1{"step": 0, "loss": 10.538154602050781, "lr": 2e-06, "grad_norm": 8.826038360595703, "tokens": 16384, "tok_per_s": 12267.008820282133, "t": 1.98}2{"step": 20, "loss": 9.062786102294922, "lr": 4.2e-05, "grad_norm": 2.396116018295288, "tokens": 344064, "tok_per_s": 12236.186788926587, "t": 28.76}3{"step": 40, "loss": 8.023894309997559, "lr": 8.199999999999999e-05, "grad_norm": 1.9327870607376099, "tokens": 671744, "tok_per_s": 12224.43886163398, "t": 55.59}4{"step": 60, "loss": 7.147858619689941, "lr": 0.00012199999999999998, "grad_norm": 1.0073579549789429, "tokens": 999424, "tok_per_s": 12227.853585676065, "t": 82.38}5{"step": 80, "loss": 6.872986793518066, "lr": 0.00016199999999999998, "grad_norm": 0.9701820015907288, "tokens": 1327104, "tok_per_s": 12350.690989394596, "t": 108.09}6{"step": 100, "loss": 6.5623087882995605, "lr": 0.00020199999999999998, "grad_norm": 1.135318398475647, "tokens": 1654784, "tok_per_s": 12246.719225784744, "t": 135.76}7{"step": 120, "loss": 6.4833784103393555, "lr": 0.000242, "grad_norm": 0.9940797090530396, "tokens": 1982464, "tok_per_s": 12290.734902855935, "t": 161.94}8{"step": 140, "loss": 6.285987854003906, "lr": 0.00028199999999999997, "grad_norm": 0.9160900115966797, "tokens": 2310144, "tok_per_s": 12263.175739855946, "t": 189.02}9{"step": 160, "loss": 6.127978324890137, "lr": 0.00032199999999999997, "grad_norm": 0.8789034485816956, "tokens": 2637824, "tok_per_s": 12244.953978378258, "t": 216.06}10{"step": 180, "loss": 6.162482261657715, "lr": 0.00036199999999999996, "grad_norm": 1.3229773044586182, "tokens": 2965504, "tok_per_s": 12291.164784312696, "t": 241.91}11{"step": 200, "loss": 6.06372594833374, "lr": 0.00040199999999999996, "grad_norm": 0.9360699653625488, "tokens": 3293184, "tok_per_s": 12260.65061054621, "t": 269.24}12{"step": 220, "loss": 5.960588455200195, "lr": 0.000442, "grad_norm": 0.9670940637588501, "tokens": 3620864, "tok_per_s": 12250.598133371244, "t": 296.21}13{"step": 240, "loss": 5.984297752380371, "lr": 0.00048199999999999995, "grad_norm": 0.8978189826011658, "tokens": 3948544, "tok_per_s": 12291.705053241867, "t": 321.88}14{"step": 260, "loss": 5.8681182861328125, "lr": 0.000522, "grad_norm": 0.8115763068199158, "tokens": 4276224, "tok_per_s": 12275.620218191996, "t": 348.99}15{"step": 280, "loss": 5.783034324645996, "lr": 0.0005619999999999999, "grad_norm": 0.8142603635787964, "tokens": 4603904, "tok_per_s": 12285.887365268558, "t": 375.37}16{"step": 300, "loss": 5.728802680969238, "lr": 0.0006, "grad_norm": 0.7503604292869568, "tokens": 4931584, "tok_per_s": 12283.22840230745, "t": 402.13}17{"step": 320, "loss": 5.7670793533325195, "lr": 0.0005999835963914726, "grad_norm": 1.6453608274459839, "tokens": 5259264, "tok_per_s": 12274.431994656205, "t": 429.12}18{"step": 340, "loss": 5.742429733276367, "lr": 0.0005999343875590635, "grad_norm": 0.7031630277633667, "tokens": 5586944, "tok_per_s": 12280.981116658615, "t": 455.57}19{"step": 360, "loss": 5.577595233917236, "lr": 0.00059985237948205, "grad_norm": 0.8332432508468628, "tokens": 5914624, "tok_per_s": 12268.441190882228, "t": 482.74}20{"step": 380, "loss": 5.530177116394043, "lr": 0.0005997375821250868, "grad_norm": 0.6786928176879883, "tokens": 6242304, "tok_per_s": 12279.671362677862, "t": 508.99}21{"step": 400, "loss": 5.6273932456970215, "lr": 0.0005995900094369953, "grad_norm": 6.397047519683838, "tokens": 6569984, "tok_per_s": 12264.629455104921, "t": 536.33}22{"step": 420, "loss": 5.520440101623535, "lr": 0.000599409679349069, "grad_norm": 0.6246231198310852, "tokens": 6897664, "tok_per_s": 12287.867050340814, "t": 561.98}23{"step": 440, "loss": 5.382430076599121, "lr": 0.0005991966137728945, "grad_norm": 0.761988639831543, "tokens": 7225344, "tok_per_s": 12279.624106426805, "t": 589.04}24{"step": 460, "loss": 5.283364772796631, "lr": 0.0005989508385976885, "grad_norm": 0.6207935214042664, "tokens": 7553024, "tok_per_s": 12270.523383262516, "t": 616.18}25{"step": 480, "loss": 5.33247184753418, "lr": 0.000598672383687153, "grad_norm": 0.5935987234115601, "tokens": 7880704, "tok_per_s": 12246.607024038762, "t": 644.14}26{"step": 499, "val_loss": 5.376418542861939, "val_ppl": 216.246409641857, "tokens": 8192000, "t": 676.9}27{"step": 500, "loss": 5.335311412811279, "lr": 0.0005983612828758463, "grad_norm": 0.6082054972648621, "tokens": 8208384, "tok_per_s": 12117.563445660973, "t": 678.04}28{"step": 520, "loss": 5.3863677978515625, "lr": 0.0005980175739650714, "grad_norm": 0.6699115037918091, "tokens": 8536064, "tok_per_s": 12089.311821260695, "t": 706.73}29{"step": 540, "loss": 5.296011924743652, "lr": 0.0005976412987182833, "grad_norm": 0.757933497428894, "tokens": 8863744, "tok_per_s": 12075.933905206339, "t": 734.64}30{"step": 560, "loss": 5.353665351867676, "lr": 0.000597232502856014, "grad_norm": 0.6468153595924377, "tokens": 9191424, "tok_per_s": 12053.971988970368, "t": 763.16}31{"step": 580, "loss": 5.164031982421875, "lr": 0.0005967912360503179, "grad_norm": 0.5246732831001282, "tokens": 9519104, "tok_per_s": 12039.288807349485, "t": 791.31}32{"step": 600, "loss": 5.383706092834473, "lr": 0.000596317551918735, "grad_norm": 0.5707435607910156, "tokens": 9846784, "tok_per_s": 12027.311249556898, "t": 819.34}33{"step": 620, "loss": 5.237800598144531, "lr": 0.0005958115080177768, "grad_norm": 0.5295183658599854, "tokens": 10174464, "tok_per_s": 12017.056818105553, "t": 847.31}34{"step": 640, "loss": 5.215066909790039, "lr": 0.0005952731658359328, "grad_norm": 0.548611581325531, "tokens": 10502144, "tok_per_s": 11992.821053121737, "t": 876.34}35{"step": 660, "loss": 5.153785705566406, "lr": 0.0005947025907861984, "grad_norm": 0.5935801863670349, "tokens": 10829824, "tok_per_s": 11977.674335609541, "t": 904.81}36{"step": 680, "loss": 5.202521324157715, "lr": 0.0005940998521981274, "grad_norm": 0.5564954876899719, "tokens": 11157504, "tok_per_s": 11959.257592686838, "t": 933.6}37{"step": 700, "loss": 5.146511554718018, "lr": 0.0005934650233094076, "grad_norm": 0.5552934408187866, "tokens": 11485184, "tok_per_s": 11941.760258932192, "t": 962.41}38{"step": 720, "loss": 5.095799446105957, "lr": 0.0005927981812569615, "grad_norm": 0.567599892616272, "tokens": 11812864, "tok_per_s": 11935.94153600311, "t": 990.33}39{"step": 740, "loss": 4.996639251708984, "lr": 0.0005920994070675743, "grad_norm": 0.578127920627594, "tokens": 12140544, "tok_per_s": 11925.37125969469, "t": 1018.69}40{"step": 760, "loss": 4.951390266418457, "lr": 0.000591368785648048, "grad_norm": 0.671257734298706, "tokens": 12468224, "tok_per_s": 11910.112552015506, "t": 1047.5}41{"step": 780, "loss": 5.068446159362793, "lr": 0.0005906064057748841, "grad_norm": 0.5128580331802368, "tokens": 12795904, "tok_per_s": 