{"step": 20, "tokens": 5242880, "loss": 2.4237618446350098, "lr": 1.6e-05, "gradient_norm": 0.4547433853149414, "tokens_per_second": 118823.23535071073, "synthetic": false, "world_size": 8} {"step": 40, "tokens": 10485760, "loss": 2.421368110179901, "lr": 3.2e-05, "gradient_norm": 0.38724222779273987, "tokens_per_second": 226882.6889937818, "synthetic": false, "world_size": 8} {"step": 60, "tokens": 15728640, "loss": 2.422343361377716, "lr": 4.8e-05, "gradient_norm": 0.3625701069831848, "tokens_per_second": 242803.99177013713, "synthetic": false, "world_size": 8} {"step": 80, "tokens": 20971520, "loss": 2.426099193096161, "lr": 6.4e-05, "gradient_norm": 0.37271827459335327, "tokens_per_second": 225895.25718160818, "synthetic": false, "world_size": 8} {"step": 100, "tokens": 26214400, "loss": 2.4167749762535093, "lr": 8e-05, "gradient_norm": 0.42548567056655884, "tokens_per_second": 231305.22447079286, "synthetic": false, "world_size": 8} {"step": 120, "tokens": 31457280, "loss": 2.4219807028770446, "lr": 9.6e-05, "gradient_norm": 0.5435653924942017, "tokens_per_second": 237626.32900824706, "synthetic": false, "world_size": 8} {"step": 140, "tokens": 36700160, "loss": 2.412984573841095, "lr": 0.000112, "gradient_norm": 0.3727414608001709, "tokens_per_second": 238539.68013729597, "synthetic": false, "world_size": 8} {"step": 160, "tokens": 41943040, "loss": 2.424735426902771, "lr": 0.000128, "gradient_norm": 0.7826135158538818, "tokens_per_second": 240421.2476117541, "synthetic": false, "world_size": 8} {"step": 180, "tokens": 47185920, "loss": 2.4225759506225586, "lr": 0.000144, "gradient_norm": 0.6050042510032654, "tokens_per_second": 228230.56432955625, "synthetic": false, "world_size": 8} {"step": 200, "tokens": 52428800, "loss": 2.424434316158295, "lr": 0.00016, "gradient_norm": 0.4388415217399597, "tokens_per_second": 234910.54151832793, "synthetic": false, "world_size": 8} {"step": 220, "tokens": 57671680, "loss": 2.4145970702171327, "lr": 0.00017600000000000002, "gradient_norm": 0.8145837187767029, "tokens_per_second": 233677.76746090996, "synthetic": false, "world_size": 8} {"step": 240, "tokens": 62914560, "loss": 2.424316036701202, "lr": 0.000192, "gradient_norm": 0.4318310618400574, "tokens_per_second": 232371.9630411241, "synthetic": false, "world_size": 8} {"step": 260, "tokens": 68157440, "loss": 2.4202601075172425, "lr": 0.00019999999377889738, "gradient_norm": 0.5223398208618164, "tokens_per_second": 240565.46435691978, "synthetic": false, "world_size": 8} {"step": 280, "tokens": 73400320, "loss": 2.4152270793914794, "lr": 0.00019999993540806477, "gradient_norm": 0.4124741554260254, "tokens_per_second": 223525.06797781272, "synthetic": false, "world_size": 8} {"step": 300, "tokens": 78643200, "loss": 2.416965973377228, "lr": 0.00019999981559429002, "gradient_norm": 0.3670460879802704, "tokens_per_second": 247501.2607649097, "synthetic": false, "world_size": 8} {"step": 320, "tokens": 83886080, "loss": 2.4188766956329344, "lr": 0.00019999963433765488, "gradient_norm": 0.4977433383464813, "tokens_per_second": 245107.577831157, "synthetic": false, "world_size": 8} {"step": 340, "tokens": 89128960, "loss": 2.426994812488556, "lr": 0.00019999939163828316, "gradient_norm": 0.37240466475486755, "tokens_per_second": 244419.31884394112, "synthetic": false, "world_size": 8} {"step": 360, "tokens": 94371840, "loss": 2.4256531834602355, "lr": 0.00019999908749634054, "gradient_norm": 0.5324045419692993, "tokens_per_second": 235864.55616616234, "synthetic": false, "world_size": 8} {"step": 380, "tokens": 99614720, "loss": 2.4082632303237914, "lr": 0.00019999872191203458, "gradient_norm": 0.4234662652015686, "tokens_per_second": 240259.36857770875, "synthetic": false, "world_size": 8} {"step": 400, "tokens": 104857600, "loss": 2.4178515911102294, "lr": 0.00019999829488561496, "gradient_norm": 0.3698056936264038, "tokens_per_second": 233577.40259881227, "synthetic": false, "world_size": 8} {"step": 420, "tokens": 110100480, "loss": 2.415105414390564, "lr": 0.00019999780641737316, "gradient_norm": 0.5662161111831665, "tokens_per_second": 235790.57026662666, "synthetic": false, "world_size": 8} {"step": 440, "tokens": 115343360, "loss": 2.4114652991294863, "lr": 0.00019999725650764267, "gradient_norm": 0.9660218954086304, "tokens_per_second": 240201.87453100967, "synthetic": false, "world_size": 8} {"step": 460, "tokens": 120586240, "loss": 2.4276467680931093, "lr": 0.00019999664515679892, "gradient_norm": 0.43404674530029297, "tokens_per_second": 235572.39406085617, "synthetic": false, "world_size": 8} {"step": 480, "tokens": 125829120, "loss": 2.4228057861328125, "lr": 0.00019999597236525926, "gradient_norm": 0.3911617696285248, "tokens_per_second": 238851.1584190067, "synthetic": false, "world_size": 8} {"step": 500, "tokens": 131072000, "loss": 2.4225757360458373, "lr": 0.00019999523813348302, "gradient_norm": 0.3626728355884552, "tokens_per_second": 235901.5319708608, "synthetic": false, "world_size": 8} {"step": 520, "tokens": 136314880, "loss": 2.417511999607086, "lr": 0.00019999444246197146, "gradient_norm": 0.5497627258300781, "tokens_per_second": 247801.87456062128, "synthetic": false, "world_size": 8} {"step": 540, "tokens": 141557760, "loss": 2.4146244764328, "lr": 0.0001999935853512678, "gradient_norm": 0.5586260557174683, "tokens_per_second": 234553.41514058874, "synthetic": false, "world_size": 8} {"step": 560, "tokens": 146800640, "loss": 2.4065285205841063, "lr": 0.0001999926668019571, "gradient_norm": 0.42175403237342834, "tokens_per_second": 234661.26254253974, "synthetic": false, "world_size": 8} {"step": 580, "tokens": 152043520, "loss": 2.425058114528656, "lr": 0.00019999168681466656, "gradient_norm": 0.7265626788139343, "tokens_per_second": 232596.95347991204, "synthetic": false, "world_size": 8} {"step": 600, "tokens": 157286400, "loss": 2.4225788831710817, "lr": 0.00019999064539006522, "gradient_norm": 0.5321910381317139, "tokens_per_second": 250277.49805511866, "synthetic": false, "world_size": 8} {"step": 620, "tokens": 162529280, "loss": 2.4045522451400756, "lr": 0.00019998954252886398, "gradient_norm": 0.39847397804260254, "tokens_per_second": 222257.70320471365, "synthetic": false, "world_size": 8} {"step": 640, "tokens": 167772160, "loss": 2.433644938468933, "lr": 0.0001999883782318158, "gradient_norm": 0.39850252866744995, "tokens_per_second": 241117.8814831391, "synthetic": false, "world_size": 8} {"step": 660, "tokens": 173015040, "loss": 2.4247612953186035, "lr": 0.00019998715249971557, "gradient_norm": 0.6602965593338013, "tokens_per_second": 242389.7788610527, "synthetic": false, "world_size": 8} {"step": 680, "tokens": 178257920, "loss": 2.4133525609970095, "lr": 0.00019998586533340006, "gradient_norm": 0.38740891218185425, "tokens_per_second": 234222.1240381335, "synthetic": false, "world_size": 8} {"step": 700, "tokens": 183500800, "loss": 2.41895250082016, "lr": 0.00019998451673374805, "gradient_norm": 1.2728599309921265, "tokens_per_second": 234849.42905653015, "synthetic": false, "world_size": 8} {"step": 720, "tokens": 188743680, "loss": 2.4288503885269166, "lr": 0.00019998310670168022, "gradient_norm": 0.3760034739971161, "tokens_per_second": 236554.34348349372, "synthetic": false, "world_size": 8} {"step": 740, "tokens": 193986560, "loss": 2.4234229564666747, "lr": 0.00019998163523815915, "gradient_norm": 0.4030475318431854, "tokens_per_second": 236125.25243765686, "synthetic": false, "world_size": 8} {"step": 760, "tokens": 199229440, "loss": 2.415709745883942, "lr": 0.0001999801023441895, "gradient_norm": 0.4366610050201416, "tokens_per_second": 237388.6573302138, "synthetic": false, "world_size": 8} {"step": 780, "tokens": 204472320, "loss": 2.427274930477142, "lr": 0.00019997850802081773, "gradient_norm": 0.3938683569431305, "tokens_per_second": 238900.0969658052, "synthetic": false, "world_size": 8} {"step": 800, "tokens": 209715200, "loss": 2.415926468372345, "lr": 0.00019997685226913223, "gradient_norm": 0.36106401681900024, "tokens_per_second": 233855.02985751926, "synthetic": false, "world_size": 8} {"step": 820, "tokens": 214958080, "loss": 2.417611134052277, "lr": 0.00019997513509026346, "gradient_norm": 0.4479476809501648, "tokens_per_second": 238521.92356577577, "synthetic": false, "world_size": 8} {"step": 840, "tokens": 220200960, "loss": 2.4081108808517455, "lr": 0.00019997335648538374, "gradient_norm": 0.48200416564941406, "tokens_per_second": 248709.44472597985, "synthetic": false, "world_size": 8} {"step": 860, "tokens": 225443840, "loss": 2.4277239561080934, "lr": 0.0001999715164557072, "gradient_norm": 0.4404383897781372, "tokens_per_second": 231895.47379154174, "synthetic": false, "world_size": 8} {"step": 880, "tokens": 230686720, "loss": 2.429773724079132, "lr": 0.00019996961500249021, "gradient_norm": 0.34431198239326477, "tokens_per_second": 241037.07114113157, "synthetic": false, "world_size": 8} {"step": 900, "tokens": 235929600, "loss": 2.421737825870514, "lr": 0.0001999676521270308, "gradient_norm": 0.37277930974960327, "tokens_per_second": 236662.07547543896, "synthetic": false, "world_size": 8} {"step": 920, "tokens": 241172480, "loss": 2.409678113460541, "lr": 0.000199965627830669, "gradient_norm": 0.565413236618042, "tokens_per_second": 243114.36066993958, "synthetic": false, "world_size": 8} {"step": 940, "tokens": 246415360, "loss": 2.421820509433746, "lr": 0.00019996354211478684, "gradient_norm": 0.441321462392807, "tokens_per_second": 232230.79103566532, "synthetic": false, "world_size": 8} {"step": 960, "tokens": 251658240, "loss": 2.4189650416374207, "lr": 0.0001999613949808082, "gradient_norm": 0.37144190073013306, "tokens_per_second": 232557.70615833992, "synthetic": false, "world_size": 8} {"step": 980, "tokens": 256901120, "loss": 2.408573877811432, "lr": 0.00019995918643019896, "gradient_norm": 0.4600794017314911, "tokens_per_second": 241242.46791315358, "synthetic": false, "world_size": 8} {"step": 1000, "tokens": 262144000, "loss": 2.4198187232017516, "lr": 0.0001999569164644669, "gradient_norm": 0.47680574655532837, "tokens_per_second": 239037.07176076944, "synthetic": false, "world_size": 8} {"step": 1020, "tokens": 267386880, "loss": 2.4134859323501585, "lr": 0.0001999545850851617, "gradient_norm": 0.6864268183708191, "tokens_per_second": 228574.86303448942, "synthetic": false, "world_size": 8} {"step": 1040, "tokens": 272629760, "loss": 2.4372740626335143, "lr": 0.000199952192293875, "gradient_norm": 0.37269529700279236, "tokens_per_second": 241852.275080761, "synthetic": false, "world_size": 8} {"step": 1060, "tokens": 277872640, "loss": 2.418045711517334, "lr": 0.00019994973809224037, "gradient_norm": 0.4666963219642639, "tokens_per_second": 251099.7540069703, "synthetic": false, "world_size": 8} {"step": 1080, "tokens": 283115520, "loss": 2.40960556268692, "lr": 0.0001999472224819333, "gradient_norm": 0.5307825207710266, "tokens_per_second": 222960.92232612584, "synthetic": false, "world_size": 8} {"step": 1100, "tokens": 288358400, "loss": 2.4085195899009704, "lr": 0.00019994464546467118, "gradient_norm": 0.5386868715286255, "tokens_per_second": 241297.04623364419, "synthetic": false, "world_size": 8} {"step": 1120, "tokens": 293601280, "loss": 2.4276673913002016, "lr": 0.00019994200704221332, "gradient_norm": 0.9972819685935974, "tokens_per_second": 234573.45616571888, "synthetic": false, "world_size": 8} {"step": 1140, "tokens": 298844160, "loss": 2.415241169929504, "lr": 0.00019993930721636105, "gradient_norm": 0.43388158082962036, "tokens_per_second": 238578.22635197724, "synthetic": false, "world_size": 8} {"step": 1160, "tokens": 304087040, "loss": 2.4098518252372743, "lr": 0.00019993654598895745, "gradient_norm": 0.3748798668384552, "tokens_per_second": 233560.02698052154, "synthetic": false, "world_size": 8} {"step": 1180, "tokens": 309329920, "loss": 2.416824460029602, "lr": 0.0001999337233618876, "gradient_norm": 0.5426247715950012, "tokens_per_second": 232530.39697707005, "synthetic": false, "world_size": 8} {"step": 1200, "tokens": 314572800, "loss": 2.4225706815719605, "lr": 0.0001999308393370786, "gradient_norm": 0.40008431673049927, "tokens_per_second": 244018.7341867074, "synthetic": false, "world_size": 8} {"step": 1220, "tokens": 319815680, "loss": 2.4138627529144285, "lr": 0.0001999278939164993, "gradient_norm": 0.5091761350631714, "tokens_per_second": 236284.77237937626, "synthetic": false, "world_size": 8} {"step": 1240, "tokens": 325058560, "loss": 2.4143186211586, "lr": 0.0001999248871021606, "gradient_norm": 0.3916034698486328, "tokens_per_second": 239466.61587186006, "synthetic": false, "world_size": 8} {"step": 1260, "tokens": 330301440, "loss": 2.4278207063674926, "lr": 0.00019992181889611518, "gradient_norm": 0.8924903869628906, "tokens_per_second": 236982.09991627888, "synthetic": false, "world_size": 8} {"step": 1280, "tokens": 335544320, "loss": 2.4137553215026855, "lr": 0.00019991868930045774, "gradient_norm": 0.46184393763542175, "tokens_per_second": 247211.45062358116, "synthetic": false, "world_size": 8} {"step": 1300, "tokens": 340787200, "loss": 2.420761251449585, "lr": 0.00019991549831732485, "gradient_norm": 0.4539565145969391, "tokens_per_second": 238837.44151638862, "synthetic": false, "world_size": 8} {"step": 1320, "tokens": 346030080, "loss": 2.4255964875221254, "lr": 0.00019991224594889502, "gradient_norm": 0.41955864429473877, "tokens_per_second": 239642.49004098884, "synthetic": false, "world_size": 8} {"step": 1340, "tokens": 351272960, "loss": 2.4129990696907044, "lr": 0.00019990893219738861, "gradient_norm": 0.6111081838607788, "tokens_per_second": 234817.73574339956, "synthetic": false, "world_size": 8} {"step": 1360, "tokens": 356515840, "loss": 2.423884117603302, "lr": 0.00019990555706506793, "gradient_norm": 0.4421883225440979, "tokens_per_second": 238616.64969810407, "synthetic": false, "world_size": 8} {"step": 1380, "tokens": 361758720, "loss": 2.4277253270149233, "lr": 0.00019990212055423715, "gradient_norm": 0.4236302375793457, "tokens_per_second": 242076.02481484597, "synthetic": false, "world_size": 8} {"step": 1400, "tokens": 367001600, "loss": 2.425757944583893, "lr": 0.00019989862266724242, "gradient_norm": 0.551115870475769, "tokens_per_second": 231974.8069906906, "synthetic": false, "world_size": 8} {"step": 1420, "tokens": 372244480, "loss": 2.424298107624054, "lr": 0.00019989506340647173, "gradient_norm": 0.45404160022735596, "tokens_per_second": 232062.9357322199, "synthetic": false, "world_size": 8} {"step": 1440, "tokens": 377487360, "loss": 2.4248749732971193, "lr": 0.000199891442774355, "gradient_norm": 0.35626426339149475, "tokens_per_second": 236256.13308724918, "synthetic": false, "world_size": 8} {"step": 1460, "tokens": 382730240, "loss": 2.4181071400642393, "lr": 0.000199887760773364, "gradient_norm": 0.7087916731834412, "tokens_per_second": 238846.85086588, "synthetic": false, "world_size": 8} {"step": 1480, "tokens": 387973120, "loss": 2.4185762882232664, "lr": 0.00019988401740601245, "gradient_norm": 0.35243478417396545, "tokens_per_second": 233631.59152805165, "synthetic": false, "world_size": 8} {"step": 1500, "tokens": 393216000, "loss": 2.4112608432769775, "lr": 0.00019988021267485596, "gradient_norm": 0.4417816996574402, "tokens_per_second": 235111.7182798643, "synthetic": false, "world_size": 8} {"step": 1520, "tokens": 398458880, "loss": 2.4221294283866883, "lr": 0.000199876346582492, "gradient_norm": 0.5070348978042603, "tokens_per_second": 244639.9753090908, "synthetic": false, "world_size": 8} {"step": 1540, "tokens": 403701760, "loss": 2.4210175275802612, "lr": 0.00019987241913155997, "gradient_norm": 0.3894330859184265, "tokens_per_second": 262981.89402896963, "synthetic": false, "world_size": 8} {"step": 1560, "tokens": 408944640, "loss": 2.427801275253296, "lr": 0.00019986843032474114, "gradient_norm": 0.493276983499527, "tokens_per_second": 286853.35980874684, "synthetic": false, "world_size": 8} {"step": 1580, "tokens": 414187520, "loss": 2.434071052074432, "lr": 0.00019986438016475862, "gradient_norm": 0.35777297616004944, "tokens_per_second": 259131.20214984185, "synthetic": false, "world_size": 8} {"step": 1600, "tokens": 419430400, "loss": 2.4194270253181456, "lr": 0.00019986026865437753, "gradient_norm": 0.37053394317626953, "tokens_per_second": 241809.7078352378, "synthetic": false, "world_size": 8} {"step": 1620, "tokens": 424673280, "loss": 2.4268874168395995, "lr": 0.00019985609579640474, "gradient_norm": 0.7007189393043518, "tokens_per_second": 234157.4897945868, "synthetic": false, "world_size": 8} {"step": 1640, "tokens": 429916160, "loss": 2.4119635462760924, "lr": 0.00019985186159368908, "gradient_norm": 0.8371211290359497, "tokens_per_second": 245736.43241382047, "synthetic": false, "world_size": 8} {"step": 1660, "tokens": 435159040, "loss": 2.423711597919464, "lr": 0.00019984756604912122, "gradient_norm": 0.44753342866897583, "tokens_per_second": 259669.41515747426, "synthetic": false, "world_size": 8} {"step": 1680, "tokens": 440401920, "loss": 2.4134703636169434, "lr": 0.00019984320916563376, "gradient_norm": 0.45285895466804504, "tokens_per_second": 234986.5966934381, "synthetic": false, "world_size": 8} {"step": 1700, "tokens": 445644800, "loss": 2.413721299171448, "lr": 0.00019983879094620115, "gradient_norm": 0.6134827136993408, "tokens_per_second": 230826.89931240142, "synthetic": false, "world_size": 8} {"step": 1720, "tokens": 450887680, "loss": 2.423062229156494, "lr": 0.00019983431139383967, "gradient_norm": 0.3909475803375244, "tokens_per_second": 242545.05126721744, "synthetic": false, "world_size": 8} {"step": 1740, "tokens": 456130560, "loss": 2.4120756506919863, "lr": 0.00019982977051160753, "gradient_norm": 0.468217134475708, "tokens_per_second": 236524.37673817534, "synthetic": false, "world_size": 8} {"step": 1760, "tokens": 461373440, "loss": 2.412274885177612, "lr": 0.00019982516830260475, "gradient_norm": 0.34312817454338074, "tokens_per_second": 231850.35247106297, "synthetic": false, "world_size": 8} {"step": 1780, "tokens": 466616320, "loss": 2.4161468744277954, "lr": 0.00019982050476997332, "gradient_norm": 0.565841794013977, "tokens_per_second": 249814.4030428664, "synthetic": false, "world_size": 8} {"step": 1800, "tokens": 471859200, "loss": 2.4178020000457763, "lr": 0.000199815779916897, "gradient_norm": 0.37697741389274597, "tokens_per_second": 285427.18764033075, "synthetic": false, "world_size": 8} {"step": 1820, "tokens": 477102080, "loss": 2.41076945066452, "lr": 0.0001998109937466015, "gradient_norm": 0.36620038747787476, "tokens_per_second": 206240.60888457036, "synthetic": false, "world_size": 8} {"step": 1840, "tokens": 482344960, "loss": 2.4114864349365233, "lr": 0.00019980614626235424, "gradient_norm": 0.3634025752544403, "tokens_per_second": 236807.32285314216, "synthetic": false, "world_size": 8} {"step": 1860, "tokens": 487587840, "loss": 2.4224168062210083, "lr": 0.00019980123746746466, "gradient_norm": 0.5248729586601257, "tokens_per_second": 237261.20059022668, "synthetic": false, "world_size": 8} {"step": 1880, "tokens": 492830720, "loss": 2.4167969942092897, "lr": 0.000199796267365284, "gradient_norm": 0.3659108579158783, "tokens_per_second": 234456.93631234314, "synthetic": false, "world_size": 8} {"step": 1900, "tokens": 498073600, "loss": 2.4106893062591555, "lr": 0.0001997912359592053, "gradient_norm": 0.4009942412376404, "tokens_per_second": 245604.7849254759, "synthetic": false, "world_size": 8} {"step": 1920, "tokens": 503316480, "loss": 2.4186774253845216, "lr": 0.00019978614325266353, "gradient_norm": 0.38536936044692993, "tokens_per_second": 234098.41031083785, "synthetic": false, "world_size": 8} {"step": 1940, "tokens": 508559360, "loss": 2.4269838452339174, "lr": 0.0001997809892491355, "gradient_norm": 0.35398682951927185, "tokens_per_second": 248216.87340630678, "synthetic": false, "world_size": 8} {"step": 1960, "tokens": 513802240, "loss": 2.39722626209259, "lr": 0.00019977577395213978, "gradient_norm": 0.8542947173118591, "tokens_per_second": 242821.85751173453, "synthetic": false, "world_size": 8} {"step": 1980, "tokens": 519045120, "loss": 2.4144457459449766, "lr": 0.00019977049736523693, "gradient_norm": 0.4741521179676056, "tokens_per_second": 239973.77702003042, "synthetic": false, "world_size": 8} {"step": 2000, "tokens": 524288000, "loss": 2.4001739263534545, "lr": 0.00019976515949202925, "gradient_norm": 0.6954247355461121, "tokens_per_second": 242991.03123454, "synthetic": false, "world_size": 8} {"step": 2020, "tokens": 529530880, "loss": 2.417385482788086, "optimizer_updates": 2010, "effective_batch": 512, "lr": 0.0001997600317493608, "gradient_norm": 0.733902096748352, "tokens_per_second": 194454.51674806396, "synthetic": false, "world_size": 8} {"step": 2040, "tokens": 534773760, "loss": 2.414969635009766, "optimizer_updates": 2020, "effective_batch": 512, "lr": 0.0001997545743783783, "gradient_norm": 0.33573660254478455, "tokens_per_second": 868945.9616410098, "synthetic": false, "world_size": 8} {"step": 2060, "tokens": 540016640, "loss": 2.4176303863525392, "optimizer_updates": 2030, "effective_batch": 512, "lr": 0.00019974905573196162, "gradient_norm": 0.44640523195266724, "tokens_per_second": 1084983.8632434544, "synthetic": false, "world_size": 8} {"step": 2080, "tokens": 545259520, "loss": 2.413969802856445, "optimizer_updates": 2040, "effective_batch": 512, "lr": 0.00019974347581387826, "gradient_norm": 0.47163036465644836, "tokens_per_second": 1089348.719032735, "synthetic": false, "world_size": 8} {"step": 2100, "tokens": 550502400, "loss": 2.4070194244384764, "optimizer_updates": 2050, "effective_batch": 512, "lr": 0.00019973783462793771, "gradient_norm": 0.32906100153923035, "tokens_per_second": 1087948.4173990209, "synthetic": false, "world_size": 8} {"step": 2120, "tokens": 555745280, "loss": 2.3920183181762695, "optimizer_updates": 2060, "effective_batch": 512, "lr": 0.00019973213217799117, "gradient_norm": 0.4525008201599121, "tokens_per_second": 1084466.6477580168, "synthetic": false, "world_size": 8} {"step": 2140, "tokens": 560988160, "loss": 2.3989633560180663, "optimizer_updates": 2070, "effective_batch": 512, "lr": 0.0001997263684679317, "gradient_norm": 0.31883180141448975, "tokens_per_second": 1091540.921112782, "synthetic": false, "world_size": 8} {"step": 2160, "tokens": 566231040, "loss": 2.416238212585449, "optimizer_updates": 2080, "effective_batch": 512, "lr": 0.00019972054350169416, "gradient_norm": 0.37149176001548767, "tokens_per_second": 1075493.7915871786, "synthetic": false, "world_size": 8} {"step": 2180, "tokens": 571473920, "loss": 2.4182947158813475, "optimizer_updates": 2090, "effective_batch": 512, "lr": 0.0001997146572832553, "gradient_norm": 0.6741521954536438, "tokens_per_second": 1070320.457902844, "synthetic": false, "world_size": 8} {"step": 2200, "tokens": 576716800, "loss": 2.4129150390625, "optimizer_updates": 2100, "effective_batch": 512, "lr": 0.0001997087098166336, "gradient_norm": 0.44900819659233093, "tokens_per_second": 1079528.2355009133, "synthetic": false, "world_size": 8} {"step": 2220, "tokens": 581959680, "loss": 2.4023815155029298, "optimizer_updates": 2110, "effective_batch": 512, "lr": 0.00019970270110588944, "gradient_norm": 0.2690970301628113, "tokens_per_second": 1086823.7787003655, "synthetic": false, "world_size": 8} {"step": 2240, "tokens": 587202560, "loss": 2.4145715713500975, "optimizer_updates": 2120, "effective_batch": 512, "lr": 0.00019969663115512493, "gradient_norm": 0.3323979675769806, "tokens_per_second": 1081508.9043533863, "synthetic": false, "world_size": 8} {"step": 2260, "tokens": 592445440, "loss": 2.406887435913086, "optimizer_updates": 2130, "effective_batch": 512, "lr": 0.00019969049996848402, "gradient_norm": 0.29103076457977295, "tokens_per_second": 995119.3815635213, "synthetic": false, "world_size": 8} {"step": 2280, "tokens": 597688320, "loss": 2.4067792892456055, "optimizer_updates": 2140, "effective_batch": 512, "lr": 0.00019968430755015252, "gradient_norm": 0.42456161975860596, "tokens_per_second": 1071353.2054936155, "synthetic": false, "world_size": 8} {"step": 2300, "tokens": 602931200, "loss": 2.4176399230957033, "optimizer_updates": 2150, "effective_batch": 512, "lr": 0.00019967805390435793, "gradient_norm": 0.2740194797515869, "tokens_per_second": 1066326.6949701486, "synthetic": false, "world_size": 8} {"step": 2320, "tokens": 608174080, "loss": 2.3995250701904296, "optimizer_updates": 2160, "effective_batch": 512, "lr": 0.00019967173903536964, "gradient_norm": 0.39699769020080566, "tokens_per_second": 1071788.901119325, "synthetic": false, "world_size": 8} {"step": 2340, "tokens": 613416960, "loss": 2.4121936798095702, "optimizer_updates": 2170, "effective_batch": 512, "lr": 0.00019966536294749882, "gradient_norm": 0.2501486837863922, "tokens_per_second": 1067153.2774449016, "synthetic": false, "world_size": 8} {"step": 2360, "tokens": 618659840, "loss": 2.409385108947754, "optimizer_updates": 2180, "effective_batch": 512, "lr": 0.00019965892564509843, "gradient_norm": 0.3688752055168152, "tokens_per_second": 1066355.0416025608, "synthetic": false, "world_size": 8} {"step": 2380, "tokens": 623902720, "loss": 2.4156734466552736, "optimizer_updates": 2190, "effective_batch": 512, "lr": 0.00019965242713256316, "gradient_norm": 0.5488168597221375, "tokens_per_second": 1076104.6654746754, "synthetic": false, "world_size": 8} {"step": 2400, "tokens": 629145600, "loss": 2.4262847900390625, "optimizer_updates": 2200, "effective_batch": 512, "lr": 0.0001996458674143296, "gradient_norm": 0.27614280581474304, "tokens_per_second": 1062296.070450696, "synthetic": false, "world_size": 8} {"step": 2420, "tokens": 634388480, "loss": 2.417021942138672, "optimizer_updates": 