971757889, "benchmark": false} | |
| {"step": 9700, "tokens": 5085593600, "loss": 2.8191699981689453, "tokens_per_second": 978773.4608429419, "lr": 0.0015, "gradient_norm": 0.08184360712766647, "benchmark": false} | |
| {"step": 9720, "tokens": 5096079360, "loss": 2.831065559387207, "tokens_per_second": 987697.0014904509, "lr": 0.0015, "gradient_norm": 0.08197537809610367, "benchmark": false} | |
| {"step": 9740, "tokens": 5106565120, "loss": 2.8351741790771485, "tokens_per_second": 979224.4827687053, "lr": 0.0015, "gradient_norm": 0.07981396466493607, "benchmark": false} | |
| {"step": 9760, "tokens": 5117050880, "loss": 2.797874641418457, "tokens_per_second": 991582.5422850944, "lr": 0.0015, "gradient_norm": 0.08326350897550583, "benchmark": false} | |
| {"step": 9780, "tokens": 5127536640, "loss": 2.8271963119506838, "tokens_per_second": 986008.5456410954, "lr": 0.0015, "gradient_norm": 0.08673147112131119, "benchmark": false} | |
| {"step": 9800, "tokens": 5138022400, "loss": 2.8382144927978517, "tokens_per_second": 984137.6778921657, "lr": 0.0015, "gradient_norm": 0.08521495759487152, "benchmark": false} | |
| {"step": 9820, "tokens": 5148508160, "loss": 2.8308244705200196, "tokens_per_second": 985082.7007959478, "lr": 0.0015, "gradient_norm": 0.08817323297262192, "benchmark": false} | |
| {"step": 9840, "tokens": 5158993920, "loss": 2.82999324798584, "tokens_per_second": 982672.575529464, "lr": 0.0015, "gradient_norm": 0.08498471230268478, "benchmark": false} | |
| {"step": 9860, "tokens": 5169479680, "loss": 2.844025993347168, "tokens_per_second": 982925.0275054633, "lr": 0.0015, "gradient_norm": 0.07543990015983582, "benchmark": false} | |
| {"step": 9880, "tokens": 5179965440, "loss": 2.869939613342285, "tokens_per_second": 986261.972579164, "lr": 0.0015, "gradient_norm": 0.08497723937034607, "benchmark": false} | |
| {"step": 9900, "tokens": 5190451200, "loss": 2.78603515625, "tokens_per_second": 841882.0764118844, "lr": 0.0015, "gradient_norm": 0.08335985243320465, "benchmark": false} | |
| {"step": 9920, "tokens": 5200936960, "loss": 2.8068157196044923, "tokens_per_second": 995466.1046283207, "lr": 0.0015, "gradient_norm": 0.09151347726583481, "benchmark": false} | |
| {"step": 9940, "tokens": 5211422720, "loss": 2.83557071685791, "tokens_per_second": 988697.6764334616, "lr": 0.0015, "gradient_norm": 0.08406423777341843, "benchmark": false} | |
| {"step": 9960, "tokens": 5221908480, "loss": 2.83525390625, "tokens_per_second": 985306.7973998113, "lr": 0.0015, "gradient_norm": 0.07898715138435364, "benchmark": false} | |
| {"step": 9980, "tokens": 5232394240, "loss": 2.809004211425781, "tokens_per_second": 990607.4548488081, "lr": 0.0015, "gradient_norm": 0.07946421951055527, "benchmark": false} | |
| {"step": 10000, "tokens": 5242880000, "loss": 2.8216739654541017, "tokens_per_second": 986454.10697014, "lr": 0.0015, "gradient_norm": 0.08943367004394531, "benchmark": false} | |
| {"step": 10020, "tokens": 5253365760, "loss": 2.8265048980712892, "tokens_per_second": 852187.0333771141, "lr": 0.0015, "gradient_norm": 0.09247152507305145, "benchmark": false} | |
| {"step": 10040, "tokens": 5263851520, "loss": 2.8199321746826174, "tokens_per_second": 988591.5887100031, "lr": 0.0015, "gradient_norm": 0.07508964091539383, "benchmark": false} | |
| {"step": 10060, "tokens": 5274337280, "loss": 2.7843997955322264, "tokens_per_second": 947101.9980625706, "lr": 0.0015, "gradient_norm": 0.08978574723005295, "benchmark": false} | |
| {"step": 10080, "tokens": 5284823040, "loss": 2.838224983215332, "tokens_per_second": 984909.651803646, "lr": 0.0015, "gradient_norm": 0.08179404586553574, "benchmark": false} | |
| {"step": 10100, "tokens": 5295308800, "loss": 2.81591796875, "tokens_per_second": 990530.4185476906, "lr": 0.0015, "gradient_norm": 0.08106435835361481, "benchmark": false} | |
| {"step": 10120, "tokens": 5305794560, "loss": 2.832396697998047, "tokens_per_second": 982642.0552642384, "lr": 0.0015, "gradient_norm": 0.09130522608757019, "benchmark": false} | |
| {"step": 10140, "tokens": 5316280320, "loss": 2.820639419555664, "tokens_per_second": 986803.1495096853, "lr": 0.0015, "gradient_norm": 0.09140259772539139, "benchmark": false} | |
| {"step": 10160, "tokens": 5326766080, "loss": 2.789868927001953, "tokens_per_second": 979686.6949881349, "lr": 0.0015, "gradient_norm": 0.08715713769197464, "benchmark": false} | |
| {"step": 10180, "tokens": 5337251840, "loss": 2.8421859741210938, "tokens_per_second": 984502.7805344424, "lr": 0.0015, "gradient_norm": 0.07708703726530075, "benchmark": false} | |
| {"step": 10200, "tokens": 5347737600, "loss": 2.8034515380859375, "tokens_per_second": 983122.4985650905, "lr": 0.0015, "gradient_norm": 0.08698373287916183, "benchmark": false} | |
| {"step": 10220, "tokens": 5358223360, "loss": 2.853319549560547, "tokens_per_second": 982718.8029421372, "lr": 0.0015, "gradient_norm": 0.08624204248189926, "benchmark": false} | |
| {"step": 10240, "tokens": 5368709120, "loss": 2.8286865234375, "tokens_per_second": 985865.5225679349, "lr": 0.0015, "gradient_norm": 0.09393741190433502, "benchmark": false} | |
| {"step": 10260, "tokens": 5379194880, "loss": 2.8509103775024416, "tokens_per_second": 976147.3089979081, "lr": 0.0015, "gradient_norm": 0.07897111028432846, "benchmark": false} | |
| {"step": 10280, "tokens": 5389680640, "loss": 2.8219797134399416, "tokens_per_second": 990605.526727717, "lr": 0.0015, "gradient_norm": 0.09325108677148819, "benchmark": false} | |
| {"step": 10300, "tokens": 5400166400, "loss": 2.810519981384277, "tokens_per_second": 978871.487950141, "lr": 0.0015, "gradient_norm": 0.0911802127957344, "benchmark": false} | |
| {"step": 10320, "tokens": 5410652160, "loss": 2.8069557189941405, "tokens_per_second": 987821.0177871822, "lr": 0.0015, "gradient_norm": 0.09953997284173965, "benchmark": false} | |
| {"step": 10340, "tokens": 5421137920, "loss": 2.8397085189819338, "tokens_per_second": 981059.6521234467, "lr": 0.0015, "gradient_norm": 0.07839950919151306, "benchmark": false} | |
| {"step": 10360, "tokens": 5431623680, "loss": 2.8285579681396484, "tokens_per_second": 787943.7196270576, "lr": 0.0015, "gradient_norm": 0.08077672123908997, "benchmark": false} | |
| {"step": 10380, "tokens": 5442109440, "loss": 2.800924873352051, "tokens_per_second": 991009.8168252638, "lr": 0.0015, "gradient_norm": 0.09587293118238449, "benchmark": false} | |
| {"step": 10400, "tokens": 5452595200, "loss": 2.8579668045043944, "tokens_per_second": 950109.330448536, "lr": 0.0015, "gradient_norm": 0.10475710779428482, "benchmark": false} | |
| {"step": 10420, "tokens": 5463080960, "loss": 2.7652172088623046, "tokens_per_second": 945194.5502981044, "lr": 0.0015, "gradient_norm": 0.18762581050395966, "benchmark": false} | |
| {"step": 10440, "tokens": 5473566720, "loss": 2.827962303161621, "tokens_per_second": 986773.3960231631, "lr": 0.0015, "gradient_norm": 0.09605003893375397, "benchmark": false} | |
| {"step": 10460, "tokens": 5484052480, "loss": 2.815045928955078, "tokens_per_second": 952905.9028428236, "lr": 0.0015, "gradient_norm": 0.09283770620822906, "benchmark": false} | |
| {"step": 10480, "tokens": 5494538240, "loss": 2.8141708374023438, "tokens_per_second": 949083.8431879994, "lr": 0.0015, "gradient_norm": 0.07634645700454712, "benchmark": false} | |
| {"step": 10500, "tokens": 5505024000, "loss": 2.8515233993530273, "tokens_per_second": 977063.5599389477, "lr": 0.0015, "gradient_norm": 0.09103018790483475, "benchmark": false} | |
| {"step": 10520, "tokens": 5515509760, "loss": 2.8071733474731446, "tokens_per_second": 856841.5024644048, "lr": 0.0015, "gradient_norm": 0.08776334673166275, "benchmark": false} | |
| {"step": 10540, "tokens": 5525995520, "loss": 2.800252151489258, "tokens_per_second": 981046.9636411724, "lr": 0.0015, "gradient_norm": 0.08854340016841888, "benchmark": false} | |
| {"step": 10560, "tokens": 5536481280, "loss": 2.83626708984375, "tokens_per_second": 983463.9553301485, "lr": 0.0015, "gradient_norm": 0.10051717609167099, "benchmark": false} | |
| {"step": 10580, "tokens": 5546967040, "loss": 2.828484535217285, "tokens_per_second": 986980.0541079927, "lr": 0.0015, "gradient_norm": 0.0855020210146904, "benchmark": false} | |
| {"step": 10600, "tokens": 5557452800, "loss": 2.812819480895996, "tokens_per_second": 979840.0683955124, "lr": 0.0015, "gradient_norm": 0.08613714575767517, "benchmark": false} | |
| {"step": 10620, "tokens": 5567938560, "loss": 2.830562210083008, "tokens_per_second": 980664.4530554473, "lr": 0.0015, "gradient_norm": 0.08211514353752136, "benchmark": false} | |
| {"step": 10640, "tokens": 5578424320, "loss": 2.814869689941406, "tokens_per_second": 985124.8025264748, "lr": 0.0015, "gradient_norm": 0.08745996654033661, "benchmark": false} | |
| {"step": 10660, "tokens": 5588910080, "loss": 2.798888397216797, "tokens_per_second": 987502.2586735309, "lr": 0.0015, "gradient_norm": 0.09800267219543457, "benchmark": false} | |
| {"step": 10680, "tokens": 5599395840, "loss": 2.848857116699219, "tokens_per_second": 983825.3047975254, "lr": 0.0015, "gradient_norm": 0.09263648092746735, "benchmark": false} | |
| {"step": 10700, "tokens": 5609881600, "loss": 2.8285358428955076, "tokens_per_second": 987688.8515747183, "lr": 0.0015, "gradient_norm": 0.08248348534107208, "benchmark": false} | |
| {"step": 10720, "tokens": 5620367360, "loss": 2.8194692611694334, "tokens_per_second": 979027.4335736551, "lr": 0.0015, "gradient_norm": 0.0825863778591156, "benchmark": false} | |
| {"step": 10740, "tokens": 5630853120, "loss": 2.8156925201416017, "tokens_per_second": 982282.8184015505, "lr": 0.0015, "gradient_norm": 0.09241942316293716, "benchmark": false} | |
| {"step": 10760, "tokens": 5641338880, "loss": 2.8242303848266603, "tokens_per_second": 984336.5119750907, "lr": 0.0015, "gradient_norm": 0.10548762232065201, "benchmark": false} | |
| {"step": 10780, "tokens": 5651824640, "loss": 2.7800342559814455, "tokens_per_second": 972867.9189022188, "lr": 0.0015, "gradient_norm": 0.09264153242111206, "benchmark": false} | |
| {"step": 10800, "tokens": 5662310400, "loss": 2.7960636138916017, "tokens_per_second": 977952.7159714339, "lr": 0.0015, "gradient_norm": 0.08692364394664764, "benchmark": false} | |
| {"step": 10820, "tokens": 5672796160, "loss": 2.8444904327392577, "tokens_per_second": 974805.1679641892, "lr": 0.0015, "gradient_norm": 0.09104796499013901, "benchmark": false} | |
| {"step": 10840, "tokens": 5683281920, "loss": 2.8026609420776367, "tokens_per_second": 981937.7110312894, "lr": 0.0015, "gradient_norm": 0.08739808946847916, "benchmark": false} | |
| {"step": 10860, "tokens": 5693767680, "loss": 2.803538703918457, "tokens_per_second": 982360.8441548214, "lr": 0.0015, "gradient_norm": 0.09446439892053604, "benchmark": false} | |
| {"step": 10880, "tokens": 5704253440, "loss": 2.7854774475097654, "tokens_per_second": 975790.516096533, "lr": 0.0015, "gradient_norm": 0.09459560364484787, "benchmark": false} | |
| {"step": 10900, "tokens": 5714739200, "loss": 2.812674140930176, "tokens_per_second": 979639.9281287481, "lr": 0.0015, "gradient_norm": 0.09237074851989746, "benchmark": false} | |
| {"step": 10920, "tokens": 5725224960, "loss": 2.792404556274414, "tokens_per_second": 978454.9943567028, "lr": 0.0015, "gradient_norm": 0.09565896540880203, "benchmark": false} | |
| {"step": 10940, "tokens": 5735710720, "loss": 2.8052703857421877, "tokens_per_second": 980657.4605480039, "lr": 0.0015, "gradient_norm": 0.0964113250374794, "benchmark": false} | |
| {"step": 10960, "tokens": 5746196480, "loss": 2.814346504211426, "tokens_per_second": 977156.1872256437, "lr": 0.0015, "gradient_norm": 0.08051484823226929, "benchmark": false} | |
| {"step": 10980, "tokens": 5756682240, "loss": 2.8020746231079103, "tokens_per_second": 977162.6497957591, "lr": 0.0015, "gradient_norm": 0.11768177151679993, "benchmark": false} | |
| {"step": 11000, "tokens": 5767168000, "loss": 2.8348876953125, "tokens_per_second": 987974.7411373939, "lr": 0.0015, "gradient_norm": 0.09453051537275314, "benchmark": false} | |
| {"step": 11020, "tokens": 5777653760, "loss": 2.8067771911621096, "tokens_per_second": 768149.5252021329, "lr": 0.0015, "gradient_norm": 0.09996025264263153, "benchmark": false} | |
| {"step": 11040, "tokens": 5788139520, "loss": 2.7988447189331054, "tokens_per_second": 974332.5963619035, "lr": 0.0015, "gradient_norm": 0.09607052057981491, "benchmark": false} | |
| {"step": 11060, "tokens": 5798625280, "loss": 2.799824905395508, "tokens_per_second": 985249.2922863617, "lr": 0.0015, "gradient_norm": 0.09087151288986206, "benchmark": false} | |
| {"step": 11080, "tokens": 5809111040, "loss": 2.814681816101074, "tokens_per_second": 971428.3503853546, "lr": 0.0015, "gradient_norm": 0.09317014366388321, "benchmark": false} | |
| {"step": 11100, "tokens": 5819596800, "loss": 2.8190017700195313, "tokens_per_second": 969915.2315686354, "lr": 0.0015, "gradient_norm": 0.08898317813873291, "benchmark": false} | |
| {"step": 11120, "tokens": 5830082560, "loss": 2.807066535949707, "tokens_per_second": 973064.1389007025, "lr": 0.0015, "gradient_norm": 0.10078496485948563, "benchmark": false} | |
| {"step": 11140, "tokens": 5840568320, "loss": 2.795416831970215, "tokens_per_second": 975718.5095579139, "lr": 0.0015, "gradient_norm": 0.10522713512182236, "benchmark": false} | |
| {"step": 11160, "tokens": 5851054080, "loss": 2.820310592651367, "tokens_per_second": 977567.7360815194, "lr": 0.0015, "gradient_norm": 0.10151451826095581, "benchmark": false} | |
| {"step": 11180, "tokens": 5861539840, "loss": 2.809165191650391, "tokens_per_second": 985815.5093693133, "lr": 0.0015, "gradient_norm": 0.09285029768943787, "benchmark": false} | |
| {"step": 11200, "tokens": 5872025600, "loss": 2.811720848083496, "tokens_per_second": 979650.1506031567, "lr": 0.0015, "gradient_norm": 0.11280045658349991, "benchmark": false} | |
| {"step": 11220, "tokens": 5882511360, "loss": 2.781954765319824, "tokens_per_second": 981459.3504546183, "lr": 0.0015, "gradient_norm": 0.09573668986558914, "benchmark": false} | |
| {"step": 11240, "tokens": 5892997120, "loss": 2.815509033203125, "tokens_per_second": 974762.4417187519, "lr": 0.0015, "gradient_norm": 0.09371116757392883, "benchmark": false} | |
| {"step": 11260, "tokens": 5903482880, "loss": 2.839525032043457, "tokens_per_second": 981038.8163443952, "lr": 0.0015, "gradient_norm": 0.0912681445479393, "benchmark": false} | |
| {"step": 11280, "tokens": 5913968640, "loss": 2.8201906204223635, "tokens_per_second": 970558.7912901905, "lr": 0.0015, "gradient_norm": 0.10620073229074478, "benchmark": false} | |
| {"step": 11300, "tokens": 5924454400, "loss": 2.8014726638793945, "tokens_per_second": 982296.9167814093, "lr": 0.0015, "gradient_norm": 0.10287808626890182, "benchmark": false} | |
| {"step": 11320, "tokens": 5934940160, "loss": 2.7945919036865234, "tokens_per_second": 989193.1315462568, "lr": 0.0015, "gradient_norm": 0.09983932971954346, "benchmark": false} | |
| {"step": 11340, "tokens": 5945425920, "loss": 2.818609619140625, "tokens_per_second": 854966.0481801034, "lr": 0.0015, "gradient_norm": 0.11522824317216873, "benchmark": false} | |
| {"step": 11360, "tokens": 5955911680, "loss": 2.8310144424438475, "tokens_per_second": 834834.1502507858, "lr": 0.0015, "gradient_norm": 0.09774244576692581, "benchmark": false} | |
| {"step": 11380, "tokens": 5966397440, "loss": 2.8156902313232424, "tokens_per_second": 942087.1261175704, "lr": 0.0015, "gradient_norm": 0.09635335952043533, "benchmark": false} | |
| {"step": 11400, "tokens": 5976883200, "loss": 2.7935056686401367, "tokens_per_second": 980674.9932491669, "lr": 0.0015, "gradient_norm": 0.09701837599277496, "benchmark": false} | |
| {"step": 11420, "tokens": 5987368960, "loss": 2.8377561569213867, "tokens_per_second": 948808.851537345, "lr": 0.0015, "gradient_norm": 0.09571969509124756, "benchmark": false} | |
| {"step": 11440, "tokens": 5997854720, "loss": 2.805942344665527, "tokens_per_second": 987704.7090549648, "lr": 0.0015, "gradient_norm": 0.09553902596235275, "benchmark": false} | |
| {"step": 11460, "tokens": 6008340480, "loss": 2.7863759994506836, "tokens_per_second": 796106.8890489151, "lr": 0.0015, "gradient_norm": 0.09852088242769241, "benchmark": false} | |
| {"step": 11480, "tokens": 6018826240, "loss": 2.799390411376953, "tokens_per_second": 982497.6750645757, "lr": 0.0015, "gradient_norm": 0.08827927708625793, "benchmark": false} | |
| {"step": 11500, "tokens": 6029312000, "loss": 2.8012603759765624, "tokens_per_second": 979171.7305241188, "lr": 0.0015, "gradient_norm": 0.0993845984339714, "benchmark": false} | |
| {"step": 11520, "tokens": 6039797760, "loss": 2.806071090698242, "tokens_per_second": 857456.8514258185, "lr": 0.0015, "gradient_norm": 0.0953318327665329, "benchmark": false} | |
| {"step": 11540, "tokens": 6050283520, "loss": 2.789183235168457, "tokens_per_second": 988145.2765951087, "lr": 0.0015, "gradient_norm": 0.09696745127439499, "benchmark": false} | |
| {"step": 11560, "tokens": 6060769280, "loss": 2.8085102081298827, "tokens_per_second": 983786.260167913, "lr": 0.0015, "gradient_norm": 0.10099394619464874, "benchmark": false} | |
| {"step": 11580, "tokens": 6071255040, "loss": 2.830649185180664, "tokens_per_second": 996520.4041977315, "lr": 0.0015, "gradient_norm": 0.11824902892112732, "benchmark": false} | |
| {"step": 11600, "tokens": 6081740800, "loss": 2.8042892456054687, "tokens_per_second": 985062.7638370555, "lr": 0.0015, "gradient_norm": 0.09543195366859436, "benchmark": false} | |
| {"step": 11620, "tokens": 6092226560, "loss": 2.782301139831543, "tokens_per_second": 991400.891897373, "lr": 0.0015, "gradient_norm": 0.1080298125743866, "benchmark": false} | |
| {"step": 11640, "tokens": 6102712320, "loss": 2.811306381225586, "tokens_per_second": 985936.3788358414, "lr": 0.0015, "gradient_norm": 0.09161733835935593, "benchmark": false} | |
| {"step": 11660, "tokens": 6113198080, "loss": 2.8197975158691406, "tokens_per_second": 992964.3221761647, "lr": 0.0015, "gradient_norm": 0.09041512757539749, "benchmark": false} | |
| {"step": 11680, "tokens": 6123683840, "loss": 2.7789400100708006, "tokens_per_second": 982425.1504099895, "lr": 0.0015, "gradient_norm": 0.10277896374464035, "benchmark": false} | |
| {"step": 11700, "tokens": 6134169600, "loss": 2.808932876586914, "tokens_per_second": 977392.8435753412, "lr": 0.0015, "gradient_norm": 0.12181688845157623, "benchmark": false} | |
| {"step": 11720, "tokens": 6144655360, "loss": 2.798422431945801, "tokens_per_second": 980918.0165294112, "lr": 0.0015, "gradient_norm": 0.10683136433362961, "benchmark": false} | |
| {"step": 11740, "tokens": 6155141120, "loss": 2.830831527709961, "tokens_per_second": 976757.4708301218, "lr": 0.0015, "gradient_norm": 0.0975671336054802, "benchmark": false} | |
| {"step": 11760, "tokens": 6165626880, "loss": 2.806202697753906, "tokens_per_second": 986801.6854679787, "lr": 0.0015, "gradient_norm": 0.09472610801458359, "benchmark": false} | |
| {"step": 11780, "tokens": 6176112640, "loss": 2.834814262390137, "tokens_per_second": 982357.5047571787, "lr": 0.0015, "gradient_norm": 0.09356431663036346, "benchmark": false} | |
| {"step": 11800, "tokens": 6186598400, "loss": 2.7874208450317384, "tokens_per_second": 980152.1211710438, "lr": 0.0015, "gradient_norm": 0.10294467955827713, "benchmark": false} | |
| {"step": 11820, "tokens": 6197084160, "loss": 2.7978897094726562, "tokens_per_second": 992943.4708471717, "lr": 0.0015, "gradient_norm": 0.09639257192611694, "benchmark": false} | |
| {"step": 11840, "tokens": 6207569920, "loss": 2.758690071105957, "tokens_per_second": 993519.8502188604, "lr": 0.0015, "gradient_norm": 0.10271412879228592, "benchmark": false} | |
| {"step": 11860, "tokens": 6218055680, "loss": 2.8122493743896486, "tokens_per_second": 976721.7935053379, "lr": 0.0015, "gradient_norm": 0.09113288670778275, "benchmark": false} | |
| {"step": 11880, "tokens": 6228541440, "loss": 2.8010377883911133, "tokens_per_second": 983710.669248456, "lr": 0.0015, "gradient_norm": 0.21072672307491302, "benchmark": false} | |
| {"step": 11900, "tokens": 6239027200, "loss": 2.784419059753418, "tokens_per_second": 988464.0306157828, "lr": 0.0015, "gradient_norm": 0.0965396985411644, "benchmark": false} | |
| {"step": 11920, "tokens": 6249512960, "loss": 2.772012138366699, "tokens_per_second": 981498.9249846302, "lr": 0.0015, "gradient_norm": 0.09328988939523697, "benchmark": false} | |
| {"step": 11940, "tokens": 6259998720, "loss": 2.7949031829833983, "tokens_per_second": 985018.5760938062, "lr": 0.0015, "gradient_norm": 0.09925438463687897, "benchmark": false} | |
| {"step": 11960, "tokens": 6270484480, "loss": 2.800166893005371, "tokens_per_second": 989799.1647813246, "lr": 0.0015, "gradient_norm": 0.1009145975112915, "benchmark": false} | |
| {"step": 11980, "tokens": 6280970240, "loss": 2.8234445571899416, "tokens_per_second": 847536.274677034, "lr": 0.0015, "gradient_norm": 0.10739849507808685, "benchmark": false} | |
| {"step": 12000, "tokens": 6291456000, "loss": 2.754237174987793, "tokens_per_second": 987605.9263153236, "lr": 0.0015, "gradient_norm": 0.10888316482305527, "benchmark": false} | |
| {"step": 12020, "tokens": 6301941760, "loss": 2.8089101791381834, "tokens_per_second": 822342.5921110236, "lr": 0.0015, "gradient_norm": 0.10958659648895264, "benchmark": false} | |
| {"step": 12040, "tokens": 6312427520, "loss": 2.8103054046630858, "tokens_per_second": 979209.831793374, "lr": 0.0015, "gradient_norm": 0.08929789811372757, "benchmark": false} | |