11887.9204368979, "t": 1077.02}42{"step": 800, "loss": 5.168520927429199, "lr": 0.0005898123600834975, "grad_norm": 5.2463555335998535, "tokens": 13123584, "tok_per_s": 11875.612775467493, "t": 1105.73}43{"step": 820, "loss": 5.072286605834961, "lr": 0.00058898674505696, "grad_norm": 0.6444844603538513, "tokens": 13451264, "tok_per_s": 11876.670710730987, "t": 1133.22}44{"step": 840, "loss": 4.948967456817627, "lr": 0.0005881296610142765, "grad_norm": 0.5277834534645081, "tokens": 13778944, "tok_per_s": 11873.161622668349, "t": 1161.15}45{"step": 860, "loss": 4.968014717102051, "lr": 0.0005872412120981961, "grad_norm": 0.5329476594924927, "tokens": 14106624, "tok_per_s": 11869.584852756028, "t": 1189.11}46{"step": 880, "loss": 4.756638526916504, "lr": 0.0005863215062625574, "grad_norm": 0.5423914194107056, "tokens": 14434304, "tok_per_s": 11877.591588374811, "t": 1215.9}47{"step": 900, "loss": 4.976390838623047, "lr": 0.0005853706552591712, "grad_norm": 0.5418165326118469, "tokens": 14761984, "tok_per_s": 11875.467479769606, "t": 1243.71}48{"step": 920, "loss": 4.84976863861084, "lr": 0.0005843887746242426, "grad_norm": 0.6431712508201599, "tokens": 15089664, "tok_per_s": 11873.266409096448, "t": 1271.54}49{"step": 940, "loss": 4.840450286865234, "lr": 0.000583375983664331, "grad_norm": 0.5837947726249695, "tokens": 15417344, "tok_per_s": 11877.077855763022, "t": 1298.72}50{"step": 960, "loss": 4.9250969886779785, "lr": 0.0005823324054418544, "grad_norm": 0.5661423206329346, "tokens": 15745024, "tok_per_s": 11868.1409528405, "t": 1327.31}51{"step": 980, "loss": 5.006077289581299, "lr": 0.0005812581667601359, "grad_norm": 1.4778692722320557, "tokens": 16072704, "tok_per_s": 11861.968977733293, "t": 1355.62}52{"step": 999, "val_loss": 4.868359494209289, "val_ppl": 130.10729994547023, "tokens": 16384000, "t": 1387.8}53{"step": 999, "checkpoint_sha256": "cda289d1d0f642b19ecbf6e6c12a162167897565760a2f30d1652474fd2adb60", "t": 1388.18}54{"step": 1000, "loss": 4.746236324310303, "lr": 0.0005801533981479964, "grad_norm": 0.5520177483558655, "tokens": 16400384, "tok_per_s": 11808.062608862347, "t": 1389.56}55{"step": 1020, "loss": 4.937170028686523, "lr": 0.0005790182338438938, "grad_norm": 0.5781713128089905, "tokens": 16728064, "tok_per_s": 11805.29816888464, "t": 1417.64}56{"step": 1040, "loss": 4.894624710083008, "lr": 0.0005778528117796123, "grad_norm": 0.5315879583358765, "tokens": 17055744, "tok_per_s": 11803.357443436133, "t": 1445.63}57{"step": 1060, "loss": 4.880748271942139, "lr": 0.0005766572735635022, "grad_norm": 1.2597907781600952, "tokens": 17383424, "tok_per_s": 11790.355502316252, "t": 1475.02}58{"step": 1080, "loss": 5.013078689575195, "lr": 0.0005754317644632738, "grad_norm": 0.6085506081581116, "tokens": 17711104, "tok_per_s": 11787.496721408717, "t": 1503.18}59{"step": 1100, "loss": 4.827304840087891, "lr": 0.000574176433388346, "grad_norm": 0.5576329827308655, "tokens": 18038784, "tok_per_s": 11797.208143102953, "t": 1529.71}60{"step": 1120, "loss": 4.837977409362793, "lr": 0.0005728914328717517, "grad_norm": 0.5152426958084106, "tokens": 18366464, "tok_per_s": 11795.445317768213, "t": 1557.72}61{"step": 1140, "loss": 4.640369415283203, "lr": 0.000571576919051606, "grad_norm": 0.5521364212036133, "tokens": 18694144, "tok_per_s": 11795.230672817028, "t": 1585.53}62{"step": 1160, "loss": 4.757654666900635, "lr": 0.0005702330516521316, "grad_norm": 0.5247706770896912, "tokens": 19021824, "tok_per_s": 11788.59224630508, "t": 1614.24}63{"step": 1180, "loss": 4.691868782043457, "lr": 0.0005688599939642524, "grad_norm": 0.5326834917068481, "tokens": 19349504, "tok_per_s": 11791.14385723584, "t": 1641.66}64{"step": 1200, "loss": 4.747924327850342, "lr": 0.000567457912825752, "grad_norm": 0.5180054903030396, "tokens": 19677184, "tok_per_s": 11792.949766833508, "t": 1669.2}65{"step": 1220, "loss": 4.812901496887207, "lr": 0.000566026978601002, "grad_norm": 0.5599668622016907, "tokens": 20004864, "tok_per_s": 11783.796474617193, "t": 1698.3}66{"step": 1240, "loss": 4.624703407287598, "lr": 0.00056456736516026, "grad_norm": 0.6033844351768494, "tokens": 20332544, "tok_per_s": 11779.719556755437, "t": 1726.71}67{"step": 1260, "loss": 4.742227077484131, "lr": 0.000563079249858545, "grad_norm": 0.5360792875289917, "tokens": 20660224, "tok_per_s": 11779.076173728605, "t": 1754.62}68{"step": 1280, "loss": 4.559293270111084, "lr": 0.000561562813514085, "grad_norm": 0.557126522064209, "tokens": 20987904, "tok_per_s": 11770.653351125746, "t": 1783.71}69{"step": 1300, "loss": 4.704896926879883, "lr": 0.0005600182403863482, "grad_norm": 0.552845299243927, "tokens": 21315584, "tok_per_s": 11774.175946588024, "t": 1811.01}70{"step": 1320, "loss": 4.649643898010254, "lr": 0.0005584457181536525, "grad_norm": 0.5440144538879395, "tokens": 21643264, "tok_per_s": 11778.277753235605, "t": 1838.2}71{"step": 1340, "loss": 4.542902946472168, "lr": 0.0005568454378903616, "grad_norm": 0.5623109340667725, "tokens": 21970944, "tok_per_s": 11782.242522633296, "t": 1865.39}72{"step": 1360, "loss": 4.589754104614258, "lr": 0.0005552175940436679, "grad_norm": 0.5271830558776855, "tokens": 22298624, "tok_per_s": 11772.282296335274, "t": 1894.81}73{"step": 1380, "loss": 4.611910820007324, "lr": 0.0005535623844099653, "grad_norm": 0.5605332255363464, "tokens": 22626304, "tok_per_s": 11767.477063289036, "t": 1923.43}74{"step": 1400, "loss": 4.653350830078125, "lr": 0.0005518800101108161, "grad_norm": 0.5224345326423645, "tokens": 22953984, "tok_per_s": 11763.642777929157, "t": 1951.91}75{"step": 1420, "loss": 4.504340171813965, "lr": 0.000550170675568512, "grad_norm": 0.5628354549407959, "tokens": 23281664, "tok_per_s": 11759.425495362444, "t": 1980.47}76{"step": 1440, "loss": 4.538120746612549, "lr": 0.0005484345884812357, "grad_norm": 0.5646089911460876, "tokens": 23609344, "tok_per_s": 11763.342947627734, "t": 2007.67}77{"step": 1460, "loss": 4.548748970031738, "lr": 0.000546671959797824, "grad_norm": 0.5454878211021423, "tokens": 23937024, "tok_per_s": 11766.325077504327, "t": 2035.01}78{"step": 1480, "loss": 4.4955878257751465, "lr": 0.0005448830036921353, "grad_norm": 0.5409777760505676, "tokens": 24264704, "tok_per_s": 11760.413489326585, "t": 2063.9}79{"step": 1499, "val_loss": 4.55281765460968, "val_ppl": 94.8994257612488, "tokens": 24576000, "t": 2098.38}80{"step": 1500, "loss": 4.449386119842529, "lr": 0.0005430679375370263, "grad_norm": 0.5416464805603027, "tokens": 24592384, "tok_per_s": 11715.626049715813, "t": 2099.75}81{"step": 1520, "loss": 4.506931304931641, "lr": 0.0005412269818779387, "grad_norm": 0.5411835312843323, "tokens": 24920064, "tok_per_s": 11709.046886550848, "t": 2128.92}82{"step": 1540, "loss": 