1{"step": 0, "loss": 0.9587475657463074, "lr": 1e-05, "grad_norm": 12.132683753967285, "tokens": 166, "tok_per_s": 104.73363890539797, "t": 2.33}2{"step": 50, "loss": 0.416197270154953, "lr": 0.00051, "grad_norm": 1.2982803583145142, "tokens": 8464, "tok_per_s": 800.3206697801855, "t": 11.32}3{"step": 100, "loss": 0.35857951641082764, "lr": 0.001, "grad_norm": 0.6623077988624573, "tokens": 16901, "tok_per_s": 1055.5585595304672, "t": 16.76}4{"step": 150, "loss": 0.33951330184936523, "lr": 0.0009993400362330058, "grad_norm": 0.6303470134735107, "tokens": 25274, "tok_per_s": 1162.0619930598682, "t": 22.49}5{"step": 200, "loss": 0.3725490868091583, "lr": 0.0009973620807194618, "grad_norm": 0.5588074326515198, "tokens": 33315, "tok_per_s": 1248.9329861845454, "t": 27.42}6{"step": 250, "loss": 0.4813978672027588, "lr": 0.000994071935143687, "grad_norm": 0.5745843052864075, "tokens": 41251, "tok_per_s": 1316.6470522320733, "t": 32.08}7{"step": 300, "loss": 0.3457086980342865, "lr": 0.000989479250069539, "grad_norm": 0.4675697088241577, "tokens": 49559, "tok_per_s": 1381.684264190781, "t": 36.61}8{"step": 350, "loss": 0.3763335943222046, "lr": 0.0009835974966336503, "grad_norm": 0.49647068977355957, "tokens": 57986, "tok_per_s": 1434.9649305703426, "t": 41.15}9{"step": 400, "loss": 0.4730722904205322, "lr": 0.0009764439270322612, "grad_norm": 0.5626928210258484, "tokens": 66476, "tok_per_s": 1470.9394090596784, "t": 45.94}10{"step": 450, "loss": 0.30037936568260193, "lr": 0.0009680395239175562, "grad_norm": 0.26431572437286377, "tokens": 74868, "tok_per_s": 1505.8035566109604, "t": 50.47}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4547446275826685, "val_loss_b2": 0.4576994574910141, "val_loss_b4": 0.46719759024088464, "val_loss_b8": 0.4924293309376709, "t": 57.01}12{"step": 500, "loss": 0.47273004055023193, "lr": 0.0009584089388519307, "grad_norm": 0.4296165108680725, "tokens": 83020, "tok_per_s": 1473.246667591344, "t": 57.1}13{"step": 550, "loss": 0.5811091661453247, "lr": 0.0009475804200007103, "grad_norm": 0.44095560908317566, "tokens": 91309, "tok_per_s": 1501.8703803659932, "t": 61.54}14{"step": 600, "loss": 0.3568495213985443, "lr": 0.0009355857292754152, "grad_norm": 0.2732602059841156, "tokens": 99553, "tok_per_s": 1519.4452995804345, "t": 66.26}15{"step": 650, "loss": 0.41019532084465027, "lr": 0.0009224600491706008, "grad_norm": 0.4475879371166229, "tokens": 107933, "tok_per_s": 1537.1858652240744, "t": 70.96}16{"step": 700, "loss": 0.32953399419784546, "lr": 0.0009082418795675396, "grad_norm": 0.3352336585521698, "tokens": 115964, "tok_per_s": 1558.7659500222267, "t": 75.14}17{"step": 750, "loss": 0.45117446780204773, "lr": 0.0008929729248074364, "grad_norm": 0.4398937523365021, "tokens": 124286, "tok_per_s": 1574.1663118073109, "t": 79.7}18{"step": 800, "loss": 0.4359722137451172, "lr": 0.0008766979713654089, "grad_norm": 0.27010226249694824, "tokens": 132702, "tok_per_s": 1582.0718277470057, "t": 84.62}19{"step": 850, "loss": 0.4674191474914551, "lr": 0.0008594647564840406, "grad_norm": 0.29178979992866516, "tokens": 141243, "tok_per_s": 1597.37917388008, "t": 89.17}20{"step": 900, "loss": 0.45510542392730713, "lr": 0.0008413238281518224, "grad_norm": 0.32126742601394653, "tokens": 149475, "tok_per_s": 1616.5676884542106, "t": 93.21}21{"step": 950, "loss": 0.3336946666240692, "lr": 0.0008223283968371944, "grad_norm": 0.23356612026691437, "tokens": 157833, "tok_per_s": 1628.6748613780935, "t": 97.65}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.455182761262355, "val_loss_b2": 0.4567319701727298, "val_loss_b4": 0.4642632203832996, "val_loss_b8": 0.4761698512739592, "t": 103.58}23{"step": 1000, "loss": 0.5612699389457703, "lr": 0.000802534179413072, "grad_norm": 0.4123404622077942, "tokens": 166058, "tok_per_s": 1613.1729748914472, "t": 103.68}24{"step": 