| {"step": 12060, "tokens": 6322913280, "loss": 2.8015066146850587, "tokens_per_second": 983909.7219845104, "lr": 0.0015, "gradient_norm": 0.0960715189576149, "benchmark": false} | |
| {"step": 12080, "tokens": 6333399040, "loss": 2.789211654663086, "tokens_per_second": 986576.222179265, "lr": 0.0015, "gradient_norm": 0.09555419534444809, "benchmark": false} | |
| {"step": 12100, "tokens": 6343884800, "loss": 2.779342842102051, "tokens_per_second": 839032.7184058921, "lr": 0.0015, "gradient_norm": 0.11269618570804596, "benchmark": false} | |
| {"step": 12120, "tokens": 6354370560, "loss": 2.8438695907592773, "tokens_per_second": 978023.8552978459, "lr": 0.0015, "gradient_norm": 0.11055967956781387, "benchmark": false} | |
| {"step": 12140, "tokens": 6364856320, "loss": 2.7945844650268556, "tokens_per_second": 968899.4351001403, "lr": 0.0015, "gradient_norm": 0.1114082932472229, "benchmark": false} | |
| {"step": 12160, "tokens": 6375342080, "loss": 2.793090057373047, "tokens_per_second": 968469.4776364955, "lr": 0.0015, "gradient_norm": 0.09585012495517731, "benchmark": false} | |
| {"step": 12180, "tokens": 6385827840, "loss": 2.78121280670166, "tokens_per_second": 968837.0522710334, "lr": 0.0015, "gradient_norm": 0.10618795454502106, "benchmark": false} | |
| {"step": 12200, "tokens": 6396313600, "loss": 2.785441780090332, "tokens_per_second": 966455.7732983519, "lr": 0.0015, "gradient_norm": 0.09828799217939377, "benchmark": false} | |
| {"step": 12220, "tokens": 6406799360, "loss": 2.7986448287963865, "tokens_per_second": 970902.9798390117, "lr": 0.0015, "gradient_norm": 0.10090534389019012, "benchmark": false} | |
| {"step": 12240, "tokens": 6417285120, "loss": 2.814933204650879, "tokens_per_second": 972558.1365765134, "lr": 0.0015, "gradient_norm": 0.11073237657546997, "benchmark": false} | |
| {"step": 12260, "tokens": 6427770880, "loss": 2.788890838623047, "tokens_per_second": 974638.7197978635, "lr": 0.0015, "gradient_norm": 0.10536236315965652, "benchmark": false} | |
| {"step": 12280, "tokens": 6438256640, "loss": 2.823429489135742, "tokens_per_second": 973988.6357724799, "lr": 0.0015, "gradient_norm": 0.11653498560190201, "benchmark": false} | |
| {"step": 12300, "tokens": 6448742400, "loss": 2.819413757324219, "tokens_per_second": 929390.072885049, "lr": 0.0015, "gradient_norm": 0.10442902147769928, "benchmark": false} | |
| {"step": 12320, "tokens": 6459228160, "loss": 2.833740234375, "tokens_per_second": 772543.6753550594, "lr": 0.0015, "gradient_norm": 0.10721367597579956, "benchmark": false} | |
| {"step": 12340, "tokens": 6469713920, "loss": 2.789055824279785, "tokens_per_second": 966814.8212758361, "lr": 0.0015, "gradient_norm": 0.09952326118946075, "benchmark": false} | |
| {"step": 12360, "tokens": 6480199680, "loss": 2.7925689697265623, "tokens_per_second": 975247.0802731954, "lr": 0.0015, "gradient_norm": 0.12145429849624634, "benchmark": false} | |
| {"step": 12380, "tokens": 6490685440, "loss": 2.8266456604003904, "tokens_per_second": 965313.8964469638, "lr": 0.0015, "gradient_norm": 0.11399828642606735, "benchmark": false} | |
| {"step": 12400, "tokens": 6501171200, "loss": 2.78804988861084, "tokens_per_second": 960203.670722355, "lr": 0.0015, "gradient_norm": 0.08776278793811798, "benchmark": false} | |
| {"step": 12420, "tokens": 6511656960, "loss": 2.8205455780029296, "tokens_per_second": 981290.9366722134, "lr": 0.0015, "gradient_norm": 0.10064391046762466, "benchmark": false} | |
| {"step": 12440, "tokens": 6522142720, "loss": 2.7763082504272463, "tokens_per_second": 950548.1511525006, "lr": 0.0015, "gradient_norm": 0.10321742296218872, "benchmark": false} | |
| {"step": 12460, "tokens": 6532628480, "loss": 2.7925830841064454, "tokens_per_second": 941279.0475299946, "lr": 0.0015, "gradient_norm": 0.09877070784568787, "benchmark": false} | |
| {"step": 12480, "tokens": 6543114240, "loss": 2.778891944885254, "tokens_per_second": 850421.2073633118, "lr": 0.0015, "gradient_norm": 0.11233720183372498, "benchmark": false} | |
| {"step": 12500, "tokens": 6553600000, "loss": 2.7939947128295897, "tokens_per_second": 973450.8494435991, "lr": 0.0015, "gradient_norm": 0.1016482263803482, "benchmark": false} | |
| {"step": 12520, "tokens": 6564085760, "loss": 2.7848548889160156, "tokens_per_second": 846373.2575825447, "lr": 0.0015, "gradient_norm": 0.10500110685825348, "benchmark": false} | |
| {"step": 12540, "tokens": 6574571520, "loss": 2.793666648864746, "tokens_per_second": 981321.1512611969, "lr": 0.0015, "gradient_norm": 0.0974324643611908, "benchmark": false} | |
| {"step": 12560, "tokens": 6585057280, "loss": 2.801418495178223, "tokens_per_second": 979704.3133449997, "lr": 0.0015, "gradient_norm": 0.1017347201704979, "benchmark": false} | |
| {"step": 12580, "tokens": 6595543040, "loss": 2.8266735076904297, "tokens_per_second": 988133.5318305237, "lr": 0.0015, "gradient_norm": 0.11285485327243805, "benchmark": false} | |
| {"step": 12600, "tokens": 6606028800, "loss": 2.798064041137695, "tokens_per_second": 968544.6581334989, "lr": 0.0015, "gradient_norm": 0.12008693069219589, "benchmark": false} | |
| {"step": 12620, "tokens": 6616514560, "loss": 2.779056167602539, "tokens_per_second": 974246.924298135, "lr": 0.0015, "gradient_norm": 0.10292800515890121, "benchmark": false} | |
| {"step": 12640, "tokens": 6627000320, "loss": 2.760360336303711, "tokens_per_second": 971397.7296126114, "lr": 0.0015, "gradient_norm": 0.1069885790348053, "benchmark": false} | |
| {"step": 12660, "tokens": 6637486080, "loss": 2.801474952697754, "tokens_per_second": 978504.4704739889, "lr": 0.0015, "gradient_norm": 0.12490136176347733, "benchmark": false} | |
| {"step": 12680, "tokens": 6647971840, "loss": 2.798496055603027, "tokens_per_second": 980442.1913900679, "lr": 0.0015, "gradient_norm": 0.11460032314062119, "benchmark": false} | |
| {"step": 12700, "tokens": 6658457600, "loss": 2.8015419006347657, "tokens_per_second": 973220.7832424595, "lr": 0.0015, "gradient_norm": 0.11687641590833664, "benchmark": false} | |
| {"step": 12720, "tokens": 6668943360, "loss": 2.7909303665161134, "tokens_per_second": 981804.2591327118, "lr": 0.0015, "gradient_norm": 0.13402538001537323, "benchmark": false} | |
| {"step": 12740, "tokens": 6679429120, "loss": 2.792036437988281, "tokens_per_second": 986014.0014381391, "lr": 0.0015, "gradient_norm": 0.10252609103918076, "benchmark": false} | |
| {"step": 12760, "tokens": 6689914880, "loss": 2.768864631652832, "tokens_per_second": 988360.89095433, "lr": 0.0015, "gradient_norm": 0.12681230902671814, "benchmark": false} | |
| {"step": 12780, "tokens": 6700400640, "loss": 2.776666259765625, "tokens_per_second": 982964.1647742782, "lr": 0.0015, "gradient_norm": 0.10406031459569931, "benchmark": false} | |
| {"step": 12800, "tokens": 6710886400, "loss": 2.7922054290771485, "tokens_per_second": 986135.2482533238, "lr": 0.0015, "gradient_norm": 0.11422515660524368, "benchmark": false} | |
| {"step": 12820, "tokens": 6721372160, "loss": 2.785415840148926, "tokens_per_second": 985157.5290273348, "lr": 0.0015, "gradient_norm": 0.10264149308204651, "benchmark": false} | |
| {"step": 12840, "tokens": 6731857920, "loss": 2.805078887939453, "tokens_per_second": 979360.6612045242, "lr": 0.0015, "gradient_norm": 0.10192272067070007, "benchmark": false} | |
| {"step": 12860, "tokens": 6742343680, "loss": 2.825607681274414, "tokens_per_second": 977634.0059499261, "lr": 0.0015, "gradient_norm": 0.10521155595779419, "benchmark": false} | |
| {"step": 12880, "tokens": 6752829440, "loss": 2.8118125915527346, "tokens_per_second": 979885.4051890227, "lr": 0.0015, "gradient_norm": 0.11813370883464813, "benchmark": false} | |
| {"step": 12900, "tokens": 6763315200, "loss": 2.8082229614257814, "tokens_per_second": 990730.8176655684, "lr": 0.0015, "gradient_norm": 0.11093993484973907, "benchmark": false} | |
| {"step": 12920, "tokens": 6773800960, "loss": 2.8015205383300783, "tokens_per_second": 830750.115379818, "lr": 0.0015, "gradient_norm": 0.1127043068408966, "benchmark": false} | |
| {"step": 12940, "tokens": 6784286720, "loss": 2.809139633178711, "tokens_per_second": 974379.8457599642, "lr": 0.0015, "gradient_norm": 0.11274027824401855, "benchmark": false} | |
| {"step": 12960, "tokens": 6794772480, "loss": 2.808652877807617, "tokens_per_second": 975053.6049672521, "lr": 0.0015, "gradient_norm": 0.10414215177297592, "benchmark": false} | |
| {"step": 12980, "tokens": 6805258240, "loss": 2.789379692077637, "tokens_per_second": 975217.6425159012, "lr": 0.0015, "gradient_norm": 0.11947929114103317, "benchmark": false} | |
| {"step": 13000, "tokens": 6815744000, "loss": 2.766477584838867, "tokens_per_second": 974659.1020516185, "lr": 0.0015, "gradient_norm": 0.10573747754096985, "benchmark": false} | |
| {"step": 13020, "tokens": 6826229760, "loss": 2.766706657409668, "tokens_per_second": 819334.3486186384, "lr": 0.0015, "gradient_norm": 0.10982190817594528, "benchmark": false} | |
| {"step": 13040, "tokens": 6836715520, "loss": 2.7889896392822267, "tokens_per_second": 974902.7983125558, "lr": 0.0015, "gradient_norm": 0.09978687763214111, "benchmark": false} | |
| {"step": 13060, "tokens": 6847201280, "loss": 2.7823381423950195, "tokens_per_second": 977186.2934301094, "lr": 0.0015, "gradient_norm": 0.10892217606306076, "benchmark": false} | |
| {"step": 13080, "tokens": 6857687040, "loss": 2.7726795196533205, "tokens_per_second": 978850.6546447634, "lr": 0.0015, "gradient_norm": 0.09092258661985397, "benchmark": false} | |
| {"step": 13100, "tokens": 6868172800, "loss": 2.800714683532715, "tokens_per_second": 980305.0475917425, "lr": 0.0015, "gradient_norm": 0.12226828932762146, "benchmark": false} | |
| {"step": 13120, "tokens": 6878658560, "loss": 2.8094324111938476, "tokens_per_second": 971826.2870966541, "lr": 0.0015, "gradient_norm": 0.1026187464594841, "benchmark": false} | |
| {"step": 13140, "tokens": 6889144320, "loss": 2.798151969909668, "tokens_per_second": 971155.9418639137, "lr": 0.0015, "gradient_norm": 0.11680211126804352, "benchmark": false} | |
| {"step": 13160, "tokens": 6899630080, "loss": 2.8011507034301757, "tokens_per_second": 976161.7806016527, "lr": 0.0015, "gradient_norm": 0.11606810986995697, "benchmark": false} | |
| {"step": 13180, "tokens": 6910115840, "loss": 2.7625892639160154, "tokens_per_second": 998782.8826195722, "lr": 0.0015, "gradient_norm": 0.1080118715763092, "benchmark": false} | |
| {"step": 13200, "tokens": 6920601600, "loss": 2.7888532638549806, "tokens_per_second": 834428.6390277194, "lr": 0.0015, "gradient_norm": 0.10792775452136993, "benchmark": false} | |
| {"step": 13220, "tokens": 6931087360, "loss": 2.770762634277344, "tokens_per_second": 984348.7338467747, "lr": 0.0015, "gradient_norm": 0.10894811153411865, "benchmark": false} | |
| {"step": 13240, "tokens": 6941573120, "loss": 2.791122627258301, "tokens_per_second": 817360.9508909244, "lr": 0.0015, "gradient_norm": 0.11274447292089462, "benchmark": false} | |
| {"step": 13260, "tokens": 6952058880, "loss": 2.791507911682129, "tokens_per_second": 814423.3989380366, "lr": 0.0015, "gradient_norm": 0.1253562569618225, "benchmark": false} | |
| {"step": 13280, "tokens": 6962544640, "loss": 2.787698173522949, "tokens_per_second": 993533.085928695, "lr": 0.0015, "gradient_norm": 0.10525481402873993, "benchmark": false} | |
| {"step": 13300, "tokens": 6973030400, "loss": 2.776492881774902, "tokens_per_second": 991714.7701083526, "lr": 0.0015, "gradient_norm": 0.11090178042650223, "benchmark": false} | |
| {"step": 13320, "tokens": 6983516160, "loss": 2.781183624267578, "tokens_per_second": 977445.8018478808, "lr": 0.0015, "gradient_norm": 0.11422978341579437, "benchmark": false} | |
| {"step": 13340, "tokens": 6994001920, "loss": 2.77828369140625, "tokens_per_second": 984796.0072479807, "lr": 0.0015, "gradient_norm": 0.11428497731685638, "benchmark": false} | |
| {"step": 13360, "tokens": 7004487680, "loss": 2.8044715881347657, "tokens_per_second": 987909.036007852, "lr": 0.0015, "gradient_norm": 0.1091688796877861, "benchmark": false} | |
| {"step": 13380, "tokens": 7014973440, "loss": 2.8291257858276366, "tokens_per_second": 992076.2403446267, "lr": 0.0015, "gradient_norm": 0.10559467226266861, "benchmark": false} | |
| {"step": 13400, "tokens": 7025459200, "loss": 2.81881103515625, "tokens_per_second": 939800.6670872662, "lr": 0.0015, "gradient_norm": 0.11850842088460922, "benchmark": false} | |
| {"step": 13420, "tokens": 7035944960, "loss": 2.8020517349243166, "tokens_per_second": 985602.3935548641, "lr": 0.0015, "gradient_norm": 0.11056564748287201, "benchmark": false} | |
| {"step": 13440, "tokens": 7046430720, "loss": 2.8099950790405273, "tokens_per_second": 984624.9842798545, "lr": 0.0015, "gradient_norm": 0.10240104049444199, "benchmark": false} | |
| {"step": 13460, "tokens": 7056916480, "loss": 2.801237106323242, "tokens_per_second": 977428.8533845174, "lr": 0.0015, "gradient_norm": 0.0954863652586937, "benchmark": false} | |
| {"step": 13480, "tokens": 7067402240, "loss": 2.813336181640625, "tokens_per_second": 990161.7610894733, "lr": 0.0015, "gradient_norm": 0.10894346982240677, "benchmark": false} | |
| {"step": 13500, "tokens": 7077888000, "loss": 2.8001928329467773, "tokens_per_second": 961178.7706554127, "lr": 0.0015, "gradient_norm": 0.11561203747987747, "benchmark": false} | |
| {"step": 13520, "tokens": 7088373760, "loss": 2.7821531295776367, "tokens_per_second": 840597.3397416604, "lr": 0.0015, "gradient_norm": 0.09781192988157272, "benchmark": false} | |
| {"step": 13540, "tokens": 7098859520, "loss": 2.7886821746826174, "tokens_per_second": 989633.9131038158, "lr": 0.0015, "gradient_norm": 0.1145467534661293, "benchmark": false} | |
| {"step": 13560, "tokens": 7109345280, "loss": 2.7986698150634766, "tokens_per_second": 992822.7311915599, "lr": 0.0015, "gradient_norm": 0.12221966683864594, "benchmark": false} | |
| {"step": 13580, "tokens": 7119831040, "loss": 2.81064453125, "tokens_per_second": 988468.4767134241, "lr": 0.0015, "gradient_norm": 0.11042139679193497, "benchmark": false} | |
| {"step": 13600, "tokens": 7130316800, "loss": 2.7997358322143553, "tokens_per_second": 990509.1251335517, "lr": 0.0015, "gradient_norm": 0.11651360243558884, "benchmark": false} | |
| {"step": 13620, "tokens": 7140802560, "loss": 2.799270820617676, "tokens_per_second": 985892.9055006963, "lr": 0.0015, "gradient_norm": 0.13365843892097473, "benchmark": false} | |
| {"step": 13640, "tokens": 7151288320, "loss": 2.809065246582031, "tokens_per_second": 982371.3983031667, "lr": 0.0015, "gradient_norm": 0.12926508486270905, "benchmark": false} | |
| {"step": 13660, "tokens": 7161774080, "loss": 2.795080375671387, "tokens_per_second": 978992.4936671671, "lr": 0.0015, "gradient_norm": 0.111018605530262, "benchmark": false} | |
| {"step": 13680, "tokens": 7172259840, "loss": 2.7762340545654296, "tokens_per_second": 987567.5708661648, "lr": 0.0015, "gradient_norm": 0.11279752105474472, "benchmark": false} | |
| {"step": 13700, "tokens": 7182745600, "loss": 2.791914367675781, "tokens_per_second": 993665.072440858, "lr": 0.0015, "gradient_norm": 0.10978860408067703, "benchmark": false} | |
| {"step": 13720, "tokens": 7193231360, "loss": 2.762933540344238, "tokens_per_second": 997256.6219546677, "lr": 0.0015, "gradient_norm": 0.10988429188728333, "benchmark": false} | |
| {"step": 13740, "tokens": 7203717120, "loss": 2.792901611328125, "tokens_per_second": 986272.0580112083, "lr": 0.0015, "gradient_norm": 0.11577098816633224, "benchmark": false} | |
| {"step": 13760, "tokens": 7214202880, "loss": 2.7878217697143555, "tokens_per_second": 985767.097813454, "lr": 0.0015, "gradient_norm": 0.10202588886022568, "benchmark": false} | |
| {"step": 13780, "tokens": 7224688640, "loss": 2.793878746032715, "tokens_per_second": 984036.116605316, "lr": 0.0015, "gradient_norm": 0.11739112436771393, "benchmark": false} | |
| {"step": 13800, "tokens": 7235174400, "loss": 2.764632797241211, "tokens_per_second": 987683.8762506432, "lr": 0.0015, "gradient_norm": 0.11182590574026108, "benchmark": false} | |
| {"step": 13820, "tokens": 7245660160, "loss": 2.7909011840820312, "tokens_per_second": 985738.4816994701, "lr": 0.0015, "gradient_norm": 0.12377017736434937, "benchmark": false} | |
| {"step": 13840, "tokens": 7256145920, "loss": 2.8005638122558594, "tokens_per_second": 996260.986465831, "lr": 0.0015, "gradient_norm": 0.11702325195074081, "benchmark": false} | |
| {"step": 13860, "tokens": 7266631680, "loss": 2.7674882888793944, "tokens_per_second": 946431.3417039429, "lr": 0.0015, "gradient_norm": 0.125955730676651, "benchmark": false} | |
| {"step": 13880, "tokens": 7277117440, "loss": 2.7438486099243162, "tokens_per_second": 971311.9990196545, "lr": 0.0015, "gradient_norm": 0.12266208976507187, "benchmark": false} | |
| {"step": 13900, "tokens": 7287603200, "loss": 2.7603336334228517, "tokens_per_second": 963924.6459587925, "lr": 0.0015, "gradient_norm": 0.11117645353078842, "benchmark": false} | |
| {"step": 13920, "tokens": 7298088960, "loss": 2.7700157165527344, "tokens_per_second": 969788.082572308, "lr": 0.0015, "gradient_norm": 0.11690377444028854, "benchmark": false} | |
| {"step": 13940, "tokens": 7308574720, "loss": 2.768319320678711, "tokens_per_second": 964042.0161144747, "lr": 0.0015, "gradient_norm": 0.1116306260228157, "benchmark": false} | |
| {"step": 13960, "tokens": 7319060480, "loss": 2.797551155090332, "tokens_per_second": 975699.4953853759, "lr": 0.0015, "gradient_norm": 0.11029012501239777, "benchmark": false} | |
| {"step": 13980, "tokens": 7329546240, "loss": 2.7930103302001954, "tokens_per_second": 970508.686897241, "lr": 0.0015, "gradient_norm": 0.12515392899513245, "benchmark": false} | |
| {"step": 14000, "tokens": 7340032000, "loss": 2.810237503051758, "tokens_per_second": 963901.6917292763, "lr": 0.0015, "gradient_norm": 0.11248497664928436, "benchmark": false} | |
| {"step": 14020, "tokens": 7350517760, "loss": 2.791335678100586, "tokens_per_second": 813652.9955171734, "lr": 0.0015, "gradient_norm": 0.11959215253591537, "benchmark": false} | |
| {"step": 14040, "tokens": 7361003520, "loss": 2.777591514587402, "tokens_per_second": 969676.2155442851, "lr": 0.0015, "gradient_norm": 0.12372884899377823, "benchmark": false} | |
| {"step": 14060, "tokens": 7371489280, "loss": 2.782402229309082, "tokens_per_second": 983219.0543881522, "lr": 0.0015, "gradient_norm": 0.11226522922515869, "benchmark": false} | |
| {"step": 14080, "tokens": 7381975040, "loss": 2.7681150436401367, "tokens_per_second": 975875.657074898, "lr": 0.0015, "gradient_norm": 0.10557014495134354, "benchmark": false} | |
| {"step": 14100, "tokens": 7392460800, "loss": 2.7867458343505858, "tokens_per_second": 966180.8714196938, "lr": 0.0015, "gradient_norm": 0.12427403032779694, "benchmark": false} | |
| {"step": 14120, "tokens": 7402946560, "loss": 2.771135711669922, "tokens_per_second": 967829.3294986727, "lr": 0.0015, "gradient_norm": 0.14234967529773712, "benchmark": false} | |
| {"step": 14140, "tokens": 7413432320, "loss": 2.7977426528930662, "tokens_per_second": 982225.6659788291, "lr": 0.0015, "gradient_norm": 0.10697734355926514, "benchmark": false} | |
| {"step": 14160, "tokens": 7423918080, "loss": 2.7943275451660154, "tokens_per_second": 943209.179024705, "lr": 0.0015, "gradient_norm": 0.12122584134340286, "benchmark": false} | |
| {"step": 14180, "tokens": 7434403840, "loss": 2.7882776260375977, "tokens_per_second": 972799.0716412093, "lr": 0.0015, "gradient_norm": 0.12172659486532211, "benchmark": false} | |
| {"step": 14200, "tokens": 7444889600, "loss": 2.7888107299804688, "tokens_per_second": 979663.2097114463, "lr": 0.0015, "gradient_norm": 0.12220656126737595, "benchmark": false} | |
| {"step": 14220, "tokens": 7455375360, "loss": 2.776138496398926, "tokens_per_second": 995039.7955782793, "lr": 0.0015, "gradient_norm": 0.12428434938192368, "benchmark": false} | |
| {"step": 14240, "tokens": 7465861120, "loss": 2.7772552490234377, "tokens_per_second": 819070.6374529089, "lr": 0.0015, "gradient_norm": 0.11531788855791092, "benchmark": false} | |
| {"step": 14260, "tokens": 7476346880, "loss": 2.7617315292358398, "tokens_per_second": 991137.677705705, "lr": 0.0015, "gradient_norm": 0.11593849956989288, "benchmark": false} | |
| {"step": 14280, "tokens": 7486832640, "loss": 2.78887825012207, "tokens_per_second": 846127.2536726185, "lr": 0.0015, "gradient_norm": 0.11124301701784134, "benchmark": false} | |
| {"step": 14300, "tokens": 7497318400, "loss": 2.7792558670043945, "tokens_per_second": 987566.68959574, "lr": 0.0015, "gradient_norm": 0.11953974515199661, "benchmark": false} | |
| {"step": 14320, "tokens": 7507804160, "loss": 2.831440734863281, "tokens_per_second": 989568.0520040918, "lr": 0.0015, "gradient_norm": 0.12550649046897888, "benchmark": false} | |
| {"step": 14340, "tokens": 7518289920, "loss": 2.801271438598633, "tokens_per_second": 988344.4859731847, "lr": 0.0015, "gradient_norm": 0.11680278927087784, "benchmark": false} | |
| {"step": 14360, "tokens": 7528775680, "loss": 2.8113771438598634, "tokens_per_second": 986148.3601785137, "lr": 0.0015, "gradient_norm": 0.11640466004610062, "benchmark": false} | |
| {"step": 14380, "tokens": 7539261440, "loss": 2.7739334106445312, "tokens_per_second": 948596.0842908887, "lr": 0.0015, "gradient_norm": 0.11652897298336029, "benchmark": false} | |
| {"step": 14400, "tokens": 7549747200, "loss": 2.759836959838867, "tokens_per_second": 984154.2147220767, "lr": 0.0015, "gradient_norm": 0.1413278579711914, "benchmark": false} | |
| {"step": 14420, "tokens": 7560232960, "loss": 2.7747310638427733, "tokens_per_second": 993582.842022985, "lr": 0.0015, "gradient_norm": 0.11072643101215363, "benchmark": false} | |