4.46286678314209, "lr": 0.0005393603604061018, "grad_norm": 0.5418587327003479, "tokens": 25247744, "tok_per_s": 11712.523059721985, "t": 2156.26}83{"step": 1560, "loss": 4.550535202026367, "lr": 0.0005374682999313519, "grad_norm": 0.9948550462722778, "tokens": 25575424, "tok_per_s": 11706.191924192692, "t": 2185.42}84{"step": 1580, "loss": 4.395641326904297, "lr": 0.000535551030354573, "grad_norm": 0.5468602776527405, "tokens": 25903104, "tok_per_s": 11708.36429591705, "t": 2213.0}85{"step": 1600, "loss": 4.452836036682129, "lr": 0.000533608784639762, "grad_norm": 0.5829842686653137, "tokens": 26230784, "tok_per_s": 11711.802983617088, "t": 2240.33}86{"step": 1620, "loss": 4.391358375549316, "lr": 0.0005316417987857215, "grad_norm": 0.5233222246170044, "tokens": 26558464, "tok_per_s": 11704.320435493784, "t": 2269.76}87{"step": 1640, "loss": 4.432625770568848, "lr": 0.0005296503117973845, "grad_norm": 0.5276442766189575, "tokens": 26886144, "tok_per_s": 11713.19016145784, "t": 2296.02}88{"step": 1660, "loss": 4.441397666931152, "lr": 0.0005276345656567725, "grad_norm": 0.5338090062141418, "tokens": 27213824, "tok_per_s": 11709.577315533745, "t": 2324.71}89{"step": 1680, "loss": 4.608345985412598, "lr": 0.000525594805293594, "grad_norm": 0.5458671450614929, "tokens": 27541504, "tok_per_s": 11706.816270307252, "t": 2353.25}90{"step": 1700, "loss": 4.404858589172363, "lr": 0.0005235312785554818, "grad_norm": 0.5006349682807922, "tokens": 27869184, "tok_per_s": 11703.181470092059, "t": 2381.98}91{"step": 1720, "loss": 4.4875993728637695, "lr": 0.000521444236177879, "grad_norm": 0.5281708240509033, "tokens": 28196864, "tok_per_s": 11706.901990885435, "t": 2409.21}92{"step": 1740, "loss": 4.452470779418945, "lr": 0.0005193339317535718, "grad_norm": 0.5706871747970581, "tokens": 28524544, "tok_per_s": 11709.705702930381, "t": 2436.62}93{"step": 1760, "loss": 4.406674385070801, "lr": 0.0005172006217018763, "grad_norm": 0.5338311195373535, "tokens": 28852224, "tok_per_s": 11705.233072294539, "t": 2465.54}94{"step": 1780, "loss": 4.415951728820801, "lr": 0.0005150445652374809, "grad_norm": 0.54909747838974, "tokens": 29179904, "tok_per_s": 11705.049532957939, "t": 2493.58}95{"step": 1800, "loss": 4.3329620361328125, "lr": 0.0005128660243389501, "grad_norm": 0.523220419883728, "tokens": 29507584, "tok_per_s": 11699.735345727024, "t": 2522.72}96{"step": 1820, "loss": 4.487624645233154, "lr": 0.0005106652637168917, "grad_norm": 0.579258143901825, "tokens": 29835264, "tok_per_s": 11702.42285860611, "t": 2550.14}97{"step": 1840, "loss": 4.522067070007324, "lr": 0.0005084425507817925, "grad_norm": 0.5385577082633972, "tokens": 30162944, "tok_per_s": 11697.895599891974, "t": 2579.14}98{"step": 1860, "loss": 4.351419448852539, "lr": 0.0005061981556115255, "grad_norm": 0.5320832133293152, "tokens": 30490624, "tok_per_s": 11699.751976479256, "t": 2606.73}99{"step": 1880, "loss": 4.346895694732666, "lr": 0.0005039323509185333, "grad_norm": 0.5495853424072266, "tokens": 30818304, "tok_per_s": 11702.60960328932, "t": 2634.1}100{"step": 1900, "loss": 4.382790565490723, "lr": 0.0005016454120166914, "grad_norm": 0.6258963346481323, "tokens": 31145984, "tok_per_s": 11697.128749691117, "t": 2663.35}101{"step": 1920, "loss": 4.427793502807617, "lr": 0.0004993376167878549, "grad_norm": 0.5516924858093262, "tokens": 31473664, "tok_per_s": 11691.72184032782, "t": 2692.6}102{"step": 1940, "loss": 4.197183609008789, "lr": 0.0004970092456480945, "grad_norm": 0.588075578212738, "tokens": 31801344, "tok_per_s": 11690.4435519863, "t": 2720.93}103{"step": 1960, "loss": 4.288908958435059, "lr": 0.0004946605815136225, "grad_norm": 0.5377606749534607, "tokens": 32129024, "tok_per_s": 11687.307367410403, "t": 2749.7}104{"step": 1980, "loss": 4.317612171173096, "lr": 0.0004922919097664167, "grad_norm": 0.5370826125144958, "tokens": 32456704, "tok_per_s": 11689.41867836808, "t": 2777.23}105{"step": 1999, "val_loss": 4.377403140068054, "val_ppl": 79.63097418334951, "tokens": 32768000, "t": 2810.66}106{"step": 1999, "checkpoint_sha256": "0aa6a9f604a8834952c90f7fdbc128abdeda90a2fab99192c8d6e82ae49cb5fd", "t": 2811.09}107{"step": 2000, "loss": 4.231821537017822, "lr": 0.0004899035182195446, "grad_norm": 0.5784196257591248, "tokens": 32784384, "tok_per_s": 11658.385223092659, "t": 2812.73}108{"step": 2020, "loss": 4.3884429931640625, "lr": 0.00048749569708219075, "grad_norm": 0.525882363319397, "tokens": 33112064, "tok_per_s": 11656.431473337303, "t": 2841.31}109{"step": 2040, "loss": 4.128255844116211, "lr": 0.0004850687389243948, "grad_norm": 0.5654372572898865, "tokens": 33439744, "tok_per_s": 11655.083826786376, "t": 2869.75}110{"step": 2060, "loss": 4.392373561859131, "lr": 0.00048262293864150137, "grad_norm": 0.5647616982460022, "tokens": 33767424, "tok_per_s": 11651.209102049805, "t": 2898.83}111{"step": 2080, "loss": 4.272017478942871, "lr": 0.0004801585934183281, "grad_norm": 0.5246736407279968, "tokens": 34095104, "tok_per_s": 11654.059240044917, "t": 2926.24}112{"step": 2100, "loss": 4.351164817810059, "lr": 0.0004776760026930552, "grad_norm": 0.5639843344688416, "tokens": 34422784, "tok_per_s": 11651.157758820587, "t": 2955.09}113{"step": 2120, "loss": 4.381256103515625, "lr": 0.0004751754681208411, "grad_norm": 0.5990827679634094, "tokens": 34750464, "tok_per_s": 11654.334181549966, "t": 2982.41}114{"step": 2140, "loss": 4.293796539306641, "lr": 0.0004726572935371689, "grad_norm": 0.5889109373092651, "tokens": 35078144, "tok_per_s": 11657.838494768248, "t": 3009.62}115{"step": 2160, "loss": 4.318106651306152, "lr": 0.00047012178492092805, "grad_norm": 0.5541678667068481, "tokens": 35405824, "tok_per_s": 11652.700123326464, "t": 3039.06}116{"step": 2180, "loss": 4.370950698852539, "lr": 0.00046756925035723536, "grad_norm": 0.523361086845398, "tokens": 35733504, "tok_per_s": 11651.574937822988, "t": 3067.48}117{"step": 2200, "loss": 4.3684163093566895, "lr": 0.00046499999999999997, "grad_norm": 0.5235266089439392, "tokens": 36061184, "tok_per_s": 11650.641940686393, "t": 3095.85}118{"step": 2220, "loss": 4.416513442993164, "lr": 0.0004624143460342372, "grad_norm": 0.5547477006912231, "tokens": 36388864, "tok_per_s": 11650.49520771614, "t": 3124.02}119{"step": 2240, "loss": 4.400991439819336, "lr": 0.00045981260263813534, "grad_norm": 0.6226858496665955, "tokens": 36716544, "tok_per_s": 11652.8716753309, "t": 3151.5}120{"step": 2260, "loss": 4.15883731842041, "lr": 0.0004571950859448811, "grad_norm": 0.5616633296012878, "tokens": 37044224, "tok_per_s": 11655.973818399472, "t": 3178.77}121{"step": 2280, "loss": 4.316667556762695, "lr": 0.0004545621140042457, "grad_norm": 0.568236231803894, "tokens": 37371904, "tok_per_s": 11653.730269233454, "t": 