2210, "effective_batch": 512, "lr": 0.00019963924649487604, "gradient_norm": 0.5514534711837769, "tokens_per_second": 1063829.8854725221, "synthetic": false, "world_size": 8} {"step": 2440, "tokens": 639631360, "loss": 2.4159740447998046, "optimizer_updates": 2220, "effective_batch": 512, "lr": 0.00019963256437872265, "gradient_norm": 0.383661687374115, "tokens_per_second": 1060809.4984805027, "synthetic": false, "world_size": 8} {"step": 2460, "tokens": 644874240, "loss": 2.4192052841186524, "optimizer_updates": 2230, "effective_batch": 512, "lr": 0.0001996258210704312, "gradient_norm": 0.26092228293418884, "tokens_per_second": 1079301.4156232341, "synthetic": false, "world_size": 8} {"step": 2480, "tokens": 650117120, "loss": 2.42635555267334, "optimizer_updates": 2240, "effective_batch": 512, "lr": 0.0001996190165746054, "gradient_norm": 0.2605257034301758, "tokens_per_second": 1082678.0769278738, "synthetic": false, "world_size": 8} {"step": 2500, "tokens": 655360000, "loss": 2.4127105712890624, "optimizer_updates": 2250, "effective_batch": 512, "lr": 0.0001996121508958907, "gradient_norm": 0.31621941924095154, "tokens_per_second": 1082396.1133938413, "synthetic": false, "world_size": 8} {"step": 2520, "tokens": 660602880, "loss": 2.4017507553100588, "optimizer_updates": 2260, "effective_batch": 512, "lr": 0.00019960522403897422, "gradient_norm": 0.36425477266311646, "tokens_per_second": 1082842.9059389168, "synthetic": false, "world_size": 8} {"step": 2540, "tokens": 665845760, "loss": 2.4089229583740233, "optimizer_updates": 2270, "effective_batch": 512, "lr": 0.00019959823600858504, "gradient_norm": 0.2799132466316223, "tokens_per_second": 1077093.30436044, "synthetic": false, "world_size": 8} {"step": 2560, "tokens": 671088640, "loss": 2.4144241333007814, "optimizer_updates": 2280, "effective_batch": 512, "lr": 0.0001995911868094938, "gradient_norm": 0.31464114785194397, "tokens_per_second": 1082680.2337850758, "synthetic": false, "world_size": 8} {"step": 2580, "tokens": 676331520, "loss": 2.4125045776367187, "optimizer_updates": 2290, "effective_batch": 512, "lr": 0.000199584076446513, "gradient_norm": 0.2955721616744995, "tokens_per_second": 1079270.2534471059, "synthetic": false, "world_size": 8} {"step": 2600, "tokens": 681574400, "loss": 2.4021699905395506, "optimizer_updates": 2300, "effective_batch": 512, "lr": 0.00019957690492449694, "gradient_norm": 0.3018452823162079, "tokens_per_second": 1070027.7175313008, "synthetic": false, "world_size": 8} {"step": 2620, "tokens": 686817280, "loss": 2.409882926940918, "optimizer_updates": 2310, "effective_batch": 512, "lr": 0.00019956967224834155, "gradient_norm": 0.3883850872516632, "tokens_per_second": 1078782.0281809457, "synthetic": false, "world_size": 8} {"step": 2640, "tokens": 692060160, "loss": 2.411549758911133, "optimizer_updates": 2320, "effective_batch": 512, "lr": 0.0001995623784229846, "gradient_norm": 0.2799171507358551, "tokens_per_second": 1079572.225391808, "synthetic": false, "world_size": 8} {"step": 2660, "tokens": 697303040, "loss": 2.405427932739258, "optimizer_updates": 2330, "effective_batch": 512, "lr": 0.00019955502345340555, "gradient_norm": 0.3338140845298767, "tokens_per_second": 1078722.285158871, "synthetic": false, "world_size": 8} {"step": 2680, "tokens": 702545920, "loss": 2.396527862548828, "optimizer_updates": 2340, "effective_batch": 512, "lr": 0.00019954760734462571, "gradient_norm": 0.2613537609577179, "tokens_per_second": 1077401.4152528117, "synthetic": false, "world_size": 8} {"step": 2700, "tokens": 707788800, "loss": 2.4136070251464843, "optimizer_updates": 2350, "effective_batch": 512, "lr": 0.000199540130101708, "gradient_norm": 0.3108280897140503, "tokens_per_second": 1079074.8955781953, "synthetic": false, "world_size": 8} {"step": 2720, "tokens": 713031680, "loss": 2.4074939727783202, "optimizer_updates": 2360, "effective_batch": 512, "lr": 0.00019953259172975717, "gradient_norm": 0.36161741614341736, "tokens_per_second": 1077645.414137091, "synthetic": false, "world_size": 8} {"step": 2740, "tokens": 718274560, "loss": 2.4105772018432616, "optimizer_updates": 2370, "effective_batch": 512, "lr": 0.00019952499223391964, "gradient_norm": 0.43543800711631775, "tokens_per_second": 1077218.1048023335, "synthetic": false, "world_size": 8} {"step": 2760, "tokens": 723517440, "loss": 2.4161453247070312, "optimizer_updates": 2380, "effective_batch": 512, "lr": 0.00019951733161938359, "gradient_norm": 0.29302316904067993, "tokens_per_second": 1090317.775879124, "synthetic": false, "world_size": 8} {"step": 2780, "tokens": 728760320, "loss": 2.4154842376708983, "optimizer_updates": 2390, "effective_batch": 512, "lr": 0.00019950960989137889, "gradient_norm": 0.3243792653083801, "tokens_per_second": 775464.7893828049, "synthetic": false, "world_size": 8} {"step": 2800, "tokens": 734003200, "loss": 2.40419864654541, "optimizer_updates": 2400, "effective_batch": 512, "lr": 0.0001995018270551772, "gradient_norm": 0.5509384274482727, "tokens_per_second": 1070468.6255003375, "synthetic": false, "world_size": 8} {"step": 2820, "tokens": 739246080, "loss": 2.407693290710449, "optimizer_updates": 2410, "effective_batch": 512, "lr": 0.00019949398311609187, "gradient_norm": 0.2751626968383789, "tokens_per_second": 1079918.408472994, "synthetic": false, "world_size": 8} {"step": 2840, "tokens": 744488960, "loss": 2.401725006103516, "optimizer_updates": 2420, "effective_batch": 512, "lr": 0.00019948607807947796, "gradient_norm": 0.31005731225013733, "tokens_per_second": 1076030.846564518, "synthetic": false, "world_size": 8} {"step": 2860, "tokens": 749731840, "loss": 2.418086624145508, "optimizer_updates": 2430, "effective_batch": 512, "lr": 0.0001994781119507322, "gradient_norm": 0.3793759047985077, "tokens_per_second": 970883.678511276, "synthetic": false, "world_size": 8} {"step": 2880, "tokens": 754974720, "loss": 2.414846420288086, "optimizer_updates": 2440, "effective_batch": 512, "lr": 0.00019947008473529307, "gradient_norm": 0.553760290145874, "tokens_per_second": 1075932.3117168865, "synthetic": false, "world_size": 8} {"step": 2900, "tokens": 760217600, "loss": 2.4163604736328126, "optimizer_updates": 2450, "effective_batch": 512, "lr": 0.00019946199643864075, "gradient_norm": 0.31862837076187134, "tokens_per_second": 1078593.741203224, "synthetic": false, "world_size": 8} {"step": 2920, "tokens": 765460480, "loss": 2.397769546508789, "optimizer_updates": 2460, "effective_batch": 512, "lr": 0.00019945384706629714, "gradient_norm": 0.42883771657943726, "tokens_per_second": 1071459.624150988, "synthetic": false, "world_size": 8} {"step": 2940, "tokens": 770703360, "loss": 2.4107580184936523, "optimizer_updates": 2470, "effective_batch": 512, "lr": 0.00019944563662382584, "gradient_norm": 0.49605223536491394, "tokens_per_second": 1072011.0213141579, "synthetic": false, "world_size": 8} {"step": 2960, "tokens": 775946240, "loss": 2.407169532775879, "optimizer_updates": 2480, "effective_batch": 512, "lr": 0.000199437365116832, "gradient_norm": 0.3221134543418884, "tokens_per_second": 1080009.1431646107, "synthetic": false, "world_size": 8} {"step": 2980, "tokens": 781189120, "loss": 2.4113981246948244, "optimizer_updates": 2490, "effective_batch": 512, "lr": 0.00019942903255096273, "gradient_norm": 0.34019264578819275, "tokens_per_second": 1080377.4849537315, "synthetic": false, "world_size": 8} {"step": 3000, "tokens": 786432000, "loss": 2.4143560409545897, "optimizer_updates": 2500, "effective_batch": 512, "lr": 0.00019942063893190658, "gradient_norm": 0.2658492922782898, "tokens_per_second": 1079761.589805275, "synthetic": false, "world_size": 8} {"step": 3020, "tokens": 791674880, "loss": 2.4064809799194338, "optimizer_updates": 2510, "effective_batch": 512, "lr": 0.0001994121842653939, "gradient_norm": 0.2675633132457733, "tokens_per_second": 853695.6856017828, "synthetic": false, "world_size": 8} {"step": 3040, "tokens": 796917760, "loss": 2.3998104095458985, "optimizer_updates": 2520, "effective_batch": 512, "lr": 0.00019940366855719665, "gradient_norm": 0.2841006815433502, "tokens_per_second": 1083346.7578188991, "synthetic": false, "world_size": 8} {"step": 3060, "tokens": 802160640, "loss": 2.411117935180664, "optimizer_updates": 2530, "effective_batch": 512, "lr": 0.00019939509181312858, "gradient_norm": 0.27457284927368164, "tokens_per_second": 1086343.3557473926, "synthetic": false, "world_size": 8} {"step": 3080, "tokens": 807403520, "loss": 2.4025611877441406, "optimizer_updates": 2540, "effective_batch": 512, "lr": 0.00019938645403904496, "gradient_norm": 0.4045385420322418, "tokens_per_second": 1080799.4498134644, "synthetic": false, "world_size": 8} {"step": 3100, "tokens": 812646400, "loss": 2.4187362670898436, "optimizer_updates": 2550, "effective_batch": 512, "lr": 0.00019937775524084283, "gradient_norm": 0.3093273937702179, "tokens_per_second": 1080257.591089501, "synthetic": false, "world_size": 8} {"step": 3120, "tokens": 817889280, "loss": 2.4079607009887694, "optimizer_updates": 2560, "effective_batch": 512, "lr": 0.00019936899542446086, "gradient_norm": 0.3316539227962494, "tokens_per_second": 1075922.5632748052, "synthetic": false, "world_size": 8} {"step": 3140, "tokens": 823132160, "loss": 2.413834571838379, "optimizer_updates": 2570, "effective_batch": 512, "lr": 0.00019936017459587936, "gradient_norm": 0.5738455057144165, "tokens_per_second": 775578.3756579517, "synthetic": false, "world_size": 8} {"step": 3160, "tokens": 828375040, "loss": 2.4028209686279296, "optimizer_updates": 2580, "effective_batch": 512, "lr": 0.00019935129276112031, "gradient_norm": 0.3474644422531128, "tokens_per_second": 1068579.674295358, "synthetic": false, "world_size": 8} {"step": 3180, "tokens": 833617920, "loss": 2.4044775009155273, "optimizer_updates": 2590, "effective_batch": 512, "lr": 0.00019934234992624735, "gradient_norm": 0.29594939947128296, "tokens_per_second": 1073570.2519572922, "synthetic": false, "world_size": 8} {"step": 3200, "tokens": 838860800, "loss": 2.4058815002441407, "optimizer_updates": 2600, "effective_batch": 512, "lr": 0.00019933334609736577, "gradient_norm": 0.28409770131111145, "tokens_per_second": 1083414.701118489, "synthetic": false, "world_size": 8} {"step": 3220, "tokens": 844103680, "loss": 2.4052461624145507, "optimizer_updates": 2610, "effective_batch": 512, "lr": 0.0001993242812806224, "gradient_norm": 0.5534052848815918, "tokens_per_second": 1083029.902619808, "synthetic": false, "world_size": 8} {"step": 3240, "tokens": 849346560, "loss": 2.396803855895996, "optimizer_updates": 2620, "effective_batch": 512, "lr": 0.0001993151554822059, "gradient_norm": 0.287785142660141, "tokens_per_second": 1077901.4380589619, "synthetic": false, "world_size": 8} {"step": 3260, "tokens": 854589440, "loss": 2.409322738647461, "optimizer_updates": 2630, "effective_batch": 512, "lr": 0.00019930596870834636, "gradient_norm": 0.5115651488304138, "tokens_per_second": 1087004.5582122384, "synthetic": false, "world_size": 8} {"step": 3280, "tokens": 859832320, "loss": 2.4080764770507814, "optimizer_updates": 2640, "effective_batch": 512, "lr": 0.00019929672096531564, "gradient_norm": 0.30532947182655334, "tokens_per_second": 1081460.1803357487, "synthetic": false, "world_size": 8} {"step": 3300, "tokens": 865075200, "loss": 2.4129144668579103, "optimizer_updates": 2650, "effective_batch": 512, "lr": 0.00019928741225942718, "gradient_norm": 0.2705957293510437, "tokens_per_second": 1081076.8511930518, "synthetic": false, "world_size": 8} {"step": 3320, "tokens": 870318080, "loss": 2.4041824340820312, "optimizer_updates": 2660, "effective_batch": 512, "lr": 0.00019927804259703598, "gradient_norm": 0.2795591652393341, "tokens_per_second": 1074398.7977841785, "synthetic": false, "world_size": 8} {"step": 3340, "tokens": 875560960, "loss": 2.407309150695801, "optimizer_updates": 2670, "effective_batch": 512, "lr": 0.00019926861198453876, "gradient_norm": 0.3084042966365814, "tokens_per_second": 1074996.280772501, "synthetic": false, "world_size": 8} {"step": 3360, "tokens": 880803840, "loss": 2.394450569152832, "optimizer_updates": 2680, "effective_batch": 512, "lr": 0.00019925912042837376, "gradient_norm": 0.2611490786075592, "tokens_per_second": 1075224.007306184, "synthetic": false, "world_size": 8} {"step": 3380, "tokens": 886046720, "loss": 2.405783462524414, "optimizer_updates": 2690, "effective_batch": 512, "lr": 0.0001992495679350209, "gradient_norm": 0.3568926453590393, "tokens_per_second": 947212.7501906728, "synthetic": false, "world_size": 8} {"step": 3400, "tokens": 891289600, "loss": 2.4198585510253907, "optimizer_updates": 2700, "effective_batch": 512, "lr": 0.00019923995451100163, "gradient_norm": 0.32659676671028137, "tokens_per_second": 1079297.9722252858, "synthetic": false, "world_size": 8} {"step": 3420, "tokens": 896532480, "loss": 2.4018348693847655, "optimizer_updates": 2710, "effective_batch": 512, "lr": 0.00019923028016287906, "gradient_norm": 0.4820714592933655, "tokens_per_second": 1075209.8233910205, "synthetic": false, "world_size": 8} {"step": 3440, "tokens": 901775360, "loss": 2.4003997802734376, "optimizer_updates": 2720, "effective_batch": 512, "lr": 0.00019922054489725786, "gradient_norm": 0.24481713771820068, "tokens_per_second": 1075045.4599235316, "synthetic": false, "world_size": 8} {"step": 3460, "tokens": 907018240, "loss": 2.4092655181884766, "optimizer_updates": 2730, "effective_batch": 512, "lr": 0.00019921074872078425, "gradient_norm": 0.3449772000312805, "tokens_per_second": 1078437.1499267663, "synthetic": false, "world_size": 8} {"step": 3480, "tokens": 912261120, "loss": 2.4127853393554686, "optimizer_updates": 2740, "effective_batch": 512, "lr": 0.00019920089164014617, "gradient_norm": 0.267623633146286, "tokens_per_second": 1084296.5662377418, "synthetic": false, "world_size": 8} {"step": 3500, "tokens": 917504000, "loss": 2.4180526733398438, "optimizer_updates": 2750, "effective_batch": 512, "lr": 0.00019919097366207297, "gradient_norm": 0.3717908263206482, "tokens_per_second": 1077378.5121490576, "synthetic": false, "world_size": 8} {"step": 3520, "tokens": 922746880, "loss": 2.4016361236572266, "optimizer_updates": 2760, "effective_batch": 512, "lr": 0.00019918099479333565, "gradient_norm": 0.24712659418582916, "tokens_per_second": 1070942.3751305242, "synthetic": false, "world_size": 8} {"step": 3540, "tokens": 927989760, "loss": 2.410274887084961, "optimizer_updates": 2770, "effective_batch": 512, "lr": 0.00019917095504074685, "gradient_norm": 0.26715603470802307, "tokens_per_second": 1076282.685995619, "synthetic": false, "world_size": 8} {"step": 3560, "tokens": 933232640, "loss": 2.409682273864746, "optimizer_updates": 2780, "effective_batch": 512, "lr": 0.00019916085441116068, "gradient_norm": 0.6275621652603149, "tokens_per_second": 1067782.2775542627, "synthetic": false, "world_size": 8} {"step": 3580, "tokens": 938475520, "loss": 2.40897274017334, "optimizer_updates": 2790, "effective_batch": 512, "lr": 0.0001991506929114728, "gradient_norm": 0.33553823828697205, "tokens_per_second": 1084897.8683468846, "synthetic": false, "world_size": 8} {"step": 3600, "tokens": 943718400, "loss": 2.4079580307006836, "optimizer_updates": 2800, "effective_batch": 512, "lr": 0.0001991404705486205, "gradient_norm": 0.36260634660720825, "tokens_per_second": 1069120.5181474532, "synthetic": false, "world_size": 8} {"step": 3620, "tokens": 948961280, "loss": 2.3994861602783204, "optimizer_updates": 2810, "effective_batch": 512, "lr": 0.00019913018732958256, "gradient_norm": 0.2978898584842682, "tokens_per_second": 1082408.925291688, "synthetic": false, "world_size": 8} {"step": 3640, "tokens": 954204160, "loss": 2.404501533508301, "optimizer_updates": 2820, "effective_batch": 512, "lr": 0.00019911984326137936, "gradient_norm": 0.3136504888534546, "tokens_per_second": 1077625.7976388272, "synthetic": false, "world_size": 8} {"step": 3660, "tokens": 959447040, "loss": 2.4052942276000975, "optimizer_updates": 2830, "effective_batch": 512, "lr": 0.00019910943835107277, "gradient_norm": 0.3838745057582855, "tokens_per_second": 1077302.0855730302, "synthetic": false, "world_size": 8} {"step": 3680, "tokens": 964689920, "loss": 2.417585563659668, "optimizer_updates": 2840, "effective_batch": 512, "lr": 0.00019909897260576623, "gradient_norm": 0.3194465935230255, "tokens_per_second": 1077734.611731174, "synthetic": false, "world_size": 8} {"step": 3700, "tokens": 969932800, "loss": 2.4063777923583984, "optimizer_updates": 2850, "effective_batch": 512, "lr": 0.00019908844603260472, "gradient_norm": 0.47948333621025085, "tokens_per_second": 1074052.2713390442, "synthetic": false, "world_size": 8} {"step": 3720, "tokens": 975175680, "loss": 2.4139442443847656, "optimizer_updates": 2860, "effective_batch": 512, "lr": 0.00019907785863877467, "gradient_norm": 0.24992723762989044, "tokens_per_second": 1081556.4183466109, "synthetic": false, "world_size": 8} {"step": 3740, "tokens": 980418560, "loss": 2.405729293823242, "optimizer_updates": 2870, "effective_batch": 512, "lr": 0.00019906721043150418, "gradient_norm": 0.3025161623954773, "tokens_per_second": 1075413.431064214, "synthetic": false, "world_size": 8} {"step": 3760, "tokens": 985661440, "loss": 2.4066028594970703, "optimizer_updates": 2880, "effective_batch": 512, "lr": 0.00019905650141806272, "gradient_norm": 0.5110344886779785, "tokens_per_second": 1078613.5172133297, "synthetic": false, "world_size": 8} {"step": 3780, "tokens": 990904320, "loss": 2.3963836669921874, "optimizer_updates": 2890, "effective_batch": 512, "lr": 0.00019904573160576137, "gradient_norm": 0.27487054467201233, "tokens_per_second": 1078191.5145948064, "synthetic": false, "world_size": 8} {"step": 3800, "tokens": 996147200, "loss": 2.4029296875, "optimizer_updates": 2900, "effective_batch": 512, "lr": 0.00019903490100195263, "gradient_norm": 0.29309117794036865, "tokens_per_second": 793849.178177313, "synthetic": false, "world_size": 8} {"step": 3820, "tokens": 1001390080, "loss": 2.406163787841797, "optimizer_updates": 2910, "effective_batch": 512, "lr": 0.0001990240096140306, "gradient_norm": 0.5138711333274841, "tokens_per_second": 611311.9442939846, "synthetic": false, "world_size": 8} {"step": 3840, "tokens": 1006632960, "loss": 2.39239444732666, "optimizer_updates": 2920, "effective_batch": 512, "lr": 0.00019901305744943082, "gradient_norm": 0.401750773191452, "tokens_per_second": 1077762.270229526, "synthetic": false, "world_size": 8} {"step": 3860, "tokens": 1011875840, "loss": 2.411357879638672, "optimizer_updates": 2930, "effective_batch": 512, "lr": 0.0001990020445156303, "gradient_norm": 0.2541477382183075, "tokens_per_second": 1065545.213731798, "synthetic": false, "world_size": 8} {"step": 3880, "tokens": 1017118720, "loss": 2.4013561248779296, "optimizer_updates": 2940, "effective_batch": 512, "lr": 0.00019899097082014757, "gradient_norm": 0.294351190328598, "tokens_per_second": 1072484.2291898434, "synthetic": false, "world_size": 8} {"step": 3900, "tokens": 1022361600, "loss": 2.4077552795410155, "optimizer_updates": 2950, "effective_batch": 512, "lr": 0.00019897983637054268, "gradient_norm": 0.35527533292770386, "tokens_per_second": 1069299.3293983687, "synthetic": false, "world_size": 8} {"step": 3920, "tokens": 1027604480, "loss": 2.409365653991699, "optimizer_updates": 2960, "effective_batch": 512, "lr": 0.00019896864117441708, "gradient_norm": 0.39855676889419556, "tokens_per_second": 1072757.5712098419, "synthetic": false, "world_size": 8} {"step": 3940, "tokens": 1032847360, "loss": 2.4143686294555664, "optimizer_updates": 2970, "effective_batch": 512, "lr": 0.00019895738523941373, "gradient_norm": 0.30666282773017883, "tokens_per_second": 1073431.6094963017, "synthetic": false, "world_size": 8} {"step": 3960, "tokens": 1038090240, "loss": 2.4096519470214846, "optimizer_updates": 2980, "effective_batch": 512, "lr": 0.0001989460685732171, "gradient_norm": 0.26375287771224976, "tokens_per_second": 1068722.2954528786, "synthetic": false, "world_size": 8} {"step": 3980, "tokens": 1043333120, "loss": 2.4053861618041994, "optimizer_updates": 2990, "effective_batch": 512, "lr": 0.00019893469118355302, "gradient_norm": 0.6713892817497253, "tokens_per_second": 1071290.1771712701, "synthetic": false, "world_size": 8} {"step": 4000, "tokens": 1048576000, "loss": 2.4024749755859376, "optimizer_updates": 3000, "effective_batch": 512, "lr": 0.00019892325307818888, "gradient_norm": 0.2692168951034546, "tokens_per_second": 1073234.5810886414, "synthetic": false, "world_size": 8} {"step": 4020, "tokens": 1053818880, "loss": 2.412051963806152, "optimizer_updates": 3010, "effective_batch": 512, "lr": 0.00019891175426493344, "gradient_norm": 0.2963908016681671, "tokens_per_second": 854441.7744746375, "synthetic": false, "world_size": 8} {"step": 4040, "tokens": 1059061760, "loss": 2.406817626953125, "optimizer_updates": 3020, "effective_batch": 512, "lr": 0.00019890019475163695, "gradient_norm": 0.7479187250137329, "tokens_per_second": 1075903.5062134687, "synthetic": false, "world_size": 8} {"step": 4060, "tokens": 1064304640, "loss": 2.405644989013672, "optimizer_updates": 3030, "effective_batch": 512, "lr": 0.00019888857454619107, "gradient_norm": 0.3861759305000305, "tokens_per_second": 1078695.0571536098, "synthetic": false, "world_size": 8} {"step": 4080, "tokens": 1069547520, "loss": 2.420920753479004, "optimizer_updates": 3040, "effective_batch": 512, "lr": 0.00019887689365652894, "gradient_norm": 0.30352210998535156, "tokens_per_second": 1074976.1791689356, "synthetic": false, "world_size": 8} {"step": 4100, "tokens": 1074790400, "loss": 2.4056177139282227, "optimizer_updates": 3050, "effective_batch": 512, "lr": 0.00019886515209062506, "gradient_norm": 0.3511843681335449, "tokens_per_second": 1074786.9673445204, "synthetic": false, "world_size": 8} {"step": 4120, "tokens": 1080033280, "loss": 2.410715866088867, "optimizer_updates": 3060, "effective_batch": 512, "lr": 0.00019885334985649547, "gradient_norm": 0.34731021523475647, "tokens_per_second": 1085095.821112431, "synthetic": false, "world_size": 8} {"step": 4140, "tokens": 1085276160, "loss": 2.4154569625854494, "optimizer_updates": 3070, "effective_batch": 512, "lr": 0.00019884148696219748, "gradient_norm": 0.5670291781425476, "tokens_per_second": 1067973.2062584006, "synthetic": false, "world_size": 8} {"step": 4160, "tokens": 1090519040, "loss": 2.4006752014160155, "optimizer_updates": 3080, "effective_batch": 512, "lr": 0.00019882956341582992, "gradient_norm": 0.48926064372062683, "tokens_per_second": 1070785.1695402581, "synthetic": false, "world_size": 8} {"step": 4180, "tokens": 1095761920, "loss": 2.402639389038086, "optimizer_updates": 3090, "effective_batch": 512, "lr": 0.000198817579225533, "gradient_norm": 0.2819086015224457, "tokens_per_second": 1083596.4594600173, "synthetic": false, "world_size": 8} {"step": 4200, "tokens": 1101004800, "loss": 2.3996654510498048, "optimizer_updates": 3100, "effective_batch": 512, "lr": 0.0001988055343994883, "gradient_norm": 0.4215976595878601, "tokens_per_second": 1071741.713633651, "synthetic": false, "world_size": 8} {"step": 4220, "tokens": 1106247680, "loss": 2.411429214477539, "optimizer_updates": 3110, "effective_batch": 512, "lr": 0.00019879342894591883, "gradient_norm": 0.258249968290329, "tokens_per_second": 1075288.6031455821, "synthetic": false, "world_size": 8} {"step": 4240, "tokens": 1111490560, "loss": 2.4046945571899414, "optimizer_updates": 3120, "effective_batch": 512, "lr": 0.000198781262873089, "gradient_norm": 0.2533469796180725, "tokens_per_second": 1082588.4092787022, "synthetic": false, "world_size": 8} {"step": 4260, "tokens": 1116733440, "loss": 2.3973110198974608, "optimizer_updates": 3130, "effective_batch": 512, "lr": 0.00019876903618930454, "gradient_norm": 0.2806715667247772, "tokens_per_second": 1073613.0947566, "synthetic": false, "world_size": 8} {"step": 4280, "tokens": 1121976320, "loss": 2.396165466308594, "optimizer_updates": 3140, "effective_batch": 512, "lr": 0.00019875674890291266, "gradient_norm": 0.3806411623954773, "tokens_per_second": 1081182.6399243735, "synthetic": false, "world_size": 8} {"step": 4300, "tokens": 1127219200, "loss": 2.3912931442260743, "optimizer_updates": 3150, "effective_batch": 512, "lr": 0.00019874440102230187, "gradient_norm": 0.4631476104259491, "tokens_per_second": 1076906.6844800445, "synthetic": false, "world_size": 8} {"step": 4320, "tokens": 1132462080, "loss": 2.4041397094726564, "optimizer_updates": 3160, "effective_batch": 512, "lr": 0.00019873199255590203, "gradient_norm": 0.4344281554222107, "tokens_per_second": 1076421.9364732981, "synthetic": false, "world_size": 8} {"step": 4340, "tokens": 1137704960, "loss": 2.403422546386719, "optimizer_updates": 3170, "effective_batch": 512, "lr": 0.00019871952351218446, "gradient_norm": 0.44735461473464966, "tokens_per_second": 1077441.444334669, "synthetic": false, "world_size": 8} {"step": 4360, "tokens": 1142947840, "loss": 2.406962585449219, "optimizer_updates": 3180, "effective_batch": 512, "lr": 0.00019870699389966173, "gradient_norm": 0.31665635108947754, "tokens_per_second": 1073067.8978616213, "synthetic": false, "world_size": 8} {"step": 4380, "tokens": 1148190720, "loss": 2.392471122741699, "optimizer_updates": 3190, "effective_batch": 512, "lr": 0.0001986944037268878, "gradient_norm": 0.3337954580783844, "tokens_per_second": 1081415.5381433445, "synthetic": false, "world_size": 8} {"step": 4400, "tokens": 1153433600, "loss": 2.3972536087036134, "optimizer_updates": 3200, "effective_batch": 512, "lr": 0.000198681753002458, "gradient_norm": 0.27933186292648315, "tokens_per_second": 