| {"step": 14440, "tokens": 7570718720, "loss": 2.7863250732421876, "tokens_per_second": 981959.3380287135, "lr": 0.0015, "gradient_norm": 0.1334671527147293, "benchmark": false} | |
| {"step": 14460, "tokens": 7581204480, "loss": 2.795541000366211, "tokens_per_second": 987438.052550711, "lr": 0.0015, "gradient_norm": 0.11582837998867035, "benchmark": false} | |
| {"step": 14480, "tokens": 7591690240, "loss": 2.759349250793457, "tokens_per_second": 986850.0911493824, "lr": 0.0015, "gradient_norm": 0.10604269802570343, "benchmark": false} | |
| {"step": 14500, "tokens": 7602176000, "loss": 2.775119972229004, "tokens_per_second": 988500.8542283837, "lr": 0.0015, "gradient_norm": 0.12106780707836151, "benchmark": false} | |
| {"step": 14520, "tokens": 7612661760, "loss": 2.78094482421875, "tokens_per_second": 861691.7279486274, "lr": 0.0015, "gradient_norm": 0.11721201986074448, "benchmark": false} | |
| {"step": 14540, "tokens": 7623147520, "loss": 2.8029096603393553, "tokens_per_second": 970426.4987138406, "lr": 0.0015, "gradient_norm": 0.1039208471775055, "benchmark": false} | |
| {"step": 14560, "tokens": 7633633280, "loss": 2.7715450286865235, "tokens_per_second": 853681.4973439367, "lr": 0.0015, "gradient_norm": 0.1236744225025177, "benchmark": false} | |
| {"step": 14580, "tokens": 7644119040, "loss": 2.7071344375610353, "tokens_per_second": 990082.1098315411, "lr": 0.0015, "gradient_norm": 0.129014790058136, "benchmark": false} | |
| {"step": 14600, "tokens": 7654604800, "loss": 2.7800420761108398, "tokens_per_second": 985127.7685421152, "lr": 0.0015, "gradient_norm": 0.12574076652526855, "benchmark": false} | |
| {"step": 14620, "tokens": 7665090560, "loss": 2.772840118408203, "tokens_per_second": 984006.8781479271, "lr": 0.0015, "gradient_norm": 0.10671056807041168, "benchmark": false} | |
| {"step": 14640, "tokens": 7675576320, "loss": 2.787381172180176, "tokens_per_second": 981182.8019479843, "lr": 0.0015, "gradient_norm": 0.12444412708282471, "benchmark": false} | |
| {"step": 14660, "tokens": 7686062080, "loss": 2.807179260253906, "tokens_per_second": 990942.8933172724, "lr": 0.0015, "gradient_norm": 0.11637486517429352, "benchmark": false} | |
| {"step": 14680, "tokens": 7696547840, "loss": 2.777162551879883, "tokens_per_second": 988375.0518143643, "lr": 0.0015, "gradient_norm": 0.11264752596616745, "benchmark": false} | |
| {"step": 14700, "tokens": 7707033600, "loss": 2.751451301574707, "tokens_per_second": 982500.7597702437, "lr": 0.0015, "gradient_norm": 0.11065639555454254, "benchmark": false} | |
| {"step": 14720, "tokens": 7717519360, "loss": 2.7805938720703125, "tokens_per_second": 990573.8294467634, "lr": 0.0015, "gradient_norm": 0.12915614247322083, "benchmark": false} | |
| {"step": 14740, "tokens": 7728005120, "loss": 2.7759862899780274, "tokens_per_second": 984932.6772831127, "lr": 0.0015, "gradient_norm": 0.12227462232112885, "benchmark": false} | |
| {"step": 14760, "tokens": 7738490880, "loss": 2.773594284057617, "tokens_per_second": 986583.2262868274, "lr": 0.0015, "gradient_norm": 0.13443267345428467, "benchmark": false} | |
| {"step": 14780, "tokens": 7748976640, "loss": 2.755499267578125, "tokens_per_second": 983851.4833784379, "lr": 0.0015, "gradient_norm": 0.140534445643425, "benchmark": false} | |
| {"step": 14800, "tokens": 7759462400, "loss": 2.809262275695801, "tokens_per_second": 991503.8447301083, "lr": 0.0015, "gradient_norm": 0.11260712891817093, "benchmark": false} | |
| {"step": 14820, "tokens": 7769948160, "loss": 2.7522346496582033, "tokens_per_second": 939397.3426870825, "lr": 0.0015, "gradient_norm": 0.13379478454589844, "benchmark": false} | |
| {"step": 14840, "tokens": 7780433920, "loss": 2.765176773071289, "tokens_per_second": 982189.8472449704, "lr": 0.0015, "gradient_norm": 0.13181689381599426, "benchmark": false} | |
| {"step": 14860, "tokens": 7790919680, "loss": 2.7400943756103517, "tokens_per_second": 981467.5389068498, "lr": 0.0015, "gradient_norm": 0.12768228352069855, "benchmark": false} | |
| {"step": 14880, "tokens": 7801405440, "loss": 2.7884395599365233, "tokens_per_second": 986269.6179671925, "lr": 0.0015, "gradient_norm": 0.12317132949829102, "benchmark": false} | |
| {"step": 14900, "tokens": 7811891200, "loss": 2.7660396575927733, "tokens_per_second": 992115.5099409415, "lr": 0.0015, "gradient_norm": 0.13060061633586884, "benchmark": false} | |
| {"step": 14920, "tokens": 7822376960, "loss": 2.771735191345215, "tokens_per_second": 991036.9703833835, "lr": 0.0015, "gradient_norm": 0.12381613999605179, "benchmark": false} | |
| {"step": 14940, "tokens": 7832862720, "loss": 2.7973310470581056, "tokens_per_second": 982117.8814135678, "lr": 0.0015, "gradient_norm": 0.13259257376194, "benchmark": false} | |
| {"step": 14960, "tokens": 7843348480, "loss": 2.8001480102539062, "tokens_per_second": 989712.792759918, "lr": 0.0015, "gradient_norm": 0.12138649076223373, "benchmark": false} | |
| {"step": 14980, "tokens": 7853834240, "loss": 2.7922641754150392, "tokens_per_second": 990706.2731206587, "lr": 0.0015, "gradient_norm": 0.11834993213415146, "benchmark": false} | |
| {"step": 15000, "tokens": 7864320000, "loss": 2.810902976989746, "tokens_per_second": 985215.5444990908, "lr": 0.0015, "gradient_norm": 0.13044802844524384, "benchmark": false} | |
| {"step": 15020, "tokens": 7874805760, "loss": 2.7654020309448244, "tokens_per_second": 823555.812169737, "lr": 0.0015, "gradient_norm": 0.12740527093410492, "benchmark": false} | |
| {"step": 15040, "tokens": 7885291520, "loss": 2.800482749938965, "tokens_per_second": 977951.2339340949, "lr": 0.0015, "gradient_norm": 0.11727306246757507, "benchmark": false} | |
| {"step": 15060, "tokens": 7895777280, "loss": 2.7801792144775392, "tokens_per_second": 984479.5907513736, "lr": 0.0015, "gradient_norm": 0.13086150586605072, "benchmark": false} | |
| {"step": 15080, "tokens": 7906263040, "loss": 2.7915508270263674, "tokens_per_second": 991798.1438708312, "lr": 0.0015, "gradient_norm": 0.1386176198720932, "benchmark": false} | |
| {"step": 15100, "tokens": 7916748800, "loss": 2.7806907653808595, "tokens_per_second": 947418.1922038253, "lr": 0.0015, "gradient_norm": 0.13433490693569183, "benchmark": false} | |
| {"step": 15120, "tokens": 7927234560, "loss": 2.7819780349731444, "tokens_per_second": 977709.2087112203, "lr": 0.0015, "gradient_norm": 0.1220981553196907, "benchmark": false} | |
| {"step": 15140, "tokens": 7937720320, "loss": 2.7758398056030273, "tokens_per_second": 981192.5939934173, "lr": 0.0015, "gradient_norm": 0.1192423552274704, "benchmark": false} | |
| {"step": 15160, "tokens": 7948206080, "loss": 2.794535827636719, "tokens_per_second": 978395.168341898, "lr": 0.0015, "gradient_norm": 0.11452946811914444, "benchmark": false} | |
| {"step": 15180, "tokens": 7958691840, "loss": 2.8224889755249025, "tokens_per_second": 993816.7651067976, "lr": 0.0015, "gradient_norm": 0.14984717965126038, "benchmark": false} | |
| {"step": 15200, "tokens": 7969177600, "loss": 2.743648910522461, "tokens_per_second": 949634.5828433512, "lr": 0.0015, "gradient_norm": 0.10898782312870026, "benchmark": false} | |
| {"step": 15220, "tokens": 7979663360, "loss": 2.779790687561035, "tokens_per_second": 914020.3761350015, "lr": 0.0015, "gradient_norm": 0.14382652938365936, "benchmark": false} | |
| {"step": 15240, "tokens": 7990149120, "loss": 2.748489570617676, "tokens_per_second": 980651.3313555524, "lr": 0.0015, "gradient_norm": 0.11789301037788391, "benchmark": false} | |
| {"step": 15260, "tokens": 8000634880, "loss": 2.7987091064453127, "tokens_per_second": 980199.5878640658, "lr": 0.0015, "gradient_norm": 0.12273319065570831, "benchmark": false} | |
| {"step": 15280, "tokens": 8011120640, "loss": 2.7595916748046876, "tokens_per_second": 978473.4606914566, "lr": 0.0015, "gradient_norm": 0.10250099748373032, "benchmark": false} | |
| {"step": 15300, "tokens": 8021606400, "loss": 2.7711753845214844, "tokens_per_second": 982610.2796507904, "lr": 0.0015, "gradient_norm": 0.12107187509536743, "benchmark": false} | |
| {"step": 15320, "tokens": 8032092160, "loss": 2.7694541931152346, "tokens_per_second": 985252.0515802435, "lr": 0.0015, "gradient_norm": 0.1299021989107132, "benchmark": false} | |
| {"step": 15340, "tokens": 8042577920, "loss": 2.756649398803711, "tokens_per_second": 983524.795475268, "lr": 0.0015, "gradient_norm": 0.1264059990644455, "benchmark": false} | |
| {"step": 15360, "tokens": 8053063680, "loss": 2.7797285079956056, "tokens_per_second": 990793.6321202533, "lr": 0.0015, "gradient_norm": 0.12407135218381882, "benchmark": false} | |
| {"step": 15380, "tokens": 8063549440, "loss": 2.764774703979492, "tokens_per_second": 960681.4674944137, "lr": 0.0015, "gradient_norm": 0.11804969608783722, "benchmark": false} | |
| {"step": 15400, "tokens": 8074035200, "loss": 2.770212745666504, "tokens_per_second": 793080.9519841595, "lr": 0.0015, "gradient_norm": 0.12192878127098083, "benchmark": false} | |
| {"step": 15420, "tokens": 8084520960, "loss": 2.782291221618652, "tokens_per_second": 990637.1932859971, "lr": 0.0015, "gradient_norm": 0.12279947847127914, "benchmark": false} | |
| {"step": 15440, "tokens": 8095006720, "loss": 2.779428482055664, "tokens_per_second": 985431.1509096528, "lr": 0.0015, "gradient_norm": 0.11921844631433487, "benchmark": false} | |
| {"step": 15460, "tokens": 8105492480, "loss": 2.789088821411133, "tokens_per_second": 984151.1761542251, "lr": 0.0015, "gradient_norm": 0.12286203354597092, "benchmark": false} | |
| {"step": 15480, "tokens": 8115978240, "loss": 2.774624824523926, "tokens_per_second": 987296.5932243799, "lr": 0.0015, "gradient_norm": 0.12382978200912476, "benchmark": false} | |
| {"step": 15500, "tokens": 8126464000, "loss": 2.7601093292236327, "tokens_per_second": 984571.0421259468, "lr": 0.0015, "gradient_norm": 0.1273164451122284, "benchmark": false} | |
| {"step": 15520, "tokens": 8136949760, "loss": 2.7832685470581056, "tokens_per_second": 861158.9010310016, "lr": 0.0015, "gradient_norm": 0.12241510301828384, "benchmark": false} | |
| {"step": 15540, "tokens": 8147435520, "loss": 2.786355209350586, "tokens_per_second": 987504.7467624149, "lr": 0.0015, "gradient_norm": 0.13968412578105927, "benchmark": false} | |
| {"step": 15560, "tokens": 8157921280, "loss": 2.771760177612305, "tokens_per_second": 991712.5755314733, "lr": 0.0015, "gradient_norm": 0.12112805247306824, "benchmark": false} | |
| {"step": 15580, "tokens": 8168407040, "loss": 2.7709102630615234, "tokens_per_second": 992927.0085300705, "lr": 0.0015, "gradient_norm": 0.12343323230743408, "benchmark": false} | |
| {"step": 15600, "tokens": 8178892800, "loss": 2.761789321899414, "tokens_per_second": 791803.2874319528, "lr": 0.0015, "gradient_norm": 0.12571533024311066, "benchmark": false} | |
| {"step": 15620, "tokens": 8189378560, "loss": 2.8006032943725585, "tokens_per_second": 988086.2202510992, "lr": 0.0015, "gradient_norm": 0.1310616433620453, "benchmark": false} | |
| {"step": 15640, "tokens": 8199864320, "loss": 2.719218063354492, "tokens_per_second": 982338.551020601, "lr": 0.0015, "gradient_norm": 0.12276970595121384, "benchmark": false} | |
| {"step": 15660, "tokens": 8210350080, "loss": 2.752928924560547, "tokens_per_second": 981419.9544678394, "lr": 0.0015, "gradient_norm": 0.12405300885438919, "benchmark": false} | |
| {"step": 15680, "tokens": 8220835840, "loss": 2.7423049926757814, "tokens_per_second": 992086.454896566, "lr": 0.0015, "gradient_norm": 0.1774618923664093, "benchmark": false} | |
| {"step": 15700, "tokens": 8231321600, "loss": 2.7865814208984374, "tokens_per_second": 988008.8031671712, "lr": 0.0015, "gradient_norm": 0.1288478523492813, "benchmark": false} | |
| {"step": 15720, "tokens": 8241807360, "loss": 2.7889198303222655, "tokens_per_second": 982714.2016490992, "lr": 0.0015, "gradient_norm": 0.12388283014297485, "benchmark": false} | |
| {"step": 15740, "tokens": 8252293120, "loss": 2.8025897979736327, "tokens_per_second": 974730.9688753263, "lr": 0.0015, "gradient_norm": 0.1334666758775711, "benchmark": false} | |
| {"step": 15760, "tokens": 8262778880, "loss": 2.784100151062012, "tokens_per_second": 816091.3532996135, "lr": 0.0015, "gradient_norm": 0.13729210197925568, "benchmark": false} | |
| {"step": 15780, "tokens": 8273264640, "loss": 2.745918846130371, "tokens_per_second": 975612.1825277328, "lr": 0.0015, "gradient_norm": 0.13625092804431915, "benchmark": false} | |
| {"step": 15800, "tokens": 8283750400, "loss": 2.7696556091308593, "tokens_per_second": 985700.6837745443, "lr": 0.0015, "gradient_norm": 0.12022973597049713, "benchmark": false} | |
| {"step": 15820, "tokens": 8294236160, "loss": 2.793374443054199, "tokens_per_second": 983604.8663832461, "lr": 0.0015, "gradient_norm": 0.13915833830833435, "benchmark": false} | |
| {"step": 15840, "tokens": 8304721920, "loss": 2.793455696105957, "tokens_per_second": 985509.9259761899, "lr": 0.0015, "gradient_norm": 0.13698719441890717, "benchmark": false} | |
| {"step": 15860, "tokens": 8315207680, "loss": 2.7685171127319337, "tokens_per_second": 984942.6903972635, "lr": 0.0015, "gradient_norm": 0.12572473287582397, "benchmark": false} | |
| {"step": 15880, "tokens": 8325693440, "loss": 2.799310874938965, "tokens_per_second": 981443.0795205814, "lr": 0.0015, "gradient_norm": 0.1338423192501068, "benchmark": false} | |
| {"step": 15900, "tokens": 8336179200, "loss": 2.739674758911133, "tokens_per_second": 986746.5066202157, "lr": 0.0015, "gradient_norm": 0.14922641217708588, "benchmark": false} | |
| {"step": 15920, "tokens": 8346664960, "loss": 2.741182327270508, "tokens_per_second": 990415.794020369, "lr": 0.0015, "gradient_norm": 0.13643869757652283, "benchmark": false} | |
| {"step": 15940, "tokens": 8357150720, "loss": 2.7580354690551756, "tokens_per_second": 987489.3635660079, "lr": 0.0015, "gradient_norm": 0.12679877877235413, "benchmark": false} | |
| {"step": 15960, "tokens": 8367636480, "loss": 2.7853540420532226, "tokens_per_second": 988360.838972838, "lr": 0.0015, "gradient_norm": 0.12756744027137756, "benchmark": false} | |
| {"step": 15980, "tokens": 8378122240, "loss": 2.7640474319458006, "tokens_per_second": 981558.347332284, "lr": 0.0015, "gradient_norm": 0.12450078874826431, "benchmark": false} | |
| {"step": 16000, "tokens": 8388608000, "loss": 2.765132522583008, "tokens_per_second": 986364.2098637007, "lr": 0.0015, "gradient_norm": 0.11989699304103851, "benchmark": false} | |
| {"step": 16020, "tokens": 8399093760, "loss": 2.7635297775268555, "tokens_per_second": 721194.026507423, "lr": 0.0015, "gradient_norm": 0.13609609007835388, "benchmark": false} | |
| {"step": 16040, "tokens": 8409579520, "loss": 2.771346855163574, "tokens_per_second": 1000970.2386190228, "lr": 0.0015, "gradient_norm": 0.11046281456947327, "benchmark": false} | |
| {"step": 16060, "tokens": 8420065280, "loss": 2.737568664550781, "tokens_per_second": 992158.553045272, "lr": 0.0015, "gradient_norm": 0.1417708545923233, "benchmark": false} | |
| {"step": 16080, "tokens": 8430551040, "loss": 2.7849164962768556, "tokens_per_second": 983467.9837204237, "lr": 0.0015, "gradient_norm": 0.1339673548936844, "benchmark": false} | |
| {"step": 16100, "tokens": 8441036800, "loss": 2.782582092285156, "tokens_per_second": 993323.0174545496, "lr": 0.0015, "gradient_norm": 0.12592069804668427, "benchmark": false} | |
| {"step": 16120, "tokens": 8451522560, "loss": 2.789615249633789, "tokens_per_second": 987606.7098180185, "lr": 0.0015, "gradient_norm": 0.1433916538953781, "benchmark": false} | |
| {"step": 16140, "tokens": 8462008320, "loss": 2.7635101318359374, "tokens_per_second": 987519.4933758049, "lr": 0.0015, "gradient_norm": 0.1438322365283966, "benchmark": false} | |
| {"step": 16160, "tokens": 8472494080, "loss": 2.79315128326416, "tokens_per_second": 943570.2114555163, "lr": 0.0015, "gradient_norm": 0.13221818208694458, "benchmark": false} | |
| {"step": 16180, "tokens": 8482979840, "loss": 2.7584300994873048, "tokens_per_second": 988068.5442700232, "lr": 0.0015, "gradient_norm": 0.13860242068767548, "benchmark": false} | |
| {"step": 16200, "tokens": 8493465600, "loss": 2.7741302490234374, "tokens_per_second": 853372.110375213, "lr": 0.0015, "gradient_norm": 0.12167493999004364, "benchmark": false} | |
| {"step": 16220, "tokens": 8503951360, "loss": 2.743886947631836, "tokens_per_second": 986954.5649848463, "lr": 0.0015, "gradient_norm": 0.14321689307689667, "benchmark": false} | |
| {"step": 16240, "tokens": 8514437120, "loss": 2.784414863586426, "tokens_per_second": 998092.0184354588, "lr": 0.0015, "gradient_norm": 0.13430804014205933, "benchmark": false} | |
| {"step": 16260, "tokens": 8524922880, "loss": 2.785556411743164, "tokens_per_second": 995103.224290704, "lr": 0.0015, "gradient_norm": 0.1189822107553482, "benchmark": false} | |
| {"step": 16280, "tokens": 8535408640, "loss": 2.782154846191406, "tokens_per_second": 986489.8569756218, "lr": 0.0015, "gradient_norm": 0.12390752881765366, "benchmark": false} | |
| {"step": 16300, "tokens": 8545894400, "loss": 2.7694122314453127, "tokens_per_second": 992801.6228052417, "lr": 0.0015, "gradient_norm": 0.11609350889921188, "benchmark": false} | |
| {"step": 16320, "tokens": 8556380160, "loss": 2.7887857437133787, "tokens_per_second": 986784.6207617229, "lr": 0.0015, "gradient_norm": 0.12866061925888062, "benchmark": false} | |
| {"step": 16340, "tokens": 8566865920, "loss": 2.7744943618774416, "tokens_per_second": 992506.2135794541, "lr": 0.0015, "gradient_norm": 0.12591111660003662, "benchmark": false} | |
| {"step": 16360, "tokens": 8577351680, "loss": 2.7659664154052734, "tokens_per_second": 957698.2343715924, "lr": 0.0015, "gradient_norm": 0.13210691511631012, "benchmark": false} | |
| {"step": 16380, "tokens": 8587837440, "loss": 2.7758440017700194, "tokens_per_second": 979198.5844032543, "lr": 0.0015, "gradient_norm": 0.1414300799369812, "benchmark": false} | |
| {"step": 16400, "tokens": 8598323200, "loss": 2.771662139892578, "tokens_per_second": 986576.9615266923, "lr": 0.0015, "gradient_norm": 0.13212408125400543, "benchmark": false} | |
| {"step": 16420, "tokens": 8608808960, "loss": 2.7619678497314455, "tokens_per_second": 974413.1486566692, "lr": 0.0015, "gradient_norm": 0.13944043219089508, "benchmark": false} | |
| {"step": 16440, "tokens": 8619294720, "loss": 2.753804016113281, "tokens_per_second": 985882.0887802038, "lr": 0.0015, "gradient_norm": 0.13302597403526306, "benchmark": false} | |
| {"step": 16460, "tokens": 8629780480, "loss": 2.753531265258789, "tokens_per_second": 980514.9105911973, "lr": 0.0015, "gradient_norm": 0.1321820169687271, "benchmark": false} | |
| {"step": 16480, "tokens": 8640266240, "loss": 2.756893539428711, "tokens_per_second": 994236.4498590342, "lr": 0.0015, "gradient_norm": 0.13825723528862, "benchmark": false} | |
| {"step": 16500, "tokens": 8650752000, "loss": 2.751681327819824, "tokens_per_second": 819637.2886612634, "lr": 0.0015, "gradient_norm": 0.12679840624332428, "benchmark": false} | |
| {"step": 16520, "tokens": 8661237760, "loss": 2.7873161315917967, "tokens_per_second": 860862.4364112108, "lr": 0.0015, "gradient_norm": 0.1185576468706131, "benchmark": false} | |
| {"step": 16540, "tokens": 8671723520, "loss": 2.7667850494384765, "tokens_per_second": 998642.0541059768, "lr": 0.0015, "gradient_norm": 0.1283944547176361, "benchmark": false} | |
| {"step": 16560, "tokens": 8682209280, "loss": 2.7945037841796876, "tokens_per_second": 978602.128790704, "lr": 0.0015, "gradient_norm": 0.12816500663757324, "benchmark": false} | |
| {"step": 16580, "tokens": 8692695040, "loss": 2.767159652709961, "tokens_per_second": 991293.4213889013, "lr": 0.0015, "gradient_norm": 0.12242449820041656, "benchmark": false} | |
| {"step": 16600, "tokens": 8703180800, "loss": 2.797515869140625, "tokens_per_second": 993813.742701105, "lr": 0.0015, "gradient_norm": 0.12738817930221558, "benchmark": false} | |
| {"step": 16620, "tokens": 8713666560, "loss": 2.738190269470215, "tokens_per_second": 990569.5727881185, "lr": 0.0015, "gradient_norm": 0.14329010248184204, "benchmark": false} | |
| {"step": 16640, "tokens": 8724152320, "loss": 2.750609016418457, "tokens_per_second": 936118.2113643799, "lr": 0.0015, "gradient_norm": 0.1231890544295311, "benchmark": false} | |
| {"step": 16660, "tokens": 8734638080, "loss": 2.7822185516357423, "tokens_per_second": 977638.3507826354, "lr": 0.0015, "gradient_norm": 0.13130663335323334, "benchmark": false} | |
| {"step": 16680, "tokens": 8745123840, "loss": 2.765430450439453, "tokens_per_second": 992580.9782912476, "lr": 0.0015, "gradient_norm": 0.13001523911952972, "benchmark": false} | |
| {"step": 16700, "tokens": 8755609600, "loss": 2.7993846893310548, "tokens_per_second": 992658.8444407133, "lr": 0.0015, "gradient_norm": 0.12987804412841797, "benchmark": false} | |
| {"step": 16720, "tokens": 8766095360, "loss": 2.7786354064941405, "tokens_per_second": 930222.1736913013, "lr": 0.0015, "gradient_norm": 0.13684336841106415, "benchmark": false} | |
| {"step": 16740, "tokens": 8776581120, "loss": 2.769214630126953, "tokens_per_second": 975331.3139433127, "lr": 0.0015, "gradient_norm": 0.1365191489458084, "benchmark": false} | |
| {"step": 16760, "tokens": 8787066880, "loss": 2.735025405883789, "tokens_per_second": 987606.3200698326, "lr": 0.0015, "gradient_norm": 0.12653587758541107, "benchmark": false} | |
| {"step": 16780, "tokens": 8797552640, "loss": 2.7759571075439453, "tokens_per_second": 977447.2956762247, "lr": 0.0015, "gradient_norm": 0.1501408964395523, "benchmark": false} | |