3207.5}122{"step": 2300, "loss": 4.269564628601074, "lr": 0.00045191400674394013, "grad_norm": 0.5399973392486572, "tokens": 37699584, "tok_per_s": 11650.245063967917, "t": 3236.59}123{"step": 2320, "loss": 4.225350379943848, "lr": 0.000449251085930741, "grad_norm": 0.5322178602218628, "tokens": 38027264, "tok_per_s": 11646.621966280994, "t": 3265.73}124{"step": 2340, "loss": 4.254165172576904, "lr": 0.00044657367513139303, "grad_norm": 0.5262772440910339, "tokens": 38354944, "tok_per_s": 11649.606915520488, "t": 3293.02}125{"step": 2360, "loss": 4.305544853210449, "lr": 0.00044388209967329364, "grad_norm": 0.5276159644126892, "tokens": 38682624, "tok_per_s": 11646.145968824367, "t": 3322.14}126{"step": 2380, "loss": 4.318025588989258, "lr": 0.00044117668660496233, "grad_norm": 0.5362470149993896, "tokens": 39010304, "tok_per_s": 11649.147628536659, "t": 3349.41}127{"step": 2400, "loss": 4.189087390899658, "lr": 0.00043845776465630177, "grad_norm": 0.5912144184112549, "tokens": 39337984, "tok_per_s": 11652.166209961133, "t": 3376.67}128{"step": 2420, "loss": 4.167083263397217, "lr": 0.00043572566419865466, "grad_norm": 0.5396695733070374, "tokens": 39665664, "tok_per_s": 11653.654786173189, "t": 3404.35}129{"step": 2440, "loss": 4.282366752624512, "lr": 0.0004329807172046608, "grad_norm": 0.5638473629951477, "tokens": 39993344, "tok_per_s": 11650.457568695849, "t": 3433.41}130{"step": 2460, "loss": 4.179342269897461, "lr": 0.00043022325720791954, "grad_norm": 0.5641481876373291, "tokens": 40321024, "tok_per_s": 11647.07079450147, "t": 3462.54}131{"step": 2480, "loss": 4.261195182800293, "lr": 0.000427453619262463, "grad_norm": 0.55649334192276, "tokens": 40648704, "tok_per_s": 11647.617384047178, "t": 3490.52}132{"step": 2499, "val_loss": 4.253906965255737, "val_ppl": 70.37984751220374, "tokens": 40960000, "t": 3524.46}133{"step": 2500, "loss": 4.270415782928467, "lr": 0.00042467213990204363, "grad_norm": 0.5214126706123352, "tokens": 40976384, "tok_per_s": 11623.909543881557, "t": 3525.82}134{"step": 2520, "loss": 4.200478553771973, "lr": 0.0004218791570992436, "grad_norm": 0.5286369919776917, "tokens": 41304064, "tok_per_s": 11627.020290283132, "t": 3553.06}135{"step": 2540, "loss": 4.271385192871094, "lr": 0.00041907501022440735, "grad_norm": 1.1362669467926025, "tokens": 41631744, "tok_per_s": 11624.355791304675, "t": 3582.07}136{"step": 2560, "loss": 4.153648376464844, "lr": 0.00041626004000440593, "grad_norm": 0.5819516181945801, "tokens": 41959424, "tok_per_s": 11623.037056115738, "t": 3610.69}137{"step": 2580, "loss": 4.239153861999512, "lr": 0.00041343458848123576, "grad_norm": 0.5144444108009338, "tokens": 42287104, "tok_per_s": 11619.319612031708, "t": 3640.02}138{"step": 2600, "loss": 4.200573444366455, "lr": 0.0004105989989704575, "grad_norm": 0.562723696231842, "tokens": 42614784, "tok_per_s": 11622.04027606792, "t": 3667.36}139{"step": 2620, "loss": 4.275785446166992, "lr": 0.0004077536160194806, "grad_norm": 0.5386180877685547, "tokens": 42942464, "tok_per_s": 11620.13482113355, "t": 3696.16}140{"step": 2640, "loss": 4.140957355499268, "lr": 0.000404898785365698, "grad_norm": 0.51993727684021, "tokens": 43270144, "tok_per_s": 11622.032355083207, "t": 3723.76}141{"step": 2660, "loss": 4.120570659637451, "lr": 0.000402034853894476, "grad_norm": 0.5389391183853149, "tokens": 43597824, "tok_per_s": 11624.461428055718, "t": 3751.17}142{"step": 2680, "loss": 4.026679992675781, "lr": 0.000399162169597005, "grad_norm": 0.542602002620697, "tokens": 43925504, "tok_per_s": 11621.979828131509, "t": 3780.16}143{"step": 2700, "loss": 4.190106391906738, "lr": 0.00039628108152801574, "grad_norm": 0.53343266248703, "tokens": 44253184, "tok_per_s": 11618.268985670818, "t": 3809.6}144{"step": 2720, "loss": 4.038628578186035, "lr": 0.000393391939763366, "grad_norm": 0.5840466022491455, "tokens": 44580864, "tok_per_s": 11619.40309369032, "t": 3837.4}145{"step": 2740, "loss": 4.085831642150879, "lr": 0.00039049509535750383, "grad_norm": 0.5408041477203369, "tokens": 44908544, "tok_per_s": 11618.701568373139, "t": 3865.84}146{"step": 2760, "loss": 4.053369045257568, "lr": 0.0003875909003008116, "grad_norm": 0.5366416573524475, "tokens": 45236224, "tok_per_s": 11620.9278906342, "t": 3893.29}147{"step": 2780, "loss": 4.154467582702637, "lr": 0.0003846797074768358, "grad_norm": 0.5264991521835327, "tokens": 45563904, "tok_per_s": 11618.84091486484, "t": 3922.2}148{"step": 2800, "loss": 4.168743133544922, "lr": 0.00038176187061940935, "grad_norm": 0.536626398563385, "tokens": 45891584, "tok_per_s": 11616.338803380988, "t": 3951.25}149{"step": 2820, "loss": 4.153240203857422, "lr": 0.0003788377442696697, "grad_norm": 0.533578634262085, "tokens": 46219264, "tok_per_s": 11615.253346568814, "t": 3979.83}150{"step": 2840, "loss": 4.130046844482422, "lr": 0.00037590768373297907, "grad_norm": 0.5270524024963379, "tokens": 46546944, "tok_per_s": 11618.32541559027, "t": 4006.98}151{"step": 2860, "loss": 4.124772071838379, "lr": 0.0003729720450357526, "grad_norm": 0.5412513613700867, "tokens": 46874624, "tok_per_s": 11617.065799558944, "t": 4035.62}152{"step": 2880, "loss": 4.045408248901367, "lr": 0.0003700311848821973, "grad_norm": 0.5562382936477661, "tokens": 47202304, "tok_per_s": 11620.032790486088, "t": 4062.79}153{"step": 2900, "loss": 4.053845405578613, "lr": 0.00036708546061097017, "grad_norm": 0.5519654154777527, "tokens": 47529984, "tok_per_s": 11622.144412185111, "t": 4090.25}154{"step": 2920, "loss": 4.138660430908203, "lr": 0.00036413523015175846, "grad_norm": 0.5388080477714539, "tokens": 47857664, "tok_per_s": 11620.688842362795, "t": 4118.96}155{"step": 2940, "loss": 4.136221885681152, "lr": 0.0003611808519817883, "grad_norm": 0.5571575164794922, "tokens": 48185344, "tok_per_s": 11617.611410784506, "t": 4148.25}156{"step": 2960, "loss": 4.039947509765625, "lr": 0.0003582226850822664, "grad_norm": 0.535615861415863, "tokens": 48513024, "tok_per_s": 11618.557089478945, "t": 4176.12}157{"step": 2980, "loss": 4.180006504058838, "lr": 0.0003552610888947618, "grad_norm": 0.5578852891921997, "tokens": 48840704, "tok_per_s": 11620.276163903865, "t": 4203.7}158{"step": 2999, "val_loss": 4.158720552921295, "val_ppl": 63.989598897214684, "tokens": 49152000, "t": 4237.64}159{"step": 2999, "checkpoint_sha256": "01088cbe14a4bbf4ef3d3f45ae99d689c24d2752c909afe60703401d5c293072", "t": 4238.01}160{"step": 3000, "loss": 4.180983543395996, "lr": 0.0003522964232775297, "grad_norm": 0.5751718878746033, "tokens": 49168384, "tok_per_s": 11599.737328140918, "t": 4239.39}161{"step": 3020, "loss": 4.092770576477051, "lr": 0.0003493290484617865, "grad_norm": 0.529112696647644, "tokens": 49496064, "tok_per_s": 