982588.1005954333, "synthetic": false, "world_size": 8} {"step": 4420, "tokens": 1158676480, "loss": 2.4127269744873048, "optimizer_updates": 3210, "effective_batch": 512, "lr": 0.000198669041735009, "gradient_norm": 0.3676000237464905, "tokens_per_second": 1069088.1343324045, "synthetic": false, "world_size": 8} {"step": 4440, "tokens": 1163919360, "loss": 2.402990531921387, "optimizer_updates": 3220, "effective_batch": 512, "lr": 0.00019865626993321873, "gradient_norm": 0.48755648732185364, "tokens_per_second": 1069259.2265564622, "synthetic": false, "world_size": 8} {"step": 4460, "tokens": 1169162240, "loss": 2.404152679443359, "optimizer_updates": 3230, "effective_batch": 512, "lr": 0.00019864343760580655, "gradient_norm": 0.45573690533638, "tokens_per_second": 1063985.4860105491, "synthetic": false, "world_size": 8} {"step": 4480, "tokens": 1174405120, "loss": 2.412680816650391, "optimizer_updates": 3240, "effective_batch": 512, "lr": 0.00019863054476153304, "gradient_norm": 0.39641496539115906, "tokens_per_second": 1070251.8527249668, "synthetic": false, "world_size": 8} {"step": 4500, "tokens": 1179648000, "loss": 2.4095199584960936, "optimizer_updates": 3250, "effective_batch": 512, "lr": 0.00019861759140920015, "gradient_norm": 0.4909226596355438, "tokens_per_second": 1068133.2306218497, "synthetic": false, "world_size": 8} {"step": 4520, "tokens": 1184890880, "loss": 2.396383857727051, "optimizer_updates": 3260, "effective_batch": 512, "lr": 0.00019860457755765116, "gradient_norm": 0.4268243610858917, "tokens_per_second": 1080466.8661887848, "synthetic": false, "world_size": 8} {"step": 4540, "tokens": 1190133760, "loss": 2.4067092895507813, "optimizer_updates": 3270, "effective_batch": 512, "lr": 0.00019859150321577062, "gradient_norm": 0.4067018926143646, "tokens_per_second": 1077834.661074047, "synthetic": false, "world_size": 8} {"step": 4560, "tokens": 1195376640, "loss": 2.410362434387207, "optimizer_updates": 3280, "effective_batch": 512, "lr": 0.00019857836839248433, "gradient_norm": 0.28151294589042664, "tokens_per_second": 1070211.4806980824, "synthetic": false, "world_size": 8} {"step": 4580, "tokens": 1200619520, "loss": 2.412201690673828, "optimizer_updates": 3290, "effective_batch": 512, "lr": 0.0001985651730967595, "gradient_norm": 0.2838471233844757, "tokens_per_second": 1071270.6101287089, "synthetic": false, "world_size": 8} {"step": 4600, "tokens": 1205862400, "loss": 2.4087074279785154, "optimizer_updates": 3300, "effective_batch": 512, "lr": 0.00019855191733760455, "gradient_norm": 0.4018658995628357, "tokens_per_second": 1068352.4610761649, "synthetic": false, "world_size": 8} {"step": 4620, "tokens": 1211105280, "loss": 2.4028413772583006, "optimizer_updates": 3310, "effective_batch": 512, "lr": 0.00019853860112406912, "gradient_norm": 0.31743237376213074, "tokens_per_second": 1070931.2792321795, "synthetic": false, "world_size": 8} {"step": 4640, "tokens": 1216348160, "loss": 2.4104259490966795, "optimizer_updates": 3320, "effective_batch": 512, "lr": 0.00019852522446524426, "gradient_norm": 0.2842850983142853, "tokens_per_second": 1076044.0883360566, "synthetic": false, "world_size": 8} {"step": 4660, "tokens": 1221591040, "loss": 2.39163818359375, "optimizer_updates": 3330, "effective_batch": 512, "lr": 0.00019851178737026215, "gradient_norm": 0.5048649907112122, "tokens_per_second": 1067604.2437408972, "synthetic": false, "world_size": 8} {"step": 4680, "tokens": 1226833920, "loss": 2.4180038452148436, "optimizer_updates": 3340, "effective_batch": 512, "lr": 0.00019849828984829635, "gradient_norm": 0.2824825644493103, "tokens_per_second": 1071269.3628990392, "synthetic": false, "world_size": 8} {"step": 4700, "tokens": 1232076800, "loss": 2.4141777038574217, "optimizer_updates": 3350, "effective_batch": 512, "lr": 0.00019848473190856158, "gradient_norm": 0.3029401898384094, "tokens_per_second": 1067198.7587758207, "synthetic": false, "world_size": 8} {"step": 4720, "tokens": 1237319680, "loss": 2.4130367279052733, "optimizer_updates": 3360, "effective_batch": 512, "lr": 0.00019847111356031385, "gradient_norm": 0.3296085596084595, "tokens_per_second": 1070399.5839441218, "synthetic": false, "world_size": 8} {"step": 4740, "tokens": 1242562560, "loss": 2.40569953918457, "optimizer_updates": 3370, "effective_batch": 512, "lr": 0.0001984574348128504, "gradient_norm": 0.2498454600572586, "tokens_per_second": 1075962.4582492379, "synthetic": false, "world_size": 8} {"step": 4760, "tokens": 1247805440, "loss": 2.395373725891113, "optimizer_updates": 3380, "effective_batch": 512, "lr": 0.00019844369567550976, "gradient_norm": 0.3871605098247528, "tokens_per_second": 1074738.2687764782, "synthetic": false, "world_size": 8} {"step": 4780, "tokens": 1253048320, "loss": 2.4037191390991213, "optimizer_updates": 3390, "effective_batch": 512, "lr": 0.00019842989615767158, "gradient_norm": 0.3774632513523102, "tokens_per_second": 1077543.175973206, "synthetic": false, "world_size": 8} {"step": 4800, "tokens": 1258291200, "loss": 2.413643646240234, "optimizer_updates": 3400, "effective_batch": 512, "lr": 0.00019841603626875678, "gradient_norm": 0.49495959281921387, "tokens_per_second": 1079886.2126322512, "synthetic": false, "world_size": 8} {"step": 4820, "tokens": 1263534080, "loss": 2.407084846496582, "optimizer_updates": 3410, "effective_batch": 512, "lr": 0.00019840211601822755, "gradient_norm": 0.28616243600845337, "tokens_per_second": 1069811.137451594, "synthetic": false, "world_size": 8} {"step": 4840, "tokens": 1268776960, "loss": 2.3930877685546874, "optimizer_updates": 3420, "effective_batch": 512, "lr": 0.00019838813541558722, "gradient_norm": 0.33768749237060547, "tokens_per_second": 1073162.932889243, "synthetic": false, "world_size": 8} {"step": 4860, "tokens": 1274019840, "loss": 2.4052505493164062, "optimizer_updates": 3430, "effective_batch": 512, "lr": 0.00019837409447038033, "gradient_norm": 0.26980262994766235, "tokens_per_second": 1079021.6571597566, "synthetic": false, "world_size": 8} {"step": 4880, "tokens": 1279262720, "loss": 2.389737129211426, "optimizer_updates": 3440, "effective_batch": 512, "lr": 0.00019835999319219266, "gradient_norm": 0.293575644493103, "tokens_per_second": 972089.8726120734, "synthetic": false, "world_size": 8} {"step": 4900, "tokens": 1284505600, "loss": 2.4111352920532227, "optimizer_updates": 3450, "effective_batch": 512, "lr": 0.00019834583159065113, "gradient_norm": 0.6155009865760803, "tokens_per_second": 1068013.52272631, "synthetic": false, "world_size": 8} {"step": 4920, "tokens": 1289748480, "loss": 2.406995391845703, "optimizer_updates": 3460, "effective_batch": 512, "lr": 0.00019833160967542386, "gradient_norm": 0.2960628271102905, "tokens_per_second": 1073096.9569728766, "synthetic": false, "world_size": 8} {"step": 4940, "tokens": 1294991360, "loss": 2.406422233581543, "optimizer_updates": 3470, "effective_batch": 512, "lr": 0.00019831732745622017, "gradient_norm": 0.26456373929977417, "tokens_per_second": 1084978.3921183427, "synthetic": false, "world_size": 8} {"step": 4960, "tokens": 1300234240, "loss": 2.400177764892578, "optimizer_updates": 3480, "effective_batch": 512, "lr": 0.00019830298494279052, "gradient_norm": 0.46445125341415405, "tokens_per_second": 1071793.4709916406, "synthetic": false, "world_size": 8} {"step": 4980, "tokens": 1305477120, "loss": 2.417866897583008, "optimizer_updates": 3490, "effective_batch": 512, "lr": 0.00019828858214492653, "gradient_norm": 0.2988024950027466, "tokens_per_second": 1077497.3410262077, "synthetic": false, "world_size": 8} {"step": 5000, "tokens": 1310720000, "loss": 2.4101186752319337, "optimizer_updates": 3500, "effective_batch": 512, "lr": 0.00019827411907246103, "gradient_norm": 0.4350506365299225, "tokens_per_second": 1083972.928718261, "synthetic": false, "world_size": 8} {"step": 5020, "tokens": 1315962880, "loss": 2.4083141326904296, "optimizer_updates": 3510, "effective_batch": 512, "lr": 0.0001982595957352679, "gradient_norm": 0.261662095785141, "tokens_per_second": 846487.5138169844, "synthetic": false, "world_size": 8} {"step": 5040, "tokens": 1321205760, "loss": 2.40734748840332, "optimizer_updates": 3520, "effective_batch": 512, "lr": 0.00019824501214326225, "gradient_norm": 0.3049387037754059, "tokens_per_second": 1085195.142637633, "synthetic": false, "world_size": 8} {"step": 5060, "tokens": 1326448640, "loss": 2.408087158203125, "optimizer_updates": 3530, "effective_batch": 512, "lr": 0.00019823036830640028, "gradient_norm": 0.2864360213279724, "tokens_per_second": 1068188.4895002935, "synthetic": false, "world_size": 8} {"step": 5080, "tokens": 1331691520, "loss": 2.4032697677612305, "optimizer_updates": 3540, "effective_batch": 512, "lr": 0.00019821566423467937, "gradient_norm": 0.27238911390304565, "tokens_per_second": 1079100.9813791565, "synthetic": false, "world_size": 8} {"step": 5100, "tokens": 1336934400, "loss": 2.4017494201660154, "optimizer_updates": 3550, "effective_batch": 512, "lr": 0.00019820089993813795, "gradient_norm": 0.2783057987689972, "tokens_per_second": 1074401.2071095845, "synthetic": false, "world_size": 8} {"step": 5120, "tokens": 1342177280, "loss": 2.3894256591796874, "optimizer_updates": 3560, "effective_batch": 512, "lr": 0.0001981860754268556, "gradient_norm": 0.31302282214164734, "tokens_per_second": 1080881.5675129709, "synthetic": false, "world_size": 8} {"step": 5140, "tokens": 1347420160, "loss": 2.400542449951172, "optimizer_updates": 3570, "effective_batch": 512, "lr": 0.00019817119071095305, "gradient_norm": 0.5919987559318542, "tokens_per_second": 1074824.9618510336, "synthetic": false, "world_size": 8} {"step": 5160, "tokens": 1352663040, "loss": 2.4034355163574217, "optimizer_updates": 3580, "effective_batch": 512, "lr": 0.00019815624580059207, "gradient_norm": 0.37383559346199036, "tokens_per_second": 768359.524460972, "synthetic": false, "world_size": 8} {"step": 5180, "tokens": 1357905920, "loss": 2.4115591049194336, "optimizer_updates": 3590, "effective_batch": 512, "lr": 0.00019814124070597556, "gradient_norm": 0.6150941252708435, "tokens_per_second": 1091174.2775286485, "synthetic": false, "world_size": 8} {"step": 5200, "tokens": 1363148800, "loss": 2.4185461044311523, "optimizer_updates": 3600, "effective_batch": 512, "lr": 0.0001981261754373475, "gradient_norm": 0.49264782667160034, "tokens_per_second": 1070570.8070140018, "synthetic": false, "world_size": 8} {"step": 5220, "tokens": 1368391680, "loss": 2.403194808959961, "optimizer_updates": 3610, "effective_batch": 512, "lr": 0.00019811105000499288, "gradient_norm": 0.2671423554420471, "tokens_per_second": 1080274.1819705844, "synthetic": false, "world_size": 8} {"step": 5240, "tokens": 1373634560, "loss": 2.3981836318969725, "optimizer_updates": 3620, "effective_batch": 512, "lr": 0.00019809586441923792, "gradient_norm": 0.3811810612678528, "tokens_per_second": 1082478.330649852, "synthetic": false, "world_size": 8} {"step": 5260, "tokens": 1378877440, "loss": 2.4027873992919924, "optimizer_updates": 3630, "effective_batch": 512, "lr": 0.00019808061869044978, "gradient_norm": 0.4793168604373932, "tokens_per_second": 1077688.093476604, "synthetic": false, "world_size": 8} {"step": 5280, "tokens": 1384120320, "loss": 2.401020050048828, "optimizer_updates": 3640, "effective_batch": 512, "lr": 0.00019806531282903672, "gradient_norm": 0.2846319377422333, "tokens_per_second": 781373.5084740453, "synthetic": false, "world_size": 8} {"step": 5300, "tokens": 1389363200, "loss": 2.410879898071289, "optimizer_updates": 3650, "effective_batch": 512, "lr": 0.00019804994684544802, "gradient_norm": 0.4860248863697052, "tokens_per_second": 1079104.2756219704, "synthetic": false, "world_size": 8} {"step": 5320, "tokens": 1394606080, "loss": 2.4125574111938475, "optimizer_updates": 3660, "effective_batch": 512, "lr": 0.00019803452075017408, "gradient_norm": 0.31927385926246643, "tokens_per_second": 1068502.2331699699, "synthetic": false, "world_size": 8} {"step": 5340, "tokens": 1399848960, "loss": 2.398985481262207, "optimizer_updates": 3670, "effective_batch": 512, "lr": 0.00019801903455374627, "gradient_norm": 0.28689709305763245, "tokens_per_second": 1071112.323692961, "synthetic": false, "world_size": 8} {"step": 5360, "tokens": 1405091840, "loss": 2.3921703338623046, "optimizer_updates": 3680, "effective_batch": 512, "lr": 0.00019800348826673703, "gradient_norm": 0.4197884202003479, "tokens_per_second": 1078260.0721289748, "synthetic": false, "world_size": 8} {"step": 5380, "tokens": 1410334720, "loss": 2.4014026641845705, "optimizer_updates": 3690, "effective_batch": 512, "lr": 0.00019798788189975976, "gradient_norm": 0.25746649503707886, "tokens_per_second": 1078702.5096041341, "synthetic": false, "world_size": 8} {"step": 5400, "tokens": 1415577600, "loss": 2.401994514465332, "optimizer_updates": 3700, "effective_batch": 512, "lr": 0.000197972215463469, "gradient_norm": 0.2992497980594635, "tokens_per_second": 1074570.549756775, "synthetic": false, "world_size": 8} {"step": 5420, "tokens": 1420820480, "loss": 2.4211942672729494, "optimizer_updates": 3710, "effective_batch": 512, "lr": 0.00019795648896856017, "gradient_norm": 0.3517383933067322, "tokens_per_second": 1083473.082652398, "synthetic": false, "world_size": 8} {"step": 5440, "tokens": 1426063360, "loss": 2.407906913757324, "optimizer_updates": 3720, "effective_batch": 512, "lr": 0.00019794070242576975, "gradient_norm": 0.4771975874900818, "tokens_per_second": 955867.8109837972, "synthetic": false, "world_size": 8} {"step": 5460, "tokens": 1431306240, "loss": 2.417267608642578, "optimizer_updates": 3730, "effective_batch": 512, "lr": 0.00019792485584587522, "gradient_norm": 0.32634007930755615, "tokens_per_second": 1069365.0627310202, "synthetic": false, "world_size": 8} {"step": 5480, "tokens": 1436549120, "loss": 2.4013975143432615, "optimizer_updates": 3740, "effective_batch": 512, "lr": 0.00019790894923969507, "gradient_norm": 0.283866822719574, "tokens_per_second": 1071374.814479246, "synthetic": false, "world_size": 8} {"step": 5500, "tokens": 1441792000, "loss": 2.39910945892334, "optimizer_updates": 3750, "effective_batch": 512, "lr": 0.00019789298261808864, "gradient_norm": 0.26798510551452637, "tokens_per_second": 1065748.089048233, "synthetic": false, "world_size": 8} {"step": 5520, "tokens": 1447034880, "loss": 2.396737289428711, "optimizer_updates": 3760, "effective_batch": 512, "lr": 0.00019787695599195646, "gradient_norm": 0.4584624469280243, "tokens_per_second": 1075096.6986671018, "synthetic": false, "world_size": 8} {"step": 5540, "tokens": 1452277760, "loss": 2.395408821105957, "optimizer_updates": 3770, "effective_batch": 512, "lr": 0.0001978608693722398, "gradient_norm": 0.43380483984947205, "tokens_per_second": 1068817.5628543873, "synthetic": false, "world_size": 8} {"step": 5560, "tokens": 1457520640, "loss": 2.4083629608154298, "optimizer_updates": 3780, "effective_batch": 512, "lr": 0.00019784472276992111, "gradient_norm": 0.3163617253303528, "tokens_per_second": 1070995.221798987, "synthetic": false, "world_size": 8} {"step": 5580, "tokens": 1462763520, "loss": 2.4116931915283204, "optimizer_updates": 3790, "effective_batch": 512, "lr": 0.00019782851619602358, "gradient_norm": 0.3090146780014038, "tokens_per_second": 1076810.7448407172, "synthetic": false, "world_size": 8} {"step": 5600, "tokens": 1468006400, "loss": 2.397060203552246, "optimizer_updates": 3800, "effective_batch": 512, "lr": 0.00019781224966161144, "gradient_norm": 0.28478720784187317, "tokens_per_second": 1072449.2735610593, "synthetic": false, "world_size": 8} {"step": 5620, "tokens": 1473249280, "loss": 2.3971088409423826, "optimizer_updates": 3810, "effective_batch": 512, "lr": 0.0001977959231777899, "gradient_norm": 0.3180620074272156, "tokens_per_second": 1076347.3677917975, "synthetic": false, "world_size": 8} {"step": 5640, "tokens": 1478492160, "loss": 2.399391937255859, "optimizer_updates": 3820, "effective_batch": 512, "lr": 0.00019777953675570496, "gradient_norm": 0.29988712072372437, "tokens_per_second": 1066885.261581398, "synthetic": false, "world_size": 8} {"step": 5660, "tokens": 1483735040, "loss": 2.4196327209472654, "optimizer_updates": 3830, "effective_batch": 512, "lr": 0.00019776309040654377, "gradient_norm": 0.38986891508102417, "tokens_per_second": 1074382.1028674997, "synthetic": false, "world_size": 8} {"step": 5680, "tokens": 1488977920, "loss": 2.412639617919922, "optimizer_updates": 3840, "effective_batch": 512, "lr": 0.0001977465841415341, "gradient_norm": 0.33308321237564087, "tokens_per_second": 1073227.3615184375, "synthetic": false, "world_size": 8} {"step": 5700, "tokens": 1494220800, "loss": 2.399138832092285, "optimizer_updates": 3850, "effective_batch": 512, "lr": 0.0001977300179719449, "gradient_norm": 0.31040987372398376, "tokens_per_second": 1068822.1032634901, "synthetic": false, "world_size": 8} {"step": 5720, "tokens": 1499463680, "loss": 2.4068981170654298, "optimizer_updates": 3860, "effective_batch": 512, "lr": 0.0001977133919090858, "gradient_norm": 0.48662126064300537, "tokens_per_second": 1079047.760397466, "synthetic": false, "world_size": 8} {"step": 5740, "tokens": 1504706560, "loss": 2.3879154205322264, "optimizer_updates": 3870, "effective_batch": 512, "lr": 0.00019769670596430744, "gradient_norm": 0.27325117588043213, "tokens_per_second": 1066455.273879064, "synthetic": false, "world_size": 8} {"step": 5760, "tokens": 1509949440, "loss": 2.401190757751465, "optimizer_updates": 3880, "effective_batch": 512, "lr": 0.00019767996014900135, "gradient_norm": 0.4009441137313843, "tokens_per_second": 1067943.911238936, "synthetic": false, "world_size": 8} {"step": 5780, "tokens": 1515192320, "loss": 2.4011035919189454, "optimizer_updates": 3890, "effective_batch": 512, "lr": 0.0001976631544745998, "gradient_norm": 0.2936387360095978, "tokens_per_second": 1061285.840359999, "synthetic": false, "world_size": 8} {"step": 5800, "tokens": 1520435200, "loss": 2.409676742553711, "optimizer_updates": 3900, "effective_batch": 512, "lr": 0.0001976462889525761, "gradient_norm": 0.2748550474643707, "tokens_per_second": 1069047.1453168304, "synthetic": false, "world_size": 8} {"step": 5820, "tokens": 1525678080, "loss": 2.3977176666259767, "optimizer_updates": 3910, "effective_batch": 512, "lr": 0.00019762936359444438, "gradient_norm": 0.5484361052513123, "tokens_per_second": 1077014.1429185434, "synthetic": false, "world_size": 8} {"step": 5840, "tokens": 1530920960, "loss": 2.4054861068725586, "optimizer_updates": 3920, "effective_batch": 512, "lr": 0.00019761237841175948, "gradient_norm": 0.3037991523742676, "tokens_per_second": 1067410.5724973083, "synthetic": false, "world_size": 8} {"step": 5860, "tokens": 1536163840, "loss": 2.401622009277344, "optimizer_updates": 3930, "effective_batch": 512, "lr": 0.00019759533341611723, "gradient_norm": 0.28564298152923584, "tokens_per_second": 1073681.0119051293, "synthetic": false, "world_size": 8} {"step": 5880, "tokens": 1541406720, "loss": 2.400746726989746, "optimizer_updates": 3940, "effective_batch": 512, "lr": 0.00019757822861915425, "gradient_norm": 0.28234222531318665, "tokens_per_second": 1070172.584879896, "synthetic": false, "world_size": 8} {"step": 5900, "tokens": 1546649600, "loss": 2.404396629333496, "optimizer_updates": 3950, "effective_batch": 512, "lr": 0.00019756106403254797, "gradient_norm": 0.2601434290409088, "tokens_per_second": 1082850.9158898757, "synthetic": false, "world_size": 8} {"step": 5920, "tokens": 1551892480, "loss": 2.401749610900879, "optimizer_updates": 3960, "effective_batch": 512, "lr": 0.00019754383966801662, "gradient_norm": 0.281626433134079, "tokens_per_second": 841681.1880050555, "synthetic": false, "world_size": 8} {"step": 5940, "tokens": 1557135360, "loss": 2.426212501525879, "optimizer_updates": 3970, "effective_batch": 512, "lr": 0.00019752655553731933, "gradient_norm": 0.3045167922973633, "tokens_per_second": 944198.7296004373, "synthetic": false, "world_size": 8} {"step": 5960, "tokens": 1562378240, "loss": 2.399074935913086, "optimizer_updates": 3980, "effective_batch": 512, "lr": 0.00019750921165225595, "gradient_norm": 0.25644734501838684, "tokens_per_second": 1073088.4282862823, "synthetic": false, "world_size": 8} {"step": 5980, "tokens": 1567621120, "loss": 2.4025205612182616, "optimizer_updates": 3990, "effective_batch": 512, "lr": 0.00019749180802466714, "gradient_norm": 0.2691061794757843, "tokens_per_second": 1078467.8338303969, "synthetic": false, "world_size": 8} {"step": 6000, "tokens": 1572864000, "loss": 2.4062095642089845, "optimizer_updates": 4000, "effective_batch": 512, "lr": 0.00019747434466643434, "gradient_norm": 0.5381504893302917, "tokens_per_second": 1085808.4236382712, "synthetic": false, "world_size": 8} {"step": 6020, "tokens": 1578106880, "loss": 2.40017147064209, "optimizer_updates": 4010, "effective_batch": 512, "lr": 0.00019745682158947981, "gradient_norm": 0.3867286741733551, "tokens_per_second": 834520.8494793788, "synthetic": false, "world_size": 8} {"step": 6040, "tokens": 1583349760, "loss": 2.40126953125, "optimizer_updates": 4020, "effective_batch": 512, "lr": 0.00019743923880576655, "gradient_norm": 0.486865371465683, "tokens_per_second": 1088027.5244297688, "synthetic": false, "world_size": 8} {"step": 6060, "tokens": 1588592640, "loss": 2.4082054138183593, "optimizer_updates": 4030, "effective_batch": 512, "lr": 0.0001974215963272983, "gradient_norm": 0.2811400592327118, "tokens_per_second": 744139.680367503, "synthetic": false, "world_size": 8} {"step": 6080, "tokens": 1593835520, "loss": 2.4035871505737303, "optimizer_updates": 4040, "effective_batch": 512, "lr": 0.00019740389416611964, "gradient_norm": 0.4180702269077301, "tokens_per_second": 990774.0806302562, "synthetic": false, "world_size": 8} {"step": 6100, "tokens": 1599078400, "loss": 2.3949134826660154, "optimizer_updates": 4050, "effective_batch": 512, "lr": 0.00019738613233431573, "gradient_norm": 0.344298779964447, "tokens_per_second": 1088868.4357720541, "synthetic": false, "world_size": 8} {"step": 6120, "tokens": 1604321280, "loss": 2.4053781509399412, "optimizer_updates": 4060, "effective_batch": 512, "lr": 0.00019736831084401265, "gradient_norm": 0.42318660020828247, "tokens_per_second": 1080684.5762804535, "synthetic": false, "world_size": 8} {"step": 6140, "tokens": 1609564160, "loss": 2.397560691833496, "optimizer_updates": 4070, "effective_batch": 512, "lr": 0.00019735042970737713, "gradient_norm": 0.32697612047195435, "tokens_per_second": 1073571.4566423616, "synthetic": false, "world_size": 8} {"step": 6160, "tokens": 1614807040, "loss": 2.4075183868408203, "optimizer_updates": 4080, "effective_batch": 512, "lr": 0.00019733248893661655, "gradient_norm": 0.27497732639312744, "tokens_per_second": 1078854.345401237, "synthetic": false, "world_size": 8} {"step": 6180, "tokens": 1620049920, "loss": 2.389638137817383, "optimizer_updates": 4090, "effective_batch": 512, "lr": 0.00019731448854397914, "gradient_norm": 0.24263279139995575, "tokens_per_second": 1078686.4749825045, "synthetic": false, "world_size": 8} {"step": 6200, "tokens": 1625292800, "loss": 2.4028556823730467, "optimizer_updates": 4100, "effective_batch": 512, "lr": 0.00019729642854175375, "gradient_norm": 0.29422473907470703, "tokens_per_second": 1087296.3164780275, "synthetic": false, "world_size": 8} {"step": 6220, "tokens": 1630535680, "loss": 2.406555938720703, "optimizer_updates": 4110, "effective_batch": 512, "lr": 0.0001972783089422699, "gradient_norm": 0.4136649966239929, "tokens_per_second": 1081408.3216417436, "synthetic": false, "world_size": 8} {"step": 6240, "tokens": 1635778560, "loss": 2.4071365356445313, "optimizer_updates": 4120, "effective_batch": 512, "lr": 0.00019726012975789789, "gradient_norm": 0.43420419096946716, "tokens_per_second": 1090005.4222450787, "synthetic": false, "world_size": 8} {"step": 6260, "tokens": 1641021440, "loss": 2.4032724380493162, "optimizer_updates": 4130, "effective_batch": 512, "lr": 0.00019724189100104862, "gradient_norm": 0.26792511343955994, "tokens_per_second": 1077531.0317983185, "synthetic": false, "world_size": 8} {"step": 6280, "tokens": 1646264320, "loss": 2.4155982971191405, "optimizer_updates": 4140, "effective_batch": 512, "lr": 0.0001972235926841737, "gradient_norm": 0.32367390394210815, "tokens_per_second": 1072355.5297660327, "synthetic": false, "world_size": 8} {"step": 6300, "tokens": 1651507200, "loss": 2.404806709289551, "optimizer_updates": 4150, "effective_batch": 512, "lr": 0.00019720523481976538, "gradient_norm": 0.27365177869796753, "tokens_per_second": 1047316.7551461895, "synthetic": false, "world_size": 8} {"step": 6320, "tokens": 1656750080, "loss": 2.3920894622802735, "optimizer_updates": 4160, "effective_batch": 512, "lr": 0.00019718681742035657, "gradient_norm": 0.3338453471660614, "tokens_per_second": 1077445.599093258, "synthetic": false, "world_size": 8} {"step": 6340, "tokens": 1661992960, "loss": 2.3944465637207033, "optimizer_updates": 4170, "effective_batch": 512, "lr": 0.00019716834049852082, "gradient_norm": 0.2662888765335083, "tokens_per_second": 1084585.5912670363, "synthetic": false, "world_size": 8} {"step": 6360, "tokens": 1667235840, "loss": 2.410458564758301, "optimizer_updates": 4180, "effective_batch": 512, "lr": 0.0001971498040668723, "gradient_norm": 0.3613188564777374, "tokens_per_second": 1074271.455125287, "synthetic": false, "world_size": 8} {"step": 6380, "tokens": 1672478720, "loss": 2.40427303314209, "optimizer_updates": 4190, "effective_batch": 512, "lr": 0.0001971312081380659, "gradient_norm": 0.24787436425685883, "tokens_per_second": 1086171.5347482127, "synthetic": false, "world_size": 8} {"step": 6400, "tokens": 