| {"step": 16800, "tokens": 8808038400, "loss": 2.755018424987793, "tokens_per_second": 981215.6592058687, "lr": 0.0015, "gradient_norm": 0.14391691982746124, "benchmark": false} | |
| {"step": 16820, "tokens": 8818524160, "loss": 2.788979148864746, "tokens_per_second": 983531.0711602477, "lr": 0.0015, "gradient_norm": 0.14247770607471466, "benchmark": false} | |
| {"step": 16840, "tokens": 8829009920, "loss": 2.7318441390991213, "tokens_per_second": 978449.6197850282, "lr": 0.0015, "gradient_norm": 0.13322368264198303, "benchmark": false} | |
| {"step": 16860, "tokens": 8839495680, "loss": 2.7271265029907226, "tokens_per_second": 979627.1698201046, "lr": 0.0015, "gradient_norm": 0.14126761257648468, "benchmark": false} | |
| {"step": 16880, "tokens": 8849981440, "loss": 2.7251302719116213, "tokens_per_second": 989323.9697494382, "lr": 0.0015, "gradient_norm": 0.13313154876232147, "benchmark": false} | |
| {"step": 16900, "tokens": 8860467200, "loss": 2.7646034240722654, "tokens_per_second": 977381.1207010148, "lr": 0.0015, "gradient_norm": 0.13809148967266083, "benchmark": false} | |
| {"step": 16920, "tokens": 8870952960, "loss": 2.767935943603516, "tokens_per_second": 976473.568332828, "lr": 0.0015, "gradient_norm": 0.12858952581882477, "benchmark": false} | |
| {"step": 16940, "tokens": 8881438720, "loss": 2.787833404541016, "tokens_per_second": 988446.4059700933, "lr": 0.0015, "gradient_norm": 0.13221263885498047, "benchmark": false} | |
| {"step": 16960, "tokens": 8891924480, "loss": 2.739687919616699, "tokens_per_second": 946188.3591020354, "lr": 0.0015, "gradient_norm": 0.15024445950984955, "benchmark": false} | |
| {"step": 16980, "tokens": 8902410240, "loss": 2.764535331726074, "tokens_per_second": 975047.8654111625, "lr": 0.0015, "gradient_norm": 0.1423749327659607, "benchmark": false} | |
| {"step": 17000, "tokens": 8912896000, "loss": 2.7730123519897463, "tokens_per_second": 981977.874173138, "lr": 0.0015, "gradient_norm": 0.13165350258350372, "benchmark": false} | |
| {"step": 17020, "tokens": 8923381760, "loss": 2.743798828125, "tokens_per_second": 818942.7578559162, "lr": 0.0015, "gradient_norm": 0.13705229759216309, "benchmark": false} | |
| {"step": 17040, "tokens": 8933867520, "loss": 2.7651670455932615, "tokens_per_second": 978044.6029568557, "lr": 0.0015, "gradient_norm": 0.14534282684326172, "benchmark": false} | |
| {"step": 17060, "tokens": 8944353280, "loss": 2.7328630447387696, "tokens_per_second": 987639.7265434645, "lr": 0.0015, "gradient_norm": 0.12985369563102722, "benchmark": false} | |
| {"step": 17080, "tokens": 8954839040, "loss": 2.7397464752197265, "tokens_per_second": 982369.9370642095, "lr": 0.0015, "gradient_norm": 0.13668425381183624, "benchmark": false} | |
| {"step": 17100, "tokens": 8965324800, "loss": 2.7487125396728516, "tokens_per_second": 981721.9066029039, "lr": 0.0015, "gradient_norm": 0.12753145396709442, "benchmark": false} | |
| {"step": 17120, "tokens": 8975810560, "loss": 2.7811796188354494, "tokens_per_second": 839985.971626661, "lr": 0.0015, "gradient_norm": 0.14358003437519073, "benchmark": false} | |
| {"step": 17140, "tokens": 8986296320, "loss": 2.7554580688476564, "tokens_per_second": 985347.3316219762, "lr": 0.0015, "gradient_norm": 0.18229703605175018, "benchmark": false} | |
| {"step": 17160, "tokens": 8996782080, "loss": 2.7388572692871094, "tokens_per_second": 844932.1286913212, "lr": 0.0015, "gradient_norm": 0.17785406112670898, "benchmark": false} | |
| {"step": 17180, "tokens": 9007267840, "loss": 2.803097724914551, "tokens_per_second": 979514.8631083402, "lr": 0.0015, "gradient_norm": 0.12167101353406906, "benchmark": false} | |
| {"step": 17200, "tokens": 9017753600, "loss": 2.7611812591552733, "tokens_per_second": 975039.7336868619, "lr": 0.0015, "gradient_norm": 0.15377944707870483, "benchmark": false} | |
| {"step": 17220, "tokens": 9028239360, "loss": 2.7499597549438475, "tokens_per_second": 973128.490147308, "lr": 0.0015, "gradient_norm": 0.1422368735074997, "benchmark": false} | |
| {"step": 17240, "tokens": 9038725120, "loss": 2.748775863647461, "tokens_per_second": 972260.7517768494, "lr": 0.0015, "gradient_norm": 0.1399778127670288, "benchmark": false} | |
| {"step": 17260, "tokens": 9049210880, "loss": 2.744195556640625, "tokens_per_second": 972503.8708408589, "lr": 0.0015, "gradient_norm": 0.15270021557807922, "benchmark": false} | |
| {"step": 17280, "tokens": 9059696640, "loss": 2.7431943893432615, "tokens_per_second": 978225.6689434211, "lr": 0.0015, "gradient_norm": 0.12992249429225922, "benchmark": false} | |
| {"step": 17300, "tokens": 9070182400, "loss": 2.7543718338012697, "tokens_per_second": 975987.3586171558, "lr": 0.0015, "gradient_norm": 0.13417218625545502, "benchmark": false} | |
| {"step": 17320, "tokens": 9080668160, "loss": 2.7811412811279297, "tokens_per_second": 981816.5988330187, "lr": 0.0015, "gradient_norm": 0.1388479769229889, "benchmark": false} | |
| {"step": 17340, "tokens": 9091153920, "loss": 2.768684196472168, "tokens_per_second": 943903.5699324543, "lr": 0.0015, "gradient_norm": 0.14744503796100616, "benchmark": false} | |
| {"step": 17360, "tokens": 9101639680, "loss": 2.7610279083251954, "tokens_per_second": 970474.3713221656, "lr": 0.0015, "gradient_norm": 0.1268206387758255, "benchmark": false} | |
| {"step": 17380, "tokens": 9112125440, "loss": 2.756797981262207, "tokens_per_second": 985683.1531752532, "lr": 0.0015, "gradient_norm": 0.1387345790863037, "benchmark": false} | |
| {"step": 17400, "tokens": 9122611200, "loss": 2.7396427154541017, "tokens_per_second": 973783.5605719051, "lr": 0.0015, "gradient_norm": 0.13147492706775665, "benchmark": false} | |
| {"step": 17420, "tokens": 9133096960, "loss": 2.7857734680175783, "tokens_per_second": 970146.2288863184, "lr": 0.0015, "gradient_norm": 0.12245149910449982, "benchmark": false} | |
| {"step": 17440, "tokens": 9143582720, "loss": 2.718976593017578, "tokens_per_second": 972567.9211390832, "lr": 0.0015, "gradient_norm": 0.1322750300168991, "benchmark": false} | |
| {"step": 17460, "tokens": 9154068480, "loss": 2.756350517272949, "tokens_per_second": 963971.2649856538, "lr": 0.0015, "gradient_norm": 0.13418878614902496, "benchmark": false} | |
| {"step": 17480, "tokens": 9164554240, "loss": 2.7274747848510743, "tokens_per_second": 962931.4099102088, "lr": 0.0015, "gradient_norm": 0.1287911832332611, "benchmark": false} | |
| {"step": 17500, "tokens": 9175040000, "loss": 2.775168228149414, "tokens_per_second": 968762.2304840548, "lr": 0.0015, "gradient_norm": 0.13094007968902588, "benchmark": false} | |
| {"step": 17520, "tokens": 9185525760, "loss": 2.7674982070922853, "tokens_per_second": 851806.8391884612, "lr": 0.0015, "gradient_norm": 0.15391556918621063, "benchmark": false} | |
| {"step": 17540, "tokens": 9196011520, "loss": 2.7649585723876955, "tokens_per_second": 978741.8174425006, "lr": 0.0015, "gradient_norm": 0.1797247678041458, "benchmark": false} | |
| {"step": 17560, "tokens": 9206497280, "loss": 2.772072601318359, "tokens_per_second": 985750.2007544704, "lr": 0.0015, "gradient_norm": 0.13320325314998627, "benchmark": false} | |
| {"step": 17580, "tokens": 9216983040, "loss": 2.7577545166015627, "tokens_per_second": 953086.8095424904, "lr": 0.0015, "gradient_norm": 0.1323719322681427, "benchmark": false} | |
| {"step": 17600, "tokens": 9227468800, "loss": 2.782675933837891, "tokens_per_second": 979929.4030871085, "lr": 0.0015, "gradient_norm": 0.13484574854373932, "benchmark": false} | |
| {"step": 17620, "tokens": 9237954560, "loss": 2.7568662643432615, "tokens_per_second": 978752.2157680575, "lr": 0.0015, "gradient_norm": 0.136736199259758, "benchmark": false} | |
| {"step": 17640, "tokens": 9248440320, "loss": 2.7740283966064454, "tokens_per_second": 976126.8638298318, "lr": 0.0015, "gradient_norm": 0.13820508122444153, "benchmark": false} | |
| {"step": 17660, "tokens": 9258926080, "loss": 2.751175308227539, "tokens_per_second": 930623.7933325432, "lr": 0.0015, "gradient_norm": 0.12927785515785217, "benchmark": false} | |
| {"step": 17680, "tokens": 9269411840, "loss": 2.763106346130371, "tokens_per_second": 981702.3470782397, "lr": 0.0015, "gradient_norm": 0.16381075978279114, "benchmark": false} | |
| {"step": 17700, "tokens": 9279897600, "loss": 2.745603561401367, "tokens_per_second": 826202.709297162, "lr": 0.0015, "gradient_norm": 0.15377523005008698, "benchmark": false} | |
| {"step": 17720, "tokens": 9290383360, "loss": 2.7421333312988283, "tokens_per_second": 981758.1328926992, "lr": 0.0015, "gradient_norm": 0.126024067401886, "benchmark": false} | |
| {"step": 17740, "tokens": 9300869120, "loss": 2.7649770736694337, "tokens_per_second": 980855.0970585875, "lr": 0.0015, "gradient_norm": 0.14470013976097107, "benchmark": false} | |
| {"step": 17760, "tokens": 9311354880, "loss": 2.7876407623291017, "tokens_per_second": 971331.0546425834, "lr": 0.0015, "gradient_norm": 0.13005363941192627, "benchmark": false} | |
| {"step": 17780, "tokens": 9321840640, "loss": 2.732707214355469, "tokens_per_second": 972760.2975310354, "lr": 0.0015, "gradient_norm": 0.14452366530895233, "benchmark": false} | |
| {"step": 17800, "tokens": 9332326400, "loss": 2.77060546875, "tokens_per_second": 989434.0325064515, "lr": 0.0015, "gradient_norm": 0.1521960347890854, "benchmark": false} | |
| {"step": 17820, "tokens": 9342812160, "loss": 2.788447952270508, "tokens_per_second": 973698.0961508178, "lr": 0.0015, "gradient_norm": 0.1329130381345749, "benchmark": false} | |
| {"step": 17840, "tokens": 9353297920, "loss": 2.741864013671875, "tokens_per_second": 979741.2364587133, "lr": 0.0015, "gradient_norm": 0.13201284408569336, "benchmark": false} | |
| {"step": 17860, "tokens": 9363783680, "loss": 2.7798189163208007, "tokens_per_second": 984993.2254714462, "lr": 0.0015, "gradient_norm": 0.14289097487926483, "benchmark": false} | |
| {"step": 17880, "tokens": 9374269440, "loss": 2.749721336364746, "tokens_per_second": 817039.2847753566, "lr": 0.0015, "gradient_norm": 0.1367609202861786, "benchmark": false} | |
| {"step": 17900, "tokens": 9384755200, "loss": 2.7631113052368166, "tokens_per_second": 990630.6345504698, "lr": 0.0015, "gradient_norm": 0.1484352946281433, "benchmark": false} | |
| {"step": 17920, "tokens": 9395240960, "loss": 2.7630970001220705, "tokens_per_second": 982863.4372793777, "lr": 0.0015, "gradient_norm": 0.1495262086391449, "benchmark": false} | |
| {"step": 17940, "tokens": 9405726720, "loss": 2.742411422729492, "tokens_per_second": 993852.2885264372, "lr": 0.0015, "gradient_norm": 0.12873972952365875, "benchmark": false} | |
| {"step": 17960, "tokens": 9416212480, "loss": 2.7404382705688475, "tokens_per_second": 979842.152883283, "lr": 0.0015, "gradient_norm": 0.14923682808876038, "benchmark": false} | |
| {"step": 17980, "tokens": 9426698240, "loss": 2.7674840927124023, "tokens_per_second": 984205.3643317616, "lr": 0.0015, "gradient_norm": 0.1542074829339981, "benchmark": false} | |
| {"step": 18000, "tokens": 9437184000, "loss": 2.7930335998535156, "tokens_per_second": 990893.5270222354, "lr": 0.0015, "gradient_norm": 0.14015617966651917, "benchmark": false} | |
| {"step": 18020, "tokens": 9447669760, "loss": 2.758540153503418, "tokens_per_second": 818144.637390868, "lr": 0.0015, "gradient_norm": 0.13568595051765442, "benchmark": false} | |
| {"step": 18040, "tokens": 9458155520, "loss": 2.773590087890625, "tokens_per_second": 987654.272992748, "lr": 0.0015, "gradient_norm": 0.17056041955947876, "benchmark": false} | |
| {"step": 18060, "tokens": 9468641280, "loss": 2.755166244506836, "tokens_per_second": 997451.8892775568, "lr": 0.0015, "gradient_norm": 0.15264220535755157, "benchmark": false} | |
| {"step": 18080, "tokens": 9479127040, "loss": 2.7567907333374024, "tokens_per_second": 823335.8497921854, "lr": 0.0015, "gradient_norm": 0.12703871726989746, "benchmark": false} | |
| {"step": 18100, "tokens": 9489612800, "loss": 2.751226234436035, "tokens_per_second": 981311.9940021969, "lr": 0.0015, "gradient_norm": 0.13139593601226807, "benchmark": false} | |
| {"step": 18120, "tokens": 9500098560, "loss": 2.761592483520508, "tokens_per_second": 987213.4140057209, "lr": 0.0015, "gradient_norm": 0.1309671401977539, "benchmark": false} | |
| {"step": 18140, "tokens": 9510584320, "loss": 2.738187789916992, "tokens_per_second": 850584.1205855551, "lr": 0.0015, "gradient_norm": 0.1313798576593399, "benchmark": false} | |
| {"step": 18160, "tokens": 9521070080, "loss": 2.760685348510742, "tokens_per_second": 983953.5986733984, "lr": 0.0015, "gradient_norm": 0.12200405448675156, "benchmark": false} | |
| {"step": 18180, "tokens": 9531555840, "loss": 2.7776906967163084, "tokens_per_second": 987756.5702489881, "lr": 0.0015, "gradient_norm": 0.13532468676567078, "benchmark": false} | |
| {"step": 18200, "tokens": 9542041600, "loss": 2.753097915649414, "tokens_per_second": 981423.3677710297, "lr": 0.0015, "gradient_norm": 0.1355116069316864, "benchmark": false} | |
| {"step": 18220, "tokens": 9552527360, "loss": 2.7980825424194338, "tokens_per_second": 977179.1044857997, "lr": 0.0015, "gradient_norm": 0.15921863913536072, "benchmark": false} | |
| {"step": 18240, "tokens": 9563013120, "loss": 2.7654159545898436, "tokens_per_second": 981370.94909307, "lr": 0.0015, "gradient_norm": 0.13426631689071655, "benchmark": false} | |
| {"step": 18260, "tokens": 9573498880, "loss": 2.734653091430664, "tokens_per_second": 985408.8420229255, "lr": 0.0015, "gradient_norm": 0.1270996332168579, "benchmark": false} | |
| {"step": 18280, "tokens": 9583984640, "loss": 2.7667760848999023, "tokens_per_second": 973075.9869128108, "lr": 0.0015, "gradient_norm": 0.15058858692646027, "benchmark": false} | |
| {"step": 18300, "tokens": 9594470400, "loss": 2.7640096664428713, "tokens_per_second": 939744.7905982776, "lr": 0.0015, "gradient_norm": 0.15722115337848663, "benchmark": false} | |
| {"step": 18320, "tokens": 9604956160, "loss": 2.7840244293212892, "tokens_per_second": 983453.4724224303, "lr": 0.0015, "gradient_norm": 0.15602311491966248, "benchmark": false} | |
| {"step": 18340, "tokens": 9615441920, "loss": 2.779916191101074, "tokens_per_second": 987107.2701568747, "lr": 0.0015, "gradient_norm": 0.13586574792861938, "benchmark": false} | |
| {"step": 18360, "tokens": 9625927680, "loss": 2.7543210983276367, "tokens_per_second": 975885.1121562502, "lr": 0.0015, "gradient_norm": 0.12298431992530823, "benchmark": false} | |
| {"step": 18380, "tokens": 9636413440, "loss": 2.7541200637817385, "tokens_per_second": 978007.5796573953, "lr": 0.0015, "gradient_norm": 0.13819445669651031, "benchmark": false} | |
| {"step": 18400, "tokens": 9646899200, "loss": 2.7527652740478517, "tokens_per_second": 979229.8178542908, "lr": 0.0015, "gradient_norm": 0.14924854040145874, "benchmark": false} | |
| {"step": 18420, "tokens": 9657384960, "loss": 2.7542049407958986, "tokens_per_second": 990100.4783217756, "lr": 0.0015, "gradient_norm": 0.12890124320983887, "benchmark": false} | |
| {"step": 18440, "tokens": 9667870720, "loss": 2.7615888595581053, "tokens_per_second": 978303.8545806182, "lr": 0.0015, "gradient_norm": 0.12055376172065735, "benchmark": false} | |
| {"step": 18460, "tokens": 9678356480, "loss": 2.744034767150879, "tokens_per_second": 984021.9975202855, "lr": 0.0015, "gradient_norm": 0.12270098924636841, "benchmark": false} | |
| {"step": 18480, "tokens": 9688842240, "loss": 2.7206756591796877, "tokens_per_second": 984063.8381700526, "lr": 0.0015, "gradient_norm": 0.14856895804405212, "benchmark": false} | |
| {"step": 18500, "tokens": 9699328000, "loss": 2.7920162200927736, "tokens_per_second": 981286.7393001046, "lr": 0.0015, "gradient_norm": 0.135093092918396, "benchmark": false} | |
| {"step": 18520, "tokens": 9709813760, "loss": 2.7670785903930666, "tokens_per_second": 856762.899164113, "lr": 0.0015, "gradient_norm": 0.1572120636701584, "benchmark": false} | |
| {"step": 18540, "tokens": 9720299520, "loss": 2.7770042419433594, "tokens_per_second": 984636.7704320224, "lr": 0.0015, "gradient_norm": 0.13100825250148773, "benchmark": false} | |
| {"step": 18560, "tokens": 9730785280, "loss": 2.7588457107543944, "tokens_per_second": 989975.3800258805, "lr": 0.0015, "gradient_norm": 0.1295267790555954, "benchmark": false} | |
| {"step": 18580, "tokens": 9741271040, "loss": 2.7459754943847656, "tokens_per_second": 982047.222593462, "lr": 0.0015, "gradient_norm": 0.13318170607089996, "benchmark": false} | |
| {"step": 18600, "tokens": 9751756800, "loss": 2.7676055908203123, "tokens_per_second": 988762.5051151864, "lr": 0.0015, "gradient_norm": 0.1925567090511322, "benchmark": false} | |
| {"step": 18620, "tokens": 9762242560, "loss": 2.7560264587402346, "tokens_per_second": 936110.6485667815, "lr": 0.0015, "gradient_norm": 0.14456474781036377, "benchmark": false} | |
| {"step": 18640, "tokens": 9772728320, "loss": 2.7433448791503907, "tokens_per_second": 974439.72205389, "lr": 0.0015, "gradient_norm": 0.14269590377807617, "benchmark": false} | |
| {"step": 18660, "tokens": 9783214080, "loss": 2.7503887176513673, "tokens_per_second": 983996.9170213623, "lr": 0.0015, "gradient_norm": 0.15311908721923828, "benchmark": false} | |
| {"step": 18680, "tokens": 9793699840, "loss": 2.734910011291504, "tokens_per_second": 842610.3019881422, "lr": 0.0015, "gradient_norm": 0.1374574452638626, "benchmark": false} | |
| {"step": 18700, "tokens": 9804185600, "loss": 2.766593170166016, "tokens_per_second": 853746.7445592219, "lr": 0.0015, "gradient_norm": 0.15296505391597748, "benchmark": false} | |
| {"step": 18720, "tokens": 9814671360, "loss": 2.777023124694824, "tokens_per_second": 987797.1293850364, "lr": 0.0015, "gradient_norm": 0.1512424647808075, "benchmark": false} | |
| {"step": 18740, "tokens": 9825157120, "loss": 2.7504552841186523, "tokens_per_second": 836360.4772060671, "lr": 0.0015, "gradient_norm": 0.15182772278785706, "benchmark": false} | |
| {"step": 18760, "tokens": 9835642880, "loss": 2.727306938171387, "tokens_per_second": 984329.6585641716, "lr": 0.0015, "gradient_norm": 0.13857623934745789, "benchmark": false} | |
| {"step": 18780, "tokens": 9846128640, "loss": 2.7347822189331055, "tokens_per_second": 991228.0074263852, "lr": 0.0015, "gradient_norm": 0.13486629724502563, "benchmark": false} | |
| {"step": 18800, "tokens": 9856614400, "loss": 2.759987449645996, "tokens_per_second": 940285.1045097407, "lr": 0.0015, "gradient_norm": 0.13096344470977783, "benchmark": false} | |
| {"step": 18820, "tokens": 9867100160, "loss": 2.725802993774414, "tokens_per_second": 970691.2985620613, "lr": 0.0015, "gradient_norm": 0.1531582623720169, "benchmark": false} | |
| {"step": 18840, "tokens": 9877585920, "loss": 2.7555524826049806, "tokens_per_second": 969109.3055810479, "lr": 0.0015, "gradient_norm": 0.1490205079317093, "benchmark": false} | |
| {"step": 18860, "tokens": 9888071680, "loss": 2.72528076171875, "tokens_per_second": 974191.9631154499, "lr": 0.0015, "gradient_norm": 0.20771285891532898, "benchmark": false} | |
| {"step": 18880, "tokens": 9898557440, "loss": 2.7407989501953125, "tokens_per_second": 973234.1554190256, "lr": 0.0015, "gradient_norm": 0.1277577430009842, "benchmark": false} | |
| {"step": 18900, "tokens": 9909043200, "loss": 2.728755569458008, "tokens_per_second": 971406.7877257998, "lr": 0.0015, "gradient_norm": 0.16711361706256866, "benchmark": false} | |
| {"step": 18920, "tokens": 9919528960, "loss": 2.7621150970458985, "tokens_per_second": 972782.1484616387, "lr": 0.0015, "gradient_norm": 0.16017542779445648, "benchmark": false} | |
| {"step": 18940, "tokens": 9930014720, "loss": 2.727202796936035, "tokens_per_second": 973235.1702008498, "lr": 0.0015, "gradient_norm": 0.15433576703071594, "benchmark": false} | |
| {"step": 18960, "tokens": 9940500480, "loss": 2.751300811767578, "tokens_per_second": 977357.1369480103, "lr": 0.0015, "gradient_norm": 0.14042624831199646, "benchmark": false} | |
| {"step": 18980, "tokens": 9950986240, "loss": 2.731955718994141, "tokens_per_second": 973377.4680011334, "lr": 0.0015, "gradient_norm": 0.13745440542697906, "benchmark": false} | |
| {"step": 19000, "tokens": 9961472000, "loss": 2.720782661437988, "tokens_per_second": 969674.3917193501, "lr": 0.0015, "gradient_norm": 0.15510135889053345, "benchmark": false} | |
| {"step": 19020, "tokens": 9971957760, "loss": 2.736471748352051, "tokens_per_second": 827558.4382417401, "lr": 0.0015, "gradient_norm": 0.14572863280773163, "benchmark": false} | |
| {"step": 19040, "tokens": 9982443520, "loss": 2.753316307067871, "tokens_per_second": 903611.3654674874, "lr": 0.0015, "gradient_norm": 0.12864474952220917, "benchmark": false} | |
| {"step": 19060, "tokens": 9992929280, "loss": 2.6966789245605467, "tokens_per_second": 983493.5365173507, "lr": 0.0015, "gradient_norm": 0.14442148804664612, "benchmark": false} | |
| {"step": 19080, "tokens": 10003415040, "loss": 2.747500991821289, "tokens_per_second": 986488.5372464606, "lr": 0.0015, "gradient_norm": 0.15878035128116608, "benchmark": false} | |
| {"step": 19100, "tokens": 10013900800, "loss": 2.7421308517456056, "tokens_per_second": 852400.9870833084, "lr": 0.0015, "gradient_norm": 0.1463121771812439, "benchmark": false} | |
| {"step": 19120, "tokens": 10024386560, "loss": 2.755142593383789, "tokens_per_second": 980298.5760051379, "lr": 0.0015, "gradient_norm": 0.14999626576900482, "benchmark": false} | |
| {"step": 19140, "tokens": 10034872320, "loss": 2.764512825012207, "tokens_per_second": 982010.3202606466, "lr": 0.0015, "gradient_norm": 0.14382047951221466, "benchmark": false} | |
| {"step": 19160, "tokens": 10045358080, "loss": 2.7893213272094726, "tokens_per_second": 981731.5379929591, "lr": 0.0015, "gradient_norm": 0.1472080945968628, "benchmark": false} | |