11597.092272818163, "t": 4268.61}162{"step": 3040, "loss": 4.0629377365112305, "lr": 0.0003463593250079383, "grad_norm": 0.5474892854690552, "tokens": 49823744, "tok_per_s": 11595.560939643, "t": 4297.44}163{"step": 3060, "loss": 4.105502128601074, "lr": 0.00034338761376177, "grad_norm": 0.8342363834381104, "tokens": 50151424, "tok_per_s": 11597.205212677118, "t": 4325.08}164{"step": 3080, "loss": 4.145478248596191, "lr": 0.00034041427581059977, "grad_norm": 0.5806731581687927, "tokens": 50479104, "tok_per_s": 11594.81427453882, "t": 4354.24}165{"step": 3100, "loss": 4.065998554229736, "lr": 0.0003374396724394037, "grad_norm": 0.5266734957695007, "tokens": 50806784, "tok_per_s": 11597.401930260172, "t": 4381.52}166{"step": 3120, "loss": 4.046976089477539, "lr": 0.0003344641650869168, "grad_norm": 0.5373362302780151, "tokens": 51134464, "tok_per_s": 11599.940600673119, "t": 4408.81}167{"step": 3140, "loss": 4.0326666831970215, "lr": 0.0003314881153017151, "grad_norm": 0.5418212413787842, "tokens": 51462144, "tok_per_s": 11602.451890150127, "t": 4436.1}168{"step": 3160, "loss": 4.104043006896973, "lr": 0.00032851188469828487, "grad_norm": 0.5828465223312378, "tokens": 51789824, "tok_per_s": 11599.187619918594, "t": 4465.6}169{"step": 3180, "loss": 3.948253870010376, "lr": 0.0003255358349130832, "grad_norm": 0.5222381353378296, "tokens": 52117504, "tok_per_s": 11598.717562240729, "t": 4494.03}170{"step": 3200, "loss": 4.206734657287598, "lr": 0.00032256032756059627, "grad_norm": 0.5611771941184998, "tokens": 52445184, "tok_per_s": 11598.044955429035, "t": 4522.54}171{"step": 3220, "loss": 4.076472282409668, "lr": 0.00031958572418940007, "grad_norm": 0.5682035088539124, "tokens": 52772864, "tok_per_s": 11597.313869426645, "t": 4551.08}172{"step": 3240, "loss": 3.881274700164795, "lr": 0.00031661238623822995, "grad_norm": 0.5410988330841064, "tokens": 53100544, "tok_per_s": 11599.778026789865, "t": 4578.36}173{"step": 3260, "loss": 4.112787246704102, "lr": 0.00031364067499206177, "grad_norm": 0.5453398823738098, "tokens": 53428224, "tok_per_s": 11598.3489765245, "t": 4607.18}174{"step": 3280, "loss": 4.042259216308594, "lr": 0.00031067095153821354, "grad_norm": 0.5254319906234741, "tokens": 53755904, "tok_per_s": 11596.062737123084, "t": 4636.35}175{"step": 3300, "loss": 4.027780532836914, "lr": 0.0003077035767224703, "grad_norm": 0.5368713736534119, "tokens": 54083584, "tok_per_s": 11593.837629205618, "t": 4665.5}176{"step": 3320, "loss": 4.048270225524902, "lr": 0.0003047389111052382, "grad_norm": 0.5798897743225098, "tokens": 54411264, "tok_per_s": 11594.94706767128, "t": 4693.31}177{"step": 3340, "loss": 3.9507741928100586, "lr": 0.0003017773149177336, "grad_norm": 0.5504516363143921, "tokens": 54738944, "tok_per_s": 11594.143632157271, "t": 4721.9}178{"step": 3360, "loss": 3.9647669792175293, "lr": 0.0002988191480182117, "grad_norm": 0.5416991114616394, "tokens": 55066624, "tok_per_s": 11596.184635204852, "t": 4749.33}179{"step": 3380, "loss": 4.000699996948242, "lr": 0.0002958647698482415, "grad_norm": 0.5480679273605347, "tokens": 55394304, "tok_per_s": 11595.102761281029, "t": 4778.03}180{"step": 3400, "loss": 3.971863031387329, "lr": 0.0002929145393890298, "grad_norm": 0.5375354290008545, "tokens": 55721984, "tok_per_s": 11594.402055720479, "t": 4806.58}181{"step": 3420, "loss": 4.104773998260498, "lr": 0.0002899688151178026, "grad_norm": 0.5447196364402771, "tokens": 56049664, "tok_per_s": 11590.86988710522, "t": 4836.32}182{"step": 3440, "loss": 4.046260833740234, "lr": 0.00028702795496424736, "grad_norm": 0.5488489866256714, "tokens": 56377344, "tok_per_s": 11592.886162092072, "t": 4863.74}183{"step": 3460, "loss": 3.960139274597168, "lr": 0.00028409231626702093, "grad_norm": 0.5675356984138489, "tokens": 56705024, "tok_per_s": 11591.251066099452, "t": 4892.7}184{"step": 3480, "loss": 3.994968891143799, "lr": 0.00028116225573033036, "grad_norm": 0.5636969208717346, "tokens": 57032704, "tok_per_s": 11592.733713437376, "t": 4920.34}185{"step": 3499, "val_loss": 4.076284086704254, "val_ppl": 58.926098247434794, "tokens": 57344000, "t": 4953.42}186{"step": 3500, "loss": 4.110962390899658, "lr": 0.00027823812938059065, "grad_norm": 0.5642924308776855, "tokens": 57360384, "tok_per_s": 11577.222286224182, "t": 4955.23}187{"step": 3520, "loss": 3.9599759578704834, "lr": 0.0002753202925231642, "grad_norm": 0.5764612555503845, "tokens": 57688064, "tok_per_s": 11575.88157647093, "t": 4984.14}188{"step": 3540, "loss": 3.9944944381713867, "lr": 0.0002724090996991884, "grad_norm": 0.5443633198738098, "tokens": 58015744, "tok_per_s": 11574.98417124486, "t": 5012.81}189{"step": 3560, "loss": 4.018226623535156, "lr": 0.00026950490464249606, "grad_norm": 0.5742700099945068, "tokens": 58343424, "tok_per_s": 11573.307568254504, "t": 5041.85}190{"step": 3580, "loss": 4.130144119262695, "lr": 0.0002666080602366339, "grad_norm": 0.5585811138153076, "tokens": 58671104, "tok_per_s": 11574.399101452585, "t": 5069.68}191{"step": 3600, "loss": 4.045418739318848, "lr": 0.00026371891847198426, "grad_norm": 0.5662236213684082, "tokens": 58998784, "tok_per_s": 11573.813791413262, "t": 5098.25}192{"step": 3620, "loss": 4.177013397216797, "lr": 0.00026083783040299483, "grad_norm": 0.5743661522865295, "tokens": 59326464, "tok_per_s": 11576.377095529744, "t": 5125.43}193{"step": 3640, "loss": 3.959064483642578, "lr": 0.0002579651461055239, "grad_norm": 0.5499097108840942, "tokens": 59654144, "tok_per_s": 11578.98264556307, "t": 5152.58}194{"step": 3660, "loss": 3.7604146003723145, "lr": 0.000255101214634302, "grad_norm": 0.5641483664512634, "tokens": 59981824, "tok_per_s": 11576.51833666578, "t": 5181.98}195{"step": 3680, "loss": 4.021690845489502, "lr": 0.0002522463839805194, "grad_norm": 0.5463368892669678, "tokens": 60309504, "tok_per_s": 11575.705473660024, "t": 5210.65}196{"step": 3700, "loss": 3.943697452545166, "lr": 0.00024940100102954256, "grad_norm": 0.5520758628845215, "tokens": 60637184, "tok_per_s": 11575.606176705642, "t": 5239.02}197{"step": 3720, "loss": 3.904292583465576, "lr": 0.00024656541151876424, "grad_norm": 0.5493237972259521, "tokens": 60964864, "tok_per_s": 11577.859974252468, "t": 5266.28}198{"step": 3740, "loss": 4.000242233276367, "lr": 0.00024373995999559398, "grad_norm": 0.5580956339836121, "tokens": 61292544, "tok_per_s": 11577.373754446042, "t": 5294.81}199{"step": 3760, "loss": 3.917473554611206, "lr": 0.0002409249897755926, "grad_norm": 0.5592621564865112, "tokens": 61620224, "tok_per_s": 11575.636270353167, "t": 5323.91}200{"step": 3780, "loss": 3.902782917022705, "lr": 0.00023812084290075633, "grad_norm": 0.5623103380203247, "tokens": 61947904, "tok_per_s": 11573.932404902851, "t": 5353.01}201{"step": 