1677721600, "loss": 2.4036121368408203, "optimizer_updates": 4200, "effective_batch": 512, "lr": 0.00019711255272479702, "gradient_norm": 0.4232339859008789, "tokens_per_second": 1074753.6413858002, "synthetic": false, "world_size": 8} {"step": 6420, "tokens": 1682964480, "loss": 2.4075794219970703, "optimizer_updates": 4210, "effective_batch": 512, "lr": 0.00019709383783980168, "gradient_norm": 0.35324546694755554, "tokens_per_second": 1085394.588303652, "synthetic": false, "world_size": 8} {"step": 6440, "tokens": 1688207360, "loss": 2.403543472290039, "optimizer_updates": 4220, "effective_batch": 512, "lr": 0.00019707506349585658, "gradient_norm": 0.47129443287849426, "tokens_per_second": 1023358.3698841574, "synthetic": false, "world_size": 8} {"step": 6460, "tokens": 1693450240, "loss": 2.392605209350586, "optimizer_updates": 4230, "effective_batch": 512, "lr": 0.00019705622970577893, "gradient_norm": 0.2645578384399414, "tokens_per_second": 1083702.2087549276, "synthetic": false, "world_size": 8} {"step": 6480, "tokens": 1698693120, "loss": 2.4022348403930662, "optimizer_updates": 4240, "effective_batch": 512, "lr": 0.00019703733648242653, "gradient_norm": 0.45666515827178955, "tokens_per_second": 1084686.4872451539, "synthetic": false, "world_size": 8} {"step": 6500, "tokens": 1703936000, "loss": 2.3881778717041016, "optimizer_updates": 4250, "effective_batch": 512, "lr": 0.00019701838383869784, "gradient_norm": 0.2741489112377167, "tokens_per_second": 1078553.3182539789, "synthetic": false, "world_size": 8} {"step": 6520, "tokens": 1709178880, "loss": 2.4069564819335936, "optimizer_updates": 4260, "effective_batch": 512, "lr": 0.00019699937178753178, "gradient_norm": 0.3059215843677521, "tokens_per_second": 1082830.9148356055, "synthetic": false, "world_size": 8} {"step": 6540, "tokens": 1714421760, "loss": 2.4054399490356446, "optimizer_updates": 4270, "effective_batch": 512, "lr": 0.00019698030034190792, "gradient_norm": 0.3327869176864624, "tokens_per_second": 975620.7636223919, "synthetic": false, "world_size": 8} {"step": 6560, "tokens": 1719664640, "loss": 2.395479202270508, "optimizer_updates": 4280, "effective_batch": 512, "lr": 0.00019696116951484628, "gradient_norm": 0.31685560941696167, "tokens_per_second": 1078711.4577861845, "synthetic": false, "world_size": 8} {"step": 6580, "tokens": 1724907520, "loss": 2.4035770416259767, "optimizer_updates": 4290, "effective_batch": 512, "lr": 0.0001969419793194075, "gradient_norm": 0.3813471794128418, "tokens_per_second": 1076823.8901838071, "synthetic": false, "world_size": 8} {"step": 6600, "tokens": 1730150400, "loss": 2.415757751464844, "optimizer_updates": 4300, "effective_batch": 512, "lr": 0.00019692272976869272, "gradient_norm": 0.28458696603775024, "tokens_per_second": 1079914.7998358216, "synthetic": false, "world_size": 8} {"step": 6620, "tokens": 1735393280, "loss": 2.392262077331543, "optimizer_updates": 4310, "effective_batch": 512, "lr": 0.0001969034208758436, "gradient_norm": 0.31611910462379456, "tokens_per_second": 1088381.7438064762, "synthetic": false, "world_size": 8} {"step": 6640, "tokens": 1740636160, "loss": 2.409408950805664, "optimizer_updates": 4320, "effective_batch": 512, "lr": 0.00019688405265404235, "gradient_norm": 0.5075562596321106, "tokens_per_second": 1079848.5465087385, "synthetic": false, "world_size": 8} {"step": 6660, "tokens": 1745879040, "loss": 2.403109550476074, "optimizer_updates": 4330, "effective_batch": 512, "lr": 0.0001968646251165116, "gradient_norm": 0.6038933396339417, "tokens_per_second": 1082013.327813115, "synthetic": false, "world_size": 8} {"step": 6680, "tokens": 1751121920, "loss": 2.410495948791504, "optimizer_updates": 4340, "effective_batch": 512, "lr": 0.00019684513827651458, "gradient_norm": 0.28775712847709656, "tokens_per_second": 1080323.4111542436, "synthetic": false, "world_size": 8} {"step": 6700, "tokens": 1756364800, "loss": 2.39151668548584, "optimizer_updates": 4350, "effective_batch": 512, "lr": 0.0001968255921473549, "gradient_norm": 0.3016052842140198, "tokens_per_second": 1071769.3730388933, "synthetic": false, "world_size": 8} {"step": 6720, "tokens": 1761607680, "loss": 2.3983749389648437, "optimizer_updates": 4360, "effective_batch": 512, "lr": 0.00019680598674237676, "gradient_norm": 0.3558538258075714, "tokens_per_second": 1078188.9806793593, "synthetic": false, "world_size": 8} {"step": 6740, "tokens": 1766850560, "loss": 2.4001287460327148, "optimizer_updates": 4370, "effective_batch": 512, "lr": 0.00019678632207496472, "gradient_norm": 0.280949205160141, "tokens_per_second": 1074961.2868514245, "synthetic": false, "world_size": 8} {"step": 6760, "tokens": 1772093440, "loss": 2.3859174728393553, "optimizer_updates": 4380, "effective_batch": 512, "lr": 0.00019676659815854385, "gradient_norm": 0.2593729794025421, "tokens_per_second": 1082625.5583491435, "synthetic": false, "world_size": 8} {"step": 6780, "tokens": 1777336320, "loss": 2.3952943801879885, "optimizer_updates": 4390, "effective_batch": 512, "lr": 0.00019674681500657967, "gradient_norm": 0.2863411009311676, "tokens_per_second": 1082551.247560905, "synthetic": false, "world_size": 8} {"step": 6800, "tokens": 1782579200, "loss": 2.414423179626465, "optimizer_updates": 4400, "effective_batch": 512, "lr": 0.00019672697263257814, "gradient_norm": 0.27903515100479126, "tokens_per_second": 1084973.3898658992, "synthetic": false, "world_size": 8} {"step": 6820, "tokens": 1787822080, "loss": 2.393045425415039, "optimizer_updates": 4410, "effective_batch": 512, "lr": 0.00019670707105008564, "gradient_norm": 0.3032151758670807, "tokens_per_second": 1080284.7798716188, "synthetic": false, "world_size": 8} {"step": 6840, "tokens": 1793064960, "loss": 2.3886642456054688, "optimizer_updates": 4420, "effective_batch": 512, "lr": 0.00019668711027268898, "gradient_norm": 0.2575092911720276, "tokens_per_second": 1084341.6778025706, "synthetic": false, "world_size": 8} {"step": 6860, "tokens": 1798307840, "loss": 2.4034915924072267, "optimizer_updates": 4430, "effective_batch": 512, "lr": 0.00019666709031401541, "gradient_norm": 0.2850595712661743, "tokens_per_second": 1071102.947684338, "synthetic": false, "world_size": 8} {"step": 6880, "tokens": 1803550720, "loss": 2.3980432510375977, "optimizer_updates": 4440, "effective_batch": 512, "lr": 0.00019664701118773248, "gradient_norm": 0.3495320677757263, "tokens_per_second": 1078724.2656222568, "synthetic": false, "world_size": 8} {"step": 6900, "tokens": 1808793600, "loss": 2.4000917434692384, "optimizer_updates": 4450, "effective_batch": 512, "lr": 0.00019662687290754828, "gradient_norm": 0.6234111189842224, "tokens_per_second": 1078433.557612513, "synthetic": false, "world_size": 8} {"step": 6920, "tokens": 1814036480, "loss": 2.3978809356689452, "optimizer_updates": 4460, "effective_batch": 512, "lr": 0.0001966066754872112, "gradient_norm": 0.3051052987575531, "tokens_per_second": 991557.2469590903, "synthetic": false, "world_size": 8} {"step": 6940, "tokens": 1819279360, "loss": 2.3974212646484374, "optimizer_updates": 4470, "effective_batch": 512, "lr": 0.00019658641894050995, "gradient_norm": 0.41600552201271057, "tokens_per_second": 1070128.5790062398, "synthetic": false, "world_size": 8} {"step": 6960, "tokens": 1824522240, "loss": 2.396326446533203, "optimizer_updates": 4480, "effective_batch": 512, "lr": 0.00019656610328127374, "gradient_norm": 0.27405110001564026, "tokens_per_second": 1077183.738884064, "synthetic": false, "world_size": 8} {"step": 6980, "tokens": 1829765120, "loss": 2.410544586181641, "optimizer_updates": 4490, "effective_batch": 512, "lr": 0.00019654572852337204, "gradient_norm": 0.2911294996738434, "tokens_per_second": 1077075.7969487333, "synthetic": false, "world_size": 8} {"step": 7000, "tokens": 1835008000, "loss": 2.393717384338379, "optimizer_updates": 4500, "effective_batch": 512, "lr": 0.0001965252946807147, "gradient_norm": 0.32125717401504517, "tokens_per_second": 1082987.7004799407, "synthetic": false, "world_size": 8} {"step": 7020, "tokens": 1840250880, "loss": 2.3958948135375975, "optimizer_updates": 4510, "effective_batch": 512, "lr": 0.0001965048017672519, "gradient_norm": 0.27358946204185486, "tokens_per_second": 830261.0754725253, "synthetic": false, "world_size": 8} {"step": 7040, "tokens": 1845493760, "loss": 2.4022405624389647, "optimizer_updates": 4520, "effective_batch": 512, "lr": 0.00019648424979697415, "gradient_norm": 0.2845967710018158, "tokens_per_second": 1066171.0877691403, "synthetic": false, "world_size": 8} {"step": 7060, "tokens": 1850736640, "loss": 2.4166233062744142, "optimizer_updates": 4530, "effective_batch": 512, "lr": 0.0001964636387839123, "gradient_norm": 0.293973445892334, "tokens_per_second": 1073263.8478354432, "synthetic": false, "world_size": 8} {"step": 7080, "tokens": 1855979520, "loss": 2.3797168731689453, "optimizer_updates": 4540, "effective_batch": 512, "lr": 0.00019644296874213744, "gradient_norm": 0.24642200767993927, "tokens_per_second": 1076363.337371611, "synthetic": false, "world_size": 8} {"step": 7100, "tokens": 1861222400, "loss": 2.407759666442871, "optimizer_updates": 4550, "effective_batch": 512, "lr": 0.000196422239685761, "gradient_norm": 0.4038476049900055, "tokens_per_second": 1069309.7324291135, "synthetic": false, "world_size": 8} {"step": 7120, "tokens": 1866465280, "loss": 2.392410087585449, "optimizer_updates": 4560, "effective_batch": 512, "lr": 0.00019640145162893476, "gradient_norm": 0.30923542380332947, "tokens_per_second": 1077825.6287920454, "synthetic": false, "world_size": 8} {"step": 7140, "tokens": 1871708160, "loss": 2.4081512451171876, "optimizer_updates": 4570, "effective_batch": 512, "lr": 0.0001963806045858507, "gradient_norm": 0.24356387555599213, "tokens_per_second": 1077807.0491330174, "synthetic": false, "world_size": 8} {"step": 7160, "tokens": 1876951040, "loss": 2.3886232376098633, "optimizer_updates": 4580, "effective_batch": 512, "lr": 0.00019635969857074108, "gradient_norm": 0.4230640232563019, "tokens_per_second": 1075744.9821505805, "synthetic": false, "world_size": 8} {"step": 7180, "tokens": 1882193920, "loss": 2.387934684753418, "optimizer_updates": 4590, "effective_batch": 512, "lr": 0.00019633873359787844, "gradient_norm": 0.3744840919971466, "tokens_per_second": 1073954.8805904419, "synthetic": false, "world_size": 8} {"step": 7200, "tokens": 1887436800, "loss": 2.4056495666503905, "optimizer_updates": 4600, "effective_batch": 512, "lr": 0.00019631770968157555, "gradient_norm": 0.26858168840408325, "tokens_per_second": 1072303.9016823247, "synthetic": false, "world_size": 8} {"step": 7220, "tokens": 1892679680, "loss": 2.402447509765625, "optimizer_updates": 4610, "effective_batch": 512, "lr": 0.00019629662683618546, "gradient_norm": 0.2767159640789032, "tokens_per_second": 1079059.410221475, "synthetic": false, "world_size": 8} {"step": 7240, "tokens": 1897922560, "loss": 2.39593620300293, "optimizer_updates": 4620, "effective_batch": 512, "lr": 0.00019627548507610142, "gradient_norm": 0.2538822591304779, "tokens_per_second": 1079123.9670839685, "synthetic": false, "world_size": 8} {"step": 7260, "tokens": 1903165440, "loss": 2.3981237411499023, "optimizer_updates": 4630, "effective_batch": 512, "lr": 0.00019625428441575688, "gradient_norm": 0.2577079236507416, "tokens_per_second": 1080488.8586409197, "synthetic": false, "world_size": 8} {"step": 7280, "tokens": 1908408320, "loss": 2.3823537826538086, "optimizer_updates": 4640, "effective_batch": 512, "lr": 0.00019623302486962554, "gradient_norm": 0.2574654221534729, "tokens_per_second": 1079025.7801390928, "synthetic": false, "world_size": 8} {"step": 7300, "tokens": 1913651200, "loss": 2.4121767044067384, "optimizer_updates": 4650, "effective_batch": 512, "lr": 0.00019621170645222133, "gradient_norm": 0.29113179445266724, "tokens_per_second": 1073247.8257408447, "synthetic": false, "world_size": 8} {"step": 7320, "tokens": 1918894080, "loss": 2.403857612609863, "optimizer_updates": 4660, "effective_batch": 512, "lr": 0.00019619032917809828, "gradient_norm": 0.42805546522140503, "tokens_per_second": 1088084.3183115032, "synthetic": false, "world_size": 8} {"step": 7340, "tokens": 1924136960, "loss": 2.3953107833862304, "optimizer_updates": 4670, "effective_batch": 512, "lr": 0.00019616889306185066, "gradient_norm": 0.3539271950721741, "tokens_per_second": 1080025.9144010379, "synthetic": false, "world_size": 8} {"step": 7360, "tokens": 1929379840, "loss": 2.4066184997558593, "optimizer_updates": 4680, "effective_batch": 512, "lr": 0.00019614739811811292, "gradient_norm": 0.3359350264072418, "tokens_per_second": 1073787.9049791382, "synthetic": false, "world_size": 8} {"step": 7380, "tokens": 1934622720, "loss": 2.387698936462402, "optimizer_updates": 4690, "effective_batch": 512, "lr": 0.00019612584436155966, "gradient_norm": 0.44445255398750305, "tokens_per_second": 1076430.955407082, "synthetic": false, "world_size": 8} {"step": 7400, "tokens": 1939865600, "loss": 2.405121421813965, "optimizer_updates": 4700, "effective_batch": 512, "lr": 0.0001961042318069056, "gradient_norm": 0.6320199966430664, "tokens_per_second": 774115.693817044, "synthetic": false, "world_size": 8} {"step": 7420, "tokens": 1945108480, "loss": 2.4065093994140625, "optimizer_updates": 4710, "effective_batch": 512, "lr": 0.00019608256046890562, "gradient_norm": 0.2551470994949341, "tokens_per_second": 1069283.7626281003, "synthetic": false, "world_size": 8} {"step": 7440, "tokens": 1950351360, "loss": 2.4003353118896484, "optimizer_updates": 4720, "effective_batch": 512, "lr": 0.0001960608303623548, "gradient_norm": 0.4164387583732605, "tokens_per_second": 1080569.8394259312, "synthetic": false, "world_size": 8} {"step": 7460, "tokens": 1955594240, "loss": 2.3931964874267577, "optimizer_updates": 4730, "effective_batch": 512, "lr": 0.0001960390415020882, "gradient_norm": 0.2529858648777008, "tokens_per_second": 1066008.874648954, "synthetic": false, "world_size": 8} {"step": 7480, "tokens": 1960837120, "loss": 2.4135738372802735, "optimizer_updates": 4740, "effective_batch": 512, "lr": 0.00019601719390298112, "gradient_norm": 0.30210280418395996, "tokens_per_second": 1072596.3786469095, "synthetic": false, "world_size": 8} {"step": 7500, "tokens": 1966080000, "loss": 2.387734222412109, "optimizer_updates": 4750, "effective_batch": 512, "lr": 0.00019599528757994892, "gradient_norm": 0.3309973478317261, "tokens_per_second": 1086953.5908791493, "synthetic": false, "world_size": 8} {"step": 7520, "tokens": 1971322880, "loss": 2.4184249877929687, "optimizer_updates": 4760, "effective_batch": 512, "lr": 0.00019597332254794704, "gradient_norm": 0.2627612352371216, "tokens_per_second": 982167.8874597676, "synthetic": false, "world_size": 8} {"step": 7540, "tokens": 1976565760, "loss": 2.4148937225341798, "optimizer_updates": 4770, "effective_batch": 512, "lr": 0.00019595129882197095, "gradient_norm": 0.30246812105178833, "tokens_per_second": 1078536.1043950303, "synthetic": false, "world_size": 8} {"step": 7560, "tokens": 1981808640, "loss": 2.3786792755126953, "optimizer_updates": 4780, "effective_batch": 512, "lr": 0.0001959292164170563, "gradient_norm": 0.2854022681713104, "tokens_per_second": 974713.9830335395, "synthetic": false, "world_size": 8} {"step": 7580, "tokens": 1987051520, "loss": 2.411305046081543, "optimizer_updates": 4790, "effective_batch": 512, "lr": 0.00019590707534827874, "gradient_norm": 0.2727746069431305, "tokens_per_second": 1088251.2411106387, "synthetic": false, "world_size": 8} {"step": 7600, "tokens": 1992294400, "loss": 2.403793716430664, "optimizer_updates": 4800, "effective_batch": 512, "lr": 0.00019588487563075398, "gradient_norm": 0.2845192551612854, "tokens_per_second": 1080978.071443701, "synthetic": false, "world_size": 8} {"step": 7620, "tokens": 1997537280, "loss": 2.3909717559814454, "optimizer_updates": 4810, "effective_batch": 512, "lr": 0.0001958626172796377, "gradient_norm": 0.24472999572753906, "tokens_per_second": 1086548.8119673368, "synthetic": false, "world_size": 8} {"step": 7640, "tokens": 2002780160, "loss": 2.394280433654785, "optimizer_updates": 4820, "effective_batch": 512, "lr": 0.00019584030031012577, "gradient_norm": 0.334248811006546, "tokens_per_second": 1085577.3026776887, "synthetic": false, "world_size": 8} {"step": 7660, "tokens": 2008023040, "loss": 2.398236846923828, "optimizer_updates": 4830, "effective_batch": 512, "lr": 0.00019581792473745391, "gradient_norm": 0.26867371797561646, "tokens_per_second": 1075574.4587046853, "synthetic": false, "world_size": 8} {"step": 7680, "tokens": 2013265920, "loss": 2.4035593032836915, "optimizer_updates": 4840, "effective_batch": 512, "lr": 0.00019579549057689797, "gradient_norm": 0.2593301236629486, "tokens_per_second": 1072781.0647741205, "synthetic": false, "world_size": 8} {"step": 7700, "tokens": 2018508800, "loss": 2.3869985580444335, "optimizer_updates": 4850, "effective_batch": 512, "lr": 0.0001957729978437737, "gradient_norm": 0.312688946723938, "tokens_per_second": 1087019.4194291704, "synthetic": false, "world_size": 8} {"step": 7720, "tokens": 2023751680, "loss": 2.400526428222656, "optimizer_updates": 4860, "effective_batch": 512, "lr": 0.0001957504465534369, "gradient_norm": 0.34964197874069214, "tokens_per_second": 1078516.9812673072, "synthetic": false, "world_size": 8} {"step": 7740, "tokens": 2028994560, "loss": 2.390365219116211, "optimizer_updates": 4870, "effective_batch": 512, "lr": 0.00019572783672128333, "gradient_norm": 0.28584709763526917, "tokens_per_second": 1079039.2327477972, "synthetic": false, "world_size": 8} {"step": 7760, "tokens": 2034237440, "loss": 2.3965206146240234, "optimizer_updates": 4880, "effective_batch": 512, "lr": 0.00019570516836274875, "gradient_norm": 0.30932149291038513, "tokens_per_second": 1075595.4999985057, "synthetic": false, "world_size": 8} {"step": 7780, "tokens": 2039480320, "loss": 2.394656944274902, "optimizer_updates": 4890, "effective_batch": 512, "lr": 0.00019568244149330882, "gradient_norm": 0.28186044096946716, "tokens_per_second": 1080543.0220620753, "synthetic": false, "world_size": 8} {"step": 7800, "tokens": 2044723200, "loss": 2.4156551361083984, "optimizer_updates": 4900, "effective_batch": 512, "lr": 0.00019565965612847918, "gradient_norm": 0.5999143719673157, "tokens_per_second": 1081393.6134263915, "synthetic": false, "world_size": 8} {"step": 7820, "tokens": 2049966080, "loss": 2.3973546981811524, "optimizer_updates": 4910, "effective_batch": 512, "lr": 0.00019563681228381536, "gradient_norm": 0.27410057187080383, "tokens_per_second": 1075243.7113090858, "synthetic": false, "world_size": 8} {"step": 7840, "tokens": 2055208960, "loss": 2.404190444946289, "optimizer_updates": 4920, "effective_batch": 512, "lr": 0.0001956139099749129, "gradient_norm": 0.3528367877006531, "tokens_per_second": 1082986.325579374, "synthetic": false, "world_size": 8} {"step": 7860, "tokens": 2060451840, "loss": 2.395619583129883, "optimizer_updates": 4930, "effective_batch": 512, "lr": 0.00019559094921740717, "gradient_norm": 0.36870813369750977, "tokens_per_second": 1082878.361471742, "synthetic": false, "world_size": 8} {"step": 7880, "tokens": 2065694720, "loss": 2.388508987426758, "optimizer_updates": 4940, "effective_batch": 512, "lr": 0.0001955679300269735, "gradient_norm": 0.2839862108230591, "tokens_per_second": 1074497.5035680241, "synthetic": false, "world_size": 8} {"step": 7900, "tokens": 2070937600, "loss": 2.4018863677978515, "optimizer_updates": 4950, "effective_batch": 512, "lr": 0.00019554485241932704, "gradient_norm": 0.5340185761451721, "tokens_per_second": 1078530.6643708127, "synthetic": false, "world_size": 8} {"step": 7920, "tokens": 2076180480, "loss": 2.4053220748901367, "optimizer_updates": 4960, "effective_batch": 512, "lr": 0.00019552171641022293, "gradient_norm": 0.6389793157577515, "tokens_per_second": 1075232.8599541837, "synthetic": false, "world_size": 8} {"step": 7940, "tokens": 2081423360, "loss": 2.401534080505371, "optimizer_updates": 4970, "effective_batch": 512, "lr": 0.0001954985220154561, "gradient_norm": 0.3411504924297333, "tokens_per_second": 1069238.7010932912, "synthetic": false, "world_size": 8} {"step": 7960, "tokens": 2086666240, "loss": 2.38968448638916, "optimizer_updates": 4980, "effective_batch": 512, "lr": 0.00019547526925086132, "gradient_norm": 0.2936791777610779, "tokens_per_second": 1082781.527568681, "synthetic": false, "world_size": 8} {"step": 7980, "tokens": 2091909120, "loss": 2.396434020996094, "optimizer_updates": 4990, "effective_batch": 512, "lr": 0.0001954519581323133, "gradient_norm": 0.26872801780700684, "tokens_per_second": 1082438.3224344966, "synthetic": false, "world_size": 8} {"step": 8000, "tokens": 2097152000, "loss": 2.3969871520996096, "optimizer_updates": 5000, "effective_batch": 512, "lr": 0.0001954285886757265, "gradient_norm": 0.3741970658302307, "tokens_per_second": 1075439.5077828886, "synthetic": false, "world_size": 8} {"step": 8020, "tokens": 2102394880, "loss": 2.3930679321289063, "optimizer_updates": 5010, "effective_batch": 512, "lr": 0.0001954051608970553, "gradient_norm": 0.45205673575401306, "tokens_per_second": 832704.4638701078, "synthetic": false, "world_size": 8} {"step": 8040, "tokens": 2107637760, "loss": 2.4138668060302733, "optimizer_updates": 5020, "effective_batch": 512, "lr": 0.0001953816748122938, "gradient_norm": 0.267042338848114, "tokens_per_second": 763592.7515501827, "synthetic": false, "world_size": 8} {"step": 8060, "tokens": 2112880640, "loss": 2.4020240783691404, "optimizer_updates": 5030, "effective_batch": 512, "lr": 0.00019535813043747595, "gradient_norm": 0.3742036819458008, "tokens_per_second": 1068334.8097873358, "synthetic": false, "world_size": 8} {"step": 8080, "tokens": 2118123520, "loss": 2.4197917938232423, "optimizer_updates": 5040, "effective_batch": 512, "lr": 0.00019533452778867547, "gradient_norm": 0.34744346141815186, "tokens_per_second": 1074203.6139943597, "synthetic": false, "world_size": 8} {"step": 8100, "tokens": 2123366400, "loss": 2.4044044494628904, "optimizer_updates": 5050, "effective_batch": 512, "lr": 0.0001953108668820059, "gradient_norm": 0.31433501839637756, "tokens_per_second": 1070187.9969051352, "synthetic": false, "world_size": 8} {"step": 8120, "tokens": 2128609280, "loss": 2.3975265502929686, "optimizer_updates": 5060, "effective_batch": 512, "lr": 0.00019528714773362057, "gradient_norm": 0.2889963984489441, "tokens_per_second": 1077232.5856348618, "synthetic": false, "world_size": 8} {"step": 8140, "tokens": 2133852160, "loss": 2.3977357864379885, "optimizer_updates": 5070, "effective_batch": 512, "lr": 0.00019526337035971248, "gradient_norm": 0.3482849597930908, "tokens_per_second": 1071874.672387926, "synthetic": false, "world_size": 8} {"step": 8160, "tokens": 2139095040, "loss": 2.3944467544555663, "optimizer_updates": 5080, "effective_batch": 512, "lr": 0.0001952395347765145, "gradient_norm": 0.25871074199676514, "tokens_per_second": 1070494.9903955543, "synthetic": false, "world_size": 8} {"step": 8180, "tokens": 2144337920, "loss": 2.395175552368164, "optimizer_updates": 5090, "effective_batch": 512, "lr": 0.00019521564100029914, "gradient_norm": 0.3556511104106903, "tokens_per_second": 1079460.7283161306, "synthetic": false, "world_size": 8} {"step": 8200, "tokens": 2149580800, "loss": 2.4082309722900392, "optimizer_updates": 5100, "effective_batch": 512, "lr": 0.00019519168904737867, "gradient_norm": 0.28078803420066833, "tokens_per_second": 1076547.5641797045, "synthetic": false, "world_size": 8} {"step": 8220, "tokens": 2154823680, "loss": 2.39276065826416, "optimizer_updates": 5110, "effective_batch": 512, "lr": 0.00019516767893410514, "gradient_norm": 0.5479381084442139, "tokens_per_second": 1074025.3459098984, "synthetic": false, "world_size": 8} {"step": 8240, "tokens": 2160066560, "loss": 2.3973714828491213, "optimizer_updates": 5120, "effective_batch": 512, "lr": 0.0001951436106768702, "gradient_norm": 0.25937163829803467, "tokens_per_second": 1068399.4640007159, "synthetic": false, "world_size": 8} {"step": 8260, "tokens": 2165309440, "loss": 2.3995506286621096, "optimizer_updates": 5130, "effective_batch": 512, "lr": 0.00019511948429210525, "gradient_norm": 0.3049241006374359, "tokens_per_second": 1084170.2234815983, "synthetic": false, "world_size": 8} {"step": 8280, "tokens": 2170552320, "loss": 2.398795318603516, "optimizer_updates": 5140, "effective_batch": 512, "lr": 0.00019509529979628136, "gradient_norm": 0.4017711877822876, "tokens_per_second": 1081415.844842252, "synthetic": false, "world_size": 8} {"step": 8300, "tokens": 2175795200, "loss": 2.3985084533691405, "optimizer_updates": 5150, "effective_batch": 512, "lr": 0.00019507105720590934, "gradient_norm": 0.33481213450431824, "tokens_per_second": 1075090.0320599393, "synthetic": false, "world_size": 8} {"step": 8320, "tokens": 2181038080, "loss": 2.386650276184082, "optimizer_updates": 5160, "effective_batch": 512, "lr": 0.00019504675653753955, "gradient_norm": 0.289760559797287, "tokens_per_second": 844870.016263649, "synthetic": false, "world_size": 8} {"step": 8340, "tokens": 2186280960, "loss": 2.397395133972168, "optimizer_updates": 5170, "effective_batch": 512, "lr": 0.00019502239780776206, "gradient_norm": 0.4466012120246887, "tokens_per_second": 1015434.2362621702, "synthetic": false, "world_size": 8} {"step": 8360, "tokens": 2191523840, "loss": 2.391375732421875, "optimizer_updates": 5180, "effective_batch": 512, "lr": 0.00019499798103320658, "gradient_norm": 0.28961360454559326, "tokens_per_second": 1078851.8496684297, "synthetic": false, "world_size": 8} {"step": 8380, "tokens": 2196766720, "loss": 2.397378158569336, "optimizer_updates": 