| {"step": 19180, "tokens": 10055843840, "loss": 2.775373840332031, "tokens_per_second": 986579.4321388454, "lr": 0.0015, "gradient_norm": 0.16339096426963806, "benchmark": false} | |
| {"step": 19200, "tokens": 10066329600, "loss": 2.7338415145874024, "tokens_per_second": 985006.8019876045, "lr": 0.0015, "gradient_norm": 0.1467619240283966, "benchmark": false} | |
| {"step": 19220, "tokens": 10076815360, "loss": 2.7391054153442385, "tokens_per_second": 986374.2817026775, "lr": 0.0015, "gradient_norm": 0.13758915662765503, "benchmark": false} | |
| {"step": 19240, "tokens": 10087301120, "loss": 2.7754047393798826, "tokens_per_second": 971840.8801934872, "lr": 0.0015, "gradient_norm": 0.14771384000778198, "benchmark": false} | |
| {"step": 19260, "tokens": 10097786880, "loss": 2.7327503204345702, "tokens_per_second": 986777.7838339044, "lr": 0.0015, "gradient_norm": 0.14304034411907196, "benchmark": false} | |
| {"step": 19280, "tokens": 10108272640, "loss": 2.737362289428711, "tokens_per_second": 960096.6457040833, "lr": 0.0015, "gradient_norm": 0.1469821035861969, "benchmark": false} | |
| {"step": 19300, "tokens": 10118758400, "loss": 2.7284309387207033, "tokens_per_second": 990246.9780272543, "lr": 0.0015, "gradient_norm": 0.1260739117860794, "benchmark": false} | |
| {"step": 19320, "tokens": 10129244160, "loss": 2.7618661880493165, "tokens_per_second": 981053.1388018135, "lr": 0.0015, "gradient_norm": 0.14013761281967163, "benchmark": false} | |
| {"step": 19340, "tokens": 10139729920, "loss": 2.711724853515625, "tokens_per_second": 990001.7675820682, "lr": 0.0015, "gradient_norm": 0.16674073040485382, "benchmark": false} | |
| {"step": 19360, "tokens": 10150215680, "loss": 2.7775001525878906, "tokens_per_second": 980875.3842120795, "lr": 0.0015, "gradient_norm": 0.14825303852558136, "benchmark": false} | |
| {"step": 19380, "tokens": 10160701440, "loss": 2.7760234832763673, "tokens_per_second": 982545.7817744224, "lr": 0.0015, "gradient_norm": 0.1374744027853012, "benchmark": false} | |
| {"step": 19400, "tokens": 10171187200, "loss": 2.699192237854004, "tokens_per_second": 981344.6805466847, "lr": 0.0015, "gradient_norm": 0.1348937451839447, "benchmark": false} | |
| {"step": 19420, "tokens": 10181672960, "loss": 2.718426513671875, "tokens_per_second": 989411.0038016039, "lr": 0.0015, "gradient_norm": 0.1586708426475525, "benchmark": false} | |
| {"step": 19440, "tokens": 10192158720, "loss": 2.7526338577270506, "tokens_per_second": 985705.693807527, "lr": 0.0015, "gradient_norm": 0.14063024520874023, "benchmark": false} | |
| {"step": 19460, "tokens": 10202644480, "loss": 2.7707040786743162, "tokens_per_second": 985252.5051055208, "lr": 0.0015, "gradient_norm": 0.16430909931659698, "benchmark": false} | |
| {"step": 19480, "tokens": 10213130240, "loss": 2.770153045654297, "tokens_per_second": 985265.7709530981, "lr": 0.0015, "gradient_norm": 0.17231428623199463, "benchmark": false} | |
| {"step": 19500, "tokens": 10223616000, "loss": 2.7508995056152346, "tokens_per_second": 987447.5489612769, "lr": 0.0015, "gradient_norm": 0.15210653841495514, "benchmark": false} | |
| {"step": 19520, "tokens": 10234101760, "loss": 2.754379463195801, "tokens_per_second": 868624.3791890546, "lr": 0.0015, "gradient_norm": 0.14836817979812622, "benchmark": false} | |
| {"step": 19540, "tokens": 10244587520, "loss": 2.7675302505493162, "tokens_per_second": 990896.1461014918, "lr": 0.0015, "gradient_norm": 0.1669021099805832, "benchmark": false} | |
| {"step": 19560, "tokens": 10255073280, "loss": 2.754825973510742, "tokens_per_second": 942646.142548731, "lr": 0.0015, "gradient_norm": 0.14446082711219788, "benchmark": false} | |
| {"step": 19580, "tokens": 10265559040, "loss": 2.769974136352539, "tokens_per_second": 987735.7227031054, "lr": 0.0015, "gradient_norm": 0.20880039036273956, "benchmark": false} | |
| {"step": 19600, "tokens": 10276044800, "loss": 2.716664505004883, "tokens_per_second": 971903.9757540174, "lr": 0.0015, "gradient_norm": 0.1424456536769867, "benchmark": false} | |
| {"step": 19620, "tokens": 10286530560, "loss": 2.784602737426758, "tokens_per_second": 976148.7554122006, "lr": 0.0015, "gradient_norm": 0.16809336841106415, "benchmark": false} | |
| {"step": 19640, "tokens": 10297016320, "loss": 2.7417274475097657, "tokens_per_second": 977024.9841617052, "lr": 0.0015, "gradient_norm": 0.12771359086036682, "benchmark": false} | |
| {"step": 19660, "tokens": 10307502080, "loss": 2.7644590377807616, "tokens_per_second": 975536.922103438, "lr": 0.0015, "gradient_norm": 0.1824571192264557, "benchmark": false} | |
| {"step": 19680, "tokens": 10317987840, "loss": 2.7277626037597655, "tokens_per_second": 973575.6069572754, "lr": 0.0015, "gradient_norm": 0.15565495193004608, "benchmark": false} | |
| {"step": 19700, "tokens": 10328473600, "loss": 2.7233196258544923, "tokens_per_second": 979733.0743139815, "lr": 0.0015, "gradient_norm": 0.13642647862434387, "benchmark": false} | |
| {"step": 19720, "tokens": 10338959360, "loss": 2.751569938659668, "tokens_per_second": 988856.8240925538, "lr": 0.0015, "gradient_norm": 0.14205482602119446, "benchmark": false} | |
| {"step": 19740, "tokens": 10349445120, "loss": 2.7716190338134767, "tokens_per_second": 817926.7112511618, "lr": 0.0015, "gradient_norm": 0.1491253674030304, "benchmark": false} | |
| {"step": 19760, "tokens": 10359930880, "loss": 2.7228086471557615, "tokens_per_second": 996178.2929142038, "lr": 0.0015, "gradient_norm": 0.16393040120601654, "benchmark": false} | |
| {"step": 19780, "tokens": 10370416640, "loss": 2.7475027084350585, "tokens_per_second": 912376.6426194644, "lr": 0.0015, "gradient_norm": 0.14863534271717072, "benchmark": false} | |
| {"step": 19800, "tokens": 10380902400, "loss": 2.7468582153320313, "tokens_per_second": 982878.9220169957, "lr": 0.0015, "gradient_norm": 0.1454748809337616, "benchmark": false} | |
| {"step": 19820, "tokens": 10391388160, "loss": 2.77371826171875, "tokens_per_second": 988750.1280899943, "lr": 0.0015, "gradient_norm": 0.14740391075611115, "benchmark": false} | |
| {"step": 19840, "tokens": 10401873920, "loss": 2.7487648010253904, "tokens_per_second": 986397.7296181752, "lr": 0.0015, "gradient_norm": 0.15100659430027008, "benchmark": false} | |
| {"step": 19860, "tokens": 10412359680, "loss": 2.7202035903930666, "tokens_per_second": 990005.2628967476, "lr": 0.0015, "gradient_norm": 0.14142200350761414, "benchmark": false} | |
| {"step": 19880, "tokens": 10422845440, "loss": 2.743912124633789, "tokens_per_second": 980083.111584104, "lr": 0.0015, "gradient_norm": 0.1572934240102768, "benchmark": false} | |
| {"step": 19900, "tokens": 10433331200, "loss": 2.7287742614746096, "tokens_per_second": 975907.5155970105, "lr": 0.0015, "gradient_norm": 0.15567274391651154, "benchmark": false} | |
| {"step": 19920, "tokens": 10443816960, "loss": 2.755885696411133, "tokens_per_second": 984160.8857441117, "lr": 0.0015, "gradient_norm": 0.15185023844242096, "benchmark": false} | |
| {"step": 19940, "tokens": 10454302720, "loss": 2.7497489929199217, "tokens_per_second": 978481.6580073143, "lr": 0.0015, "gradient_norm": 0.1444910168647766, "benchmark": false} | |
| {"step": 19960, "tokens": 10464788480, "loss": 2.759548377990723, "tokens_per_second": 985718.732058168, "lr": 0.0015, "gradient_norm": 0.17241807281970978, "benchmark": false} | |
| {"step": 19980, "tokens": 10475274240, "loss": 2.765959548950195, "tokens_per_second": 984693.2569846577, "lr": 0.0015, "gradient_norm": 0.15740971267223358, "benchmark": false} | |
| {"step": 20000, "tokens": 10485760000, "loss": 2.7601818084716796, "tokens_per_second": 837521.6981495382, "lr": 0.0015, "gradient_norm": 0.140048548579216, "benchmark": false} | |
| {"step": 20020, "tokens": 10496245760, "loss": 2.7482187271118166, "tokens_per_second": 815863.3869617886, "lr": 0.0015, "gradient_norm": 0.14850586652755737, "benchmark": false} | |
| {"step": 20040, "tokens": 10506731520, "loss": 2.7507583618164064, "tokens_per_second": 982837.1355751838, "lr": 0.0015, "gradient_norm": 0.15282844007015228, "benchmark": false} | |
| {"step": 20060, "tokens": 10517217280, "loss": 2.7343465805053713, "tokens_per_second": 996236.5602341059, "lr": 0.0015, "gradient_norm": 0.1375744342803955, "benchmark": false} | |
| {"step": 20080, "tokens": 10527703040, "loss": 2.760054588317871, "tokens_per_second": 844460.4750382531, "lr": 0.0015, "gradient_norm": 0.16157233715057373, "benchmark": false} | |
| {"step": 20100, "tokens": 10538188800, "loss": 2.7180532455444335, "tokens_per_second": 982018.1308888848, "lr": 0.0015, "gradient_norm": 0.14448480308055878, "benchmark": false} | |
| {"step": 20120, "tokens": 10548674560, "loss": 2.769293212890625, "tokens_per_second": 972250.4932649111, "lr": 0.0015, "gradient_norm": 0.14115169644355774, "benchmark": false} | |
| {"step": 20140, "tokens": 10559160320, "loss": 2.743351173400879, "tokens_per_second": 975515.970219282, "lr": 0.0015, "gradient_norm": 0.14357905089855194, "benchmark": false} | |
| {"step": 20160, "tokens": 10569646080, "loss": 2.7633874893188475, "tokens_per_second": 978432.818261292, "lr": 0.0015, "gradient_norm": 0.15365487337112427, "benchmark": false} | |
| {"step": 20180, "tokens": 10580131840, "loss": 2.7610193252563477, "tokens_per_second": 976707.4679605602, "lr": 0.0015, "gradient_norm": 0.14246156811714172, "benchmark": false} | |
| {"step": 20200, "tokens": 10590617600, "loss": 2.740561103820801, "tokens_per_second": 977446.473636771, "lr": 0.0015, "gradient_norm": 0.16009457409381866, "benchmark": false} | |
| {"step": 20220, "tokens": 10601103360, "loss": 2.720977783203125, "tokens_per_second": 974762.7170033227, "lr": 0.0015, "gradient_norm": 0.20825006067752838, "benchmark": false} | |
| {"step": 20240, "tokens": 10611589120, "loss": 2.7392934799194335, "tokens_per_second": 986141.0148407788, "lr": 0.0015, "gradient_norm": 0.15124203264713287, "benchmark": false} | |
| {"step": 20260, "tokens": 10622074880, "loss": 2.7258880615234373, "tokens_per_second": 831364.0932077336, "lr": 0.0015, "gradient_norm": 0.2038249969482422, "benchmark": false} | |
| {"step": 20280, "tokens": 10632560640, "loss": 2.7766510009765626, "tokens_per_second": 981821.9761783535, "lr": 0.0015, "gradient_norm": 0.13956715166568756, "benchmark": false} | |
| {"step": 20300, "tokens": 10643046400, "loss": 2.7324808120727537, "tokens_per_second": 979214.5308953221, "lr": 0.0015, "gradient_norm": 0.1723640114068985, "benchmark": false} | |
| {"step": 20320, "tokens": 10653532160, "loss": 2.7113363265991213, "tokens_per_second": 970684.5656375552, "lr": 0.0015, "gradient_norm": 0.13509832322597504, "benchmark": false} | |
| {"step": 20340, "tokens": 10664017920, "loss": 2.761567497253418, "tokens_per_second": 982388.4414941983, "lr": 0.0015, "gradient_norm": 0.13982176780700684, "benchmark": false} | |
| {"step": 20360, "tokens": 10674503680, "loss": 2.7360662460327148, "tokens_per_second": 977945.0388315676, "lr": 0.0015, "gradient_norm": 0.15452997386455536, "benchmark": false} | |
| {"step": 20380, "tokens": 10684989440, "loss": 2.7244327545166014, "tokens_per_second": 982084.2929775625, "lr": 0.0015, "gradient_norm": 0.14956440031528473, "benchmark": false} | |
| {"step": 20400, "tokens": 10695475200, "loss": 2.76476993560791, "tokens_per_second": 971121.3641976244, "lr": 0.0015, "gradient_norm": 0.1706211119890213, "benchmark": false} | |
| {"step": 20420, "tokens": 10705960960, "loss": 2.753704071044922, "tokens_per_second": 980687.0851026584, "lr": 0.0015, "gradient_norm": 0.1481383889913559, "benchmark": false} | |
| {"step": 20440, "tokens": 10716446720, "loss": 2.753870964050293, "tokens_per_second": 978169.9813464287, "lr": 0.0015, "gradient_norm": 0.15416103601455688, "benchmark": false} | |
| {"step": 20460, "tokens": 10726932480, "loss": 2.7352483749389647, "tokens_per_second": 978425.8752704178, "lr": 0.0015, "gradient_norm": 0.15846577286720276, "benchmark": false} | |
| {"step": 20480, "tokens": 10737418240, "loss": 2.733202362060547, "tokens_per_second": 989329.4571691591, "lr": 0.0015, "gradient_norm": 0.14727097749710083, "benchmark": false} | |
| {"step": 20500, "tokens": 10747904000, "loss": 2.743163299560547, "tokens_per_second": 990398.8649932749, "lr": 0.0015, "gradient_norm": 0.14675293862819672, "benchmark": false} | |
| {"step": 20520, "tokens": 10758389760, "loss": 2.7502891540527346, "tokens_per_second": 778152.2190613195, "lr": 0.0015, "gradient_norm": 0.1588241308927536, "benchmark": false} | |
| {"step": 20540, "tokens": 10768875520, "loss": 2.7529842376708986, "tokens_per_second": 993998.8605152208, "lr": 0.0015, "gradient_norm": 0.13833782076835632, "benchmark": false} | |
| {"step": 20560, "tokens": 10779361280, "loss": 2.7573177337646486, "tokens_per_second": 984597.292859046, "lr": 0.0015, "gradient_norm": 0.14055199921131134, "benchmark": false} | |
| {"step": 20580, "tokens": 10789847040, "loss": 2.762322998046875, "tokens_per_second": 983528.5535243816, "lr": 0.0015, "gradient_norm": 0.17151477932929993, "benchmark": false} | |
| {"step": 20600, "tokens": 10800332800, "loss": 2.7454185485839844, "tokens_per_second": 978846.9869995496, "lr": 0.0015, "gradient_norm": 0.16418181359767914, "benchmark": false} | |
| {"step": 20620, "tokens": 10810818560, "loss": 2.7720109939575197, "tokens_per_second": 988054.4007539555, "lr": 0.0015, "gradient_norm": 0.1813291758298874, "benchmark": false} | |
| {"step": 20640, "tokens": 10821304320, "loss": 2.744840621948242, "tokens_per_second": 983213.2232795581, "lr": 0.0015, "gradient_norm": 0.1516708880662918, "benchmark": false} | |
| {"step": 20660, "tokens": 10831790080, "loss": 2.751976203918457, "tokens_per_second": 942926.3424132457, "lr": 0.0015, "gradient_norm": 0.14769695699214935, "benchmark": false} | |
| {"step": 20680, "tokens": 10842275840, "loss": 2.7134735107421877, "tokens_per_second": 987092.7115713909, "lr": 0.0015, "gradient_norm": 0.21292518079280853, "benchmark": false} | |
| {"step": 20700, "tokens": 10852761600, "loss": 2.712258148193359, "tokens_per_second": 985639.3671655391, "lr": 0.0015, "gradient_norm": 0.14630071818828583, "benchmark": false} | |
| {"step": 20720, "tokens": 10863247360, "loss": 2.7553104400634765, "tokens_per_second": 976125.8297539846, "lr": 0.0015, "gradient_norm": 0.15526510775089264, "benchmark": false} | |
| {"step": 20740, "tokens": 10873733120, "loss": 2.7063453674316404, "tokens_per_second": 984479.200702056, "lr": 0.0015, "gradient_norm": 0.16980494558811188, "benchmark": false} | |
| {"step": 20760, "tokens": 10884218880, "loss": 2.731993293762207, "tokens_per_second": 995509.2724137008, "lr": 0.0015, "gradient_norm": 0.17160440981388092, "benchmark": false} | |
| {"step": 20780, "tokens": 10894704640, "loss": 2.764567565917969, "tokens_per_second": 851389.117484721, "lr": 0.0015, "gradient_norm": 0.15944555401802063, "benchmark": false} | |
| {"step": 20800, "tokens": 10905190400, "loss": 2.7618080139160157, "tokens_per_second": 983265.0437103453, "lr": 0.0015, "gradient_norm": 0.15064853429794312, "benchmark": false} | |
| {"step": 20820, "tokens": 10915676160, "loss": 2.7552326202392576, "tokens_per_second": 948031.7664346788, "lr": 0.0015, "gradient_norm": 0.16517570614814758, "benchmark": false} | |
| {"step": 20840, "tokens": 10926161920, "loss": 2.7202905654907226, "tokens_per_second": 983289.6722699247, "lr": 0.0015, "gradient_norm": 0.1581203043460846, "benchmark": false} | |
| {"step": 20860, "tokens": 10936647680, "loss": 2.741757392883301, "tokens_per_second": 839273.6218400227, "lr": 0.0015, "gradient_norm": 0.15664806962013245, "benchmark": false} | |
| {"step": 20880, "tokens": 10947133440, "loss": 2.74169807434082, "tokens_per_second": 988738.4109788855, "lr": 0.0015, "gradient_norm": 0.1459798365831375, "benchmark": false} | |
| {"step": 20900, "tokens": 10957619200, "loss": 2.739409065246582, "tokens_per_second": 976486.3894187118, "lr": 0.0015, "gradient_norm": 0.1331249326467514, "benchmark": false} | |
| {"step": 20920, "tokens": 10968104960, "loss": 2.6998008728027343, "tokens_per_second": 987056.8220554556, "lr": 0.0015, "gradient_norm": 0.15153661370277405, "benchmark": false} | |
| {"step": 20940, "tokens": 10978590720, "loss": 2.738968276977539, "tokens_per_second": 987221.1977737239, "lr": 0.0015, "gradient_norm": 0.1653854250907898, "benchmark": false} | |
| {"step": 20960, "tokens": 10989076480, "loss": 2.7486549377441407, "tokens_per_second": 796103.0779271537, "lr": 0.0015, "gradient_norm": 0.1491522192955017, "benchmark": false} | |
| {"step": 20980, "tokens": 10999562240, "loss": 2.7450157165527345, "tokens_per_second": 987344.8799541212, "lr": 0.0015, "gradient_norm": 0.1675918698310852, "benchmark": false} | |
| {"step": 21000, "tokens": 11010048000, "loss": 2.7119800567626955, "tokens_per_second": 992182.775109319, "lr": 0.0015, "gradient_norm": 0.14855486154556274, "benchmark": false} | |
| {"step": 21020, "tokens": 11020533760, "loss": 2.7412237167358398, "tokens_per_second": 823605.7211595208, "lr": 0.0015, "gradient_norm": 0.1713978499174118, "benchmark": false} | |
| {"step": 21040, "tokens": 11031019520, "loss": 2.71264591217041, "tokens_per_second": 957452.7862116075, "lr": 0.0015, "gradient_norm": 0.16591550409793854, "benchmark": false} | |
| {"step": 21060, "tokens": 11041505280, "loss": 2.764055633544922, "tokens_per_second": 996040.605801838, "lr": 0.0015, "gradient_norm": 0.17413797974586487, "benchmark": false} | |
| {"step": 21080, "tokens": 11051991040, "loss": 2.7366050720214843, "tokens_per_second": 984438.3881484806, "lr": 0.0015, "gradient_norm": 0.16170263290405273, "benchmark": false} | |
| {"step": 21100, "tokens": 11062476800, "loss": 2.7537540435791015, "tokens_per_second": 974425.6193885907, "lr": 0.0015, "gradient_norm": 0.17343269288539886, "benchmark": false} | |
| {"step": 21120, "tokens": 11072962560, "loss": 2.738983917236328, "tokens_per_second": 985374.9987583428, "lr": 0.0015, "gradient_norm": 0.158656507730484, "benchmark": false} | |
| {"step": 21140, "tokens": 11083448320, "loss": 2.7355117797851562, "tokens_per_second": 977298.3800180755, "lr": 0.0015, "gradient_norm": 0.1741272658109665, "benchmark": false} | |
| {"step": 21160, "tokens": 11093934080, "loss": 2.696071243286133, "tokens_per_second": 979845.1336802829, "lr": 0.0015, "gradient_norm": 0.1505553275346756, "benchmark": false} | |
| {"step": 21180, "tokens": 11104419840, "loss": 2.7300960540771486, "tokens_per_second": 975829.9134785949, "lr": 0.0015, "gradient_norm": 0.1768353432416916, "benchmark": false} | |
| {"step": 21200, "tokens": 11114905600, "loss": 2.7417701721191405, "tokens_per_second": 986108.9429896275, "lr": 0.0015, "gradient_norm": 0.14486666023731232, "benchmark": false} | |
| {"step": 21220, "tokens": 11125391360, "loss": 2.718777084350586, "tokens_per_second": 992414.8132202647, "lr": 0.0015, "gradient_norm": 0.14299793541431427, "benchmark": false} | |
| {"step": 21240, "tokens": 11135877120, "loss": 2.7259212493896485, "tokens_per_second": 942023.4272862579, "lr": 0.0015, "gradient_norm": 0.13855697214603424, "benchmark": false} | |
| {"step": 21260, "tokens": 11146362880, "loss": 2.740422821044922, "tokens_per_second": 983212.163423991, "lr": 0.0015, "gradient_norm": 0.15689922869205475, "benchmark": false} | |
| {"step": 21280, "tokens": 11156848640, "loss": 2.720681381225586, "tokens_per_second": 978011.6094534147, "lr": 0.0015, "gradient_norm": 0.1587376594543457, "benchmark": false} | |
| {"step": 21300, "tokens": 11167334400, "loss": 2.7434682846069336, "tokens_per_second": 980170.1354157731, "lr": 0.0015, "gradient_norm": 0.17932246625423431, "benchmark": false} | |
| {"step": 21320, "tokens": 11177820160, "loss": 2.7346736907958986, "tokens_per_second": 977269.4832037757, "lr": 0.0015, "gradient_norm": 0.158131942152977, "benchmark": false} | |
| {"step": 21340, "tokens": 11188305920, "loss": 2.7307449340820313, "tokens_per_second": 990176.4721529327, "lr": 0.0015, "gradient_norm": 0.15123187005519867, "benchmark": false} | |
| {"step": 21360, "tokens": 11198791680, "loss": 2.7435989379882812, "tokens_per_second": 986110.9989490642, "lr": 0.0015, "gradient_norm": 0.14342011511325836, "benchmark": false} | |
| {"step": 21380, "tokens": 11209277440, "loss": 2.7513710021972657, "tokens_per_second": 989794.7038225255, "lr": 0.0015, "gradient_norm": 0.15389376878738403, "benchmark": false} | |
| {"step": 21400, "tokens": 11219763200, "loss": 2.749925994873047, "tokens_per_second": 981904.2400100403, "lr": 0.0015, "gradient_norm": 0.14500971138477325, "benchmark": false} | |
| {"step": 21420, "tokens": 11230248960, "loss": 2.734673500061035, "tokens_per_second": 982116.1622711776, "lr": 0.0015, "gradient_norm": 0.16096125543117523, "benchmark": false} | |
| {"step": 21440, "tokens": 11240734720, "loss": 2.736710548400879, "tokens_per_second": 995268.361997205, "lr": 0.0015, "gradient_norm": 0.15058793127536774, "benchmark": false} | |
| {"step": 21460, "tokens": 11251220480, "loss": 2.7553260803222654, "tokens_per_second": 942099.8717380728, "lr": 0.0015, "gradient_norm": 0.17784038186073303, "benchmark": false} | |
| {"step": 21480, "tokens": 11261706240, "loss": 2.721171569824219, "tokens_per_second": 984823.765624844, "lr": 0.0015, "gradient_norm": 0.1572302281856537, "benchmark": false} | |
| {"step": 21500, "tokens": 11272192000, "loss": 2.7307083129882814, "tokens_per_second": 977356.4326711252, "lr": 0.0015, "gradient_norm": 0.1457183063030243, "benchmark": false} | |