3800, "loss": 4.045053482055664, "lr": 0.00023532786009795634, "grad_norm": 0.5493343472480774, "tokens": 62275584, "tok_per_s": 11576.10886221121, "t": 5380.31}202{"step": 3820, "loss": 4.035120010375977, "lr": 0.0002325463807375371, "grad_norm": 0.5667306184768677, "tokens": 62603264, "tok_per_s": 11574.20379848079, "t": 5409.5}203{"step": 3840, "loss": 4.002408027648926, "lr": 0.00022977674279208034, "grad_norm": 0.5492165088653564, "tokens": 62930944, "tok_per_s": 11576.377089696263, "t": 5436.79}204{"step": 3860, "loss": 4.010754108428955, "lr": 0.00022701928279533916, "grad_norm": 0.5650079846382141, "tokens": 63258624, "tok_per_s": 11578.523310325681, "t": 5464.09}205{"step": 3880, "loss": 4.072173118591309, "lr": 0.00022427433580134536, "grad_norm": 0.598127543926239, "tokens": 63586304, "tok_per_s": 11580.383044802815, "t": 5491.51}206{"step": 3900, "loss": 3.9902126789093018, "lr": 0.0002215422353436983, "grad_norm": 0.5532431602478027, "tokens": 63913984, "tok_per_s": 11577.041542373525, "t": 5521.4}207{"step": 3920, "loss": 3.8755486011505127, "lr": 0.00021882331339503767, "grad_norm": 0.5454591512680054, "tokens": 64241664, "tok_per_s": 11577.402404052884, "t": 5549.53}208{"step": 3940, "loss": 3.9723997116088867, "lr": 0.00021611790032670633, "grad_norm": 0.5648732781410217, "tokens": 64569344, "tok_per_s": 11577.031145315133, "t": 5578.01}209{"step": 3960, "loss": 4.01093053817749, "lr": 0.0002134263248686069, "grad_norm": 0.5775900483131409, "tokens": 64897024, "tok_per_s": 11578.616200441384, "t": 5605.55}210{"step": 3980, "loss": 3.90216064453125, "lr": 0.00021074891406925903, "grad_norm": 0.5466880202293396, "tokens": 65224704, "tok_per_s": 11577.200550459853, "t": 5634.54}211{"step": 3999, "val_loss": 4.0112474918365475, "val_ppl": 55.21570876292144, "tokens": 65536000, "t": 5668.99}212{"step": 3999, "checkpoint_sha256": "1defac6e92e64f97536e0c6d03a5ad0f431d8bc6cbc78392fcd088a15efaf557", "t": 5669.37}213{"step": 4000, "loss": 3.962883234024048, "lr": 0.00020808599325605992, "grad_norm": 0.5598580241203308, "tokens": 65552384, "tok_per_s": 11561.020262288332, "t": 5670.76}214{"step": 4020, "loss": 3.9114115238189697, "lr": 0.0002054378859957543, "grad_norm": 0.5523264408111572, "tokens": 65880064, "tok_per_s": 11559.453836876024, "t": 5699.88}215{"step": 4040, "loss": 3.91835355758667, "lr": 0.00020280491405511884, "grad_norm": 0.5684453845024109, "tokens": 66207744, "tok_per_s": 11561.263558356273, "t": 5727.33}216{"step": 4060, "loss": 4.060446739196777, "lr": 0.00020018739736186444, "grad_norm": 0.5896223783493042, "tokens": 66535424, "tok_per_s": 11560.698828062677, "t": 5755.95}217{"step": 4080, "loss": 4.083343029022217, "lr": 0.00019758565396576288, "grad_norm": 0.568533182144165, "tokens": 66863104, "tok_per_s": 11562.029005289642, "t": 5783.63}218{"step": 4100, "loss": 3.9439985752105713, "lr": 0.00019500000000000005, "grad_norm": 0.5773836374282837, "tokens": 67190784, "tok_per_s": 11563.784358023158, "t": 5811.09}219{"step": 4120, "loss": 3.813251256942749, "lr": 0.0001924307496427646, "grad_norm": 0.5718711614608765, "tokens": 67518464, "tok_per_s": 11560.73883504852, "t": 5840.97}220{"step": 4140, "loss": 3.793492317199707, "lr": 0.000189878215079072, "grad_norm": 0.5597081184387207, "tokens": 67846144, "tok_per_s": 11560.29938081825, "t": 5869.53}221{"step": 4160, "loss": 3.9493250846862793, "lr": 0.00018734270646283112, "grad_norm": 0.5616011023521423, "tokens": 68173824, "tok_per_s": 11560.322394282883, "t": 5897.87}222{"step": 4180, "loss": 3.8800625801086426, "lr": 0.0001848245318791589, "grad_norm": 0.550301194190979, "tokens": 68501504, "tok_per_s": 11561.836976458999, "t": 5925.44}223{"step": 4200, "loss": 3.836061954498291, "lr": 0.00018232399730694481, "grad_norm": 0.5758439898490906, "tokens": 68829184, "tok_per_s": 11561.382130904814, "t": 5954.01}224{"step": 4220, "loss": 3.8811402320861816, "lr": 0.00017984140658167184, "grad_norm": 0.5658969879150391, "tokens": 69156864, "tok_per_s": 11560.042820097335, "t": 5983.05}225{"step": 4240, "loss": 3.8178927898406982, "lr": 0.00017737706135849857, "grad_norm": 0.5584120750427246, "tokens": 69484544, "tok_per_s": 11558.705750259509, "t": 6012.09}226{"step": 4260, "loss": 3.942742347717285, "lr": 0.00017493126107560525, "grad_norm": 0.5712693929672241, "tokens": 69812224, "tok_per_s": 11561.05464668217, "t": 6039.21}227{"step": 4280, "loss": 3.9611594676971436, "lr": 0.00017250430291780933, "grad_norm": 0.5624386668205261, "tokens": 70139904, "tok_per_s": 11559.63639961476, "t": 6068.3}228{"step": 4300, "loss": 4.0740766525268555, "lr": 0.0001700964817804554, "grad_norm": 0.5950373411178589, "tokens": 70467584, "tok_per_s": 11561.908158682603, "t": 6095.45}229{"step": 4320, "loss": 3.9431636333465576, "lr": 0.00016770809023358322, "grad_norm": 0.5978004932403564, "tokens": 70795264, "tok_per_s": 11564.137920502184, "t": 6122.61}230{"step": 4340, "loss": 3.7616939544677734, "lr": 0.00016533941848637757, "grad_norm": 0.5960965752601624, "tokens": 71122944, "tok_per_s": 11564.849615749808, "t": 6150.57}231{"step": 4360, "loss": 3.8475029468536377, "lr": 0.00016299075435190547, "grad_norm": 0.5656423568725586, "tokens": 71450624, "tok_per_s": 11564.091210004042, "t": 6179.31}232{"step": 4380, "loss": 3.911325454711914, "lr": 0.000160662383212145, "grad_norm": 0.5660343170166016, "tokens": 71778304, "tok_per_s": 11561.790236658328, "t": 6208.88}233{"step": 4400, "loss": 3.8917365074157715, "lr": 0.00015835458798330867, "grad_norm": 0.5705775022506714, "tokens": 72105984, "tok_per_s": 11563.96163458225, "t": 6236.05}234{"step": 4420, "loss": 3.8357012271881104, "lr": 0.00015606764908146668, "grad_norm": 0.6175817847251892, "tokens": 72433664, "tok_per_s": 11563.629199508314, "t": 6264.56}235{"step": 4440, "loss": 3.9402458667755127, "lr": 0.00015380184438847444, "grad_norm": 0.5682572722434998, "tokens": 72761344, "tok_per_s": 11565.777961491118, "t": 6291.73}236{"step": 4460, "loss": 3.9123647212982178, "lr": 0.0001515574492182075, "grad_norm": 0.5742660760879517, "tokens": 73089024, "tok_per_s": 11564.787390080484, "t": 6320.61}237{"step": 4480, "loss": 3.8569695949554443, "lr": 0.00014933473628310837, "grad_norm": 0.5776249766349792, "tokens": 73416704, "tok_per_s": 11563.360530311495, "t": 6349.72}238{"step": 4499, "val_loss": 3.957085204124451, "val_ppl": 52.304646175065805, "tokens": 73728000, "t": 6384.15}239{"step": 4500, "loss": 3.900219440460205, "lr": 0.00014713397566104992, "grad_norm": 0.5595879554748535, "tokens": 73744384, "tok_per_s": 11549.85744394998, "t": 6385.52}240{"step": 4520, "loss": 3.9554238319396973, "lr": 0.0001449554347625191, "grad_norm": 0.5791251063346863, "tokens": 74072064, "tok_per_s": 