5190, "effective_batch": 512, "lr": 0.0001949735062305424, "gradient_norm": 0.4094952940940857, "tokens_per_second": 988812.7620130898, "synthetic": false, "world_size": 8} {"step": 8400, "tokens": 2202009600, "loss": 2.403168869018555, "optimizer_updates": 5200, "effective_batch": 512, "lr": 0.00019494897341647854, "gradient_norm": 0.3901428282260895, "tokens_per_second": 1073587.1096046565, "synthetic": false, "world_size": 8} {"step": 8420, "tokens": 2207252480, "loss": 2.3871139526367187, "optimizer_updates": 5210, "effective_batch": 512, "lr": 0.00019492438260776353, "gradient_norm": 0.27541184425354004, "tokens_per_second": 1072665.9145931068, "synthetic": false, "world_size": 8} {"step": 8440, "tokens": 2212495360, "loss": 2.4038873672485352, "optimizer_updates": 5220, "effective_batch": 512, "lr": 0.00019489973382118544, "gradient_norm": 0.3324790596961975, "tokens_per_second": 1076209.0750463184, "synthetic": false, "world_size": 8} {"step": 8460, "tokens": 2217738240, "loss": 2.3912769317626954, "optimizer_updates": 5230, "effective_batch": 512, "lr": 0.00019487502707357204, "gradient_norm": 0.3696848452091217, "tokens_per_second": 1075450.747813302, "synthetic": false, "world_size": 8} {"step": 8480, "tokens": 2222981120, "loss": 2.394892692565918, "optimizer_updates": 5240, "effective_batch": 512, "lr": 0.00019485026238179066, "gradient_norm": 0.3094117343425751, "tokens_per_second": 1074976.8082227116, "synthetic": false, "world_size": 8} {"step": 8500, "tokens": 2228224000, "loss": 2.393073081970215, "optimizer_updates": 5250, "effective_batch": 512, "lr": 0.0001948254397627481, "gradient_norm": 0.2524051368236542, "tokens_per_second": 1070145.8983969695, "synthetic": false, "world_size": 8} {"step": 8520, "tokens": 2233466880, "loss": 2.4027336120605467, "optimizer_updates": 5260, "effective_batch": 512, "lr": 0.00019480055923339076, "gradient_norm": 0.25065577030181885, "tokens_per_second": 1068480.8483251838, "synthetic": false, "world_size": 8} {"step": 8540, "tokens": 2238709760, "loss": 2.388503837585449, "optimizer_updates": 5270, "effective_batch": 512, "lr": 0.0001947756208107046, "gradient_norm": 0.26303595304489136, "tokens_per_second": 1076657.5134707994, "synthetic": false, "world_size": 8} {"step": 8560, "tokens": 2243952640, "loss": 2.3947427749633787, "optimizer_updates": 5280, "effective_batch": 512, "lr": 0.00019475062451171504, "gradient_norm": 0.4380919337272644, "tokens_per_second": 1085038.6987738025, "synthetic": false, "world_size": 8} {"step": 8580, "tokens": 2249195520, "loss": 2.3944059371948243, "optimizer_updates": 5290, "effective_batch": 512, "lr": 0.0001947255703534871, "gradient_norm": 0.3670923113822937, "tokens_per_second": 1077583.5185974971, "synthetic": false, "world_size": 8} {"step": 8600, "tokens": 2254438400, "loss": 2.398793411254883, "optimizer_updates": 5300, "effective_batch": 512, "lr": 0.00019470045835312525, "gradient_norm": 0.4921986162662506, "tokens_per_second": 1069115.5853929361, "synthetic": false, "world_size": 8} {"step": 8620, "tokens": 2259681280, "loss": 2.4125364303588865, "optimizer_updates": 5310, "effective_batch": 512, "lr": 0.00019467528852777337, "gradient_norm": 0.3292478919029236, "tokens_per_second": 1078274.0048921593, "synthetic": false, "world_size": 8} {"step": 8640, "tokens": 2264924160, "loss": 2.410202407836914, "optimizer_updates": 5320, "effective_batch": 512, "lr": 0.00019465006089461497, "gradient_norm": 0.31531447172164917, "tokens_per_second": 1077152.5842267347, "synthetic": false, "world_size": 8} {"step": 8660, "tokens": 2270167040, "loss": 2.3872385025024414, "optimizer_updates": 5330, "effective_batch": 512, "lr": 0.0001946247754708729, "gradient_norm": 0.4988994598388672, "tokens_per_second": 1066772.7514468273, "synthetic": false, "world_size": 8} {"step": 8680, "tokens": 2275409920, "loss": 2.396767425537109, "optimizer_updates": 5340, "effective_batch": 512, "lr": 0.00019459943227380957, "gradient_norm": 0.24508267641067505, "tokens_per_second": 1070537.2866687586, "synthetic": false, "world_size": 8} {"step": 8700, "tokens": 2280652800, "loss": 2.411361503601074, "optimizer_updates": 5350, "effective_batch": 512, "lr": 0.00019457403132072678, "gradient_norm": 0.3812515139579773, "tokens_per_second": 974289.9233876899, "synthetic": false, "world_size": 8} {"step": 8720, "tokens": 2285895680, "loss": 2.395097541809082, "optimizer_updates": 5360, "effective_batch": 512, "lr": 0.0001945485726289657, "gradient_norm": 0.5145018696784973, "tokens_per_second": 1068220.2364295565, "synthetic": false, "world_size": 8} {"step": 8740, "tokens": 2291138560, "loss": 2.4003427505493162, "optimizer_updates": 5370, "effective_batch": 512, "lr": 0.00019452305621590703, "gradient_norm": 0.27327850461006165, "tokens_per_second": 1074336.7814753822, "synthetic": false, "world_size": 8} {"step": 8760, "tokens": 2296381440, "loss": 2.3856863021850585, "optimizer_updates": 5380, "effective_batch": 512, "lr": 0.00019449748209897076, "gradient_norm": 0.35120564699172974, "tokens_per_second": 1070703.2744172188, "synthetic": false, "world_size": 8} {"step": 8780, "tokens": 2301624320, "loss": 2.3972497940063477, "optimizer_updates": 5390, "effective_batch": 512, "lr": 0.0001944718502956164, "gradient_norm": 0.2977376878261566, "tokens_per_second": 1082472.4328573935, "synthetic": false, "world_size": 8} {"step": 8800, "tokens": 2306867200, "loss": 2.401014709472656, "optimizer_updates": 5400, "effective_batch": 512, "lr": 0.0001944461608233427, "gradient_norm": 0.35320591926574707, "tokens_per_second": 1076718.6579112073, "synthetic": false, "world_size": 8} {"step": 8820, "tokens": 2312110080, "loss": 2.387520408630371, "optimizer_updates": 5410, "effective_batch": 512, "lr": 0.00019442041369968795, "gradient_norm": 0.2550714313983917, "tokens_per_second": 1076212.5935591308, "synthetic": false, "world_size": 8} {"step": 8840, "tokens": 2317352960, "loss": 2.405298042297363, "optimizer_updates": 5420, "effective_batch": 512, "lr": 0.00019439460894222964, "gradient_norm": 0.36710190773010254, "tokens_per_second": 1073309.748465922, "synthetic": false, "world_size": 8} {"step": 8860, "tokens": 2322595840, "loss": 2.392351531982422, "optimizer_updates": 5430, "effective_batch": 512, "lr": 0.00019436874656858472, "gradient_norm": 0.33056506514549255, "tokens_per_second": 1078150.9368805306, "synthetic": false, "world_size": 8} {"step": 8880, "tokens": 2327838720, "loss": 2.404359817504883, "optimizer_updates": 5440, "effective_batch": 512, "lr": 0.00019434282659640942, "gradient_norm": 0.2545923888683319, "tokens_per_second": 1072416.992254152, "synthetic": false, "world_size": 8} {"step": 8900, "tokens": 2333081600, "loss": 2.3991062164306642, "optimizer_updates": 5450, "effective_batch": 512, "lr": 0.00019431684904339924, "gradient_norm": 0.33180639147758484, "tokens_per_second": 1070061.773327292, "synthetic": false, "world_size": 8} {"step": 8920, "tokens": 2338324480, "loss": 2.382297134399414, "optimizer_updates": 5460, "effective_batch": 512, "lr": 0.00019429081392728913, "gradient_norm": 0.42530447244644165, "tokens_per_second": 1071510.6950745748, "synthetic": false, "world_size": 8} {"step": 8940, "tokens": 2343567360, "loss": 2.399586868286133, "optimizer_updates": 5470, "effective_batch": 512, "lr": 0.00019426472126585323, "gradient_norm": 0.3345787227153778, "tokens_per_second": 970979.4622140708, "synthetic": false, "world_size": 8} {"step": 8960, "tokens": 2348810240, "loss": 2.4119781494140624, "optimizer_updates": 5480, "effective_batch": 512, "lr": 0.000194238571076905, "gradient_norm": 0.4411163926124573, "tokens_per_second": 1086335.2449915553, "synthetic": false, "world_size": 8} {"step": 8980, "tokens": 2354053120, "loss": 2.393244171142578, "optimizer_updates": 5490, "effective_batch": 512, "lr": 0.00019421236337829716, "gradient_norm": 0.25020986795425415, "tokens_per_second": 1071477.0718478656, "synthetic": false, "world_size": 8} {"step": 9000, "tokens": 2359296000, "loss": 2.410208511352539, "optimizer_updates": 5500, "effective_batch": 512, "lr": 0.00019418609818792172, "gradient_norm": 0.3392656445503235, "tokens_per_second": 1072639.7373723155, "synthetic": false, "world_size": 8} {"step": 9020, "tokens": 2364538880, "loss": 2.4028903961181642, "optimizer_updates": 5510, "effective_batch": 512, "lr": 0.00019415977552370988, "gradient_norm": 0.25902870297431946, "tokens_per_second": 839290.4651496568, "synthetic": false, "world_size": 8} {"step": 9040, "tokens": 2369781760, "loss": 2.3877038955688477, "optimizer_updates": 5520, "effective_batch": 512, "lr": 0.00019413339540363218, "gradient_norm": 0.3128425180912018, "tokens_per_second": 1070856.7149290747, "synthetic": false, "world_size": 8} {"step": 9060, "tokens": 2375024640, "loss": 2.3967409133911133, "optimizer_updates": 5530, "effective_batch": 512, "lr": 0.00019410695784569825, "gradient_norm": 0.3063395023345947, "tokens_per_second": 1074804.3574362106, "synthetic": false, "world_size": 8} {"step": 9080, "tokens": 2380267520, "loss": 2.4013221740722654, "optimizer_updates": 5540, "effective_batch": 512, "lr": 0.00019408046286795708, "gradient_norm": 0.31426525115966797, "tokens_per_second": 1069552.123403827, "synthetic": false, "world_size": 8} {"step": 9100, "tokens": 2385510400, "loss": 2.3956871032714844, "optimizer_updates": 5550, "effective_batch": 512, "lr": 0.00019405391048849676, "gradient_norm": 0.2826276123523712, "tokens_per_second": 1077204.7210103017, "synthetic": false, "world_size": 8} {"step": 9120, "tokens": 2390753280, "loss": 2.395943260192871, "optimizer_updates": 5560, "effective_batch": 512, "lr": 0.00019402730072544456, "gradient_norm": 0.2712933421134949, "tokens_per_second": 1075069.1291535695, "synthetic": false, "world_size": 8} {"step": 9140, "tokens": 2395996160, "loss": 2.391941452026367, "optimizer_updates": 5570, "effective_batch": 512, "lr": 0.00019400063359696705, "gradient_norm": 0.37841254472732544, "tokens_per_second": 1074322.8283376524, "synthetic": false, "world_size": 8} {"step": 9160, "tokens": 2401239040, "loss": 2.3957923889160155, "optimizer_updates": 5580, "effective_batch": 512, "lr": 0.00019397390912126976, "gradient_norm": 0.32357242703437805, "tokens_per_second": 1070266.5377479966, "synthetic": false, "world_size": 8} {"step": 9180, "tokens": 2406481920, "loss": 2.3969137191772463, "optimizer_updates": 5590, "effective_batch": 512, "lr": 0.00019394712731659754, "gradient_norm": 0.39270761609077454, "tokens_per_second": 1087948.878856898, "synthetic": false, "world_size": 8} {"step": 9200, "tokens": 2411724800, "loss": 2.3969192504882812, "optimizer_updates": 5600, "effective_batch": 512, "lr": 0.00019392028820123438, "gradient_norm": 0.5119566917419434, "tokens_per_second": 1071348.22823472, "synthetic": false, "world_size": 8} {"step": 9220, "tokens": 2416967680, "loss": 2.3931087493896483, "optimizer_updates": 5610, "effective_batch": 512, "lr": 0.00019389339179350326, "gradient_norm": 0.2677290737628937, "tokens_per_second": 1074098.126129305, "synthetic": false, "world_size": 8} {"step": 9240, "tokens": 2422210560, "loss": 2.385633659362793, "optimizer_updates": 5620, "effective_batch": 512, "lr": 0.00019386643811176635, "gradient_norm": 0.29030531644821167, "tokens_per_second": 1073706.2584068796, "synthetic": false, "world_size": 8} {"step": 9260, "tokens": 2427453440, "loss": 2.3997364044189453, "optimizer_updates": 5630, "effective_batch": 512, "lr": 0.000193839427174425, "gradient_norm": 0.4082205593585968, "tokens_per_second": 1069230.744936379, "synthetic": false, "world_size": 8} {"step": 9280, "tokens": 2432696320, "loss": 2.3988866806030273, "optimizer_updates": 5640, "effective_batch": 512, "lr": 0.0001938123589999195, "gradient_norm": 0.4067729115486145, "tokens_per_second": 1068756.457789972, "synthetic": false, "world_size": 8} {"step": 9300, "tokens": 2437939200, "loss": 2.3917800903320314, "optimizer_updates": 5650, "effective_batch": 512, "lr": 0.0001937852336067293, "gradient_norm": 0.29295629262924194, "tokens_per_second": 1070638.176252823, "synthetic": false, "world_size": 8} {"step": 9320, "tokens": 2443182080, "loss": 2.373714065551758, "optimizer_updates": 5660, "effective_batch": 512, "lr": 0.00019375805101337295, "gradient_norm": 0.27869972586631775, "tokens_per_second": 1073998.4391958034, "synthetic": false, "world_size": 8} {"step": 9340, "tokens": 2448424960, "loss": 2.4031925201416016, "optimizer_updates": 5670, "effective_batch": 512, "lr": 0.00019373081123840794, "gradient_norm": 0.29043447971343994, "tokens_per_second": 1075468.5368715993, "synthetic": false, "world_size": 8} {"step": 9360, "tokens": 2453667840, "loss": 2.3872713088989257, "optimizer_updates": 5680, "effective_batch": 512, "lr": 0.00019370351430043092, "gradient_norm": 0.2608568072319031, "tokens_per_second": 1069583.2455676978, "synthetic": false, "world_size": 8} {"step": 9380, "tokens": 2458910720, "loss": 2.398963737487793, "optimizer_updates": 5690, "effective_batch": 512, "lr": 0.00019367616021807746, "gradient_norm": 0.2934209704399109, "tokens_per_second": 1078710.2115924081, "synthetic": false, "world_size": 8} {"step": 9400, "tokens": 2464153600, "loss": 2.399530601501465, "optimizer_updates": 5700, "effective_batch": 512, "lr": 0.0001936487490100222, "gradient_norm": 0.3656269907951355, "tokens_per_second": 1068147.263025519, "synthetic": false, "world_size": 8} {"step": 9420, "tokens": 2469396480, "loss": 2.386840057373047, "optimizer_updates": 5710, "effective_batch": 512, "lr": 0.00019362128069497878, "gradient_norm": 0.3115318715572357, "tokens_per_second": 1078956.602737949, "synthetic": false, "world_size": 8} {"step": 9440, "tokens": 2474639360, "loss": 2.392811393737793, "optimizer_updates": 5720, "effective_batch": 512, "lr": 0.0001935937552916998, "gradient_norm": 0.31566208600997925, "tokens_per_second": 1082896.1729629596, "synthetic": false, "world_size": 8} {"step": 9460, "tokens": 2479882240, "loss": 2.3997779846191407, "optimizer_updates": 5730, "effective_batch": 512, "lr": 0.00019356617281897687, "gradient_norm": 0.2920985817909241, "tokens_per_second": 1067903.4862782198, "synthetic": false, "world_size": 8} {"step": 9480, "tokens": 2485125120, "loss": 2.397170639038086, "optimizer_updates": 5740, "effective_batch": 512, "lr": 0.0001935385332956405, "gradient_norm": 0.30951687693595886, "tokens_per_second": 1068324.8837041627, "synthetic": false, "world_size": 8} {"step": 9500, "tokens": 2490368000, "loss": 2.3959638595581056, "optimizer_updates": 5750, "effective_batch": 512, "lr": 0.00019351083674056023, "gradient_norm": 0.26119065284729004, "tokens_per_second": 1066022.4182129356, "synthetic": false, "world_size": 8} {"step": 9520, "tokens": 2495610880, "loss": 2.3856124877929688, "optimizer_updates": 5760, "effective_batch": 512, "lr": 0.00019348308317264446, "gradient_norm": 0.2656605541706085, "tokens_per_second": 1073815.3386392973, "synthetic": false, "world_size": 8} {"step": 9540, "tokens": 2500853760, "loss": 2.392926788330078, "optimizer_updates": 5770, "effective_batch": 512, "lr": 0.00019345527261084057, "gradient_norm": 0.3506447970867157, "tokens_per_second": 767416.4186770675, "synthetic": false, "world_size": 8} {"step": 9560, "tokens": 2506096640, "loss": 2.389323043823242, "optimizer_updates": 5780, "effective_batch": 512, "lr": 0.00019342740507413483, "gradient_norm": 0.2691989243030548, "tokens_per_second": 1082242.4333357813, "synthetic": false, "world_size": 8} {"step": 9580, "tokens": 2511339520, "loss": 2.390110206604004, "optimizer_updates": 5790, "effective_batch": 512, "lr": 0.00019339948058155236, "gradient_norm": 0.30460259318351746, "tokens_per_second": 1077887.0378388115, "synthetic": false, "world_size": 8} {"step": 9600, "tokens": 2516582400, "loss": 2.393666648864746, "optimizer_updates": 5800, "effective_batch": 512, "lr": 0.00019337149915215729, "gradient_norm": 0.4163968563079834, "tokens_per_second": 952645.864808939, "synthetic": false, "world_size": 8} {"step": 9620, "tokens": 2521825280, "loss": 2.3965618133544924, "optimizer_updates": 5810, "effective_batch": 512, "lr": 0.00019334346080505244, "gradient_norm": 0.28929537534713745, "tokens_per_second": 1074349.3891705486, "synthetic": false, "world_size": 8} {"step": 9640, "tokens": 2527068160, "loss": 2.382668685913086, "optimizer_updates": 5820, "effective_batch": 512, "lr": 0.00019331536555937962, "gradient_norm": 0.26054927706718445, "tokens_per_second": 1074953.5736981835, "synthetic": false, "world_size": 8} {"step": 9660, "tokens": 2532311040, "loss": 2.3904253005981446, "optimizer_updates": 5830, "effective_batch": 512, "lr": 0.0001932872134343195, "gradient_norm": 0.3710925579071045, "tokens_per_second": 1073655.8394109448, "synthetic": false, "world_size": 8} {"step": 9680, "tokens": 2537553920, "loss": 2.388010787963867, "optimizer_updates": 5840, "effective_batch": 512, "lr": 0.00019325900444909147, "gradient_norm": 0.28592649102211, "tokens_per_second": 1068283.4910600318, "synthetic": false, "world_size": 8} {"step": 9700, "tokens": 2542796800, "loss": 2.386717414855957, "optimizer_updates": 5850, "effective_batch": 512, "lr": 0.00019323073862295383, "gradient_norm": 0.49926021695137024, "tokens_per_second": 1062887.3636263385, "synthetic": false, "world_size": 8} {"step": 9720, "tokens": 2548039680, "loss": 2.393436241149902, "optimizer_updates": 5860, "effective_batch": 512, "lr": 0.00019320241597520365, "gradient_norm": 0.25704285502433777, "tokens_per_second": 1078083.1289924842, "synthetic": false, "world_size": 8} {"step": 9740, "tokens": 2553282560, "loss": 2.3982946395874025, "optimizer_updates": 5870, "effective_batch": 512, "lr": 0.00019317403652517682, "gradient_norm": 0.24244925379753113, "tokens_per_second": 1080530.5645125997, "synthetic": false, "world_size": 8} {"step": 9760, "tokens": 2558525440, "loss": 2.3910987854003904, "optimizer_updates": 5880, "effective_batch": 512, "lr": 0.00019314560029224794, "gradient_norm": 0.33084815740585327, "tokens_per_second": 1083005.478898814, "synthetic": false, "world_size": 8} {"step": 9780, "tokens": 2563768320, "loss": 2.3914796829223635, "optimizer_updates": 5890, "effective_batch": 512, "lr": 0.00019311710729583042, "gradient_norm": 0.2807586193084717, "tokens_per_second": 1067767.0698015676, "synthetic": false, "world_size": 8} {"step": 9800, "tokens": 2569011200, "loss": 2.383182907104492, "optimizer_updates": 5900, "effective_batch": 512, "lr": 0.00019308855755537647, "gradient_norm": 0.2815781235694885, "tokens_per_second": 1065950.9577433309, "synthetic": false, "world_size": 8} {"step": 9820, "tokens": 2574254080, "loss": 2.4031585693359374, "optimizer_updates": 5910, "effective_batch": 512, "lr": 0.00019305995109037698, "gradient_norm": 0.2900153398513794, "tokens_per_second": 1077155.167298174, "synthetic": false, "world_size": 8} {"step": 9840, "tokens": 2579496960, "loss": 2.4064519882202147, "optimizer_updates": 5920, "effective_batch": 512, "lr": 0.00019303128792036155, "gradient_norm": 0.3413235545158386, "tokens_per_second": 1072638.7601567248, "synthetic": false, "world_size": 8} {"step": 9860, "tokens": 2584739840, "loss": 2.393929672241211, "optimizer_updates": 5930, "effective_batch": 512, "lr": 0.00019300256806489857, "gradient_norm": 0.281597763299942, "tokens_per_second": 1075207.9927860387, "synthetic": false, "world_size": 8} {"step": 9880, "tokens": 2589982720, "loss": 2.4053272247314452, "optimizer_updates": 5940, "effective_batch": 512, "lr": 0.000192973791543595, "gradient_norm": 0.25473663210868835, "tokens_per_second": 1071725.5816589308, "synthetic": false, "world_size": 8} {"step": 9900, "tokens": 2595225600, "loss": 2.3934551239013673, "optimizer_updates": 5950, "effective_batch": 512, "lr": 0.00019294495837609668, "gradient_norm": 0.32497769594192505, "tokens_per_second": 1088886.315069512, "synthetic": false, "world_size": 8} {"step": 9920, "tokens": 2600468480, "loss": 2.3957145690917967, "optimizer_updates": 5960, "effective_batch": 512, "lr": 0.00019291606858208793, "gradient_norm": 0.3388836979866028, "tokens_per_second": 1088675.9699313454, "synthetic": false, "world_size": 8} {"step": 9940, "tokens": 2605711360, "loss": 2.4074153900146484, "optimizer_updates": 5970, "effective_batch": 512, "lr": 0.00019288712218129182, "gradient_norm": 0.4501953125, "tokens_per_second": 1079687.381068718, "synthetic": false, "world_size": 8} {"step": 9960, "tokens": 2610954240, "loss": 2.3806365966796874, "optimizer_updates": 5980, "effective_batch": 512, "lr": 0.00019285811919347002, "gradient_norm": 0.3228522837162018, "tokens_per_second": 768500.6837393342, "synthetic": false, "world_size": 8} {"step": 9980, "tokens": 2616197120, "loss": 2.3920515060424803, "optimizer_updates": 5990, "effective_batch": 512, "lr": 0.00019282905963842296, "gradient_norm": 0.2860528230667114, "tokens_per_second": 1078567.45072474, "synthetic": false, "world_size": 8} {"step": 10000, "tokens": 2621440000, "loss": 2.3772245407104493, "optimizer_updates": 6000, "effective_batch": 512, "lr": 0.00019279994353598953, "gradient_norm": 0.25547531247138977, "tokens_per_second": 1085365.9441473833, "synthetic": false, "world_size": 8} {"step": 10020, "tokens": 2626682880, "loss": 2.3921876907348634, "optimizer_updates": 6010, "effective_batch": 512, "lr": 0.00019277077090604732, "gradient_norm": 0.3107287883758545, "tokens_per_second": 846930.0385398527, "synthetic": false, "world_size": 8} {"step": 10040, "tokens": 2631925760, "loss": 2.391459083557129, "optimizer_updates": 6020, "effective_batch": 512, "lr": 0.00019274154176851242, "gradient_norm": 0.3499651551246643, "tokens_per_second": 1081054.486628766, "synthetic": false, "world_size": 8} {"step": 10060, "tokens": 2637168640, "loss": 2.3863210678100586, "optimizer_updates": 6030, "effective_batch": 512, "lr": 0.0001927122561433396, "gradient_norm": 0.31145673990249634, "tokens_per_second": 1079658.7571923973, "synthetic": false, "world_size": 8} {"step": 10080, "tokens": 2642411520, "loss": 2.3873939514160156, "optimizer_updates": 6040, "effective_batch": 512, "lr": 0.00019268291405052216, "gradient_norm": 0.28810232877731323, "tokens_per_second": 1078556.7194484062, "synthetic": false, "world_size": 8} {"step": 10100, "tokens": 2647654400, "loss": 2.3909275054931642, "optimizer_updates": 6050, "effective_batch": 512, "lr": 0.00019265351551009193, "gradient_norm": 0.30632612109184265, "tokens_per_second": 1082772.1992939203, "synthetic": false, "world_size": 8} {"step": 10120, "tokens": 2652897280, "loss": 2.3930410385131835, "optimizer_updates": 6060, "effective_batch": 512, "lr": 0.0001926240605421193, "gradient_norm": 0.3564566969871521, "tokens_per_second": 1090902.713746235, "synthetic": false, "world_size": 8} {"step": 10140, "tokens": 2658140160, "loss": 2.3956565856933594, "optimizer_updates": 6070, "effective_batch": 512, "lr": 0.00019259454916671311, "gradient_norm": 0.4076920747756958, "tokens_per_second": 765085.6814865689, "synthetic": false, "world_size": 8} {"step": 10160, "tokens": 2663383040, "loss": 2.38726806640625, "optimizer_updates": 6080, "effective_batch": 512, "lr": 0.00019256498140402087, "gradient_norm": 0.3674609363079071, "tokens_per_second": 1086848.7066352558, "synthetic": false, "world_size": 8} {"step": 10180, "tokens": 2668625920, "loss": 2.395906448364258, "optimizer_updates": 6090, "effective_batch": 512, "lr": 0.00019253535727422843, "gradient_norm": 0.2678608298301697, "tokens_per_second": 1082029.3359829127, "synthetic": false, "world_size": 8} {"step": 10200, "tokens": 2673868800, "loss": 2.388737106323242, "optimizer_updates": 6100, "effective_batch": 512, "lr": 0.00019250567679756018, "gradient_norm": 0.3893381357192993, "tokens_per_second": 1074649.4970858612, "synthetic": false, "world_size": 8} {"step": 10220, "tokens": 2679111680, "loss": 2.392924118041992, "optimizer_updates": 6110, "effective_batch": 512, "lr": 0.000192475939994279, "gradient_norm": 0.2807143032550812, "tokens_per_second": 1073114.8404366225, "synthetic": false, "world_size": 8} {"step": 10240, "tokens": 2684354560, "loss": 2.394382095336914, "optimizer_updates": 6120, "effective_batch": 512, "lr": 0.00019244614688468617, "gradient_norm": 0.2558378577232361, "tokens_per_second": 1073932.2879103327, "synthetic": false, "world_size": 8} {"step": 10260, "tokens": 2689597440, "loss": 2.3776674270629883, "optimizer_updates": 6130, "effective_batch": 512, "lr": 0.00019241629748912147, "gradient_norm": 0.26080262660980225, "tokens_per_second": 1078022.7839710312, "synthetic": false, "world_size": 8} {"step": 10280, "tokens": 2694840320, "loss": 2.405781555175781, "optimizer_updates": 6140, "effective_batch": 512, "lr": 0.00019238639182796304, "gradient_norm": 0.2713005840778351, "tokens_per_second": 1085903.1205429377, "synthetic": false, "world_size": 8} {"step": 10300, "tokens": 2700083200, "loss": 2.389243507385254, "optimizer_updates": 6150, "effective_batch": 512, "lr": 0.00019235642992162754, "gradient_norm": 0.2810785174369812, "tokens_per_second": 1072019.2194464896, "synthetic": false, "world_size": 8} {"step": 10320, "tokens": 2705326080, "loss": 2.3979862213134764, "optimizer_updates": 6160, "effective_batch": 512, "lr": 0.0001923264117905699, "gradient_norm": 0.2951488196849823, "tokens_per_second": 1078961.6900004586, "synthetic": false, "world_size": 8} {"step": 10340, "tokens": 2710568960, "loss": 2.385090637207031, "optimizer_updates": 6170, "effective_batch": 512, "lr": 0.0001922963374552835, "gradient_norm": 0.35433465242385864, "tokens_per_second": 1075983.5524645757, "synthetic": false, "world_size": 8} {"step": 10360, "tokens": 2715811840, "loss": 2.4004011154174805, "optimizer_updates": 6180, "effective_batch": 512, "lr": 