| {"step": 21520, "tokens": 11282677760, "loss": 2.739332580566406, "tokens_per_second": 861968.9537989718, "lr": 0.0015, "gradient_norm": 0.1666897088289261, "benchmark": false} | |
| {"step": 21540, "tokens": 11293163520, "loss": 2.6986692428588865, "tokens_per_second": 989445.1097467432, "lr": 0.0015, "gradient_norm": 0.1420649290084839, "benchmark": false} | |
| {"step": 21560, "tokens": 11303649280, "loss": 2.75574951171875, "tokens_per_second": 988670.3337918094, "lr": 0.0015, "gradient_norm": 0.1459985226392746, "benchmark": false} | |
| {"step": 21580, "tokens": 11314135040, "loss": 2.728601837158203, "tokens_per_second": 814876.4121760112, "lr": 0.0015, "gradient_norm": 0.16379660367965698, "benchmark": false} | |
| {"step": 21600, "tokens": 11324620800, "loss": 2.744864654541016, "tokens_per_second": 982885.1191783481, "lr": 0.0015, "gradient_norm": 0.17417514324188232, "benchmark": false} | |
| {"step": 21620, "tokens": 11335106560, "loss": 2.7458520889282227, "tokens_per_second": 978655.0484006297, "lr": 0.0015, "gradient_norm": 0.14431726932525635, "benchmark": false} | |
| {"step": 21640, "tokens": 11345592320, "loss": 2.7496265411376952, "tokens_per_second": 980379.3584159111, "lr": 0.0015, "gradient_norm": 0.16225294768810272, "benchmark": false} | |
| {"step": 21660, "tokens": 11356078080, "loss": 2.7229021072387694, "tokens_per_second": 980503.9152276393, "lr": 0.0015, "gradient_norm": 0.1511487066745758, "benchmark": false} | |
| {"step": 21680, "tokens": 11366563840, "loss": 2.6968250274658203, "tokens_per_second": 981793.100795127, "lr": 0.0015, "gradient_norm": 0.1597747653722763, "benchmark": false} | |
| {"step": 21700, "tokens": 11377049600, "loss": 2.7261899948120116, "tokens_per_second": 985415.4796970023, "lr": 0.0015, "gradient_norm": 0.15097445249557495, "benchmark": false} | |
| {"step": 21720, "tokens": 11387535360, "loss": 2.7518178939819338, "tokens_per_second": 980859.979874736, "lr": 0.0015, "gradient_norm": 0.16923417150974274, "benchmark": false} | |
| {"step": 21740, "tokens": 11398021120, "loss": 2.73089599609375, "tokens_per_second": 990311.7282315026, "lr": 0.0015, "gradient_norm": 0.1532820463180542, "benchmark": false} | |
| {"step": 21760, "tokens": 11408506880, "loss": 2.745311737060547, "tokens_per_second": 980719.1997586043, "lr": 0.0015, "gradient_norm": 0.16841423511505127, "benchmark": false} | |
| {"step": 21780, "tokens": 11418992640, "loss": 2.7404130935668944, "tokens_per_second": 979405.6731532753, "lr": 0.0015, "gradient_norm": 0.158935546875, "benchmark": false} | |
| {"step": 21800, "tokens": 11429478400, "loss": 2.743579864501953, "tokens_per_second": 855127.0073245649, "lr": 0.0015, "gradient_norm": 0.17852526903152466, "benchmark": false} | |
| {"step": 21820, "tokens": 11439964160, "loss": 2.7386568069458006, "tokens_per_second": 978846.331389176, "lr": 0.0015, "gradient_norm": 0.15770407021045685, "benchmark": false} | |
| {"step": 21840, "tokens": 11450449920, "loss": 2.75250129699707, "tokens_per_second": 984080.8761217202, "lr": 0.0015, "gradient_norm": 0.15558847784996033, "benchmark": false} | |
| {"step": 21860, "tokens": 11460935680, "loss": 2.7566801071166993, "tokens_per_second": 990439.0792607005, "lr": 0.0015, "gradient_norm": 0.16141757369041443, "benchmark": false} | |
| {"step": 21880, "tokens": 11471421440, "loss": 2.74230842590332, "tokens_per_second": 951037.6351988931, "lr": 0.0015, "gradient_norm": 0.14985457062721252, "benchmark": false} | |
| {"step": 21900, "tokens": 11481907200, "loss": 2.748712921142578, "tokens_per_second": 991670.753559233, "lr": 0.0015, "gradient_norm": 0.14954110980033875, "benchmark": false} | |
| {"step": 21920, "tokens": 11492392960, "loss": 2.7262691497802733, "tokens_per_second": 942358.7270998231, "lr": 0.0015, "gradient_norm": 0.1459842324256897, "benchmark": false} | |
| {"step": 21940, "tokens": 11502878720, "loss": 2.7390167236328127, "tokens_per_second": 979283.1353459321, "lr": 0.0015, "gradient_norm": 0.18871814012527466, "benchmark": false} | |
| {"step": 21960, "tokens": 11513364480, "loss": 2.7490068435668946, "tokens_per_second": 938317.9829802986, "lr": 0.0015, "gradient_norm": 0.1540951132774353, "benchmark": false} | |
| {"step": 21980, "tokens": 11523850240, "loss": 2.7099571228027344, "tokens_per_second": 972480.1144068335, "lr": 0.0015, "gradient_norm": 0.14107529819011688, "benchmark": false} | |
| {"step": 22000, "tokens": 11534336000, "loss": 2.7759721755981444, "tokens_per_second": 971667.9170136879, "lr": 0.0015, "gradient_norm": 0.17356452345848083, "benchmark": false} | |
| {"step": 22020, "tokens": 11544821760, "loss": 2.7497358322143555, "tokens_per_second": 724434.4823868582, "lr": 0.0015, "gradient_norm": 0.18714021146297455, "benchmark": false} | |
| {"step": 22040, "tokens": 11555307520, "loss": 2.7553672790527344, "tokens_per_second": 998087.4912387363, "lr": 0.0015, "gradient_norm": 0.17349259555339813, "benchmark": false} | |
| {"step": 22060, "tokens": 11565793280, "loss": 2.7409873962402345, "tokens_per_second": 986650.8122801217, "lr": 0.0015, "gradient_norm": 0.17116031050682068, "benchmark": false} | |
| {"step": 22080, "tokens": 11576279040, "loss": 2.7698875427246095, "tokens_per_second": 989118.4513079759, "lr": 0.0015, "gradient_norm": 0.14208100736141205, "benchmark": false} | |
| {"step": 22100, "tokens": 11586764800, "loss": 2.7190452575683595, "tokens_per_second": 977903.7618479038, "lr": 0.0015, "gradient_norm": 0.16330455243587494, "benchmark": false} | |
| {"step": 22120, "tokens": 11597250560, "loss": 2.733467674255371, "tokens_per_second": 975912.8255018233, "lr": 0.0015, "gradient_norm": 0.1591573804616928, "benchmark": false} | |
| {"step": 22140, "tokens": 11607736320, "loss": 2.734206771850586, "tokens_per_second": 986866.2360169833, "lr": 0.0015, "gradient_norm": 0.14705494046211243, "benchmark": false} | |
| {"step": 22160, "tokens": 11618222080, "loss": 2.732360076904297, "tokens_per_second": 982698.1122261145, "lr": 0.0015, "gradient_norm": 0.15297280251979828, "benchmark": false} | |
| {"step": 22180, "tokens": 11628707840, "loss": 2.7533525466918944, "tokens_per_second": 988020.6197262544, "lr": 0.0015, "gradient_norm": 0.1841764599084854, "benchmark": false} | |
| {"step": 22200, "tokens": 11639193600, "loss": 2.773965072631836, "tokens_per_second": 993955.6179272636, "lr": 0.0015, "gradient_norm": 0.18932831287384033, "benchmark": false} | |
| {"step": 22220, "tokens": 11649679360, "loss": 2.7061439514160157, "tokens_per_second": 815656.6707442304, "lr": 0.0015, "gradient_norm": 0.16487881541252136, "benchmark": false} | |
| {"step": 22240, "tokens": 11660165120, "loss": 2.7166574478149412, "tokens_per_second": 984095.7390775424, "lr": 0.0015, "gradient_norm": 0.1970110982656479, "benchmark": false} | |
| {"step": 22260, "tokens": 11670650880, "loss": 2.7431781768798826, "tokens_per_second": 984059.1844724049, "lr": 0.0015, "gradient_norm": 0.151424840092659, "benchmark": false} | |
| {"step": 22280, "tokens": 11681136640, "loss": 2.732481002807617, "tokens_per_second": 977936.1405606852, "lr": 0.0015, "gradient_norm": 0.1688004434108734, "benchmark": false} | |
| {"step": 22300, "tokens": 11691622400, "loss": 2.766814422607422, "tokens_per_second": 982810.666410442, "lr": 0.0015, "gradient_norm": 0.15200839936733246, "benchmark": false} | |
| {"step": 22320, "tokens": 11702108160, "loss": 2.7585573196411133, "tokens_per_second": 990307.7058714413, "lr": 0.0015, "gradient_norm": 0.1416952908039093, "benchmark": false} | |
| {"step": 22340, "tokens": 11712593920, "loss": 2.7188957214355467, "tokens_per_second": 980424.0788560681, "lr": 0.0015, "gradient_norm": 0.15630201995372772, "benchmark": false} | |
| {"step": 22360, "tokens": 11723079680, "loss": 2.767004203796387, "tokens_per_second": 981029.2964908364, "lr": 0.0015, "gradient_norm": 0.16679169237613678, "benchmark": false} | |
| {"step": 22380, "tokens": 11733565440, "loss": 2.7169044494628904, "tokens_per_second": 977972.6244887251, "lr": 0.0015, "gradient_norm": 0.16138620674610138, "benchmark": false} | |
| {"step": 22400, "tokens": 11744051200, "loss": 2.727964401245117, "tokens_per_second": 943245.7465022448, "lr": 0.0015, "gradient_norm": 0.16078802943229675, "benchmark": false} | |
| {"step": 22420, "tokens": 11754536960, "loss": 2.7490095138549804, "tokens_per_second": 987484.3991830078, "lr": 0.0015, "gradient_norm": 0.209112748503685, "benchmark": false} | |
| {"step": 22440, "tokens": 11765022720, "loss": 2.7280370712280275, "tokens_per_second": 981686.6813707558, "lr": 0.0015, "gradient_norm": 0.15952308475971222, "benchmark": false} | |
| {"step": 22460, "tokens": 11775508480, "loss": 2.754163360595703, "tokens_per_second": 972285.4477234452, "lr": 0.0015, "gradient_norm": 0.1407448798418045, "benchmark": false} | |
| {"step": 22480, "tokens": 11785994240, "loss": 2.7208763122558595, "tokens_per_second": 971143.0324648671, "lr": 0.0015, "gradient_norm": 0.19335061311721802, "benchmark": false} | |
| {"step": 22500, "tokens": 11796480000, "loss": 2.7467601776123045, "tokens_per_second": 987608.7978001876, "lr": 0.0015, "gradient_norm": 0.19316506385803223, "benchmark": false} | |
| {"step": 22520, "tokens": 11806965760, "loss": 2.7422876358032227, "tokens_per_second": 797201.4905023478, "lr": 0.0015, "gradient_norm": 0.21255578100681305, "benchmark": false} | |
| {"step": 22540, "tokens": 11817451520, "loss": 2.713323402404785, "tokens_per_second": 990451.1165206017, "lr": 0.0015, "gradient_norm": 0.15564727783203125, "benchmark": false} | |
| {"step": 22560, "tokens": 11827937280, "loss": 2.7529138565063476, "tokens_per_second": 991175.4776028433, "lr": 0.0015, "gradient_norm": 0.17195403575897217, "benchmark": false} | |
| {"step": 22580, "tokens": 11838423040, "loss": 2.7437063217163087, "tokens_per_second": 989924.6231135604, "lr": 0.0015, "gradient_norm": 0.14951170980930328, "benchmark": false} | |
| {"step": 22600, "tokens": 11848908800, "loss": 2.7254108428955077, "tokens_per_second": 976515.8239663645, "lr": 0.0015, "gradient_norm": 0.17607435584068298, "benchmark": false} | |
| {"step": 22620, "tokens": 11859394560, "loss": 2.736210060119629, "tokens_per_second": 985185.592590826, "lr": 0.0015, "gradient_norm": 0.16749103367328644, "benchmark": false} | |
| {"step": 22640, "tokens": 11869880320, "loss": 2.7173587799072267, "tokens_per_second": 982670.3650734085, "lr": 0.0015, "gradient_norm": 0.1508210152387619, "benchmark": false} | |
| {"step": 22660, "tokens": 11880366080, "loss": 2.697875213623047, "tokens_per_second": 980351.5196823806, "lr": 0.0015, "gradient_norm": 0.21907557547092438, "benchmark": false} | |
| {"step": 22680, "tokens": 11890851840, "loss": 2.759917449951172, "tokens_per_second": 980425.1640524918, "lr": 0.0015, "gradient_norm": 0.16676445305347443, "benchmark": false} | |
| {"step": 22700, "tokens": 11901337600, "loss": 2.733831787109375, "tokens_per_second": 974616.0804307584, "lr": 0.0015, "gradient_norm": 0.1655387431383133, "benchmark": false} | |
| {"step": 22720, "tokens": 11911823360, "loss": 2.708760070800781, "tokens_per_second": 985925.6912039809, "lr": 0.0015, "gradient_norm": 0.17306725680828094, "benchmark": false} | |
| {"step": 22740, "tokens": 11922309120, "loss": 2.736784553527832, "tokens_per_second": 980869.196601884, "lr": 0.0015, "gradient_norm": 0.14454922080039978, "benchmark": false} | |
| {"step": 22760, "tokens": 11932794880, "loss": 2.7834232330322264, "tokens_per_second": 983148.1310335987, "lr": 0.0015, "gradient_norm": 0.16931472718715668, "benchmark": false} | |
| {"step": 22780, "tokens": 11943280640, "loss": 2.732033920288086, "tokens_per_second": 976335.1762465194, "lr": 0.0015, "gradient_norm": 0.1618155688047409, "benchmark": false} | |
| {"step": 22800, "tokens": 11953766400, "loss": 2.7394859313964846, "tokens_per_second": 977758.5020315396, "lr": 0.0015, "gradient_norm": 0.1539624035358429, "benchmark": false} | |
| {"step": 22820, "tokens": 11964252160, "loss": 2.7179994583129883, "tokens_per_second": 974339.111910358, "lr": 0.0015, "gradient_norm": 0.1711590737104416, "benchmark": false} | |
| {"step": 22840, "tokens": 11974737920, "loss": 2.743486785888672, "tokens_per_second": 854666.6894576467, "lr": 0.0015, "gradient_norm": 0.17832402884960175, "benchmark": false} | |
| {"step": 22860, "tokens": 11985223680, "loss": 2.695712089538574, "tokens_per_second": 992177.1291471939, "lr": 0.0015, "gradient_norm": 0.16526660323143005, "benchmark": false} | |
| {"step": 22880, "tokens": 11995709440, "loss": 2.72046012878418, "tokens_per_second": 951362.6459908113, "lr": 0.0015, "gradient_norm": 0.18344907462596893, "benchmark": false} | |
| {"step": 22900, "tokens": 12006195200, "loss": 2.740768814086914, "tokens_per_second": 992362.528786665, "lr": 0.0015, "gradient_norm": 0.15671274065971375, "benchmark": false} | |
| {"step": 22920, "tokens": 12016680960, "loss": 2.6955699920654297, "tokens_per_second": 951507.7682270459, "lr": 0.0015, "gradient_norm": 0.17387978732585907, "benchmark": false} | |
| {"step": 22940, "tokens": 12027166720, "loss": 2.746495819091797, "tokens_per_second": 973142.2797433673, "lr": 0.0015, "gradient_norm": 0.1785355806350708, "benchmark": false} | |
| {"step": 22960, "tokens": 12037652480, "loss": 2.741334342956543, "tokens_per_second": 982407.4831120628, "lr": 0.0015, "gradient_norm": 0.16480481624603271, "benchmark": false} | |
| {"step": 22980, "tokens": 12048138240, "loss": 2.6979450225830077, "tokens_per_second": 983168.0924193689, "lr": 0.0015, "gradient_norm": 0.15850849449634552, "benchmark": false} | |
| {"step": 23000, "tokens": 12058624000, "loss": 2.7307880401611326, "tokens_per_second": 839554.3026868133, "lr": 0.0015, "gradient_norm": 0.24211981892585754, "benchmark": false} | |
| {"step": 23020, "tokens": 12069109760, "loss": 2.7809255599975584, "tokens_per_second": 823841.549096626, "lr": 0.0015, "gradient_norm": 0.1513972282409668, "benchmark": false} | |
| {"step": 23040, "tokens": 12079595520, "loss": 2.7394290924072267, "tokens_per_second": 988362.8729466494, "lr": 0.0015, "gradient_norm": 0.15792645514011383, "benchmark": false} | |
| {"step": 23060, "tokens": 12090081280, "loss": 2.7023691177368163, "tokens_per_second": 820437.2006449708, "lr": 0.0015, "gradient_norm": 0.17823415994644165, "benchmark": false} | |
| {"step": 23080, "tokens": 12100567040, "loss": 2.715198516845703, "tokens_per_second": 995391.4749122, "lr": 0.0015, "gradient_norm": 0.15440329909324646, "benchmark": false} | |
| {"step": 23100, "tokens": 12111052800, "loss": 2.7461761474609374, "tokens_per_second": 988061.972473647, "lr": 0.0015, "gradient_norm": 0.15957710146903992, "benchmark": false} | |
| {"step": 23120, "tokens": 12121538560, "loss": 2.724147987365723, "tokens_per_second": 980578.3726612739, "lr": 0.0015, "gradient_norm": 0.17278163135051727, "benchmark": false} | |
| {"step": 23140, "tokens": 12132024320, "loss": 2.754043769836426, "tokens_per_second": 985226.7322503136, "lr": 0.0015, "gradient_norm": 0.22024716436862946, "benchmark": false} | |
| {"step": 23160, "tokens": 12142510080, "loss": 2.731894874572754, "tokens_per_second": 980348.4368271609, "lr": 0.0015, "gradient_norm": 0.15541252493858337, "benchmark": false} | |
| {"step": 23180, "tokens": 12152995840, "loss": 2.7097692489624023, "tokens_per_second": 997549.1565507487, "lr": 0.0015, "gradient_norm": 0.15943562984466553, "benchmark": false} | |
| {"step": 23200, "tokens": 12163481600, "loss": 2.751483345031738, "tokens_per_second": 944566.9233428874, "lr": 0.0015, "gradient_norm": 0.17701444029808044, "benchmark": false} | |
| {"step": 23220, "tokens": 12173967360, "loss": 2.7640371322631836, "tokens_per_second": 977257.0459434326, "lr": 0.0015, "gradient_norm": 0.17089636623859406, "benchmark": false} | |
| {"step": 23240, "tokens": 12184453120, "loss": 2.7475223541259766, "tokens_per_second": 975449.2397139923, "lr": 0.0015, "gradient_norm": 0.1631258875131607, "benchmark": false} | |
| {"step": 23260, "tokens": 12194938880, "loss": 2.7236154556274412, "tokens_per_second": 973521.2856512073, "lr": 0.0015, "gradient_norm": 0.16909870505332947, "benchmark": false} | |
| {"step": 23280, "tokens": 12205424640, "loss": 2.699797248840332, "tokens_per_second": 976898.4389892312, "lr": 0.0015, "gradient_norm": 0.16072680056095123, "benchmark": false} | |
| {"step": 23300, "tokens": 12215910400, "loss": 2.741334915161133, "tokens_per_second": 970897.1113090056, "lr": 0.0015, "gradient_norm": 0.15408019721508026, "benchmark": false} | |
| {"step": 23320, "tokens": 12226396160, "loss": 2.734232711791992, "tokens_per_second": 973084.9755779211, "lr": 0.0015, "gradient_norm": 0.16748568415641785, "benchmark": false} | |
| {"step": 23340, "tokens": 12236881920, "loss": 2.746814155578613, "tokens_per_second": 982949.2788587323, "lr": 0.0015, "gradient_norm": 0.1644047051668167, "benchmark": false} | |
| {"step": 23360, "tokens": 12247367680, "loss": 2.758271026611328, "tokens_per_second": 939649.6989787506, "lr": 0.0015, "gradient_norm": 0.15047994256019592, "benchmark": false} | |
| {"step": 23380, "tokens": 12257853440, "loss": 2.6909440994262694, "tokens_per_second": 981560.7162533015, "lr": 0.0015, "gradient_norm": 0.17243516445159912, "benchmark": false} | |
| {"step": 23400, "tokens": 12268339200, "loss": 2.7408588409423826, "tokens_per_second": 986579.8663767203, "lr": 0.0015, "gradient_norm": 0.1580459177494049, "benchmark": false} | |
| {"step": 23420, "tokens": 12278824960, "loss": 2.7183855056762694, "tokens_per_second": 990117.7527912708, "lr": 0.0015, "gradient_norm": 0.18431591987609863, "benchmark": false} | |
| {"step": 23440, "tokens": 12289310720, "loss": 2.7668739318847657, "tokens_per_second": 942779.4816503015, "lr": 0.0015, "gradient_norm": 0.18806596100330353, "benchmark": false} | |
| {"step": 23460, "tokens": 12299796480, "loss": 2.698024940490723, "tokens_per_second": 968831.3757156752, "lr": 0.0015, "gradient_norm": 0.14793908596038818, "benchmark": false} | |
| {"step": 23480, "tokens": 12310282240, "loss": 2.734004592895508, "tokens_per_second": 980424.4883550106, "lr": 0.0015, "gradient_norm": 0.17792144417762756, "benchmark": false} | |
| {"step": 23500, "tokens": 12320768000, "loss": 2.752076530456543, "tokens_per_second": 980861.8585807844, "lr": 0.0015, "gradient_norm": 0.16015037894248962, "benchmark": false} | |
| {"step": 23520, "tokens": 12331253760, "loss": 2.692813491821289, "tokens_per_second": 862408.2630488093, "lr": 0.0015, "gradient_norm": 0.18024979531764984, "benchmark": false} | |
| {"step": 23540, "tokens": 12341739520, "loss": 2.728947067260742, "tokens_per_second": 987058.8550356231, "lr": 0.0015, "gradient_norm": 0.1586086004972458, "benchmark": false} | |
| {"step": 23560, "tokens": 12352225280, "loss": 2.7300254821777346, "tokens_per_second": 978136.5913378326, "lr": 0.0015, "gradient_norm": 0.20043253898620605, "benchmark": false} | |
| {"step": 23580, "tokens": 12362711040, "loss": 2.726719856262207, "tokens_per_second": 982405.9500716801, "lr": 0.0015, "gradient_norm": 0.18047048151493073, "benchmark": false} | |
| {"step": 23600, "tokens": 12373196800, "loss": 2.701414108276367, "tokens_per_second": 983577.6080914661, "lr": 0.0015, "gradient_norm": 0.16489489376544952, "benchmark": false} | |
| {"step": 23620, "tokens": 12383682560, "loss": 2.7320817947387694, "tokens_per_second": 992333.8487153981, "lr": 0.0015, "gradient_norm": 0.1562538892030716, "benchmark": false} | |
| {"step": 23640, "tokens": 12394168320, "loss": 2.739698028564453, "tokens_per_second": 976710.0950048219, "lr": 0.0015, "gradient_norm": 0.16973872482776642, "benchmark": false} | |
| {"step": 23660, "tokens": 12404654080, "loss": 2.751960563659668, "tokens_per_second": 987349.6143285821, "lr": 0.0015, "gradient_norm": 0.15999120473861694, "benchmark": false} | |
| {"step": 23680, "tokens": 12415139840, "loss": 2.7270740509033202, "tokens_per_second": 987985.7287669099, "lr": 0.0015, "gradient_norm": 0.18945136666297913, "benchmark": false} | |
| {"step": 23700, "tokens": 12425625600, "loss": 2.704849433898926, "tokens_per_second": 983824.8703053284, "lr": 0.0015, "gradient_norm": 0.17708808183670044, "benchmark": false} | |
| {"step": 23720, "tokens": 12436111360, "loss": 2.7558177947998046, "tokens_per_second": 989139.4448910474, "lr": 0.0015, "gradient_norm": 0.1752818524837494, "benchmark": false} | |
| {"step": 23740, "tokens": 12446597120, "loss": 2.730978012084961, "tokens_per_second": 982777.2282523635, "lr": 0.0015, "gradient_norm": 0.15310852229595184, "benchmark": false} | |
| {"step": 23760, "tokens": 12457082880, "loss": 2.7246047973632814, "tokens_per_second": 982690.981759592, "lr": 0.0015, "gradient_norm": 0.1571061611175537, "benchmark": false} | |
| {"step": 23780, "tokens": 12467568640, "loss": 2.7162429809570314, "tokens_per_second": 984878.9155530491, "lr": 0.0015, "gradient_norm": 0.20194852352142334, "benchmark": false} | |
| {"step": 23800, "tokens": 12478054400, "loss": 2.726548957824707, "tokens_per_second": 989109.3510746496, "lr": 0.0015, "gradient_norm": 0.15705883502960205, "benchmark": false} | |
| {"step": 23820, "tokens": 12488540160, "loss": 2.7108827590942384, "tokens_per_second": 985988.6919874253, "lr": 0.0015, "gradient_norm": 0.18265320360660553, "benchmark": false} | |
| {"step": 23840, "tokens": 12499025920, "loss": 2.7446414947509767, "tokens_per_second": 936322.7147520928, "lr": 0.0015, "gradient_norm": 0.17438428103923798, "benchmark": false} | |
| {"step": 23860, "tokens": 12509511680, "loss": 2.7243513107299804, "tokens_per_second": 989719.791013387, "lr": 0.0015, "gradient_norm": 0.16358651220798492, "benchmark": false} | |