1050, "loss": 0.3879508972167969, "lr": 0.0007819992357296598, "grad_norm": 0.28126126527786255, "tokens": 174370, "tok_per_s": 1622.1807832252387, "t": 108.24}25{"step": 1100, "loss": 0.3443715274333954, "lr": 0.0007607837983149056, "grad_norm": 0.24038703739643097, "tokens": 182838, "tok_per_s": 1634.4497437229577, "t": 112.61}26{"step": 1150, "loss": 0.4506535232067108, "lr": 0.0007389500957021191, "grad_norm": 0.43171966075897217, "tokens": 190769, "tok_per_s": 1642.4584074083805, "t": 116.89}27{"step": 1200, "loss": 0.5331219434738159, "lr": 0.0007165621699029615, "grad_norm": 0.3437538146972656, "tokens": 199061, "tok_per_s": 1654.2753293241844, "t": 121.08}28{"step": 1250, "loss": 0.3246280252933502, "lr": 0.000693685688561191, "grad_norm": 0.31401529908180237, "tokens": 207183, "tok_per_s": 1663.529762413905, "t": 125.29}29{"step": 1300, "loss": 0.49369895458221436, "lr": 0.0006703877523381495, "grad_norm": 0.33418017625808716, "tokens": 215576, "tok_per_s": 1671.9744461111936, "t": 129.68}30{"step": 1350, "loss": 0.44625866413116455, "lr": 0.0006467366980949609, "grad_norm": 0.35450857877731323, "tokens": 223982, "tok_per_s": 1679.9820054300847, "t": 134.07}31{"step": 1400, "loss": 0.3400077223777771, "lr": 0.0006228018984487442, "grad_norm": 0.40103113651275635, "tokens": 232005, "tok_per_s": 1687.7905464279254, "t": 138.21}32{"step": 1450, "loss": 0.35400691628456116, "lr": 0.0005986535582907738, "grad_norm": 0.3097715377807617, "tokens": 239958, "tok_per_s": 1698.8072357927113, "t": 142.0}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45043140823116085, "val_loss_b2": 0.4485380775297493, "val_loss_b4": 0.4521428329595619, "val_loss_b8": 0.46208552364764865, "t": 147.96}34{"step": 1500, "loss": 0.5442107915878296, "lr": 0.000574362508863438, "grad_norm": 0.5512535572052002, "tokens": 248410, "tok_per_s": 1686.4382856443276, "t": 148.04}35{"step": 1550, "loss": 0.3353046774864197, "lr": 0.00055, "grad_norm": 0.2754747271537781, "tokens": 256596, "tok_per_s": 1692.2042691297509, "t": 152.38}36{"step": 1600, "loss": 0.36919912695884705, "lr": 0.0005256374911365621, "grad_norm": 0.24496881663799286, "tokens": 264965, "tok_per_s": 1699.115008849131, "t": 156.69}37{"step": 1650, "loss": 0.4531036913394928, "lr": 0.0005013464417092262, "grad_norm": 0.29862138628959656, "tokens": 273349, "tok_per_s": 1705.706950206732, "t": 161.0}38{"step": 1700, "loss": 0.33033427596092224, "lr": 0.00047719810155125587, "grad_norm": 0.29646068811416626, "tokens": 281608, "tok_per_s": 1709.7028222905767, "t": 165.46}39{"step": 1750, "loss": 0.4564732313156128, "lr": 0.0004532633019050392, "grad_norm": 0.3093721568584442, "tokens": 290020, "tok_per_s": 1715.218176046323, "t": 169.83}40{"step": 1800, "loss": 0.29056641459465027, "lr": 0.0004296122476618507, "grad_norm": 0.20187434554100037, "tokens": 298457, "tok_per_s": 1721.7970712820236, "t": 174.1}41{"step": 1850, "loss": 0.3737407624721527, "lr": 0.00040631431143880916, "grad_norm": 0.2570992708206177, "tokens": 306802, "tok_per_s": 1725.558126180396, "t": 178.54}42{"step": 1900, "loss": 0.3128495216369629, "lr": 0.00038343783009703845, "grad_norm": 0.23575252294540405, "tokens": 314844, "tok_per_s": 1732.4238941639364, "t": 182.48}43{"step": 1950, "loss": 0.3390340805053711, "lr": 0.000361049904297881, "grad_norm": 0.3710695505142212, "tokens": 323167, "tok_per_s": 1736.9841560121818, "t": 186.8}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4508482367608158, "val_loss_b2": 0.44989526465704077, "val_loss_b4": 0.45414784461068897, "val_loss_b8": 0.4614719420950538, "t": 192.38}45{"step": 2000, "loss": 0.44438406825065613, "lr": 0.0003392162016850945, "grad_norm": 0.3720014691352844, "tokens": 331553, "tok_per_s": 1729.370493564422, "t": 192.46}46{"step": 2050, "loss": 0.42018190026283264, "lr": 0.0003180007642703402, "grad_norm": 