0.00019226620693630006, "gradient_norm": 0.4022766351699829, "tokens_per_second": 1068938.1622050276, "synthetic": false, "world_size": 8} {"step": 10380, "tokens": 2721054720, "loss": 2.3912097930908205, "optimizer_updates": 6190, "effective_batch": 512, "lr": 0.00019223602025418974, "gradient_norm": 0.2891143262386322, "tokens_per_second": 1079751.7756036546, "synthetic": false, "world_size": 8} {"step": 10400, "tokens": 2726297600, "loss": 2.3939022064208983, "optimizer_updates": 6200, "effective_batch": 512, "lr": 0.000192205777429561, "gradient_norm": 0.3266652524471283, "tokens_per_second": 1071739.7149347938, "synthetic": false, "world_size": 8} {"step": 10420, "tokens": 2731540480, "loss": 2.3865243911743166, "optimizer_updates": 6210, "effective_batch": 512, "lr": 0.00019217547848306051, "gradient_norm": 0.29840490221977234, "tokens_per_second": 1071590.2322385402, "synthetic": false, "world_size": 8} {"step": 10440, "tokens": 2736783360, "loss": 2.390354347229004, "optimizer_updates": 6220, "effective_batch": 512, "lr": 0.00019214512343537342, "gradient_norm": 0.29386407136917114, "tokens_per_second": 1077927.624947908, "synthetic": false, "world_size": 8} {"step": 10460, "tokens": 2742026240, "loss": 2.391864013671875, "optimizer_updates": 6230, "effective_batch": 512, "lr": 0.00019211471230722314, "gradient_norm": 0.2576778829097748, "tokens_per_second": 1069596.7216719298, "synthetic": false, "world_size": 8} {"step": 10480, "tokens": 2747269120, "loss": 2.3883922576904295, "optimizer_updates": 6240, "effective_batch": 512, "lr": 0.0001920842451193713, "gradient_norm": 0.2733248472213745, "tokens_per_second": 1072202.7578469284, "synthetic": false, "world_size": 8} {"step": 10500, "tokens": 2752512000, "loss": 2.3936973571777345, "optimizer_updates": 6250, "effective_batch": 512, "lr": 0.00019205372189261787, "gradient_norm": 0.41731172800064087, "tokens_per_second": 1084011.7137606132, "synthetic": false, "world_size": 8} {"step": 10520, "tokens": 2757754880, "loss": 2.398428726196289, "optimizer_updates": 6260, "effective_batch": 512, "lr": 0.000192023142647801, "gradient_norm": 0.256709486246109, "tokens_per_second": 1079008.4365950397, "synthetic": false, "world_size": 8} {"step": 10540, "tokens": 2762997760, "loss": 2.3993091583251953, "optimizer_updates": 6270, "effective_batch": 512, "lr": 0.00019199250740579722, "gradient_norm": 0.28281280398368835, "tokens_per_second": 1073282.5737260517, "synthetic": false, "world_size": 8} {"step": 10560, "tokens": 2768240640, "loss": 2.4094032287597655, "optimizer_updates": 6280, "effective_batch": 512, "lr": 0.00019196181618752112, "gradient_norm": 0.3429691791534424, "tokens_per_second": 1081643.2246043945, "synthetic": false, "world_size": 8} {"step": 10580, "tokens": 2773483520, "loss": 2.3957635879516603, "optimizer_updates": 6290, "effective_batch": 512, "lr": 0.00019193106901392568, "gradient_norm": 0.47463297843933105, "tokens_per_second": 1088037.1624660161, "synthetic": false, "world_size": 8} {"step": 10600, "tokens": 2778726400, "loss": 2.399154281616211, "optimizer_updates": 6300, "effective_batch": 512, "lr": 0.0001919002659060019, "gradient_norm": 0.32078805565834045, "tokens_per_second": 726887.5360469732, "synthetic": false, "world_size": 8} {"step": 10620, "tokens": 2783969280, "loss": 2.389419364929199, "optimizer_updates": 6310, "effective_batch": 512, "lr": 0.00019186940688477913, "gradient_norm": 0.2621883451938629, "tokens_per_second": 1083487.2274374748, "synthetic": false, "world_size": 8} {"step": 10640, "tokens": 2789212160, "loss": 2.3907358169555666, "optimizer_updates": 6320, "effective_batch": 512, "lr": 0.00019183849197132476, "gradient_norm": 0.2727360427379608, "tokens_per_second": 1080014.0684075614, "synthetic": false, "world_size": 8} {"step": 10660, "tokens": 2794455040, "loss": 2.399557113647461, "optimizer_updates": 6330, "effective_batch": 512, "lr": 0.00019180752118674443, "gradient_norm": 0.24050450325012207, "tokens_per_second": 1084156.1977996265, "synthetic": false, "world_size": 8} {"step": 10680, "tokens": 2799697920, "loss": 2.37747802734375, "optimizer_updates": 6340, "effective_batch": 512, "lr": 0.0001917764945521819, "gradient_norm": 0.2553296983242035, "tokens_per_second": 759872.3555665761, "synthetic": false, "world_size": 8} {"step": 10700, "tokens": 2804940800, "loss": 2.398075294494629, "optimizer_updates": 6350, "effective_batch": 512, "lr": 0.00019174541208881902, "gradient_norm": 0.30305418372154236, "tokens_per_second": 1067008.8949296167, "synthetic": false, "world_size": 8} {"step": 10720, "tokens": 2810183680, "loss": 2.406041717529297, "optimizer_updates": 6360, "effective_batch": 512, "lr": 0.00019171427381787576, "gradient_norm": 0.2663538157939911, "tokens_per_second": 1067236.0301017752, "synthetic": false, "world_size": 8} {"step": 10740, "tokens": 2815426560, "loss": 2.390765571594238, "optimizer_updates": 6370, "effective_batch": 512, "lr": 0.0001916830797606103, "gradient_norm": 0.44601932168006897, "tokens_per_second": 1059899.0167309975, "synthetic": false, "world_size": 8} {"step": 10760, "tokens": 2820669440, "loss": 2.3953123092651367, "optimizer_updates": 6380, "effective_batch": 512, "lr": 0.0001916518299383188, "gradient_norm": 0.3006560802459717, "tokens_per_second": 1067134.1257704883, "synthetic": false, "world_size": 8} {"step": 10780, "tokens": 2825912320, "loss": 2.3918212890625, "optimizer_updates": 6390, "effective_batch": 512, "lr": 0.0001916205243723354, "gradient_norm": 0.34893685579299927, "tokens_per_second": 1084153.2596077821, "synthetic": false, "world_size": 8} {"step": 10800, "tokens": 2831155200, "loss": 2.4020919799804688, "optimizer_updates": 6400, "effective_batch": 512, "lr": 0.0001915891630840325, "gradient_norm": 0.3268541991710663, "tokens_per_second": 1080750.14984844, "synthetic": false, "world_size": 8} {"step": 10820, "tokens": 2836398080, "loss": 2.3999874114990236, "optimizer_updates": 6410, "effective_batch": 512, "lr": 0.00019155774609482047, "gradient_norm": 0.24324452877044678, "tokens_per_second": 766588.4018290789, "synthetic": false, "world_size": 8} {"step": 10840, "tokens": 2841640960, "loss": 2.4007699966430662, "optimizer_updates": 6420, "effective_batch": 512, "lr": 0.0001915262734261476, "gradient_norm": 0.2590756118297577, "tokens_per_second": 1075707.0713399558, "synthetic": false, "world_size": 8} {"step": 10860, "tokens": 2846883840, "loss": 2.3994895935058596, "optimizer_updates": 6430, "effective_batch": 512, "lr": 0.0001914947450995003, "gradient_norm": 0.4087420701980591, "tokens_per_second": 1073643.3365736464, "synthetic": false, "world_size": 8} {"step": 10880, "tokens": 2852126720, "loss": 2.3973913192749023, "optimizer_updates": 6440, "effective_batch": 512, "lr": 0.00019146316113640303, "gradient_norm": 0.3098648488521576, "tokens_per_second": 1030046.5197264658, "synthetic": false, "world_size": 8} {"step": 10900, "tokens": 2857369600, "loss": 2.407391357421875, "optimizer_updates": 6450, "effective_batch": 512, "lr": 0.00019143152155841805, "gradient_norm": 0.33116939663887024, "tokens_per_second": 1070037.5103594118, "synthetic": false, "world_size": 8} {"step": 10920, "tokens": 2862612480, "loss": 2.3869451522827148, "optimizer_updates": 6460, "effective_batch": 512, "lr": 0.00019139982638714575, "gradient_norm": 0.32708820700645447, "tokens_per_second": 1082392.4296729497, "synthetic": false, "world_size": 8} {"step": 10940, "tokens": 2867855360, "loss": 2.4026769638061523, "optimizer_updates": 6470, "effective_batch": 512, "lr": 0.00019136807564422442, "gradient_norm": 0.2574533522129059, "tokens_per_second": 1082521.0105399233, "synthetic": false, "world_size": 8} {"step": 10960, "tokens": 2873098240, "loss": 2.4029367446899412, "optimizer_updates": 6480, "effective_batch": 512, "lr": 0.0001913362693513303, "gradient_norm": 0.39710670709609985, "tokens_per_second": 987446.7927958535, "synthetic": false, "world_size": 8} {"step": 10980, "tokens": 2878341120, "loss": 2.383078765869141, "optimizer_updates": 6490, "effective_batch": 512, "lr": 0.0001913044075301775, "gradient_norm": 0.2709159553050995, "tokens_per_second": 1085425.8579351616, "synthetic": false, "world_size": 8} {"step": 11000, "tokens": 2883584000, "loss": 2.3970556259155273, "optimizer_updates": 6500, "effective_batch": 512, "lr": 0.00019127249020251807, "gradient_norm": 0.27784839272499084, "tokens_per_second": 1087637.7470318524, "synthetic": false, "world_size": 8} {"step": 11020, "tokens": 2888826880, "loss": 2.3799039840698244, "optimizer_updates": 6510, "effective_batch": 512, "lr": 0.00019124051739014203, "gradient_norm": 0.26372140645980835, "tokens_per_second": 841196.3593528951, "synthetic": false, "world_size": 8} {"step": 11040, "tokens": 2894069760, "loss": 2.4039947509765627, "optimizer_updates": 6520, "effective_batch": 512, "lr": 0.00019120848911487718, "gradient_norm": 0.39861372113227844, "tokens_per_second": 1080839.135314858, "synthetic": false, "world_size": 8} {"step": 11060, "tokens": 2899312640, "loss": 2.401116943359375, "optimizer_updates": 6530, "effective_batch": 512, "lr": 0.00019117640539858922, "gradient_norm": 0.39576759934425354, "tokens_per_second": 1081047.7704517008, "synthetic": false, "world_size": 8} {"step": 11080, "tokens": 2904555520, "loss": 2.4016672134399415, "optimizer_updates": 6540, "effective_batch": 512, "lr": 0.0001911442662631817, "gradient_norm": 0.3129770755767822, "tokens_per_second": 1083150.467964942, "synthetic": false, "world_size": 8} {"step": 11100, "tokens": 2909798400, "loss": 2.4078342437744142, "optimizer_updates": 6550, "effective_batch": 512, "lr": 0.000191112071730596, "gradient_norm": 0.5917227864265442, "tokens_per_second": 1074439.951393995, "synthetic": false, "world_size": 8} {"step": 11120, "tokens": 2915041280, "loss": 2.405833435058594, "optimizer_updates": 6560, "effective_batch": 512, "lr": 0.00019107982182281128, "gradient_norm": 0.47208672761917114, "tokens_per_second": 1082773.8140348152, "synthetic": false, "world_size": 8} {"step": 11140, "tokens": 2920284160, "loss": 2.4051748275756837, "optimizer_updates": 6570, "effective_batch": 512, "lr": 0.00019104751656184464, "gradient_norm": 0.3093683421611786, "tokens_per_second": 1086881.210571559, "synthetic": false, "world_size": 8} {"step": 11160, "tokens": 2925527040, "loss": 2.39865779876709, "optimizer_updates": 6580, "effective_batch": 512, "lr": 0.0001910151559697508, "gradient_norm": 0.29828372597694397, "tokens_per_second": 1076982.4744502504, "synthetic": false, "world_size": 8} {"step": 11180, "tokens": 2930769920, "loss": 2.3871929168701174, "optimizer_updates": 6590, "effective_batch": 512, "lr": 0.00019098274006862235, "gradient_norm": 0.32915589213371277, "tokens_per_second": 1083110.301974965, "synthetic": false, "world_size": 8} {"step": 11200, "tokens": 2936012800, "loss": 2.393580436706543, "optimizer_updates": 6600, "effective_batch": 512, "lr": 0.00019095026888058965, "gradient_norm": 0.27868613600730896, "tokens_per_second": 1084809.0676245713, "synthetic": false, "world_size": 8} {"step": 11220, "tokens": 2941255680, "loss": 2.393860626220703, "optimizer_updates": 6610, "effective_batch": 512, "lr": 0.00019091774242782075, "gradient_norm": 0.35031962394714355, "tokens_per_second": 1080552.4528992488, "synthetic": false, "world_size": 8} {"step": 11240, "tokens": 2946498560, "loss": 2.3889942169189453, "optimizer_updates": 6620, "effective_batch": 512, "lr": 0.00019088516073252144, "gradient_norm": 0.2750079035758972, "tokens_per_second": 1082339.0474884282, "synthetic": false, "world_size": 8} {"step": 11260, "tokens": 2951741440, "loss": 2.3878015518188476, "optimizer_updates": 6630, "effective_batch": 512, "lr": 0.00019085252381693526, "gradient_norm": 0.2809862494468689, "tokens_per_second": 1085168.79641018, "synthetic": false, "world_size": 8} {"step": 11280, "tokens": 2956984320, "loss": 2.390361785888672, "optimizer_updates": 6640, "effective_batch": 512, "lr": 0.00019081983170334343, "gradient_norm": 0.3490244448184967, "tokens_per_second": 1074395.8109472042, "synthetic": false, "world_size": 8} {"step": 11300, "tokens": 2962227200, "loss": 2.3959850311279296, "optimizer_updates": 6650, "effective_batch": 512, "lr": 0.00019078708441406484, "gradient_norm": 0.38715028762817383, "tokens_per_second": 1086773.4270646402, "synthetic": false, "world_size": 8} {"step": 11320, "tokens": 2967470080, "loss": 2.3911985397338866, "optimizer_updates": 6660, "effective_batch": 512, "lr": 0.00019075428197145607, "gradient_norm": 0.32563334703445435, "tokens_per_second": 1086260.9950728456, "synthetic": false, "world_size": 8} {"step": 11340, "tokens": 2972712960, "loss": 2.3952747344970704, "optimizer_updates": 6670, "effective_batch": 512, "lr": 0.00019072142439791135, "gradient_norm": 0.27564042806625366, "tokens_per_second": 1080270.4412126536, "synthetic": false, "world_size": 8} {"step": 11360, "tokens": 2977955840, "loss": 2.3958850860595704, "optimizer_updates": 6680, "effective_batch": 512, "lr": 0.00019068851171586247, "gradient_norm": 0.32375437021255493, "tokens_per_second": 1078679.8106218704, "synthetic": false, "world_size": 8} {"step": 11380, "tokens": 2983198720, "loss": 2.3826038360595705, "optimizer_updates": 6690, "effective_batch": 512, "lr": 0.00019065554394777901, "gradient_norm": 0.3493642508983612, "tokens_per_second": 1093490.50212727, "synthetic": false, "world_size": 8} {"step": 11400, "tokens": 2988441600, "loss": 2.385450744628906, "optimizer_updates": 6700, "effective_batch": 512, "lr": 0.00019062252111616803, "gradient_norm": 0.3753660321235657, "tokens_per_second": 1082688.7021361445, "synthetic": false, "world_size": 8} {"step": 11420, "tokens": 2993684480, "loss": 2.39696044921875, "optimizer_updates": 6710, "effective_batch": 512, "lr": 0.00019058944324357418, "gradient_norm": 0.29922863841056824, "tokens_per_second": 1085966.6699226915, "synthetic": false, "world_size": 8} {"step": 11440, "tokens": 2998927360, "loss": 2.390297508239746, "optimizer_updates": 6720, "effective_batch": 512, "lr": 0.00019055631035257975, "gradient_norm": 0.2952173352241516, "tokens_per_second": 1088763.7498772277, "synthetic": false, "world_size": 8} {"step": 11460, "tokens": 3004170240, "loss": 2.3835451126098635, "optimizer_updates": 6730, "effective_batch": 512, "lr": 0.00019052312246580454, "gradient_norm": 0.2754843533039093, "tokens_per_second": 1085092.8411713482, "synthetic": false, "world_size": 8} {"step": 11480, "tokens": 3009413120, "loss": 2.3827583312988283, "optimizer_updates": 6740, "effective_batch": 512, "lr": 0.00019048987960590592, "gradient_norm": 0.2440820038318634, "tokens_per_second": 1088331.5825427463, "synthetic": false, "world_size": 8} {"step": 11500, "tokens": 3014656000, "loss": 2.4030874252319334, "optimizer_updates": 6750, "effective_batch": 512, "lr": 0.00019045658179557882, "gradient_norm": 0.5409376621246338, "tokens_per_second": 1086330.3781140365, "synthetic": false, "world_size": 8} {"step": 11520, "tokens": 3019898880, "loss": 2.389718437194824, "optimizer_updates": 6760, "effective_batch": 512, "lr": 0.00019042322905755559, "gradient_norm": 0.31075355410575867, "tokens_per_second": 1081035.0777368085, "synthetic": false, "world_size": 8} {"step": 11540, "tokens": 3025141760, "loss": 2.394654083251953, "optimizer_updates": 6770, "effective_batch": 512, "lr": 0.00019038982141460616, "gradient_norm": 0.2884260416030884, "tokens_per_second": 1087273.8180863278, "synthetic": false, "world_size": 8} {"step": 11560, "tokens": 3030384640, "loss": 2.388075065612793, "optimizer_updates": 6780, "effective_batch": 512, "lr": 0.000190356358889538, "gradient_norm": 0.29409992694854736, "tokens_per_second": 1085187.1898285847, "synthetic": false, "world_size": 8} {"step": 11580, "tokens": 3035627520, "loss": 2.387080764770508, "optimizer_updates": 6790, "effective_batch": 512, "lr": 0.00019032284150519583, "gradient_norm": 0.2632215619087219, "tokens_per_second": 1090820.3200701245, "synthetic": false, "world_size": 8} {"step": 11600, "tokens": 3040870400, "loss": 2.3937955856323243, "optimizer_updates": 6800, "effective_batch": 512, "lr": 0.00019028926928446206, "gradient_norm": 0.4526060223579407, "tokens_per_second": 1081174.9297650808, "synthetic": false, "world_size": 8} {"step": 11620, "tokens": 3046113280, "loss": 2.3997488021850586, "optimizer_updates": 6810, "effective_batch": 512, "lr": 0.0001902556422502564, "gradient_norm": 0.38708555698394775, "tokens_per_second": 1090028.2346507378, "synthetic": false, "world_size": 8} {"step": 11640, "tokens": 3051356160, "loss": 2.3839189529418947, "optimizer_updates": 6820, "effective_batch": 512, "lr": 0.00019022196042553608, "gradient_norm": 0.250175803899765, "tokens_per_second": 1087078.3285272985, "synthetic": false, "world_size": 8} {"step": 11660, "tokens": 3056599040, "loss": 2.3962936401367188, "optimizer_updates": 6830, "effective_batch": 512, "lr": 0.00019018822383329558, "gradient_norm": 0.34462523460388184, "tokens_per_second": 773906.0181991244, "synthetic": false, "world_size": 8} {"step": 11680, "tokens": 3061841920, "loss": 2.386645698547363, "optimizer_updates": 6840, "effective_batch": 512, "lr": 0.00019015443249656698, "gradient_norm": 0.30489134788513184, "tokens_per_second": 764488.4466228513, "synthetic": false, "world_size": 8} {"step": 11700, "tokens": 3067084800, "loss": 2.3853641510009767, "optimizer_updates": 6850, "effective_batch": 512, "lr": 0.0001901205864384195, "gradient_norm": 0.3411217927932739, "tokens_per_second": 1079126.475866903, "synthetic": false, "world_size": 8} {"step": 11720, "tokens": 3072327680, "loss": 2.3940013885498046, "optimizer_updates": 6860, "effective_batch": 512, "lr": 0.00019008668568195995, "gradient_norm": 0.31015729904174805, "tokens_per_second": 1073548.9996771286, "synthetic": false, "world_size": 8} {"step": 11740, "tokens": 3077570560, "loss": 2.385579490661621, "optimizer_updates": 6870, "effective_batch": 512, "lr": 0.00019005273025033228, "gradient_norm": 0.3631921410560608, "tokens_per_second": 1076190.226530477, "synthetic": false, "world_size": 8} {"step": 11760, "tokens": 3082813440, "loss": 2.3959514617919924, "optimizer_updates": 6880, "effective_batch": 512, "lr": 0.00019001872016671792, "gradient_norm": 0.34700649976730347, "tokens_per_second": 1078669.3924576358, "synthetic": false, "world_size": 8} {"step": 11780, "tokens": 3088056320, "loss": 2.3890609741210938, "optimizer_updates": 6890, "effective_batch": 512, "lr": 0.0001899846554543355, "gradient_norm": 0.3295591175556183, "tokens_per_second": 1079013.7153150477, "synthetic": false, "world_size": 8} {"step": 11800, "tokens": 3093299200, "loss": 2.3877283096313477, "optimizer_updates": 6900, "effective_batch": 512, "lr": 0.00018995053613644108, "gradient_norm": 0.29105886816978455, "tokens_per_second": 1071187.3415953377, "synthetic": false, "world_size": 8} {"step": 11820, "tokens": 3098542080, "loss": 2.3825382232666015, "optimizer_updates": 6910, "effective_batch": 512, "lr": 0.0001899163622363278, "gradient_norm": 0.29648756980895996, "tokens_per_second": 1073046.1634094487, "synthetic": false, "world_size": 8} {"step": 11840, "tokens": 3103784960, "loss": 2.3975366592407226, "optimizer_updates": 6920, "effective_batch": 512, "lr": 0.00018988213377732623, "gradient_norm": 0.2913408577442169, "tokens_per_second": 1081688.0757213992, "synthetic": false, "world_size": 8} {"step": 11860, "tokens": 3109027840, "loss": 2.3928924560546876, "optimizer_updates": 6930, "effective_batch": 512, "lr": 0.00018984785078280417, "gradient_norm": 0.30172544717788696, "tokens_per_second": 1083211.81386613, "synthetic": false, "world_size": 8} {"step": 11880, "tokens": 3114270720, "loss": 2.4007097244262696, "optimizer_updates": 6940, "effective_batch": 512, "lr": 0.0001898135132761666, "gradient_norm": 0.25690770149230957, "tokens_per_second": 1089309.6034500813, "synthetic": false, "world_size": 8} {"step": 11900, "tokens": 3119513600, "loss": 2.3947027206420897, "optimizer_updates": 6950, "effective_batch": 512, "lr": 0.00018977912128085567, "gradient_norm": 0.24762360751628876, "tokens_per_second": 1087351.0310667213, "synthetic": false, "world_size": 8} {"step": 11920, "tokens": 3124756480, "loss": 2.3875850677490233, "optimizer_updates": 6960, "effective_batch": 512, "lr": 0.0001897446748203508, "gradient_norm": 0.25578591227531433, "tokens_per_second": 1077501.5340603369, "synthetic": false, "world_size": 8} {"step": 11940, "tokens": 3129999360, "loss": 2.4007720947265625, "optimizer_updates": 6970, "effective_batch": 512, "lr": 0.00018971017391816866, "gradient_norm": 0.3199092447757721, "tokens_per_second": 1081882.8117805333, "synthetic": false, "world_size": 8} {"step": 11960, "tokens": 3135242240, "loss": 2.393507957458496, "optimizer_updates": 6980, "effective_batch": 512, "lr": 0.00018967561859786297, "gradient_norm": 0.3659023642539978, "tokens_per_second": 1091073.8617673141, "synthetic": false, "world_size": 8} {"step": 11980, "tokens": 3140485120, "loss": 2.407205581665039, "optimizer_updates": 6990, "effective_batch": 512, "lr": 0.0001896410088830246, "gradient_norm": 0.2768135666847229, "tokens_per_second": 1080996.1735380765, "synthetic": false, "world_size": 8} {"step": 12000, "tokens": 3145728000, "loss": 2.3877685546875, "optimizer_updates": 7000, "effective_batch": 512, "lr": 0.00018960634479728164, "gradient_norm": 0.32061833143234253, "tokens_per_second": 1077824.830227891, "synthetic": false, "world_size": 8} {"step": 12020, "tokens": 3150970880, "loss": 2.3956684112548827, "optimizer_updates": 7010, "effective_batch": 512, "lr": 0.00018957162636429927, "gradient_norm": 0.29091691970825195, "tokens_per_second": 833137.2322635698, "synthetic": false, "world_size": 8} {"step": 12040, "tokens": 3156213760, "loss": 2.3974504470825195, "optimizer_updates": 7020, "effective_batch": 512, "lr": 0.00018953685360777973, "gradient_norm": 0.32986027002334595, "tokens_per_second": 1079196.9652720639, "synthetic": false, "world_size": 8} {"step": 12060, "tokens": 3161456640, "loss": 2.394356918334961, "optimizer_updates": 7030, "effective_batch": 512, "lr": 0.00018950202655146237, "gradient_norm": 0.2631206512451172, "tokens_per_second": 1082084.4197724233, "synthetic": false, "world_size": 8} {"step": 12080, "tokens": 3166699520, "loss": 2.4017091751098634, "optimizer_updates": 7040, "effective_batch": 512, "lr": 0.00018946714521912364, "gradient_norm": 0.3378404974937439, "tokens_per_second": 1066075.2629572477, "synthetic": false, "world_size": 8} {"step": 12100, "tokens": 3171942400, "loss": 2.3854740142822264, "optimizer_updates": 7050, "effective_batch": 512, "lr": 0.00018943220963457702, "gradient_norm": 0.5001056790351868, "tokens_per_second": 1072652.3360023012, "synthetic": false, "world_size": 8} {"step": 12120, "tokens": 3177185280, "loss": 2.3962697982788086, "optimizer_updates": 7060, "effective_batch": 512, "lr": 0.000189397219821673, "gradient_norm": 0.304232120513916, "tokens_per_second": 1067380.7752903455, "synthetic": false, "world_size": 8} {"step": 12140, "tokens": 3182428160, "loss": 2.3897777557373048, "optimizer_updates": 7070, "effective_batch": 512, "lr": 0.00018936217580429915, "gradient_norm": 0.32460108399391174, "tokens_per_second": 1072698.0239110496, "synthetic": false, "world_size": 8} {"step": 12160, "tokens": 3187671040, "loss": 2.3905569076538087, "optimizer_updates": 7080, "effective_batch": 512, "lr": 0.00018932707760638, "gradient_norm": 0.2511589527130127, "tokens_per_second": 1076691.3571813363, "synthetic": false, "world_size": 8} {"step": 12180, "tokens": 3192913920, "loss": 2.39556884765625, "optimizer_updates": 7090, "effective_batch": 512, "lr": 0.00018929192525187708, "gradient_norm": 0.3180333971977234, "tokens_per_second": 1078201.7496787128, "synthetic": false, "world_size": 8} {"step": 12200, "tokens": 3198156800, "loss": 2.3980804443359376, "optimizer_updates": 7100, "effective_batch": 512, "lr": 0.00018925671876478893, "gradient_norm": 0.4492955803871155, "tokens_per_second": 1078327.1730939401, "synthetic": false, "world_size": 8} {"step": 12220, "tokens": 3203399680, "loss": 2.4010677337646484, "optimizer_updates": 7110, "effective_batch": 512, "lr": 0.00018922145816915094, "gradient_norm": 0.30106136202812195, "tokens_per_second": 763162.0986549244, "synthetic": false, "world_size": 8} {"step": 12240, "tokens": 3208642560, "loss": 2.4025177001953124, "optimizer_updates": 7120, "effective_batch": 512, "lr": 0.0001891861434890356, "gradient_norm": 0.32913362979888916, "tokens_per_second": 1082980.620224654, "synthetic": false, "world_size": 8} {"step": 12260, "tokens": 3213885440, "loss": 2.3919692993164063, "optimizer_updates": 7130, "effective_batch": 512, "lr": 0.0001891507747485522, "gradient_norm": 0.31005963683128357, "tokens_per_second": 1076093.8228076587, "synthetic": false, "world_size": 8} {"step": 12280, "tokens": 3219128320, "loss": 2.3875139236450194, "optimizer_updates": 7140, "effective_batch": 512, "lr": 0.00018911535197184694, "gradient_norm": 0.31991565227508545, "tokens_per_second": 1080139.707087382, "synthetic": false, "world_size": 8} {"step": 12300, "tokens": 3224371200, "loss": 2.3862064361572264, "optimizer_updates": 7150, "effective_batch": 512, "lr": 0.00018907987518310303, "gradient_norm": 0.28225284814834595, "tokens_per_second": 1078873.9622507652, "synthetic": false, "world_size": 8} {"step": 12320, "tokens": 3229614080, "loss": 2.410198211669922, "optimizer_updates": 7160, "effective_batch": 512, "lr": 0.00018904434440654037, "gradient_norm": 0.26571789383888245, "tokens_per_second": 1078468.1408740107, "synthetic": false, "world_size": 8} {"step": 12340, "tokens": 3234856960, "loss": 2.390116882324219, "optimizer_updates": 