| {"step": 23880, "tokens": 12519997440, "loss": 2.700775146484375, "tokens_per_second": 850381.8881175189, "lr": 0.0015, "gradient_norm": 0.14233604073524475, "benchmark": false} | |
| {"step": 23900, "tokens": 12530483200, "loss": 2.708213043212891, "tokens_per_second": 981935.8923766576, "lr": 0.0015, "gradient_norm": 0.15410612523555756, "benchmark": false} | |
| {"step": 23920, "tokens": 12540968960, "loss": 2.7601694107055663, "tokens_per_second": 975348.6145191451, "lr": 0.0015, "gradient_norm": 0.16925016045570374, "benchmark": false} | |
| {"step": 23940, "tokens": 12551454720, "loss": 2.691547393798828, "tokens_per_second": 975890.01228013, "lr": 0.0015, "gradient_norm": 0.15195700526237488, "benchmark": false} | |
| {"step": 23960, "tokens": 12561940480, "loss": 2.7447614669799805, "tokens_per_second": 997427.3005360373, "lr": 0.0015, "gradient_norm": 0.15338551998138428, "benchmark": false} | |
| {"step": 23980, "tokens": 12572426240, "loss": 2.7036411285400392, "tokens_per_second": 741396.487194083, "lr": 0.0015, "gradient_norm": 0.1688719540834427, "benchmark": false} | |
| {"step": 24000, "tokens": 12582912000, "loss": 2.718919372558594, "tokens_per_second": 982995.1583360904, "lr": 0.0015, "gradient_norm": 0.16046124696731567, "benchmark": false} | |
| {"step": 24020, "tokens": 12593397760, "loss": 2.7086679458618166, "tokens_per_second": 822883.7265012966, "lr": 0.0015, "gradient_norm": 0.1530439257621765, "benchmark": false} | |
| {"step": 24040, "tokens": 12603883520, "loss": 2.7279077529907227, "tokens_per_second": 980074.5210769067, "lr": 0.0015, "gradient_norm": 0.1471797525882721, "benchmark": false} | |
| {"step": 24060, "tokens": 12614369280, "loss": 2.7342641830444334, "tokens_per_second": 987047.5209221236, "lr": 0.0015, "gradient_norm": 0.15901459753513336, "benchmark": false} | |
| {"step": 24080, "tokens": 12624855040, "loss": 2.715492057800293, "tokens_per_second": 975792.0311073642, "lr": 0.0015, "gradient_norm": 0.15931537747383118, "benchmark": false} | |
| {"step": 24100, "tokens": 12635340800, "loss": 2.746675491333008, "tokens_per_second": 973183.5604599785, "lr": 0.0015, "gradient_norm": 0.18187576532363892, "benchmark": false} | |
| {"step": 24120, "tokens": 12645826560, "loss": 2.728923225402832, "tokens_per_second": 966498.0331267812, "lr": 0.0015, "gradient_norm": 0.16409577429294586, "benchmark": false} | |
| {"step": 24140, "tokens": 12656312320, "loss": 2.7178735733032227, "tokens_per_second": 979731.1730105949, "lr": 0.0015, "gradient_norm": 0.17806899547576904, "benchmark": false} | |
| {"step": 24160, "tokens": 12666798080, "loss": 2.734188461303711, "tokens_per_second": 946900.7145102122, "lr": 0.0015, "gradient_norm": 0.17147523164749146, "benchmark": false} | |
| {"step": 24180, "tokens": 12677283840, "loss": 2.733744239807129, "tokens_per_second": 942682.6766520035, "lr": 0.0015, "gradient_norm": 0.14357127249240875, "benchmark": false} | |
| {"step": 24200, "tokens": 12687769600, "loss": 2.737649917602539, "tokens_per_second": 973583.0387597032, "lr": 0.0015, "gradient_norm": 0.1436576396226883, "benchmark": false} | |
| {"step": 24220, "tokens": 12698255360, "loss": 2.7071475982666016, "tokens_per_second": 979589.5314190785, "lr": 0.0015, "gradient_norm": 0.17472463846206665, "benchmark": false} | |
| {"step": 24240, "tokens": 12708741120, "loss": 2.7472345352172853, "tokens_per_second": 972794.1637925358, "lr": 0.0015, "gradient_norm": 0.16535499691963196, "benchmark": false} | |
| {"step": 24260, "tokens": 12719226880, "loss": 2.6695518493652344, "tokens_per_second": 977291.9768466636, "lr": 0.0015, "gradient_norm": 0.1795545518398285, "benchmark": false} | |
| {"step": 24280, "tokens": 12729712640, "loss": 2.6967180252075194, "tokens_per_second": 978615.7269919422, "lr": 0.0015, "gradient_norm": 0.1853446513414383, "benchmark": false} | |
| {"step": 24300, "tokens": 12740198400, "loss": 2.723759078979492, "tokens_per_second": 923797.2413669531, "lr": 0.0015, "gradient_norm": 0.15290920436382294, "benchmark": false} | |
| {"step": 24320, "tokens": 12750684160, "loss": 2.709815788269043, "tokens_per_second": 980742.8477774544, "lr": 0.0015, "gradient_norm": 0.15692360699176788, "benchmark": false} | |
| {"step": 24340, "tokens": 12761169920, "loss": 2.7332801818847656, "tokens_per_second": 973711.0864105033, "lr": 0.0015, "gradient_norm": 0.16655956208705902, "benchmark": false} | |
| {"step": 24360, "tokens": 12771655680, "loss": 2.731781005859375, "tokens_per_second": 935934.1305565705, "lr": 0.0015, "gradient_norm": 0.14994950592517853, "benchmark": false} | |
| {"step": 24380, "tokens": 12782141440, "loss": 2.7372161865234377, "tokens_per_second": 978849.1870642671, "lr": 0.0015, "gradient_norm": 0.15712763369083405, "benchmark": false} | |
| {"step": 24400, "tokens": 12792627200, "loss": 2.712113952636719, "tokens_per_second": 969126.9337453893, "lr": 0.0015, "gradient_norm": 0.21027062833309174, "benchmark": false} | |
| {"step": 24420, "tokens": 12803112960, "loss": 2.723113250732422, "tokens_per_second": 977330.2162728749, "lr": 0.0015, "gradient_norm": 0.15226221084594727, "benchmark": false} | |
| {"step": 24440, "tokens": 12813598720, "loss": 2.705478286743164, "tokens_per_second": 978175.9817552314, "lr": 0.0015, "gradient_norm": 0.1717212200164795, "benchmark": false} | |
| {"step": 24460, "tokens": 12824084480, "loss": 2.7126705169677736, "tokens_per_second": 977215.6988787913, "lr": 0.0015, "gradient_norm": 0.1603756994009018, "benchmark": false} | |
| {"step": 24480, "tokens": 12834570240, "loss": 2.7191001892089846, "tokens_per_second": 974751.5215301592, "lr": 0.0015, "gradient_norm": 0.1522199809551239, "benchmark": false} | |
| {"step": 24500, "tokens": 12845056000, "loss": 2.742268371582031, "tokens_per_second": 974151.1406168258, "lr": 0.0015, "gradient_norm": 0.14085350930690765, "benchmark": false} | |
| {"step": 24520, "tokens": 12855541760, "loss": 2.7326705932617186, "tokens_per_second": 859391.8270237506, "lr": 0.0015, "gradient_norm": 0.16558785736560822, "benchmark": false} | |
| {"step": 24540, "tokens": 12866027520, "loss": 2.748618507385254, "tokens_per_second": 988211.2074317696, "lr": 0.0015, "gradient_norm": 0.1730576902627945, "benchmark": false} | |
| {"step": 24560, "tokens": 12876513280, "loss": 2.7072637557983397, "tokens_per_second": 975251.9939386911, "lr": 0.0015, "gradient_norm": 0.18000374734401703, "benchmark": false} | |
| {"step": 24580, "tokens": 12886999040, "loss": 2.728672218322754, "tokens_per_second": 993402.8065784546, "lr": 0.0015, "gradient_norm": 0.16314634680747986, "benchmark": false} | |
| {"step": 24600, "tokens": 12897484800, "loss": 2.7285837173461913, "tokens_per_second": 977100.0310438578, "lr": 0.0015, "gradient_norm": 0.1763191521167755, "benchmark": false} | |
| {"step": 24620, "tokens": 12907970560, "loss": 2.724655342102051, "tokens_per_second": 978006.7473834212, "lr": 0.0015, "gradient_norm": 0.16820791363716125, "benchmark": false} | |
| {"step": 24640, "tokens": 12918456320, "loss": 2.733455467224121, "tokens_per_second": 978093.4924589752, "lr": 0.0015, "gradient_norm": 0.16100598871707916, "benchmark": false} | |
| {"step": 24660, "tokens": 12928942080, "loss": 2.760820198059082, "tokens_per_second": 980837.6779266831, "lr": 0.0015, "gradient_norm": 0.1536797136068344, "benchmark": false} | |
| {"step": 24680, "tokens": 12939427840, "loss": 2.723988723754883, "tokens_per_second": 983784.9199724655, "lr": 0.0015, "gradient_norm": 0.1587965190410614, "benchmark": false} | |
| {"step": 24700, "tokens": 12949913600, "loss": 2.746841621398926, "tokens_per_second": 990003.1935612746, "lr": 0.0015, "gradient_norm": 0.1642487496137619, "benchmark": false} | |
| {"step": 24720, "tokens": 12960399360, "loss": 2.7254114151000977, "tokens_per_second": 988393.9002624903, "lr": 0.0015, "gradient_norm": 0.17209990322589874, "benchmark": false} | |
| {"step": 24740, "tokens": 12970885120, "loss": 2.7513980865478516, "tokens_per_second": 978505.9027070585, "lr": 0.0015, "gradient_norm": 0.15300320088863373, "benchmark": false} | |
| {"step": 24760, "tokens": 12981370880, "loss": 2.734958839416504, "tokens_per_second": 980636.4471639422, "lr": 0.0015, "gradient_norm": 0.1650846004486084, "benchmark": false} | |
| {"step": 24780, "tokens": 12991856640, "loss": 2.718367576599121, "tokens_per_second": 986314.9481937576, "lr": 0.0015, "gradient_norm": 0.19709423184394836, "benchmark": false} | |
| {"step": 24800, "tokens": 13002342400, "loss": 2.7138040542602537, "tokens_per_second": 837358.2747874942, "lr": 0.0015, "gradient_norm": 0.1700221747159958, "benchmark": false} | |
| {"step": 24820, "tokens": 13012828160, "loss": 2.696123504638672, "tokens_per_second": 987345.7378730789, "lr": 0.0015, "gradient_norm": 0.1795865297317505, "benchmark": false} | |
| {"step": 24840, "tokens": 13023313920, "loss": 2.7571231842041017, "tokens_per_second": 988318.0462214734, "lr": 0.0015, "gradient_norm": 0.15772154927253723, "benchmark": false} | |
| {"step": 24860, "tokens": 13033799680, "loss": 2.687510681152344, "tokens_per_second": 977481.8296891522, "lr": 0.0015, "gradient_norm": 0.1580677032470703, "benchmark": false} | |
| {"step": 24880, "tokens": 13044285440, "loss": 2.718827247619629, "tokens_per_second": 988198.1770153214, "lr": 0.0015, "gradient_norm": 0.16674473881721497, "benchmark": false} | |
| {"step": 24900, "tokens": 13054771200, "loss": 2.745186996459961, "tokens_per_second": 990662.412500728, "lr": 0.0015, "gradient_norm": 0.1693478524684906, "benchmark": false} | |
| {"step": 24920, "tokens": 13065256960, "loss": 2.7452892303466796, "tokens_per_second": 960075.2523763671, "lr": 0.0015, "gradient_norm": 0.16753168404102325, "benchmark": false} | |
| {"step": 24940, "tokens": 13075742720, "loss": 2.724387359619141, "tokens_per_second": 991013.5827467868, "lr": 0.0015, "gradient_norm": 0.16112184524536133, "benchmark": false} | |
| {"step": 24960, "tokens": 13086228480, "loss": 2.6991626739501955, "tokens_per_second": 939572.5153784158, "lr": 0.0015, "gradient_norm": 0.1650470644235611, "benchmark": false} | |
| {"step": 24980, "tokens": 13096714240, "loss": 2.714500617980957, "tokens_per_second": 984047.7388723607, "lr": 0.0015, "gradient_norm": 0.1731661707162857, "benchmark": false} | |
| {"step": 25000, "tokens": 13107200000, "loss": 2.7156171798706055, "tokens_per_second": 999762.4758471423, "lr": 0.0015, "gradient_norm": 0.17807134985923767, "benchmark": false} | |
| {"step": 25020, "tokens": 13117685760, "loss": 2.6884231567382812, "tokens_per_second": 727366.9593482548, "lr": 0.0015, "gradient_norm": 0.16767993569374084, "benchmark": false} | |
| {"step": 25040, "tokens": 13128171520, "loss": 2.7099437713623047, "tokens_per_second": 994332.6324797974, "lr": 0.0015, "gradient_norm": 0.17758285999298096, "benchmark": false} | |
| {"step": 25060, "tokens": 13138657280, "loss": 2.700517463684082, "tokens_per_second": 984705.5389486365, "lr": 0.0015, "gradient_norm": 0.23347370326519012, "benchmark": false} | |
| {"step": 25080, "tokens": 13149143040, "loss": 2.6942159652709963, "tokens_per_second": 985476.2811881976, "lr": 0.0015, "gradient_norm": 0.16518275439739227, "benchmark": false} | |
| {"step": 25100, "tokens": 13159628800, "loss": 2.7206411361694336, "tokens_per_second": 976840.2746375389, "lr": 0.0015, "gradient_norm": 0.167807474732399, "benchmark": false} | |
| {"step": 25120, "tokens": 13170114560, "loss": 2.71688232421875, "tokens_per_second": 981336.4678855721, "lr": 0.0015, "gradient_norm": 0.1545390486717224, "benchmark": false} | |
| {"step": 25140, "tokens": 13180600320, "loss": 2.7528863906860352, "tokens_per_second": 989493.8997773362, "lr": 0.0015, "gradient_norm": 0.15789680182933807, "benchmark": false} | |
| {"step": 25160, "tokens": 13191086080, "loss": 2.700876998901367, "tokens_per_second": 947862.8710981589, "lr": 0.0015, "gradient_norm": 0.15821625292301178, "benchmark": false} | |
| {"step": 25180, "tokens": 13201571840, "loss": 2.7612741470336912, "tokens_per_second": 987733.281823754, "lr": 0.0015, "gradient_norm": 0.17948000133037567, "benchmark": false} | |
| {"step": 25200, "tokens": 13212057600, "loss": 2.7171072006225585, "tokens_per_second": 988937.4923877334, "lr": 0.0015, "gradient_norm": 0.16124427318572998, "benchmark": false} | |
| {"step": 25220, "tokens": 13222543360, "loss": 2.712229537963867, "tokens_per_second": 983116.2090141976, "lr": 0.0015, "gradient_norm": 0.15388359129428864, "benchmark": false} | |
| {"step": 25240, "tokens": 13233029120, "loss": 2.7224248886108398, "tokens_per_second": 996714.4744441932, "lr": 0.0015, "gradient_norm": 0.22359180450439453, "benchmark": false} | |
| {"step": 25260, "tokens": 13243514880, "loss": 2.694599723815918, "tokens_per_second": 908828.6252031595, "lr": 0.0015, "gradient_norm": 0.19058111310005188, "benchmark": false} | |
| {"step": 25280, "tokens": 13254000640, "loss": 2.713223457336426, "tokens_per_second": 990776.1588023092, "lr": 0.0015, "gradient_norm": 0.17816558480262756, "benchmark": false} | |
| {"step": 25300, "tokens": 13264486400, "loss": 2.738983917236328, "tokens_per_second": 809118.9423379953, "lr": 0.0015, "gradient_norm": 0.1730477660894394, "benchmark": false} | |
| {"step": 25320, "tokens": 13274972160, "loss": 2.732411193847656, "tokens_per_second": 989205.5441194046, "lr": 0.0015, "gradient_norm": 0.15712766349315643, "benchmark": false} | |
| {"step": 25340, "tokens": 13285457920, "loss": 2.7172979354858398, "tokens_per_second": 987990.7211883516, "lr": 0.0015, "gradient_norm": 0.20486809313297272, "benchmark": false} | |
| {"step": 25360, "tokens": 13295943680, "loss": 2.7464277267456056, "tokens_per_second": 980088.4231299085, "lr": 0.0015, "gradient_norm": 0.17930281162261963, "benchmark": false} | |
| {"step": 25380, "tokens": 13306429440, "loss": 2.7713504791259767, "tokens_per_second": 979269.3335938716, "lr": 0.0015, "gradient_norm": 0.1711287647485733, "benchmark": false} | |
| {"step": 25400, "tokens": 13316915200, "loss": 2.739446449279785, "tokens_per_second": 980389.1165573467, "lr": 0.0015, "gradient_norm": 0.18435411155223846, "benchmark": false} | |
| {"step": 25420, "tokens": 13327400960, "loss": 2.699550437927246, "tokens_per_second": 985711.6419913521, "lr": 0.0015, "gradient_norm": 0.15506623685359955, "benchmark": false} | |
| {"step": 25440, "tokens": 13337886720, "loss": 2.720584487915039, "tokens_per_second": 980468.8073252274, "lr": 0.0015, "gradient_norm": 0.16505908966064453, "benchmark": false} | |
| {"step": 25460, "tokens": 13348372480, "loss": 2.7270036697387696, "tokens_per_second": 979712.4978044042, "lr": 0.0015, "gradient_norm": 0.1670805960893631, "benchmark": false} | |
| {"step": 25480, "tokens": 13358858240, "loss": 2.7266567230224608, "tokens_per_second": 978889.1120942757, "lr": 0.0015, "gradient_norm": 0.21402980387210846, "benchmark": false} | |
| {"step": 25500, "tokens": 13369344000, "loss": 2.7207874298095702, "tokens_per_second": 987622.1601941576, "lr": 0.0015, "gradient_norm": 0.17039531469345093, "benchmark": false} | |
| {"step": 25520, "tokens": 13379829760, "loss": 2.720967102050781, "tokens_per_second": 863418.1523505475, "lr": 0.0015, "gradient_norm": 0.15465085208415985, "benchmark": false} | |
| {"step": 25540, "tokens": 13390315520, "loss": 2.705210494995117, "tokens_per_second": 986263.6408655782, "lr": 0.0015, "gradient_norm": 0.16867955029010773, "benchmark": false} | |
| {"step": 25560, "tokens": 13400801280, "loss": 2.70369815826416, "tokens_per_second": 994968.8319761851, "lr": 0.0015, "gradient_norm": 0.1720699965953827, "benchmark": false} | |
| {"step": 25580, "tokens": 13411287040, "loss": 2.7260082244873045, "tokens_per_second": 979677.8507507413, "lr": 0.0015, "gradient_norm": 0.18026603758335114, "benchmark": false} | |
| {"step": 25600, "tokens": 13421772800, "loss": 2.7517717361450194, "tokens_per_second": 987180.0865562145, "lr": 0.0015, "gradient_norm": 0.1635952591896057, "benchmark": false} | |
| {"step": 25620, "tokens": 13432258560, "loss": 2.7445987701416015, "tokens_per_second": 987334.6934547427, "lr": 0.0015, "gradient_norm": 0.163328617811203, "benchmark": false} | |
| {"step": 25640, "tokens": 13442744320, "loss": 2.7319095611572264, "tokens_per_second": 985746.4177469084, "lr": 0.0015, "gradient_norm": 0.19899290800094604, "benchmark": false} | |
| {"step": 25660, "tokens": 13453230080, "loss": 2.7432483673095702, "tokens_per_second": 983310.3173556111, "lr": 0.0015, "gradient_norm": 0.14155735075473785, "benchmark": false} | |
| {"step": 25680, "tokens": 13463715840, "loss": 2.7118148803710938, "tokens_per_second": 990796.7422514698, "lr": 0.0015, "gradient_norm": 0.1868363618850708, "benchmark": false} | |
| {"step": 25700, "tokens": 13474201600, "loss": 2.75546875, "tokens_per_second": 991267.8788928532, "lr": 0.0015, "gradient_norm": 0.15769007802009583, "benchmark": false} | |
| {"step": 25720, "tokens": 13484687360, "loss": 2.7101598739624024, "tokens_per_second": 984038.6052657312, "lr": 0.0015, "gradient_norm": 0.1749272644519806, "benchmark": false} | |
| {"step": 25740, "tokens": 13495173120, "loss": 2.717189598083496, "tokens_per_second": 983889.3881470837, "lr": 0.0015, "gradient_norm": 0.18509364128112793, "benchmark": false} | |
| {"step": 25760, "tokens": 13505658880, "loss": 2.7148542404174805, "tokens_per_second": 839912.5602758507, "lr": 0.0015, "gradient_norm": 0.1599634289741516, "benchmark": false} | |
| {"step": 25780, "tokens": 13516144640, "loss": 2.7045000076293944, "tokens_per_second": 994192.546646092, "lr": 0.0015, "gradient_norm": 0.19591711461544037, "benchmark": false} | |
| {"step": 25800, "tokens": 13526630400, "loss": 2.729766082763672, "tokens_per_second": 980055.1570253664, "lr": 0.0015, "gradient_norm": 0.1845395863056183, "benchmark": false} | |
| {"step": 25820, "tokens": 13537116160, "loss": 2.731121826171875, "tokens_per_second": 980725.0812283977, "lr": 0.0015, "gradient_norm": 0.162481889128685, "benchmark": false} | |
| {"step": 25840, "tokens": 13547601920, "loss": 2.726731872558594, "tokens_per_second": 985687.2415539611, "lr": 0.0015, "gradient_norm": 0.16009148955345154, "benchmark": false} | |
| {"step": 25860, "tokens": 13558087680, "loss": 2.741087532043457, "tokens_per_second": 983406.2939001678, "lr": 0.0015, "gradient_norm": 0.19843797385692596, "benchmark": false} | |
| {"step": 25880, "tokens": 13568573440, "loss": 2.6949687957763673, "tokens_per_second": 980544.0728278547, "lr": 0.0015, "gradient_norm": 0.16291506588459015, "benchmark": false} | |
| {"step": 25900, "tokens": 13579059200, "loss": 2.6820772171020506, "tokens_per_second": 978290.6403665856, "lr": 0.0015, "gradient_norm": 0.15936020016670227, "benchmark": false} | |
| {"step": 25920, "tokens": 13589544960, "loss": 2.7093645095825196, "tokens_per_second": 850106.0294220387, "lr": 0.0015, "gradient_norm": 0.199713796377182, "benchmark": false} | |
| {"step": 25940, "tokens": 13600030720, "loss": 2.7047935485839845, "tokens_per_second": 987127.2054923556, "lr": 0.0015, "gradient_norm": 0.17227420210838318, "benchmark": false} | |
| {"step": 25960, "tokens": 13610516480, "loss": 2.708211135864258, "tokens_per_second": 854841.7415926263, "lr": 0.0015, "gradient_norm": 0.17577874660491943, "benchmark": false} | |
| {"step": 25980, "tokens": 13621002240, "loss": 2.712994384765625, "tokens_per_second": 973681.908757307, "lr": 0.0015, "gradient_norm": 0.1609300822019577, "benchmark": false} | |
| {"step": 26000, "tokens": 13631488000, "loss": 2.724579620361328, "tokens_per_second": 967542.1501508587, "lr": 0.0015, "gradient_norm": 0.1633884310722351, "benchmark": false} | |
| {"step": 26020, "tokens": 13641973760, "loss": 2.7292980194091796, "tokens_per_second": 818497.4700031824, "lr": 0.0015, "gradient_norm": 0.16491888463497162, "benchmark": false} | |
| {"step": 26040, "tokens": 13652459520, "loss": 2.7431610107421873, "tokens_per_second": 986377.2939282341, "lr": 0.0015, "gradient_norm": 0.16621766984462738, "benchmark": false} | |
| {"step": 26060, "tokens": 13662945280, "loss": 2.7311733245849608, "tokens_per_second": 936785.07679417, "lr": 0.0015, "gradient_norm": 0.1704351156949997, "benchmark": false} | |
| {"step": 26080, "tokens": 13673431040, "loss": 2.7357757568359373, "tokens_per_second": 973855.9108424016, "lr": 0.0015, "gradient_norm": 0.18583223223686218, "benchmark": false} | |
| {"step": 26100, "tokens": 13683916800, "loss": 2.7040576934814453, "tokens_per_second": 969912.2554433204, "lr": 0.0015, "gradient_norm": 0.1684197634458542, "benchmark": false} | |
| {"step": 26120, "tokens": 13694402560, "loss": 2.7078725814819338, "tokens_per_second": 992305.4772842126, "lr": 0.0015, "gradient_norm": 0.20440128445625305, "benchmark": false} | |
| {"step": 26140, "tokens": 13704888320, "loss": 2.726815032958984, "tokens_per_second": 941490.2826228602, "lr": 0.0015, "gradient_norm": 0.1905585527420044, "benchmark": false} | |
| {"step": 26160, "tokens": 13715374080, "loss": 2.7499265670776367, "tokens_per_second": 984392.7393389025, "lr": 0.0015, "gradient_norm": 0.199491947889328, "benchmark": false} | |
| {"step": 26180, "tokens": 13725859840, "loss": 2.7178987503051757, "tokens_per_second": 984612.3927632245, "lr": 0.0015, "gradient_norm": 0.1800057739019394, "benchmark": false} | |
| {"step": 26200, "tokens": 13736345600, "loss": 2.706588935852051, "tokens_per_second": 992586.9614493968, "lr": 0.0015, "gradient_norm": 0.20683439075946808, "benchmark": false} | |
| {"step": 26220, "tokens": 13746831360, "loss": 2.7586248397827147, "tokens_per_second": 808955.7270861325, "lr": 0.0015, "gradient_norm": 0.1834464967250824, "benchmark": false} | |