11551.858150088292, "t": 6412.78}241{"step": 4540, "loss": 3.8150556087493896, "lr": 0.00014279937829812366, "grad_norm": 0.5590927600860596, "tokens": 74399744, "tok_per_s": 11550.828260871835, "t": 6441.72}242{"step": 4560, "loss": 3.792018413543701, "lr": 0.00014066606824642808, "grad_norm": 0.5811460018157959, "tokens": 74727424, "tok_per_s": 11552.671204872138, "t": 6469.05}243{"step": 4580, "loss": 3.759868621826172, "lr": 0.0001385557638221209, "grad_norm": 0.572047770023346, "tokens": 75055104, "tok_per_s": 11554.365421175793, "t": 6496.46}244{"step": 4600, "loss": 3.800534248352051, "lr": 0.0001364687214445182, "grad_norm": 0.5741000175476074, "tokens": 75382784, "tok_per_s": 11554.324567762942, "t": 6524.85}245{"step": 4620, "loss": 3.8696978092193604, "lr": 0.00013440519470640598, "grad_norm": 0.6237900853157043, "tokens": 75710464, "tok_per_s": 11554.072040147503, "t": 6553.35}246{"step": 4640, "loss": 3.943920612335205, "lr": 0.00013236543434322733, "grad_norm": 0.5705210566520691, "tokens": 76038144, "tok_per_s": 11552.62606413038, "t": 6582.54}247{"step": 4660, "loss": 3.7643725872039795, "lr": 0.00013034968820261554, "grad_norm": 0.5851072669029236, "tokens": 76365824, "tok_per_s": 11554.693671882093, "t": 6609.72}248{"step": 4680, "loss": 3.8417506217956543, "lr": 0.00012835820121427852, "grad_norm": 0.5822275876998901, "tokens": 76693504, "tok_per_s": 11554.239013189506, "t": 6638.34}249{"step": 4700, "loss": 3.8552558422088623, "lr": 0.00012639121536023803, "grad_norm": 0.5749747157096863, "tokens": 77021184, "tok_per_s": 11555.92077454996, "t": 6665.73}250{"step": 4720, "loss": 3.877544403076172, "lr": 0.00012444896964542695, "grad_norm": 0.5795513987541199, "tokens": 77348864, "tok_per_s": 11555.125192265208, "t": 6694.54}251{"step": 4740, "loss": 3.855560302734375, "lr": 0.00012253170006864812, "grad_norm": 0.5813860297203064, "tokens": 77676544, "tok_per_s": 11553.848127747267, "t": 6723.64}252{"step": 4760, "loss": 3.9683942794799805, "lr": 0.00012063963959389822, "grad_norm": 0.5823618173599243, "tokens": 78004224, "tok_per_s": 11552.457505885966, "t": 6752.82}253{"step": 4780, "loss": 3.827885150909424, "lr": 0.00011877301812206132, "grad_norm": 0.5629019141197205, "tokens": 78331904, "tok_per_s": 11554.108498220257, "t": 6780.21}254{"step": 4800, "loss": 3.8732705116271973, "lr": 0.00011693206246297376, "grad_norm": 0.6126952171325684, "tokens": 78659584, "tok_per_s": 11553.165489637673, "t": 6809.13}255{"step": 4820, "loss": 3.753878355026245, "lr": 0.00011511699630786462, "grad_norm": 0.6059414744377136, "tokens": 78987264, "tok_per_s": 11554.472144458165, "t": 6836.72}256{"step": 4840, "loss": 4.004238605499268, "lr": 0.00011332804020217591, "grad_norm": 0.5791417360305786, "tokens": 79314944, "tok_per_s": 11555.287329584366, "t": 6864.6}257{"step": 4860, "loss": 3.7956504821777344, "lr": 0.00011156541151876422, "grad_norm": 0.594039261341095, "tokens": 79642624, "tok_per_s": 11554.656880093267, "t": 6893.33}258{"step": 4880, "loss": 3.903764486312866, "lr": 0.00010982932443148792, "grad_norm": 0.5707221031188965, "tokens": 79970304, "tok_per_s": 11551.781497839473, "t": 6923.42}259{"step": 4900, "loss": 3.8113834857940674, "lr": 0.00010811998988918382, "grad_norm": 0.6023657917976379, "tokens": 80297984, "tok_per_s": 11553.437096988495, "t": 6950.78}260{"step": 4920, "loss": 3.8437676429748535, "lr": 0.00010643761559003459, "grad_norm": 0.5618969798088074, "tokens": 80625664, "tok_per_s": 11552.96747676362, "t": 6979.43}261{"step": 4940, "loss": 3.911839008331299, "lr": 0.00010478240595633218, "grad_norm": 0.5965155959129333, "tokens": 80953344, "tok_per_s": 11554.25529240919, "t": 7007.01}262{"step": 4960, "loss": 3.9762771129608154, "lr": 0.00010315456210963839, "grad_norm": 0.5922918915748596, "tokens": 81281024, "tok_per_s": 11554.737882554518, "t": 7035.08}263{"step": 4980, "loss": 3.800461530685425, "lr": 0.0001015542818463474, "grad_norm": 0.5719321966171265, "tokens": 81608704, "tok_per_s": 11554.03089926349, "t": 7063.87}264{"step": 4999, "val_loss": 3.9170217752456664, "val_ppl": 50.250564225568326, "tokens": 81920000, "t": 7098.86}265{"step": 4999, "checkpoint_sha256": "f09f039d5f72ac5fb5bdab0899b9f829650b3c0101cf509c62d1f4aaf0e6bb5f", "t": 7099.15}266{"step": 5000, "loss": 3.9287047386169434, "lr": 9.998175961365173e-05, "grad_norm": 0.5943207144737244, "tokens": 81936384, "tok_per_s": 11540.023799157347, "t": 7100.83}267{"step": 5020, "loss": 3.853404998779297, "lr": 9.843718648591489e-05, "grad_norm": 0.5844020247459412, "tokens": 82264064, "tok_per_s": 11541.101026861128, "t": 7128.56}268{"step": 5040, "loss": 3.861715793609619, "lr": 9.692075014145502e-05, "grad_norm": 0.586184024810791, "tokens": 82591744, "tok_per_s": 11539.954421434737, "t": 7157.67}269{"step": 5060, "loss": 3.7985501289367676, "lr": 9.543263483973994e-05, "grad_norm": 0.5837913155555725, "tokens": 82919424, "tok_per_s": 11541.87261737775, "t": 7184.87}270{"step": 5080, "loss": 3.9008865356445312, "lr": 9.39730213989981e-05, "grad_norm": 0.5807478427886963, "tokens": 83247104, "tok_per_s": 11543.789493249493, "t": 7212.06}271{"step": 5100, "loss": 3.8417551517486572, "lr": 9.254208717424797e-05, "grad_norm": 0.5791102647781372, "tokens": 83574784, "tok_per_s": 11545.686514623943, "t": 7239.26}272{"step": 5120, "loss": 3.8045313358306885, "lr": 9.114000603574761e-05, "grad_norm": 0.5828171372413635, "tokens": 83902464, "tok_per_s": 11543.956937651712, "t": 7268.73}273{"step": 5140, "loss": 3.9080166816711426, "lr": 8.976694834786837e-05, "grad_norm": 0.5843819379806519, "tokens": 84230144, "tok_per_s": 11543.657775211985, "t": 7297.3}274{"step": 5160, "loss": 3.749263286590576, "lr": 8.842308094839385e-05, "grad_norm": 0.5649449229240417, "tokens": 84557824, "tok_per_s": 11544.058148752227, "t": 7325.43}275{"step": 5180, "loss": 3.858259677886963, "lr": 8.710856712824807e-05, "grad_norm": 0.5771579742431641, "tokens": 84885504, "tok_per_s": 11544.122094995391, "t": 7353.78}276{"step": 5200, "loss": 3.790924549102783, "lr": 8.582356661165409e-05, "grad_norm": 0.5768647789955139, "tokens": 85213184, "tok_per_s": 11545.853513065293, "t": 7381.06}277{"step": 5220, "loss": 3.7866573333740234, "lr": 8.456823553672612e-05, "grad_norm": 0.56633460521698, "tokens": 85540864, "tok_per_s": 11545.18819581383, "t": 7409.86}278{"step": 5240, "loss": 3.8559517860412598, "lr": 8.334272643649774e-05, "grad_norm": 0.6036170721054077, "tokens": 85868544, "tok_per_s": 11543.96703405992, "t": 7439.03}279{"step": 5260, "loss": 3.857818603515625, "lr": 8.214718822038769e-05, "grad_norm": 0.590832531452179, "tokens": 86196224, "tok_per_s": 11543.041741204966, "t": 7468.02}280{"step": 5280, "loss": 