7170, "effective_batch": 512, "lr": 0.00018900875966641588, "gradient_norm": 0.29313576221466064, "tokens_per_second": 780397.1447491716, "synthetic": false, "world_size": 8} {"step": 12360, "tokens": 3240099840, "loss": 2.3921194076538086, "optimizer_updates": 7180, "effective_batch": 512, "lr": 0.00018897312098702324, "gradient_norm": 0.26301923394203186, "tokens_per_second": 1081640.2057954082, "synthetic": false, "world_size": 8} {"step": 12380, "tokens": 3245342720, "loss": 2.381418991088867, "optimizer_updates": 7190, "effective_batch": 512, "lr": 0.00018893742839269293, "gradient_norm": 0.3135789632797241, "tokens_per_second": 1074521.1286526495, "synthetic": false, "world_size": 8} {"step": 12400, "tokens": 3250585600, "loss": 2.399422836303711, "optimizer_updates": 7200, "effective_batch": 512, "lr": 0.00018890168190779236, "gradient_norm": 0.36441245675086975, "tokens_per_second": 1081194.198997159, "synthetic": false, "world_size": 8} {"step": 12420, "tokens": 3255828480, "loss": 2.3900428771972657, "optimizer_updates": 7210, "effective_batch": 512, "lr": 0.00018886588155672557, "gradient_norm": 0.29129311442375183, "tokens_per_second": 1067206.1122976502, "synthetic": false, "world_size": 8} {"step": 12440, "tokens": 3261071360, "loss": 2.398511505126953, "optimizer_updates": 7220, "effective_batch": 512, "lr": 0.00018883002736393349, "gradient_norm": 0.34780198335647583, "tokens_per_second": 1081458.4776052255, "synthetic": false, "world_size": 8} {"step": 12460, "tokens": 3266314240, "loss": 2.3831417083740236, "optimizer_updates": 7230, "effective_batch": 512, "lr": 0.00018879411935389382, "gradient_norm": 0.3269995152950287, "tokens_per_second": 1077499.8078874808, "synthetic": false, "world_size": 8} {"step": 12480, "tokens": 3271557120, "loss": 2.4000009536743163, "optimizer_updates": 7240, "effective_batch": 512, "lr": 0.00018875815755112086, "gradient_norm": 0.26717203855514526, "tokens_per_second": 1078917.0457931585, "synthetic": false, "world_size": 8} {"step": 12500, "tokens": 3276800000, "loss": 2.3945896148681642, "optimizer_updates": 7250, "effective_batch": 512, "lr": 0.0001887221419801658, "gradient_norm": 0.33733150362968445, "tokens_per_second": 1086317.196170291, "synthetic": false, "world_size": 8} {"step": 12520, "tokens": 3282042880, "loss": 2.4030269622802733, "optimizer_updates": 7260, "effective_batch": 512, "lr": 0.00018868607266561642, "gradient_norm": 0.26063400506973267, "tokens_per_second": 1076339.0602147277, "synthetic": false, "world_size": 8} {"step": 12540, "tokens": 3287285760, "loss": 2.3892423629760744, "optimizer_updates": 7270, "effective_batch": 512, "lr": 0.00018864994963209726, "gradient_norm": 0.35699769854545593, "tokens_per_second": 1075317.0281671379, "synthetic": false, "world_size": 8} {"step": 12560, "tokens": 3292528640, "loss": 2.3934276580810545, "optimizer_updates": 7280, "effective_batch": 512, "lr": 0.0001886137729042695, "gradient_norm": 0.3143589496612549, "tokens_per_second": 1085493.611901802, "synthetic": false, "world_size": 8} {"step": 12580, "tokens": 3297771520, "loss": 2.3966583251953124, "optimizer_updates": 7290, "effective_batch": 512, "lr": 0.00018857754250683098, "gradient_norm": 0.2608412504196167, "tokens_per_second": 1078876.801752591, "synthetic": false, "world_size": 8} {"step": 12600, "tokens": 3303014400, "loss": 2.3978593826293944, "optimizer_updates": 7300, "effective_batch": 512, "lr": 0.0001885412584645162, "gradient_norm": 0.3170347809791565, "tokens_per_second": 1081907.5573396748, "synthetic": false, "world_size": 8} {"step": 12620, "tokens": 3308257280, "loss": 2.3994863510131834, "optimizer_updates": 7310, "effective_batch": 512, "lr": 0.00018850492080209626, "gradient_norm": 0.27530637383461, "tokens_per_second": 1089755.1393277587, "synthetic": false, "world_size": 8} {"step": 12640, "tokens": 3313500160, "loss": 2.385036659240723, "optimizer_updates": 7320, "effective_batch": 512, "lr": 0.0001884685295443789, "gradient_norm": 0.33372581005096436, "tokens_per_second": 1086340.589799935, "synthetic": false, "world_size": 8} {"step": 12660, "tokens": 3318743040, "loss": 2.3871133804321287, "optimizer_updates": 7330, "effective_batch": 512, "lr": 0.0001884320847162084, "gradient_norm": 0.43845507502555847, "tokens_per_second": 1071392.3375860888, "synthetic": false, "world_size": 8} {"step": 12680, "tokens": 3323985920, "loss": 2.392990493774414, "optimizer_updates": 7340, "effective_batch": 512, "lr": 0.00018839558634246563, "gradient_norm": 0.27105143666267395, "tokens_per_second": 1082997.390380405, "synthetic": false, "world_size": 8} {"step": 12700, "tokens": 3329228800, "loss": 2.3882896423339846, "optimizer_updates": 7350, "effective_batch": 512, "lr": 0.00018835903444806807, "gradient_norm": 0.2612197697162628, "tokens_per_second": 1071569.169289593, "synthetic": false, "world_size": 8} {"step": 12720, "tokens": 3334471680, "loss": 2.3884088516235353, "optimizer_updates": 7360, "effective_batch": 512, "lr": 0.00018832242905796964, "gradient_norm": 0.32720109820365906, "tokens_per_second": 1071725.9056611885, "synthetic": false, "world_size": 8} {"step": 12740, "tokens": 3339714560, "loss": 2.3767911911010744, "optimizer_updates": 7370, "effective_batch": 512, "lr": 0.00018828577019716088, "gradient_norm": 0.2801586389541626, "tokens_per_second": 1085457.6617588296, "synthetic": false, "world_size": 8} {"step": 12760, "tokens": 3344957440, "loss": 2.3849706649780273, "optimizer_updates": 7380, "effective_batch": 512, "lr": 0.00018824905789066877, "gradient_norm": 0.3898175358772278, "tokens_per_second": 1079046.181854573, "synthetic": false, "world_size": 8} {"step": 12780, "tokens": 3350200320, "loss": 2.387661361694336, "optimizer_updates": 7390, "effective_batch": 512, "lr": 0.00018821229216355677, "gradient_norm": 0.27363818883895874, "tokens_per_second": 1079906.4244360952, "synthetic": false, "world_size": 8} {"step": 12800, "tokens": 3355443200, "loss": 2.389677047729492, "optimizer_updates": 7400, "effective_batch": 512, "lr": 0.00018817547304092488, "gradient_norm": 0.2573050558567047, "tokens_per_second": 1073485.9059514264, "synthetic": false, "world_size": 8} {"step": 12820, "tokens": 3360686080, "loss": 2.3892927169799805, "optimizer_updates": 7410, "effective_batch": 512, "lr": 0.0001881386005479095, "gradient_norm": 0.26100555062294006, "tokens_per_second": 1084995.536517209, "synthetic": false, "world_size": 8} {"step": 12840, "tokens": 3365928960, "loss": 2.384502983093262, "optimizer_updates": 7420, "effective_batch": 512, "lr": 0.0001881016747096834, "gradient_norm": 0.295233815908432, "tokens_per_second": 1089272.5172795954, "synthetic": false, "world_size": 8} {"step": 12860, "tokens": 3371171840, "loss": 2.3927967071533205, "optimizer_updates": 7430, "effective_batch": 512, "lr": 0.00018806469555145594, "gradient_norm": 0.30531591176986694, "tokens_per_second": 790051.2178259111, "synthetic": false, "world_size": 8} {"step": 12880, "tokens": 3376414720, "loss": 2.383497619628906, "optimizer_updates": 7440, "effective_batch": 512, "lr": 0.00018802766309847279, "gradient_norm": 0.33203309774398804, "tokens_per_second": 1079014.309368494, "synthetic": false, "world_size": 8} {"step": 12900, "tokens": 3381657600, "loss": 2.376381492614746, "optimizer_updates": 7450, "effective_batch": 512, "lr": 0.00018799057737601592, "gradient_norm": 0.253694623708725, "tokens_per_second": 1080787.5164002674, "synthetic": false, "world_size": 8} {"step": 12920, "tokens": 3386900480, "loss": 2.390928840637207, "optimizer_updates": 7460, "effective_batch": 512, "lr": 0.0001879534384094038, "gradient_norm": 0.26253682374954224, "tokens_per_second": 1077736.367645323, "synthetic": false, "world_size": 8} {"step": 12940, "tokens": 3392143360, "loss": 2.389724349975586, "optimizer_updates": 7470, "effective_batch": 512, "lr": 0.00018791624622399122, "gradient_norm": 0.25417840480804443, "tokens_per_second": 1081748.7612552966, "synthetic": false, "world_size": 8} {"step": 12960, "tokens": 3397386240, "loss": 2.391812324523926, "optimizer_updates": 7480, "effective_batch": 512, "lr": 0.00018787900084516918, "gradient_norm": 0.28199321031570435, "tokens_per_second": 720646.8184498382, "synthetic": false, "world_size": 8} {"step": 12980, "tokens": 3402629120, "loss": 2.3951663970947266, "optimizer_updates": 7490, "effective_batch": 512, "lr": 0.00018784170229836522, "gradient_norm": 0.3154486417770386, "tokens_per_second": 990261.0928247841, "synthetic": false, "world_size": 8} {"step": 13000, "tokens": 3407872000, "loss": 2.3920974731445312, "optimizer_updates": 7500, "effective_batch": 512, "lr": 0.00018780435060904298, "gradient_norm": 0.27441954612731934, "tokens_per_second": 1078590.0098268758, "synthetic": false, "world_size": 8} {"step": 13020, "tokens": 3413114880, "loss": 2.391861152648926, "optimizer_updates": 7510, "effective_batch": 512, "lr": 0.00018776694580270248, "gradient_norm": 0.2639999985694885, "tokens_per_second": 844626.8533370313, "synthetic": false, "world_size": 8} {"step": 13040, "tokens": 3418357760, "loss": 2.390507698059082, "optimizer_updates": 7520, "effective_batch": 512, "lr": 0.00018772948790487994, "gradient_norm": 0.36428672075271606, "tokens_per_second": 1080911.4551424095, "synthetic": false, "world_size": 8} {"step": 13060, "tokens": 3423600640, "loss": 2.3893301010131838, "optimizer_updates": 7530, "effective_batch": 512, "lr": 0.00018769197694114788, "gradient_norm": 0.32379183173179626, "tokens_per_second": 1078875.8189289279, "synthetic": false, "world_size": 8} {"step": 13080, "tokens": 3428843520, "loss": 2.393930435180664, "optimizer_updates": 7540, "effective_batch": 512, "lr": 0.00018765441293711505, "gradient_norm": 0.3102536201477051, "tokens_per_second": 1080482.6812367644, "synthetic": false, "world_size": 8} {"step": 13100, "tokens": 3434086400, "loss": 2.3870590209960936, "optimizer_updates": 7550, "effective_batch": 512, "lr": 0.00018761679591842634, "gradient_norm": 0.414165198802948, "tokens_per_second": 1079771.5916426638, "synthetic": false, "world_size": 8} {"step": 13120, "tokens": 3439329280, "loss": 2.366392707824707, "optimizer_updates": 7560, "effective_batch": 512, "lr": 0.00018757912591076294, "gradient_norm": 0.2523617446422577, "tokens_per_second": 1091247.4529092673, "synthetic": false, "world_size": 8} {"step": 13140, "tokens": 3444572160, "loss": 2.383786201477051, "optimizer_updates": 7570, "effective_batch": 512, "lr": 0.00018754140293984214, "gradient_norm": 0.360199511051178, "tokens_per_second": 1095803.808810546, "synthetic": false, "world_size": 8} {"step": 13160, "tokens": 3449815040, "loss": 2.3823144912719725, "optimizer_updates": 7580, "effective_batch": 512, "lr": 0.00018750362703141737, "gradient_norm": 0.45556196570396423, "tokens_per_second": 1089255.6628981046, "synthetic": false, "world_size": 8} {"step": 13180, "tokens": 3455057920, "loss": 2.399328422546387, "optimizer_updates": 7590, "effective_batch": 512, "lr": 0.0001874657982112783, "gradient_norm": 0.2689400911331177, "tokens_per_second": 1096636.78320402, "synthetic": false, "world_size": 8} {"step": 13200, "tokens": 3460300800, "loss": 2.392593002319336, "optimizer_updates": 7600, "effective_batch": 512, "lr": 0.0001874279165052506, "gradient_norm": 0.32528817653656006, "tokens_per_second": 1099686.748460802, "synthetic": false, "world_size": 8} {"step": 13220, "tokens": 3465543680, "loss": 2.402349662780762, "optimizer_updates": 7610, "effective_batch": 512, "lr": 0.00018738998193919615, "gradient_norm": 0.3259202837944031, "tokens_per_second": 1098575.4414443665, "synthetic": false, "world_size": 8} {"step": 13240, "tokens": 3470786560, "loss": 2.4005359649658202, "optimizer_updates": 7620, "effective_batch": 512, "lr": 0.00018735199453901282, "gradient_norm": 0.25480785965919495, "tokens_per_second": 1089651.194600284, "synthetic": false, "world_size": 8} {"step": 13260, "tokens": 3476029440, "loss": 2.3939306259155275, "optimizer_updates": 7630, "effective_batch": 512, "lr": 0.00018731395433063466, "gradient_norm": 0.2875044047832489, "tokens_per_second": 1096279.8184241722, "synthetic": false, "world_size": 8} {"step": 13280, "tokens": 3481272320, "loss": 2.3905811309814453, "optimizer_updates": 7640, "effective_batch": 512, "lr": 0.00018727586134003173, "gradient_norm": 0.3654201626777649, "tokens_per_second": 1099870.5926970819, "synthetic": false, "world_size": 8} {"step": 13300, "tokens": 3486515200, "loss": 2.384011077880859, "optimizer_updates": 7650, "effective_batch": 512, "lr": 0.00018723771559321002, "gradient_norm": 0.252570778131485, "tokens_per_second": 1101968.6562960749, "synthetic": false, "world_size": 8} {"step": 13320, "tokens": 3491758080, "loss": 2.392843246459961, "optimizer_updates": 7660, "effective_batch": 512, "lr": 0.00018719951711621168, "gradient_norm": 0.3693111836910248, "tokens_per_second": 1093377.8105051694, "synthetic": false, "world_size": 8} {"step": 13340, "tokens": 3497000960, "loss": 2.394160842895508, "optimizer_updates": 7670, "effective_batch": 512, "lr": 0.0001871612659351148, "gradient_norm": 0.29101821780204773, "tokens_per_second": 1068900.8736816277, "synthetic": false, "world_size": 8} {"step": 13360, "tokens": 3502243840, "loss": 2.383749771118164, "optimizer_updates": 7680, "effective_batch": 512, "lr": 0.00018712296207603347, "gradient_norm": 0.3420950770378113, "tokens_per_second": 1078012.9574599073, "synthetic": false, "world_size": 8} {"step": 13380, "tokens": 3507486720, "loss": 2.395415687561035, "optimizer_updates": 7690, "effective_batch": 512, "lr": 0.0001870846055651177, "gradient_norm": 0.26478952169418335, "tokens_per_second": 1071108.3106421323, "synthetic": false, "world_size": 8} {"step": 13400, "tokens": 3512729600, "loss": 2.3940618515014647, "optimizer_updates": 7700, "effective_batch": 512, "lr": 0.00018704619642855347, "gradient_norm": 0.331720232963562, "tokens_per_second": 1075211.419402924, "synthetic": false, "world_size": 8} {"step": 13420, "tokens": 3517972480, "loss": 2.403769302368164, "optimizer_updates": 7710, "effective_batch": 512, "lr": 0.00018700773469256272, "gradient_norm": 0.32040682435035706, "tokens_per_second": 1074149.439237495, "synthetic": false, "world_size": 8} {"step": 13440, "tokens": 3523215360, "loss": 2.386505126953125, "optimizer_updates": 7720, "effective_batch": 512, "lr": 0.0001869692203834033, "gradient_norm": 0.2940349578857422, "tokens_per_second": 1079988.4454105531, "synthetic": false, "world_size": 8} {"step": 13460, "tokens": 3528458240, "loss": 2.388849449157715, "optimizer_updates": 7730, "effective_batch": 512, "lr": 0.00018693065352736883, "gradient_norm": 0.2486383467912674, "tokens_per_second": 1082782.020865591, "synthetic": false, "world_size": 8} {"step": 13480, "tokens": 3533701120, "loss": 2.3834064483642576, "optimizer_updates": 7740, "effective_batch": 512, "lr": 0.000186892034150789, "gradient_norm": 0.37987151741981506, "tokens_per_second": 1085760.1058275485, "synthetic": false, "world_size": 8} {"step": 13500, "tokens": 3538944000, "loss": 2.3974224090576173, "optimizer_updates": 7750, "effective_batch": 512, "lr": 0.00018685336228002914, "gradient_norm": 0.267354816198349, "tokens_per_second": 1087754.7120215879, "synthetic": false, "world_size": 8} {"step": 13520, "tokens": 3544186880, "loss": 2.403158760070801, "optimizer_updates": 7760, "effective_batch": 512, "lr": 0.00018681463794149064, "gradient_norm": 0.24261610209941864, "tokens_per_second": 1084479.9351181542, "synthetic": false, "world_size": 8} {"step": 13540, "tokens": 3549429760, "loss": 2.3888980865478517, "optimizer_updates": 7770, "effective_batch": 512, "lr": 0.00018677586116161055, "gradient_norm": 0.2748847007751465, "tokens_per_second": 1075731.4689491547, "synthetic": false, "world_size": 8} {"step": 13560, "tokens": 3554672640, "loss": 2.391330528259277, "optimizer_updates": 7780, "effective_batch": 512, "lr": 0.00018673703196686177, "gradient_norm": 0.28281280398368835, "tokens_per_second": 1077598.5131055631, "synthetic": false, "world_size": 8} {"step": 13580, "tokens": 3559915520, "loss": 2.390452766418457, "optimizer_updates": 7790, "effective_batch": 512, "lr": 0.00018669815038375298, "gradient_norm": 0.2895902693271637, "tokens_per_second": 1079299.5541691233, "synthetic": false, "world_size": 8} {"step": 13600, "tokens": 3565158400, "loss": 2.3944751739501955, "optimizer_updates": 7800, "effective_batch": 512, "lr": 0.00018665921643882863, "gradient_norm": 0.27617427706718445, "tokens_per_second": 1078155.1512123223, "synthetic": false, "world_size": 8} {"step": 13620, "tokens": 3570401280, "loss": 2.3890478134155275, "optimizer_updates": 7810, "effective_batch": 512, "lr": 0.00018662023015866898, "gradient_norm": 0.32051169872283936, "tokens_per_second": 1077416.9090946948, "synthetic": false, "world_size": 8} {"step": 13640, "tokens": 3575644160, "loss": 2.401527214050293, "optimizer_updates": 7820, "effective_batch": 512, "lr": 0.00018658119156988987, "gradient_norm": 0.2580038011074066, "tokens_per_second": 1081255.5580958475, "synthetic": false, "world_size": 8} {"step": 13660, "tokens": 3580887040, "loss": 2.3942699432373047, "optimizer_updates": 7830, "effective_batch": 512, "lr": 0.00018654210069914294, "gradient_norm": 0.27556613087654114, "tokens_per_second": 1075829.7102464996, "synthetic": false, "world_size": 8} {"step": 13680, "tokens": 3586129920, "loss": 2.385118103027344, "optimizer_updates": 7840, "effective_batch": 512, "lr": 0.00018650295757311562, "gradient_norm": 0.3190172612667084, "tokens_per_second": 1082074.7267810726, "synthetic": false, "world_size": 8} {"step": 13700, "tokens": 3591372800, "loss": 2.387841796875, "optimizer_updates": 7850, "effective_batch": 512, "lr": 0.00018646376221853083, "gradient_norm": 0.38301998376846313, "tokens_per_second": 1079015.5169439702, "synthetic": false, "world_size": 8} {"step": 13720, "tokens": 3596615680, "loss": 2.3735893249511717, "optimizer_updates": 7860, "effective_batch": 512, "lr": 0.00018642451466214727, "gradient_norm": 0.32575327157974243, "tokens_per_second": 1082470.216934856, "synthetic": false, "world_size": 8} {"step": 13740, "tokens": 3601858560, "loss": 2.395421028137207, "optimizer_updates": 7870, "effective_batch": 512, "lr": 0.00018638521493075918, "gradient_norm": 0.3484358489513397, "tokens_per_second": 1078773.6148630604, "synthetic": false, "world_size": 8} {"step": 13760, "tokens": 3607101440, "loss": 2.3876440048217775, "optimizer_updates": 7880, "effective_batch": 512, "lr": 0.00018634586305119657, "gradient_norm": 0.2490418553352356, "tokens_per_second": 947082.0228452502, "synthetic": false, "world_size": 8} {"step": 13780, "tokens": 3612344320, "loss": 2.402612495422363, "optimizer_updates": 7890, "effective_batch": 512, "lr": 0.0001863064590503249, "gradient_norm": 0.25981035828590393, "tokens_per_second": 783073.537028411, "synthetic": false, "world_size": 8} {"step": 13800, "tokens": 3617587200, "loss": 2.3979570388793947, "optimizer_updates": 7900, "effective_batch": 512, "lr": 0.0001862670029550453, "gradient_norm": 0.2401091754436493, "tokens_per_second": 1070364.7826419652, "synthetic": false, "world_size": 8} {"step": 13820, "tokens": 3622830080, "loss": 2.388353157043457, "optimizer_updates": 7910, "effective_batch": 512, "lr": 0.00018622749479229445, "gradient_norm": 0.30291274189949036, "tokens_per_second": 1073981.391756003, "synthetic": false, "world_size": 8} {"step": 13840, "tokens": 3628072960, "loss": 2.3768362045288085, "optimizer_updates": 7920, "effective_batch": 512, "lr": 0.0001861879345890445, "gradient_norm": 0.2718992233276367, "tokens_per_second": 1078835.5211081812, "synthetic": false, "world_size": 8} {"step": 13860, "tokens": 3633315840, "loss": 2.3894651412963865, "optimizer_updates": 7930, "effective_batch": 512, "lr": 0.00018614832237230332, "gradient_norm": 0.3394937515258789, "tokens_per_second": 1077181.1581489602, "synthetic": false, "world_size": 8} {"step": 13880, "tokens": 3638558720, "loss": 2.4014188766479494, "optimizer_updates": 7940, "effective_batch": 512, "lr": 0.00018610865816911406, "gradient_norm": 0.39912500977516174, "tokens_per_second": 1077151.7235921174, "synthetic": false, "world_size": 8} {"step": 13900, "tokens": 3643801600, "loss": 2.3943309783935547, "optimizer_updates": 7950, "effective_batch": 512, "lr": 0.00018606894200655548, "gradient_norm": 0.2410793900489807, "tokens_per_second": 1095398.320568263, "synthetic": false, "world_size": 8} {"step": 13920, "tokens": 3649044480, "loss": 2.39959602355957, "optimizer_updates": 7960, "effective_batch": 512, "lr": 0.00018602917391174182, "gradient_norm": 0.29904359579086304, "tokens_per_second": 1093307.3364849882, "synthetic": false, "world_size": 8} {"step": 13940, "tokens": 3654287360, "loss": 2.389427375793457, "optimizer_updates": 7970, "effective_batch": 512, "lr": 0.00018598935391182276, "gradient_norm": 0.28723934292793274, "tokens_per_second": 1094976.0349924578, "synthetic": false, "world_size": 8} {"step": 13960, "tokens": 3659530240, "loss": 2.3919261932373046, "optimizer_updates": 7980, "effective_batch": 512, "lr": 0.00018594948203398334, "gradient_norm": 0.4056797921657562, "tokens_per_second": 1095558.1899920672, "synthetic": false, "world_size": 8} {"step": 13980, "tokens": 3664773120, "loss": 2.389388656616211, "optimizer_updates": 7990, "effective_batch": 512, "lr": 0.0001859095583054442, "gradient_norm": 0.2824580669403076, "tokens_per_second": 1098511.4134220213, "synthetic": false, "world_size": 8} {"step": 14000, "tokens": 3670016000, "loss": 2.3998403549194336, "optimizer_updates": 8000, "effective_batch": 512, "lr": 0.00018586958275346117, "gradient_norm": 0.28082454204559326, "tokens_per_second": 1101421.699411788, "synthetic": false, "world_size": 8} {"step": 14020, "tokens": 3675258880, "loss": 2.3999195098876953, "optimizer_updates": 8010, "effective_batch": 512, "lr": 0.0001858295554053256, "gradient_norm": 0.3021344542503357, "tokens_per_second": 843922.120024778, "synthetic": false, "world_size": 8} {"step": 14040, "tokens": 3680501760, "loss": 2.388470458984375, "optimizer_updates": 8020, "effective_batch": 512, "lr": 0.00018578947628836414, "gradient_norm": 0.2576628029346466, "tokens_per_second": 1093354.9074269286, "synthetic": false, "world_size": 8} {"step": 14060, "tokens": 3685744640, "loss": 2.3888113021850588, "optimizer_updates": 8030, "effective_batch": 512, "lr": 0.00018574934542993878, "gradient_norm": 0.3422890305519104, "tokens_per_second": 1088994.2799032582, "synthetic": false, "world_size": 8} {"step": 14080, "tokens": 3690987520, "loss": 2.392970848083496, "optimizer_updates": 8040, "effective_batch": 512, "lr": 0.00018570916285744692, "gradient_norm": 0.2678871750831604, "tokens_per_second": 1086542.3989060835, "synthetic": false, "world_size": 8} {"step": 14100, "tokens": 3696230400, "loss": 2.396981048583984, "optimizer_updates": 8050, "effective_batch": 512, "lr": 0.00018566892859832107, "gradient_norm": 0.25842249393463135, "tokens_per_second": 1098133.1681271812, "synthetic": false, "world_size": 8} {"step": 14120, "tokens": 3701473280, "loss": 2.393467330932617, "optimizer_updates": 8060, "effective_batch": 512, "lr": 0.0001856286426800293, "gradient_norm": 0.3003844916820526, "tokens_per_second": 1097956.784689283, "synthetic": false, "world_size": 8} {"step": 14140, "tokens": 3706716160, "loss": 2.390326499938965, "optimizer_updates": 8070, "effective_batch": 512, "lr": 0.00018558830513007468, "gradient_norm": 0.28551653027534485, "tokens_per_second": 1090489.8264269892, "synthetic": false, "world_size": 8} {"step": 14160, "tokens": 3711959040, "loss": 2.4084503173828127, "optimizer_updates": 8080, "effective_batch": 512, "lr": 0.0001855479159759957, "gradient_norm": 0.2606048583984375, "tokens_per_second": 1089800.222621056, "synthetic": false, "world_size": 8} {"step": 14180, "tokens": 3717201920, "loss": 2.387027931213379, "optimizer_updates": 8090, "effective_batch": 512, "lr": 0.00018550747524536602, "gradient_norm": 0.3032197058200836, "tokens_per_second": 1100078.7214723763, "synthetic": false, "world_size": 8} {"step": 14200, "tokens": 3722444800, "loss": 2.3982732772827147, "optimizer_updates": 8100, "effective_batch": 512, "lr": 0.00018546698296579455, "gradient_norm": 0.2600707411766052, "tokens_per_second": 1099163.2187972793, "synthetic": false, "world_size": 8} {"step": 14220, "tokens": 3727687680, "loss": 2.3769020080566405, "optimizer_updates": 8110, "effective_batch": 512, "lr": 0.00018542643916492533, "gradient_norm": 0.30514639616012573, "tokens_per_second": 1090373.9403962195, "synthetic": false, "world_size": 8} {"step": 14240, "tokens": 3732930560, "loss": 2.3886003494262695, "optimizer_updates": 8120, "effective_batch": 512, "lr": 0.0001853858438704376, "gradient_norm": 0.28653523325920105, "tokens_per_second": 1102752.8097579505, "synthetic": false, "world_size": 8} {"step": 14260, "tokens": 3738173440, "loss": 2.394387435913086, "optimizer_updates": 8130, "effective_batch": 512, "lr": 0.0001853451971100458, "gradient_norm": 0.2942037880420685, "tokens_per_second": 1101832.7061331049, "synthetic": false, "world_size": 8} {"step": 14280, "tokens": 3743416320, "loss": 2.3948774337768555, "optimizer_updates": 8140, "effective_batch": 512, "lr": 0.00018530449891149942, "gradient_norm": 0.3764469623565674, "tokens_per_second": 1095824.7892136392, "synthetic": false, "world_size": 8} {"step": 14300, "tokens": 3748659200, "loss": 2.4016674041748045, "optimizer_updates": 8150, "effective_batch": 512, "lr": 0.00018526374930258316, "gradient_norm": 0.3044964671134949, "tokens_per_second": 1095830.0491585152, "synthetic": false, "world_size": 8} {"step": 14320, "tokens": 3753902080, "loss": 