| {"step": 26240, "tokens": 13757317120, "loss": 2.7532941818237306, "tokens_per_second": 985567.9996337787, "lr": 0.0015, "gradient_norm": 0.2323581427335739, "benchmark": false} | |
| {"step": 26260, "tokens": 13767802880, "loss": 2.7399723052978517, "tokens_per_second": 982790.6838803282, "lr": 0.0015, "gradient_norm": 0.1736874282360077, "benchmark": false} | |
| {"step": 26280, "tokens": 13778288640, "loss": 2.7137556076049805, "tokens_per_second": 978838.3625999705, "lr": 0.0015, "gradient_norm": 0.18246124684810638, "benchmark": false} | |
| {"step": 26300, "tokens": 13788774400, "loss": 2.762215423583984, "tokens_per_second": 989272.4660260667, "lr": 0.0015, "gradient_norm": 0.18547014892101288, "benchmark": false} | |
| {"step": 26320, "tokens": 13799260160, "loss": 2.6851032257080076, "tokens_per_second": 980936.5772437012, "lr": 0.0015, "gradient_norm": 0.17275771498680115, "benchmark": false} | |
| {"step": 26340, "tokens": 13809745920, "loss": 2.7219158172607423, "tokens_per_second": 813696.1839928847, "lr": 0.0015, "gradient_norm": 0.1801224797964096, "benchmark": false} | |
| {"step": 26360, "tokens": 13820231680, "loss": 2.7224075317382814, "tokens_per_second": 981610.3190471472, "lr": 0.0015, "gradient_norm": 0.1656225472688675, "benchmark": false} | |
| {"step": 26380, "tokens": 13830717440, "loss": 2.692645454406738, "tokens_per_second": 979452.5686858577, "lr": 0.0015, "gradient_norm": 0.21354517340660095, "benchmark": false} | |
| {"step": 26400, "tokens": 13841203200, "loss": 2.7110664367675783, "tokens_per_second": 977782.7420926125, "lr": 0.0015, "gradient_norm": 0.15516646206378937, "benchmark": false} | |
| {"step": 26420, "tokens": 13851688960, "loss": 2.7424766540527346, "tokens_per_second": 981957.8310408042, "lr": 0.0015, "gradient_norm": 0.17319349944591522, "benchmark": false} | |
| {"step": 26440, "tokens": 13862174720, "loss": 2.7235631942749023, "tokens_per_second": 985692.4451058855, "lr": 0.0015, "gradient_norm": 0.1800365447998047, "benchmark": false} | |
| {"step": 26460, "tokens": 13872660480, "loss": 2.729097366333008, "tokens_per_second": 992203.155856663, "lr": 0.0015, "gradient_norm": 0.16647778451442719, "benchmark": false} | |
| {"step": 26480, "tokens": 13883146240, "loss": 2.7267486572265627, "tokens_per_second": 988070.7718164688, "lr": 0.0015, "gradient_norm": 0.1715329885482788, "benchmark": false} | |
| {"step": 26500, "tokens": 13893632000, "loss": 2.7060214996337892, "tokens_per_second": 991145.660072251, "lr": 0.0015, "gradient_norm": 0.1872853934764862, "benchmark": false} | |
| {"step": 26520, "tokens": 13904117760, "loss": 2.736189842224121, "tokens_per_second": 856868.2480380794, "lr": 0.0015, "gradient_norm": 0.15069472789764404, "benchmark": false} | |
| {"step": 26540, "tokens": 13914603520, "loss": 2.682301902770996, "tokens_per_second": 978042.5496547779, "lr": 0.0015, "gradient_norm": 0.17297181487083435, "benchmark": false} | |
| {"step": 26560, "tokens": 13925089280, "loss": 2.7173273086547853, "tokens_per_second": 982403.8772163352, "lr": 0.0015, "gradient_norm": 0.18856073915958405, "benchmark": false} | |
| {"step": 26580, "tokens": 13935575040, "loss": 2.726406478881836, "tokens_per_second": 992744.8377322793, "lr": 0.0015, "gradient_norm": 0.2031981199979782, "benchmark": false} | |
| {"step": 26600, "tokens": 13946060800, "loss": 2.7248741149902345, "tokens_per_second": 985972.6020680341, "lr": 0.0015, "gradient_norm": 0.21781203150749207, "benchmark": false} | |
| {"step": 26620, "tokens": 13956546560, "loss": 2.725321960449219, "tokens_per_second": 988393.4587429643, "lr": 0.0015, "gradient_norm": 0.18965676426887512, "benchmark": false} | |
| {"step": 26640, "tokens": 13967032320, "loss": 2.7370019912719727, "tokens_per_second": 986091.1794719244, "lr": 0.0015, "gradient_norm": 0.20296072959899902, "benchmark": false} | |
| {"step": 26660, "tokens": 13977518080, "loss": 2.7060466766357423, "tokens_per_second": 983155.7902593856, "lr": 0.0015, "gradient_norm": 0.18533267080783844, "benchmark": false} | |
| {"step": 26680, "tokens": 13988003840, "loss": 2.7029600143432617, "tokens_per_second": 988924.2545065327, "lr": 0.0015, "gradient_norm": 0.16446125507354736, "benchmark": false} | |
| {"step": 26700, "tokens": 13998489600, "loss": 2.717823600769043, "tokens_per_second": 991886.7740613186, "lr": 0.0015, "gradient_norm": 0.1786622554063797, "benchmark": false} | |
| {"step": 26720, "tokens": 14008975360, "loss": 2.7423500061035155, "tokens_per_second": 832390.0355931271, "lr": 0.0015, "gradient_norm": 0.1688917726278305, "benchmark": false} | |
| {"step": 26740, "tokens": 14019461120, "loss": 2.7214933395385743, "tokens_per_second": 994976.402505684, "lr": 0.0015, "gradient_norm": 0.169357568025589, "benchmark": false} | |
| {"step": 26760, "tokens": 14029946880, "loss": 2.733596420288086, "tokens_per_second": 982344.8654231534, "lr": 0.0015, "gradient_norm": 0.1823183000087738, "benchmark": false} | |
| {"step": 26780, "tokens": 14040432640, "loss": 2.7370426177978517, "tokens_per_second": 984832.4687065443, "lr": 0.0015, "gradient_norm": 0.17733104526996613, "benchmark": false} | |
| {"step": 26800, "tokens": 14050918400, "loss": 2.7315513610839846, "tokens_per_second": 986112.6263908717, "lr": 0.0015, "gradient_norm": 0.1987716555595398, "benchmark": false} | |
| {"step": 26820, "tokens": 14061404160, "loss": 2.7281627655029297, "tokens_per_second": 988505.0177402959, "lr": 0.0015, "gradient_norm": 0.18695585429668427, "benchmark": false} | |
| {"step": 26840, "tokens": 14071889920, "loss": 2.704783058166504, "tokens_per_second": 982573.5864396394, "lr": 0.0015, "gradient_norm": 0.16781634092330933, "benchmark": false} | |
| {"step": 26860, "tokens": 14082375680, "loss": 2.753675079345703, "tokens_per_second": 982370.1544556798, "lr": 0.0015, "gradient_norm": 0.14744165539741516, "benchmark": false} | |
| {"step": 26880, "tokens": 14092861440, "loss": 2.747810935974121, "tokens_per_second": 986904.237444794, "lr": 0.0015, "gradient_norm": 0.1833619475364685, "benchmark": false} | |
| {"step": 26900, "tokens": 14103347200, "loss": 2.7446100234985353, "tokens_per_second": 845989.4148910131, "lr": 0.0015, "gradient_norm": 0.21386535465717316, "benchmark": false} | |
| {"step": 26920, "tokens": 14113832960, "loss": 2.705735778808594, "tokens_per_second": 983059.521218753, "lr": 0.0015, "gradient_norm": 0.17069242894649506, "benchmark": false} | |
| {"step": 26940, "tokens": 14124318720, "loss": 2.700437545776367, "tokens_per_second": 983736.9920812615, "lr": 0.0015, "gradient_norm": 0.2033543586730957, "benchmark": false} | |
| {"step": 26960, "tokens": 14134804480, "loss": 2.7299921035766603, "tokens_per_second": 970803.0368257932, "lr": 0.0015, "gradient_norm": 0.16589409112930298, "benchmark": false} | |
| {"step": 26980, "tokens": 14145290240, "loss": 2.757349967956543, "tokens_per_second": 964245.0973920216, "lr": 0.0015, "gradient_norm": 0.18727724254131317, "benchmark": false} | |
| {"step": 27000, "tokens": 14155776000, "loss": 2.7379180908203127, "tokens_per_second": 974215.3208308646, "lr": 0.0015, "gradient_norm": 0.2257988452911377, "benchmark": false} | |
| {"step": 27020, "tokens": 14166261760, "loss": 2.7172765731811523, "tokens_per_second": 811788.9719791115, "lr": 0.0015, "gradient_norm": 0.19278764724731445, "benchmark": false} | |
| {"step": 27040, "tokens": 14176747520, "loss": 2.7182212829589845, "tokens_per_second": 971720.963860744, "lr": 0.0015, "gradient_norm": 0.21001334488391876, "benchmark": false} | |
| {"step": 27060, "tokens": 14187233280, "loss": 2.7089679718017576, "tokens_per_second": 979600.6869423535, "lr": 0.0015, "gradient_norm": 0.1708393692970276, "benchmark": false} | |
| {"step": 27080, "tokens": 14197719040, "loss": 2.7108909606933596, "tokens_per_second": 987109.5546218049, "lr": 0.0015, "gradient_norm": 0.18828046321868896, "benchmark": false} | |
| {"step": 27100, "tokens": 14208204800, "loss": 2.734965133666992, "tokens_per_second": 947571.5373417245, "lr": 0.0015, "gradient_norm": 0.2005746215581894, "benchmark": false} | |
| {"step": 27120, "tokens": 14218690560, "loss": 2.7572681427001955, "tokens_per_second": 838238.7888027055, "lr": 0.0015, "gradient_norm": 0.2550247609615326, "benchmark": false} | |
| {"step": 27140, "tokens": 14229176320, "loss": 2.7336267471313476, "tokens_per_second": 956864.912182367, "lr": 0.0015, "gradient_norm": 0.1868649125099182, "benchmark": false} | |
| {"step": 27160, "tokens": 14239662080, "loss": 2.7183982849121096, "tokens_per_second": 830803.1190357794, "lr": 0.0015, "gradient_norm": 0.17510153353214264, "benchmark": false} | |
| {"step": 27180, "tokens": 14250147840, "loss": 2.7133583068847655, "tokens_per_second": 980444.6896745623, "lr": 0.0015, "gradient_norm": 0.1707877814769745, "benchmark": false} | |
| {"step": 27200, "tokens": 14260633600, "loss": 2.6855865478515626, "tokens_per_second": 973210.4967959782, "lr": 0.0015, "gradient_norm": 0.1834012120962143, "benchmark": false} | |
| {"step": 27220, "tokens": 14271119360, "loss": 2.6898183822631836, "tokens_per_second": 981870.5842834172, "lr": 0.0015, "gradient_norm": 0.1635410636663437, "benchmark": false} | |
| {"step": 27240, "tokens": 14281605120, "loss": 2.70388126373291, "tokens_per_second": 974343.3163104206, "lr": 0.0015, "gradient_norm": 0.21058093011379242, "benchmark": false} | |
| {"step": 27260, "tokens": 14292090880, "loss": 2.7224603652954102, "tokens_per_second": 972456.5306671232, "lr": 0.0015, "gradient_norm": 0.1737559288740158, "benchmark": false} | |
| {"step": 27280, "tokens": 14302576640, "loss": 2.736484146118164, "tokens_per_second": 970663.2625875013, "lr": 0.0015, "gradient_norm": 0.1654696762561798, "benchmark": false} | |
| {"step": 27300, "tokens": 14313062400, "loss": 2.7216865539550783, "tokens_per_second": 978398.1105732487, "lr": 0.0015, "gradient_norm": 0.1685521900653839, "benchmark": false} | |
| {"step": 27320, "tokens": 14323548160, "loss": 2.719791603088379, "tokens_per_second": 972420.345852193, "lr": 0.0015, "gradient_norm": 0.1878766268491745, "benchmark": false} | |
| {"step": 27340, "tokens": 14334033920, "loss": 2.7190860748291015, "tokens_per_second": 970450.1077730856, "lr": 0.0015, "gradient_norm": 0.1653362214565277, "benchmark": false} | |
| {"step": 27360, "tokens": 14344519680, "loss": 2.721321868896484, "tokens_per_second": 981448.450743318, "lr": 0.0015, "gradient_norm": 0.1611962467432022, "benchmark": false} | |
| {"step": 27380, "tokens": 14355005440, "loss": 2.722399139404297, "tokens_per_second": 974914.0950692896, "lr": 0.0015, "gradient_norm": 0.22382064163684845, "benchmark": false} | |
| {"step": 27400, "tokens": 14365491200, "loss": 2.714438629150391, "tokens_per_second": 973640.3224892041, "lr": 0.0015, "gradient_norm": 0.17069153487682343, "benchmark": false} | |
| {"step": 27420, "tokens": 14375976960, "loss": 2.7425457000732423, "tokens_per_second": 975793.2755096899, "lr": 0.0015, "gradient_norm": 0.17039325833320618, "benchmark": false} | |
| {"step": 27440, "tokens": 14386462720, "loss": 2.705694580078125, "tokens_per_second": 843683.6538941357, "lr": 0.0015, "gradient_norm": 0.22451409697532654, "benchmark": false} | |
| {"step": 27460, "tokens": 14396948480, "loss": 2.7052997589111327, "tokens_per_second": 978615.1971650729, "lr": 0.0015, "gradient_norm": 0.20833070576190948, "benchmark": false} | |
| {"step": 27480, "tokens": 14407434240, "loss": 2.723668670654297, "tokens_per_second": 980042.4707011795, "lr": 0.0015, "gradient_norm": 0.17610988020896912, "benchmark": false} | |
| {"step": 27500, "tokens": 14417920000, "loss": 2.697346496582031, "tokens_per_second": 974398.2166323537, "lr": 0.0015, "gradient_norm": 0.17268800735473633, "benchmark": false} | |
| {"step": 27520, "tokens": 14428405760, "loss": 2.736563873291016, "tokens_per_second": 848288.5264664899, "lr": 0.0015, "gradient_norm": 0.17833539843559265, "benchmark": false} | |
| {"step": 27540, "tokens": 14438891520, "loss": 2.693071174621582, "tokens_per_second": 970698.4969644077, "lr": 0.0015, "gradient_norm": 0.20651768147945404, "benchmark": false} | |
| {"step": 27560, "tokens": 14449377280, "loss": 2.7164464950561524, "tokens_per_second": 979064.8373483644, "lr": 0.0015, "gradient_norm": 0.18882517516613007, "benchmark": false} | |
| {"step": 27580, "tokens": 14459863040, "loss": 2.731233596801758, "tokens_per_second": 980660.6930201402, "lr": 0.0015, "gradient_norm": 0.18132050335407257, "benchmark": false} | |
| {"step": 27600, "tokens": 14470348800, "loss": 2.7476808547973635, "tokens_per_second": 979811.8536908344, "lr": 0.0015, "gradient_norm": 0.17652148008346558, "benchmark": false} | |
| {"step": 27620, "tokens": 14480834560, "loss": 2.742958641052246, "tokens_per_second": 968153.1947297973, "lr": 0.0015, "gradient_norm": 0.17978568375110626, "benchmark": false} | |
| {"step": 27640, "tokens": 14491320320, "loss": 2.6967796325683593, "tokens_per_second": 972524.8710592854, "lr": 0.0015, "gradient_norm": 0.16653485596179962, "benchmark": false} | |
| {"step": 27660, "tokens": 14501806080, "loss": 2.691618537902832, "tokens_per_second": 984818.3744932573, "lr": 0.0015, "gradient_norm": 0.19368651509284973, "benchmark": false} | |
| {"step": 27680, "tokens": 14512291840, "loss": 2.6729225158691405, "tokens_per_second": 828267.4200520681, "lr": 0.0015, "gradient_norm": 0.19490785896778107, "benchmark": false} | |
| {"step": 27700, "tokens": 14522777600, "loss": 2.6924310684204102, "tokens_per_second": 977649.4146888462, "lr": 0.0015, "gradient_norm": 0.17885956168174744, "benchmark": false} | |
| {"step": 27720, "tokens": 14533263360, "loss": 2.728214073181152, "tokens_per_second": 973693.5141362102, "lr": 0.0015, "gradient_norm": 0.21110530197620392, "benchmark": false} | |
| {"step": 27740, "tokens": 14543749120, "loss": 2.709841728210449, "tokens_per_second": 972993.7774869222, "lr": 0.0015, "gradient_norm": 0.1710556447505951, "benchmark": false} | |
| {"step": 27760, "tokens": 14554234880, "loss": 2.7399322509765627, "tokens_per_second": 970426.7659089611, "lr": 0.0015, "gradient_norm": 0.17956961691379547, "benchmark": false} | |
| {"step": 27780, "tokens": 14564720640, "loss": 2.729500579833984, "tokens_per_second": 976814.656735601, "lr": 0.0015, "gradient_norm": 0.20494452118873596, "benchmark": false} | |
| {"step": 27800, "tokens": 14575206400, "loss": 2.723870849609375, "tokens_per_second": 972816.7359314272, "lr": 0.0015, "gradient_norm": 0.16382421553134918, "benchmark": false} | |
| {"step": 27820, "tokens": 14585692160, "loss": 2.713217926025391, "tokens_per_second": 975075.9961074116, "lr": 0.0015, "gradient_norm": 0.18931762874126434, "benchmark": false} | |
| {"step": 27840, "tokens": 14596177920, "loss": 2.6997257232666017, "tokens_per_second": 989722.6929217199, "lr": 0.0015, "gradient_norm": 0.1539795845746994, "benchmark": false} | |
| {"step": 27860, "tokens": 14606663680, "loss": 2.689684295654297, "tokens_per_second": 841727.3918574338, "lr": 0.0015, "gradient_norm": 0.1626945436000824, "benchmark": false} | |
| {"step": 27880, "tokens": 14617149440, "loss": 2.747370719909668, "tokens_per_second": 970746.5883628117, "lr": 0.0015, "gradient_norm": 0.18976539373397827, "benchmark": false} | |
| {"step": 27900, "tokens": 14627635200, "loss": 2.7361568450927733, "tokens_per_second": 965693.6629111602, "lr": 0.0015, "gradient_norm": 0.17063546180725098, "benchmark": false} | |
| {"step": 27920, "tokens": 14638120960, "loss": 2.7415027618408203, "tokens_per_second": 973208.4045714834, "lr": 0.0015, "gradient_norm": 0.18788912892341614, "benchmark": false} | |
| {"step": 27940, "tokens": 14648606720, "loss": 2.699085998535156, "tokens_per_second": 967242.1150041102, "lr": 0.0015, "gradient_norm": 0.1698664277791977, "benchmark": false} | |
| {"step": 27960, "tokens": 14659092480, "loss": 2.710794448852539, "tokens_per_second": 971998.9333785562, "lr": 0.0015, "gradient_norm": 0.15751716494560242, "benchmark": false} | |
| {"step": 27980, "tokens": 14669578240, "loss": 2.707795333862305, "tokens_per_second": 966638.7383064849, "lr": 0.0015, "gradient_norm": 0.1895906627178192, "benchmark": false} | |
| {"step": 28000, "tokens": 14680064000, "loss": 2.7293113708496093, "tokens_per_second": 983400.759093925, "lr": 0.0015, "gradient_norm": 0.20459537208080292, "benchmark": false} | |
| {"step": 28020, "tokens": 14690549760, "loss": 2.7033313751220702, "tokens_per_second": 733110.2691602296, "lr": 0.0015, "gradient_norm": 0.16380923986434937, "benchmark": false} | |
| {"step": 28040, "tokens": 14701035520, "loss": 2.7154237747192385, "tokens_per_second": 982207.2376210534, "lr": 0.0015, "gradient_norm": 0.19475558400154114, "benchmark": false} | |
| {"step": 28060, "tokens": 14711521280, "loss": 2.681853485107422, "tokens_per_second": 945412.9039389335, "lr": 0.0015, "gradient_norm": 0.2263222336769104, "benchmark": false} | |
| {"step": 28080, "tokens": 14722007040, "loss": 2.7147281646728514, "tokens_per_second": 958340.254903997, "lr": 0.0015, "gradient_norm": 0.17466644942760468, "benchmark": false} | |
| {"step": 28100, "tokens": 14732492800, "loss": 2.6936927795410157, "tokens_per_second": 929234.3664731835, "lr": 0.0015, "gradient_norm": 0.19458916783332825, "benchmark": false} | |
| {"step": 28120, "tokens": 14742978560, "loss": 2.691815185546875, "tokens_per_second": 976019.1507491164, "lr": 0.0015, "gradient_norm": 0.1861569732427597, "benchmark": false} | |
| {"step": 28140, "tokens": 14753464320, "loss": 2.7600332260131837, "tokens_per_second": 829225.0087726458, "lr": 0.0015, "gradient_norm": 0.2019202709197998, "benchmark": false} | |
| {"step": 28160, "tokens": 14763950080, "loss": 2.6984375, "tokens_per_second": 974758.9257041318, "lr": 0.0015, "gradient_norm": 0.20592443645000458, "benchmark": false} | |
| {"step": 28180, "tokens": 14774435840, "loss": 2.7179227828979493, "tokens_per_second": 975377.3493138999, "lr": 0.0015, "gradient_norm": 0.17361409962177277, "benchmark": false} | |
| {"step": 28200, "tokens": 14784921600, "loss": 2.715019416809082, "tokens_per_second": 975951.8261859085, "lr": 0.0015, "gradient_norm": 0.19439297914505005, "benchmark": false} | |
| {"step": 28220, "tokens": 14795407360, "loss": 2.7537019729614256, "tokens_per_second": 966435.4284252971, "lr": 0.0015, "gradient_norm": 0.20145413279533386, "benchmark": false} | |
| {"step": 28240, "tokens": 14805893120, "loss": 2.6983736038208006, "tokens_per_second": 974435.2538451034, "lr": 0.0015, "gradient_norm": 0.16358453035354614, "benchmark": false} | |
| {"step": 28260, "tokens": 14816378880, "loss": 2.7062435150146484, "tokens_per_second": 978858.8450378526, "lr": 0.0015, "gradient_norm": 0.17861990630626678, "benchmark": false} | |
| {"step": 28280, "tokens": 14826864640, "loss": 2.685271453857422, "tokens_per_second": 971597.1472537437, "lr": 0.0015, "gradient_norm": 0.2024940699338913, "benchmark": false} | |
| {"step": 28300, "tokens": 14837350400, "loss": 2.7068309783935547, "tokens_per_second": 975386.9027002855, "lr": 0.0015, "gradient_norm": 0.15980087220668793, "benchmark": false} | |
| {"step": 28320, "tokens": 14847836160, "loss": 2.717203140258789, "tokens_per_second": 981444.4818704984, "lr": 0.0015, "gradient_norm": 0.18326503038406372, "benchmark": false} | |
| {"step": 28340, "tokens": 14858321920, "loss": 2.7370832443237303, "tokens_per_second": 978146.9677676647, "lr": 0.0015, "gradient_norm": 0.1777624487876892, "benchmark": false} | |
| {"step": 28360, "tokens": 14868807680, "loss": 2.7065557479858398, "tokens_per_second": 976829.9330950398, "lr": 0.0015, "gradient_norm": 0.21732781827449799, "benchmark": false} | |
| {"step": 28380, "tokens": 14879293440, "loss": 2.6789697647094726, "tokens_per_second": 974337.8487540164, "lr": 0.0015, "gradient_norm": 0.18991118669509888, "benchmark": false} | |
| {"step": 28400, "tokens": 14889779200, "loss": 2.6932584762573244, "tokens_per_second": 968527.3888425346, "lr": 0.0015, "gradient_norm": 0.22206197679042816, "benchmark": false} | |
| {"step": 28420, "tokens": 14900264960, "loss": 2.700602149963379, "tokens_per_second": 979506.5395886932, "lr": 0.0015, "gradient_norm": 0.20620445907115936, "benchmark": false} | |
| {"step": 28440, "tokens": 14910750720, "loss": 2.720328521728516, "tokens_per_second": 974976.6692820517, "lr": 0.0015, "gradient_norm": 0.1743403524160385, "benchmark": false} | |
| {"step": 28460, "tokens": 14921236480, "loss": 2.741766929626465, "tokens_per_second": 970294.3910813988, "lr": 0.0015, "gradient_norm": 0.2103685885667801, "benchmark": false} | |
| {"step": 28480, "tokens": 14931722240, "loss": 2.744537353515625, "tokens_per_second": 972864.209021596, "lr": 0.0015, "gradient_norm": 0.18234020471572876, "benchmark": false} | |
| {"step": 28500, "tokens": 14942208000, "loss": 2.7238285064697267, "tokens_per_second": 968884.8161675986, "lr": 0.0015, "gradient_norm": 0.20309224724769592, "benchmark": false} | |
| {"step": 28520, "tokens": 14952693760, "loss": 2.725404739379883, "tokens_per_second": 834541.532623829, "lr": 0.0015, "gradient_norm": 0.1847103238105774, "benchmark": false} | |
| {"step": 28540, "tokens": 14963179520, "loss": 2.7304409027099608, "tokens_per_second": 985902.771852649, "lr": 0.0015, "gradient_norm": 0.17321354150772095, "benchmark": false} | |
| {"step": 28560, "tokens": 14973665280, "loss": 2.727642059326172, "tokens_per_second": 994465.8637124703, "lr": 0.0015, "gradient_norm": 0.17678822576999664, "benchmark": false} | |
| {"step": 28580, "tokens": 14984151040, "loss": 2.681191825866699, "tokens_per_second": 988715.9310217054, "lr": 0.0015, "gradient_norm": 0.1811339110136032, "benchmark": false} | |