3.8089985847473145, "lr": 8.098176615610612e-05, "grad_norm": 0.5837736129760742, "tokens": 86523904, "tok_per_s": 11544.735299253369, "t": 7495.31}281{"step": 5300, "loss": 3.729093313217163, "lr": 7.984660185200352e-05, "grad_norm": 0.5829435586929321, "tokens": 86851584, "tok_per_s": 11543.877992195296, "t": 7524.25}282{"step": 5320, "loss": 3.79866886138916, "lr": 7.874183323986404e-05, "grad_norm": 0.5758870244026184, "tokens": 87179264, "tok_per_s": 11545.581373394647, "t": 7551.52}283{"step": 5340, "loss": 3.85446834564209, "lr": 7.76675945581456e-05, "grad_norm": 0.5752629637718201, "tokens": 87506944, "tok_per_s": 11547.36954656337, "t": 7578.73}284{"step": 5360, "loss": 3.789114475250244, "lr": 7.662401633566895e-05, "grad_norm": 0.5718693733215332, "tokens": 87834624, "tok_per_s": 11546.979012343047, "t": 7607.38}285{"step": 5380, "loss": 3.6952404975891113, "lr": 7.561122537575734e-05, "grad_norm": 0.5910956859588623, "tokens": 88162304, "tok_per_s": 11546.87632803104, "t": 7635.81}286{"step": 5400, "loss": 3.8815152645111084, "lr": 7.462934474082865e-05, "grad_norm": 0.5759338140487671, "tokens": 88489984, "tok_per_s": 11545.790709781168, "t": 7664.91}287{"step": 5420, "loss": 4.046452045440674, "lr": 7.36784937374426e-05, "grad_norm": 0.6042420864105225, "tokens": 88817664, "tok_per_s": 11545.50851820901, "t": 7693.48}288{"step": 5440, "loss": 3.7572991847991943, "lr": 7.27587879018039e-05, "grad_norm": 0.5804364681243896, "tokens": 89145344, "tok_per_s": 11546.780616024904, "t": 7721.01}289{"step": 5460, "loss": 3.8507866859436035, "lr": 7.187033898572343e-05, "grad_norm": 0.5794432759284973, "tokens": 89473024, "tok_per_s": 11547.378430238676, "t": 7748.98}290{"step": 5480, "loss": 3.731966733932495, "lr": 7.101325494303994e-05, "grad_norm": 0.5920389890670776, "tokens": 89800704, "tok_per_s": 11546.92697569402, "t": 7777.66}291{"step": 5499, "val_loss": 3.887117636203766, "val_ppl": 48.770110536442886, "tokens": 90112000, "t": 7813.41}292{"step": 5500, "loss": 3.9196672439575195, "lr": 7.018763991650238e-05, "grad_norm": 0.6001965403556824, "tokens": 90128384, "tok_per_s": 11534.021598855534, "t": 7814.78}293{"step": 5520, "loss": 3.8390917778015137, "lr": 6.939359422511588e-05, "grad_norm": 0.5888873934745789, "tokens": 90456064, "tok_per_s": 11535.491951955515, "t": 7842.19}294{"step": 5540, "loss": 3.8811357021331787, "lr": 6.863121435195203e-05, "grad_norm": 0.5845345258712769, "tokens": 90783744, "tok_per_s": 11534.633071129776, "t": 7871.18}295{"step": 5560, "loss": 3.7738800048828125, "lr": 6.790059293242561e-05, "grad_norm": 0.5928100943565369, "tokens": 91111424, "tok_per_s": 11535.80731025614, "t": 7898.78}296{"step": 5580, "loss": 3.835395574569702, "lr": 6.720181874303845e-05, "grad_norm": 0.5779862403869629, "tokens": 91439104, "tok_per_s": 11537.383975466677, "t": 7926.1}297{"step": 5600, "loss": 3.815725803375244, "lr": 6.653497669059239e-05, "grad_norm": 0.579407811164856, "tokens": 91766784, "tok_per_s": 11535.913175032281, "t": 7955.52}298{"step": 5620, "loss": 3.761955499649048, "lr": 6.590014780187247e-05, "grad_norm": 0.5867651700973511, "tokens": 92094464, "tok_per_s": 11535.090516233922, "t": 7984.5}299{"step": 5640, "loss": 3.8077659606933594, "lr": 6.529740921380147e-05, "grad_norm": 0.5797607898712158, "tokens": 92422144, "tok_per_s": 11535.485589128413, "t": 8012.63}300{"step": 5660, "loss": 3.789388656616211, "lr": 6.47268341640671e-05, "grad_norm": 0.5859403610229492, "tokens": 92749824, "tok_per_s": 11535.285421023631, "t": 8041.17}301{"step": 5680, "loss": 3.8692054748535156, "lr": 6.418849198222306e-05, "grad_norm": 0.5814026594161987, "tokens": 93077504, "tok_per_s": 11536.586077977248, "t": 8068.67}302{"step": 5700, "loss": 3.8076140880584717, "lr": 6.368244808126497e-05, "grad_norm": 0.5866917371749878, "tokens": 93405184, "tok_per_s": 11536.014408981831, "t": 8097.48}303{"step": 5720, "loss": 3.7942938804626465, "lr": 6.320876394968206e-05, "grad_norm": 0.572772741317749, "tokens": 93732864, "tok_per_s": 11535.139908600137, "t": 8126.5}304{"step": 5740, "loss": 3.8309621810913086, "lr": 6.276749714398588e-05, "grad_norm": 0.5950015783309937, "tokens": 94060544, "tok_per_s": 11534.120242321984, "t": 8155.62}305{"step": 5760, "loss": 3.825157642364502, "lr": 6.23587012817167e-05, "grad_norm": 0.609603762626648, "tokens": 94388224, "tok_per_s": 11535.867126376139, "t": 8182.79}306{"step": 5780, "loss": 3.729236125946045, "lr": 6.198242603492857e-05, "grad_norm": 0.5921071171760559, "tokens": 94715904, "tok_per_s": 11534.939763906073, "t": 8211.86}307{"step": 5800, "loss": 3.8878514766693115, "lr": 6.163871712415363e-05, "grad_norm": 0.6161739826202393, "tokens": 95043584, "tok_per_s": 11536.696837804526, "t": 8239.01}308{"step": 5820, "loss": 3.8525753021240234, "lr": 6.132761631284691e-05, "grad_norm": 0.5878046751022339, "tokens": 95371264, "tok_per_s": 11538.254949744933, "t": 8266.3}309{"step": 5840, "loss": 3.8129560947418213, "lr": 6.10491614023115e-05, "grad_norm": 0.5896515846252441, "tokens": 95698944, "tok_per_s": 11538.439787215593, "t": 8294.57}310{"step": 5860, "loss": 3.7627148628234863, "lr": 6.08033862271055e-05, "grad_norm": 0.6002752780914307, "tokens": 96026624, "tok_per_s": 11537.950833802404, "t": 8323.32}311{"step": 5880, "loss": 3.917717933654785, "lr": 6.059032065093087e-05, "grad_norm": 0.5864716172218323, "tokens": 96354304, "tok_per_s": 11536.854347275696, "t": 8352.51}312{"step": 5900, "loss": 3.671173572540283, "lr": 6.040999056300463e-05, "grad_norm": 0.596362292766571, "tokens": 96681984, "tok_per_s": 11537.971918323201, "t": 8380.1}313{"step": 5920, "loss": 3.816864013671875, "lr": 6.026241787491321e-05, "grad_norm": 0.5997350811958313, "tokens": 97009664, "tok_per_s": 11537.623532511629, "t": 8408.76}314{"step": 5940, "loss": 3.8800463676452637, "lr": 6.014762051794997e-05, "grad_norm": 0.5878621339797974, "tokens": 97337344, "tok_per_s": 11539.057999128861, "t": 8436.11}315{"step": 5960, "loss": 3.8143668174743652, "lr": 6.0065612440936474e-05, "grad_norm": 0.599541425704956, "tokens": 97665024, "tok_per_s": 11540.68232762661, "t": 8463.32}316{"step": 5980, "loss": 3.7237539291381836, "lr": 6.001640360852739e-05, "grad_norm": 0.5826242566108704, "tokens": 97992704, "tok_per_s": 11539.89272352153, "t": 8492.29}317{"step": 5999, "loss": 3.8935680389404297, "lr": 6.000004100943553e-05, "grad_norm": 0.5838854908943176, "tokens": 98304000, "tok_per_s": 11538.776028145761, "t": 8520.09}318{"step": 5999, "val_loss": 3.8689021825790406, "val_ppl": 47.88978297376415, "tokens": 98304000, "t": 8526.68}319{"step": 5999, "checkpoint_sha256": "1552f1ec984ec895a40814cd466bde59abaf35e4bfe1ea35b9d43ff4cfe9b9d0", "t": 8527.03}320