0.3618614971637726, "tokens": 339799, "tok_per_s": 1734.7279948023265, "t": 196.63}47{"step": 2100, "loss": 0.3199816346168518, "lr": 0.000297465820586928, "grad_norm": 0.2395184189081192, "tokens": 348148, "tok_per_s": 1742.041460685226, "t": 200.6}48{"step": 2150, "loss": 0.3512192368507385, "lr": 0.0002776716031628058, "grad_norm": 0.25014984607696533, "tokens": 356667, "tok_per_s": 1751.7993711021136, "t": 204.35}49{"step": 2200, "loss": 0.2849022448062897, "lr": 0.00025867617184817756, "grad_norm": 0.35519489645957947, "tokens": 365197, "tok_per_s": 1760.6328035339156, "t": 208.17}50{"step": 2250, "loss": 0.4442078471183777, "lr": 0.00024053524351595949, "grad_norm": 0.39114829897880554, "tokens": 373572, "tok_per_s": 1763.9730882432812, "t": 212.52}51{"step": 2300, "loss": 0.3452511131763458, "lr": 0.0002233020286345913, "grad_norm": 0.47498202323913574, "tokens": 381835, "tok_per_s": 1766.642512379873, "t": 216.88}52{"step": 2350, "loss": 0.45814019441604614, "lr": 0.00020702707519256364, "grad_norm": 0.3437453806400299, "tokens": 390126, "tok_per_s": 1769.4613632739802, "t": 221.22}53{"step": 2400, "loss": 0.35813790559768677, "lr": 0.00019175812043246033, "grad_norm": 0.36190396547317505, "tokens": 398650, "tok_per_s": 1774.4023077278825, "t": 225.41}54{"step": 2450, "loss": 0.35604628920555115, "lr": 0.00017753995082939931, "grad_norm": 0.3039295971393585, "tokens": 406902, "tok_per_s": 1776.9793643048092, "t": 229.73}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4467861989614939, "val_loss_b2": 0.44532113712135946, "val_loss_b4": 0.4475096283786223, "val_loss_b8": 0.4498667474918732, "t": 235.9}56{"step": 2500, "loss": 0.4565381705760956, "lr": 0.00016441427072458494, "grad_norm": 0.3703247606754303, "tokens": 415163, "tok_per_s": 1764.8164208981966, "t": 235.99}57{"step": 2550, "loss": 0.3345218598842621, "lr": 0.0001524195799992897, "grad_norm": 0.3045977056026459, "tokens": 423133, "tok_per_s": 1764.49623138468, "t": 240.55}58{"step": 2600, "loss": 0.29139894247055054, "lr": 0.0001415910611480694, "grad_norm": 0.35079488158226013, "tokens": 431396, "tok_per_s": 1765.8758484594837, "t": 245.04}59{"step": 2650, "loss": 0.41321200132369995, "lr": 0.00013196047608244387, "grad_norm": 0.42440265417099, "tokens": 439671, "tok_per_s": 1766.6454437219877, "t": 249.62}60{"step": 2700, "loss": 0.374813973903656, "lr": 0.00012355607296773896, "grad_norm": 0.36727219820022583, "tokens": 448101, "tok_per_s": 1771.7822701975956, "t": 253.65}61{"step": 2750, "loss": 0.5043808817863464, "lr": 0.00011640250336634969, "grad_norm": 0.37488019466400146, "tokens": 456477, "tok_per_s": 1777.3011106258966, "t": 257.58}62{"step": 2800, "loss": 0.38318097591400146, "lr": 0.00011052074993046101, "grad_norm": 0.3170720636844635, "tokens": 464767, "tok_per_s": 1781.3656770916289, "t": 261.65}63{"step": 2850, "loss": 0.3289879858493805, "lr": 0.00010592806485631325, "grad_norm": 0.4041926860809326, "tokens": 473172, "tok_per_s": 1785.7982591950447, "t": 265.71}64{"step": 2900, "loss": 0.3445678651332855, "lr": 0.00010263791928053818, "grad_norm": 0.3933316469192505, "tokens": 481142, "tok_per_s": 1786.6614479369155, "t": 270.04}65{"step": 2950, "loss": 0.4019872844219208, "lr": 0.0001006599637669943, "grad_norm": 0.32456082105636597, "tokens": 489885, "tok_per_s": 1792.1062785655922, "t": 274.1}66{"step": 2999, "loss": 0.3841724395751953, "lr": 0.0001000002640500325, "grad_norm": 0.31035804748535156, "tokens": 497821, "tok_per_s": 1794.0003322162677, "t": 278.24}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4460072186029621, "val_loss_b2": 0.444317830378578, "val_loss_b4": 0.4455499099122297, "val_loss_b8": 0.4461924166089505, "t": 280.03}68{"step": 2999, "checkpoint_sha256": "d5d35da1c2fd5f918d9215edc54c1000100974c54ac4898b788569bfadf53e37", "t": 280.19}69