2.378767967224121, "optimizer_updates": 8160, "effective_batch": 512, "lr": 0.00018522294831111675, "gradient_norm": 0.30506205558776855, "tokens_per_second": 1082432.4101187475, "synthetic": false, "world_size": 8} {"step": 14340, "tokens": 3759144960, "loss": 2.3843082427978515, "optimizer_updates": 8170, "effective_batch": 512, "lr": 0.000185182095964955, "gradient_norm": 0.2452254444360733, "tokens_per_second": 767290.4934875439, "synthetic": false, "world_size": 8} {"step": 14360, "tokens": 3764387840, "loss": 2.3873538970947266, "optimizer_updates": 8180, "effective_batch": 512, "lr": 0.00018514119229198783, "gradient_norm": 0.30375048518180847, "tokens_per_second": 1098960.1937246935, "synthetic": false, "world_size": 8} {"step": 14380, "tokens": 3769630720, "loss": 2.399671936035156, "optimizer_updates": 8190, "effective_batch": 512, "lr": 0.00018510023732014018, "gradient_norm": 0.2572016716003418, "tokens_per_second": 1088527.2905687785, "synthetic": false, "world_size": 8} {"step": 14400, "tokens": 3774873600, "loss": 2.392842674255371, "optimizer_updates": 8200, "effective_batch": 512, "lr": 0.00018505923107737198, "gradient_norm": 0.2816340923309326, "tokens_per_second": 1096432.1673508447, "synthetic": false, "world_size": 8} {"step": 14420, "tokens": 3780116480, "loss": 2.386870193481445, "optimizer_updates": 8210, "effective_batch": 512, "lr": 0.00018501817359167815, "gradient_norm": 0.4364010989665985, "tokens_per_second": 1089564.8074497476, "synthetic": false, "world_size": 8} {"step": 14440, "tokens": 3785359360, "loss": 2.386576271057129, "optimizer_updates": 8220, "effective_batch": 512, "lr": 0.0001849770648910887, "gradient_norm": 0.30786803364753723, "tokens_per_second": 1095279.1640071752, "synthetic": false, "world_size": 8} {"step": 14460, "tokens": 3790602240, "loss": 2.3884695053100584, "optimizer_updates": 8230, "effective_batch": 512, "lr": 0.0001849359050036685, "gradient_norm": 0.3003600239753723, "tokens_per_second": 1095601.5295924589, "synthetic": false, "world_size": 8} {"step": 14480, "tokens": 3795845120, "loss": 2.3858516693115233, "optimizer_updates": 8240, "effective_batch": 512, "lr": 0.0001848946939575174, "gradient_norm": 0.31665438413619995, "tokens_per_second": 1099418.0092994457, "synthetic": false, "world_size": 8} {"step": 14500, "tokens": 3801088000, "loss": 2.38226261138916, "optimizer_updates": 8250, "effective_batch": 512, "lr": 0.0001848534317807702, "gradient_norm": 0.26084303855895996, "tokens_per_second": 1101465.0221834793, "synthetic": false, "world_size": 8} {"step": 14520, "tokens": 3806330880, "loss": 2.3918834686279298, "optimizer_updates": 8260, "effective_batch": 512, "lr": 0.00018481211850159655, "gradient_norm": 0.3103562295436859, "tokens_per_second": 1101546.6040224468, "synthetic": false, "world_size": 8} {"step": 14540, "tokens": 3811573760, "loss": 2.396833610534668, "optimizer_updates": 8270, "effective_batch": 512, "lr": 0.000184770754148201, "gradient_norm": 0.46629491448402405, "tokens_per_second": 1104966.6678216737, "synthetic": false, "world_size": 8} {"step": 14560, "tokens": 3816816640, "loss": 2.3870849609375, "optimizer_updates": 8280, "effective_batch": 512, "lr": 0.00018472933874882306, "gradient_norm": 0.2929612100124359, "tokens_per_second": 1101428.7646267181, "synthetic": false, "world_size": 8} {"step": 14580, "tokens": 3822059520, "loss": 2.3971818923950194, "optimizer_updates": 8290, "effective_batch": 512, "lr": 0.00018468787233173693, "gradient_norm": 0.4666120707988739, "tokens_per_second": 1079630.9730082783, "synthetic": false, "world_size": 8} {"step": 14600, "tokens": 3827302400, "loss": 2.3883169174194334, "optimizer_updates": 8300, "effective_batch": 512, "lr": 0.00018464635492525182, "gradient_norm": 0.24783195555210114, "tokens_per_second": 1098244.9769329622, "synthetic": false, "world_size": 8} {"step": 14620, "tokens": 3832545280, "loss": 2.394028663635254, "optimizer_updates": 8310, "effective_batch": 512, "lr": 0.00018460478655771156, "gradient_norm": 0.27787429094314575, "tokens_per_second": 1099731.4349319246, "synthetic": false, "world_size": 8} {"step": 14640, "tokens": 3837788160, "loss": 2.395635795593262, "optimizer_updates": 8320, "effective_batch": 512, "lr": 0.00018456316725749494, "gradient_norm": 0.3953946530818939, "tokens_per_second": 1096502.925741811, "synthetic": false, "world_size": 8} {"step": 14660, "tokens": 3843031040, "loss": 2.3908178329467775, "optimizer_updates": 8330, "effective_batch": 512, "lr": 0.00018452149705301544, "gradient_norm": 0.2615557610988617, "tokens_per_second": 1095789.4883517944, "synthetic": false, "world_size": 8} {"step": 14680, "tokens": 3848273920, "loss": 2.3922868728637696, "optimizer_updates": 8340, "effective_batch": 512, "lr": 0.00018447977597272125, "gradient_norm": 0.34103697538375854, "tokens_per_second": 1106253.2694303468, "synthetic": false, "world_size": 8} {"step": 14700, "tokens": 3853516800, "loss": 2.3961166381835937, "optimizer_updates": 8350, "effective_batch": 512, "lr": 0.0001844380040450954, "gradient_norm": 0.3564259111881256, "tokens_per_second": 1094446.9314887738, "synthetic": false, "world_size": 8} {"step": 14720, "tokens": 3858759680, "loss": 2.400427055358887, "optimizer_updates": 8360, "effective_batch": 512, "lr": 0.00018439618129865556, "gradient_norm": 0.2571365535259247, "tokens_per_second": 1106002.0011368892, "synthetic": false, "world_size": 8} {"step": 14740, "tokens": 3864002560, "loss": 2.3789058685302735, "optimizer_updates": 8370, "effective_batch": 512, "lr": 0.0001843543077619541, "gradient_norm": 0.3935917615890503, "tokens_per_second": 1094328.425427671, "synthetic": false, "world_size": 8} {"step": 14760, "tokens": 3869245440, "loss": 2.388604927062988, "optimizer_updates": 8380, "effective_batch": 512, "lr": 0.0001843123834635781, "gradient_norm": 0.42879366874694824, "tokens_per_second": 777569.099145737, "synthetic": false, "world_size": 8} {"step": 14780, "tokens": 3874488320, "loss": 2.390719985961914, "optimizer_updates": 8390, "effective_batch": 512, "lr": 0.00018427040843214926, "gradient_norm": 0.39833176136016846, "tokens_per_second": 1088699.7155500273, "synthetic": false, "world_size": 8} {"step": 14800, "tokens": 3879731200, "loss": 2.3840940475463865, "optimizer_updates": 8400, "effective_batch": 512, "lr": 0.00018422838269632394, "gradient_norm": 0.25161051750183105, "tokens_per_second": 1074459.0277526747, "synthetic": false, "world_size": 8} {"step": 14820, "tokens": 3884974080, "loss": 2.396030235290527, "optimizer_updates": 8410, "effective_batch": 512, "lr": 0.0001841863062847931, "gradient_norm": 0.3210544288158417, "tokens_per_second": 1085576.6863556185, "synthetic": false, "world_size": 8} {"step": 14840, "tokens": 3890216960, "loss": 2.4000988006591797, "optimizer_updates": 8420, "effective_batch": 512, "lr": 0.00018414417922628227, "gradient_norm": 0.30702099204063416, "tokens_per_second": 1082396.7683570674, "synthetic": false, "world_size": 8} {"step": 14860, "tokens": 3895459840, "loss": 2.407484436035156, "optimizer_updates": 8430, "effective_batch": 512, "lr": 0.00018410200154955162, "gradient_norm": 0.3589920401573181, "tokens_per_second": 1085486.9114873428, "synthetic": false, "world_size": 8} {"step": 14880, "tokens": 3900702720, "loss": 2.3894704818725585, "optimizer_updates": 8440, "effective_batch": 512, "lr": 0.00018405977328339585, "gradient_norm": 0.2778353989124298, "tokens_per_second": 1095621.50629865, "synthetic": false, "world_size": 8} {"step": 14900, "tokens": 3905945600, "loss": 2.3901836395263674, "optimizer_updates": 8450, "effective_batch": 512, "lr": 0.00018401749445664416, "gradient_norm": 0.24386528134346008, "tokens_per_second": 1078068.7607177687, "synthetic": false, "world_size": 8} {"step": 14920, "tokens": 3911188480, "loss": 2.3974145889282226, "optimizer_updates": 8460, "effective_batch": 512, "lr": 0.00018397516509816034, "gradient_norm": 0.2937007248401642, "tokens_per_second": 1081922.6585999688, "synthetic": false, "world_size": 8} {"step": 14940, "tokens": 3916431360, "loss": 2.373910903930664, "optimizer_updates": 8470, "effective_batch": 512, "lr": 0.00018393278523684258, "gradient_norm": 0.24417375028133392, "tokens_per_second": 1091944.2212184572, "synthetic": false, "world_size": 8} {"step": 14960, "tokens": 3921674240, "loss": 2.3849105834960938, "optimizer_updates": 8480, "effective_batch": 512, "lr": 0.0001838903549016236, "gradient_norm": 0.2726725935935974, "tokens_per_second": 1083625.406270807, "synthetic": false, "world_size": 8} {"step": 14980, "tokens": 3926917120, "loss": 2.3913528442382814, "optimizer_updates": 8490, "effective_batch": 512, "lr": 0.00018384787412147066, "gradient_norm": 0.38872918486595154, "tokens_per_second": 1055116.988229407, "synthetic": false, "world_size": 8} {"step": 15000, "tokens": 3932160000, "loss": 2.3942468643188475, "optimizer_updates": 8500, "effective_batch": 512, "lr": 0.00018380534292538535, "gradient_norm": 0.32428064942359924, "tokens_per_second": 1087319.9593171433, "synthetic": false, "world_size": 8} {"step": 15020, "tokens": 3937402880, "loss": 2.393207550048828, "optimizer_updates": 8510, "effective_batch": 512, "lr": 0.00018376276134240367, "gradient_norm": 0.3028677701950073, "tokens_per_second": 842772.0691737896, "synthetic": false, "world_size": 8} {"step": 15040, "tokens": 3942645760, "loss": 2.4075069427490234, "optimizer_updates": 8520, "effective_batch": 512, "lr": 0.0001837201294015961, "gradient_norm": 0.25918251276016235, "tokens_per_second": 990239.8569840792, "synthetic": false, "world_size": 8} {"step": 15060, "tokens": 3947888640, "loss": 2.3888587951660156, "optimizer_updates": 8530, "effective_batch": 512, "lr": 0.00018367744713206747, "gradient_norm": 0.2379051297903061, "tokens_per_second": 1081800.6905717691, "synthetic": false, "world_size": 8} {"step": 15080, "tokens": 3953131520, "loss": 2.391790008544922, "optimizer_updates": 8540, "effective_batch": 512, "lr": 0.0001836347145629569, "gradient_norm": 0.26546499133110046, "tokens_per_second": 1087984.3882132138, "synthetic": false, "world_size": 8} {"step": 15100, "tokens": 3958374400, "loss": 2.401493263244629, "optimizer_updates": 8550, "effective_batch": 512, "lr": 0.000183591931723438, "gradient_norm": 0.4074949026107788, "tokens_per_second": 1085665.9421447297, "synthetic": false, "world_size": 8} {"step": 15120, "tokens": 3963617280, "loss": 2.3949115753173826, "optimizer_updates": 8560, "effective_batch": 512, "lr": 0.00018354909864271853, "gradient_norm": 0.39805516600608826, "tokens_per_second": 976912.9141189966, "synthetic": false, "world_size": 8} {"step": 15140, "tokens": 3968860160, "loss": 2.383805274963379, "optimizer_updates": 8570, "effective_batch": 512, "lr": 0.00018350621535004064, "gradient_norm": 0.35964930057525635, "tokens_per_second": 808943.3578604467, "synthetic": false, "world_size": 8} {"step": 15160, "tokens": 3974103040, "loss": 2.39825439453125, "optimizer_updates": 8580, "effective_batch": 512, "lr": 0.00018346328187468077, "gradient_norm": 0.32327350974082947, "tokens_per_second": 1081949.015586506, "synthetic": false, "world_size": 8} {"step": 15180, "tokens": 3979345920, "loss": 2.390394592285156, "optimizer_updates": 8590, "effective_batch": 512, "lr": 0.0001834202982459496, "gradient_norm": 0.2621242105960846, "tokens_per_second": 1080685.8192605716, "synthetic": false, "world_size": 8} {"step": 15200, "tokens": 3984588800, "loss": 2.388499450683594, "optimizer_updates": 8600, "effective_batch": 512, "lr": 0.00018337726449319203, "gradient_norm": 0.2711612582206726, "tokens_per_second": 1079894.4355899037, "synthetic": false, "world_size": 8} {"step": 15220, "tokens": 3989831680, "loss": 2.378384590148926, "optimizer_updates": 8610, "effective_batch": 512, "lr": 0.00018333418064578718, "gradient_norm": 0.26613348722457886, "tokens_per_second": 1088608.7539216904, "synthetic": false, "world_size": 8} {"step": 15240, "tokens": 3995074560, "loss": 2.384092903137207, "optimizer_updates": 8620, "effective_batch": 512, "lr": 0.00018329104673314844, "gradient_norm": 0.2658315598964691, "tokens_per_second": 1082101.297046609, "synthetic": false, "world_size": 8} {"step": 15260, "tokens": 4000317440, "loss": 2.3870534896850586, "optimizer_updates": 8630, "effective_batch": 512, "lr": 0.00018324786278472327, "gradient_norm": 0.258500337600708, "tokens_per_second": 888446.9333083057, "synthetic": false, "world_size": 8} {"step": 15280, "tokens": 4005560320, "loss": 2.385426330566406, "optimizer_updates": 8640, "effective_batch": 512, "lr": 0.00018320462882999336, "gradient_norm": 0.30244824290275574, "tokens_per_second": 1090946.3122897763, "synthetic": false, "world_size": 8} {"step": 15300, "tokens": 4010803200, "loss": 2.3716768264770507, "optimizer_updates": 8650, "effective_batch": 512, "lr": 0.00018316134489847454, "gradient_norm": 0.37162578105926514, "tokens_per_second": 1034109.7093796638, "synthetic": false, "world_size": 8} {"step": 15320, "tokens": 4016046080, "loss": 2.3836360931396485, "optimizer_updates": 8660, "effective_batch": 512, "lr": 0.00018311801101971673, "gradient_norm": 0.27355390787124634, "tokens_per_second": 1076139.3168932009, "synthetic": false, "world_size": 8} {"step": 15340, "tokens": 4021288960, "loss": 2.3949636459350585, "optimizer_updates": 8670, "effective_batch": 512, "lr": 0.000183074627223304, "gradient_norm": 0.47458475828170776, "tokens_per_second": 1080900.811995161, "synthetic": false, "world_size": 8} {"step": 15360, "tokens": 4026531840, "loss": 2.39017333984375, "optimizer_updates": 8680, "effective_batch": 512, "lr": 0.0001830311935388544, "gradient_norm": 0.2960445284843445, "tokens_per_second": 1081459.1497166029, "synthetic": false, "world_size": 8} {"step": 15380, "tokens": 4031774720, "loss": 2.400224304199219, "optimizer_updates": 8690, "effective_batch": 512, "lr": 0.00018298770999602016, "gradient_norm": 0.2801525592803955, "tokens_per_second": 1089253.7304883278, "synthetic": false, "world_size": 8} {"step": 15400, "tokens": 4037017600, "loss": 2.391048049926758, "optimizer_updates": 8700, "effective_batch": 512, "lr": 0.00018294417662448743, "gradient_norm": 0.2691399157047272, "tokens_per_second": 1085739.3332237166, "synthetic": false, "world_size": 8} {"step": 15420, "tokens": 4042260480, "loss": 2.3926551818847654, "optimizer_updates": 8710, "effective_batch": 512, "lr": 0.00018290059345397645, "gradient_norm": 0.3712269961833954, "tokens_per_second": 1082149.4423113232, "synthetic": false, "world_size": 8} {"step": 15440, "tokens": 4047503360, "loss": 2.3850914001464845, "optimizer_updates": 8720, "effective_batch": 512, "lr": 0.00018285696051424148, "gradient_norm": 0.3129231333732605, "tokens_per_second": 1088500.959961984, "synthetic": false, "world_size": 8} {"step": 15460, "tokens": 4052746240, "loss": 2.3912174224853517, "optimizer_updates": 8730, "effective_batch": 512, "lr": 0.00018281327783507066, "gradient_norm": 0.3042137622833252, "tokens_per_second": 1091869.6098515072, "synthetic": false, "world_size": 8} {"step": 15480, "tokens": 4057989120, "loss": 2.3840959548950194, "optimizer_updates": 8740, "effective_batch": 512, "lr": 0.00018276954544628625, "gradient_norm": 0.33308446407318115, "tokens_per_second": 1095541.0746281494, "synthetic": false, "world_size": 8} {"step": 15500, "tokens": 4063232000, "loss": 2.3917884826660156, "optimizer_updates": 8750, "effective_batch": 512, "lr": 0.00018272576337774425, "gradient_norm": 0.3578082323074341, "tokens_per_second": 1094569.8868463412, "synthetic": false, "world_size": 8} {"step": 15520, "tokens": 4068474880, "loss": 2.386028289794922, "optimizer_updates": 8760, "effective_batch": 512, "lr": 0.0001826819316593347, "gradient_norm": 0.23939530551433563, "tokens_per_second": 1107361.4789320668, "synthetic": false, "world_size": 8} {"step": 15540, "tokens": 4073717760, "loss": 2.3943323135375976, "optimizer_updates": 8770, "effective_batch": 512, "lr": 0.0001826380503209815, "gradient_norm": 0.2912493050098419, "tokens_per_second": 1098824.5511873076, "synthetic": false, "world_size": 8} {"step": 15560, "tokens": 4078960640, "loss": 2.385649490356445, "optimizer_updates": 8780, "effective_batch": 512, "lr": 0.00018259411939264245, "gradient_norm": 0.3268474340438843, "tokens_per_second": 1103546.364879917, "synthetic": false, "world_size": 8} {"step": 15580, "tokens": 4084203520, "loss": 2.390755271911621, "optimizer_updates": 8790, "effective_batch": 512, "lr": 0.0001825501389043092, "gradient_norm": 0.2792099714279175, "tokens_per_second": 1105027.2219920855, "synthetic": false, "world_size": 8} {"step": 15600, "tokens": 4089446400, "loss": 2.387217712402344, "optimizer_updates": 8800, "effective_batch": 512, "lr": 0.00018250610888600718, "gradient_norm": 0.26421335339546204, "tokens_per_second": 1099812.4346395442, "synthetic": false, "world_size": 8} {"step": 15620, "tokens": 4094689280, "loss": 2.387693977355957, "optimizer_updates": 8810, "effective_batch": 512, "lr": 0.0001824620293677957, "gradient_norm": 0.2593616843223572, "tokens_per_second": 1102737.231799257, "synthetic": false, "world_size": 8} {"step": 15640, "tokens": 4099932160, "loss": 2.3878171920776365, "optimizer_updates": 8820, "effective_batch": 512, "lr": 0.00018241790037976788, "gradient_norm": 0.28339219093322754, "tokens_per_second": 1090995.5103038035, "synthetic": false, "world_size": 8} {"step": 15660, "tokens": 4105175040, "loss": 2.390359115600586, "optimizer_updates": 8830, "effective_batch": 512, "lr": 0.0001823737219520505, "gradient_norm": 0.2595963180065155, "tokens_per_second": 1104310.529913783, "synthetic": false, "world_size": 8} {"step": 15680, "tokens": 4110417920, "loss": 2.3785236358642576, "optimizer_updates": 8840, "effective_batch": 512, "lr": 0.00018232949411480418, "gradient_norm": 0.24776910245418549, "tokens_per_second": 1099706.9004965415, "synthetic": false, "world_size": 8} {"step": 15700, "tokens": 4115660800, "loss": 2.3928993225097654, "optimizer_updates": 8850, "effective_batch": 512, "lr": 0.00018228521689822333, "gradient_norm": 0.2712155282497406, "tokens_per_second": 1107327.471673198, "synthetic": false, "world_size": 8} {"step": 15720, "tokens": 4120903680, "loss": 2.3810853958129883, "optimizer_updates": 8860, "effective_batch": 512, "lr": 0.0001822408903325359, "gradient_norm": 0.3113566040992737, "tokens_per_second": 1096941.072403211, "synthetic": false, "world_size": 8} {"step": 15740, "tokens": 4126146560, "loss": 2.396220016479492, "optimizer_updates": 8870, "effective_batch": 512, "lr": 0.0001821965144480037, "gradient_norm": 0.24658633768558502, "tokens_per_second": 1102884.6797255215, "synthetic": false, "world_size": 8} {"step": 15760, "tokens": 4131389440, "loss": 2.386733818054199, "optimizer_updates": 8880, "effective_batch": 512, "lr": 0.00018215208927492213, "gradient_norm": 0.4082566797733307, "tokens_per_second": 1100900.8321202495, "synthetic": false, "world_size": 8} {"step": 15780, "tokens": 4136632320, "loss": 2.3908205032348633, "optimizer_updates": 8890, "effective_batch": 512, "lr": 0.0001821076148436202, "gradient_norm": 0.2681064009666443, "tokens_per_second": 1107641.8545501318, "synthetic": false, "world_size": 8} {"step": 15800, "tokens": 4141875200, "loss": 2.379403305053711, "optimizer_updates": 8900, "effective_batch": 512, "lr": 0.00018206309118446067, "gradient_norm": 0.2534909248352051, "tokens_per_second": 1105785.0030529497, "synthetic": false, "world_size": 8} {"step": 15820, "tokens": 4147118080, "loss": 2.3828811645507812, "optimizer_updates": 8910, "effective_batch": 512, "lr": 0.0001820185183278398, "gradient_norm": 0.281145840883255, "tokens_per_second": 1099334.3845301832, "synthetic": false, "world_size": 8} {"step": 15840, "tokens": 4152360960, "loss": 2.393284225463867, "optimizer_updates": 8920, "effective_batch": 512, "lr": 0.00018197389630418743, "gradient_norm": 0.35858842730522156, "tokens_per_second": 1077161.381735035, "synthetic": false, "world_size": 8} {"step": 15860, "tokens": 4157603840, "loss": 2.384071159362793, "optimizer_updates": 8930, "effective_batch": 512, "lr": 0.00018192922514396708, "gradient_norm": 0.27086305618286133, "tokens_per_second": 961498.7402013371, "synthetic": false, "world_size": 8} {"step": 15880, "tokens": 4162846720, "loss": 2.3898998260498048, "optimizer_updates": 8940, "effective_batch": 512, "lr": 0.00018188450487767569, "gradient_norm": 0.24761052429676056, "tokens_per_second": 1098867.6804499875, "synthetic": false, "world_size": 8} {"step": 15900, "tokens": 4168089600, "loss": 2.3989578247070313, "optimizer_updates": 8950, "effective_batch": 512, "lr": 0.00018183973553584384, "gradient_norm": 0.3268137276172638, "tokens_per_second": 1104461.6952876728, "synthetic": false, "world_size": 8} {"step": 15920, "tokens": 4173332480, "loss": 2.376369667053223, "optimizer_updates": 8960, "effective_batch": 512, "lr": 0.00018179491714903547, "gradient_norm": 0.23853887617588043, "tokens_per_second": 1083204.140783605, "synthetic": false, "world_size": 8} {"step": 15940, "tokens": 4178575360, "loss": 2.384567070007324, "optimizer_updates": 8970, "effective_batch": 512, "lr": 0.00018175004974784815, "gradient_norm": 0.27509379386901855, "tokens_per_second": 784197.8727130693, "synthetic": false, "world_size": 8} {"step": 15960, "tokens": 4183818240, "loss": 2.394584846496582, "optimizer_updates": 8980, "effective_batch": 512, "lr": 0.00018170513336291286, "gradient_norm": 0.2350265234708786, "tokens_per_second": 1091616.1282781719, "synthetic": false, "world_size": 8} {"step": 15980, "tokens": 4189061120, "loss": 2.385172653198242, "optimizer_updates": 8990, "effective_batch": 512, "lr": 0.00018166016802489393, "gradient_norm": 0.33851152658462524, "tokens_per_second": 1092428.3754242957, "synthetic": false, "world_size": 8} {"step": 16000, "tokens": 4194304000, "loss": 2.3983413696289064, "optimizer_updates": 9000, "effective_batch": 512, "lr": 0.00018161515376448925, "gradient_norm": 0.27874794602394104, "tokens_per_second": 1097114.4609637763, "synthetic": false, "world_size": 8} {"step": 16020, "tokens": 4199546880, "loss": 2.3813772201538086, "optimizer_updates": 9010, "effective_batch": 512, "lr": 0.00018157009061243006, "gradient_norm": 0.2662685513496399, "tokens_per_second": 852921.993931249, "synthetic": false, "world_size": 8} {"step": 16040, "tokens": 4204789760, "loss": 2.3899261474609377, "optimizer_updates": 9020, "effective_batch": 512, "lr": 0.00018152497859948093, "gradient_norm": 0.2847583293914795, "tokens_per_second": 1092620.1042327215, "synthetic": false, "world_size": 8} {"step": 16060, "tokens": 4210032640, "loss": 2.383426856994629, "optimizer_updates": 9030, "effective_batch": 512, "lr": 0.0001814798177564398, "gradient_norm": 0.27118298411369324, "tokens_per_second": 1100565.0426615253, "synthetic": false, "world_size": 8} {"step": 16080, "tokens": 4215275520, "loss": 2.3911518096923827, "optimizer_updates": 9040, "effective_batch": 512, "lr": 0.00018143460811413808, "gradient_norm": 0.37566885352134705, "tokens_per_second": 1097819.5118460974, "synthetic": false, "world_size": 8} {"step": 16100, "tokens": 4220518400, "loss": 2.38848819732666, "optimizer_updates": 9050, "effective_batch": 512, "lr": 0.00018138934970344029, "gradient_norm": 0.31464624404907227, "tokens_per_second": 1096335.1192491646, "synthetic": false, "world_size": 8} {"step": 16120, "tokens": 4225761280, "loss": 2.3911237716674805, "optimizer_updates": 9060, "effective_batch": 512, "lr": 0.00018134404255524435, "gradient_norm": 0.3954991102218628, "tokens_per_second": 1100959.6215895137, "synthetic": false, "world_size": 8} {"step": 16140, "tokens": 4231004160, "loss": 2.384889030456543, "optimizer_updates": 9070, "effective_batch": 512, "lr": 0.00018129868670048143, "gradient_norm": 0.28214916586875916, "tokens_per_second": 1098794.7200997823, "synthetic": false, "world_size": 8} {"step": 16160, "tokens": 4236247040, "loss": 2.4029447555541994, "optimizer_updates": 9080, "effective_batch": 512, "lr": 0.00018125328217011603, "gradient_norm": 0.2835961580276489, "tokens_per_second": 1104490.074641009, "synthetic": false, "world_size": 8} {"step": 16180, "tokens": 4241489920, "loss": 2.3870689392089846, "optimizer_updates": 9090, "effective_batch": 512, "lr": 0.00018120782899514577, "gradient_norm": 0.3689574599266052, "tokens_per_second": 1096595.85692519, "synthetic": false, "world_size": 8} {"step": 16200, "tokens": 4246732800, "loss": 2.392436218261719, "optimizer_updates": 9100, "effective_batch": 512, "lr": 0.00018116232720660153, "gradient_norm": 0.2807919979095459, "tokens_per_second": 1102916.1891716628, "synthetic": false, "world_size": 8} {"step": 16220, "tokens": 4251975680, "loss": 2.398534393310547, "optimizer_updates": 9110, "effective_batch": 512, "lr": 0.00018111677683554738, "gradient_norm": 0.2640790045261383, "tokens_per_second": 1108358.0377307406, "synthetic": false, "world_size": 8} {"step": 16240, "tokens": 4257218560, "loss": 2.4069450378417967, "optimizer_updates": 9120, "effective_batch": 512, "lr": 0.00018107117791308058, "gradient_norm": 0.2730957269668579, "tokens_per_second": 1100969.9300494094, "synthetic": false, "world_size": 8} {"step": 16260, "tokens": 4262461440, "loss": 2.3916088104248048, "optimizer_updates": 9130, "effective_batch": 512, "lr": 0.00018102553047033142, "gradient_norm": 0.2577408254146576, "tokens_per_second": 1097889.971970331, "synthetic": false, "world_size": 8} {"step": 16280, "tokens": 4267704320, "loss": 2.3778921127319337, "optimizer_updates": 9140, "effective_batch": 512, "lr": 0.00018097983453846348, "gradient_norm": 0.34581902623176575, "tokens_per_second": 1100633.1534241757, "synthetic": false, "world_size": 8} {"step": 16300, "tokens": 4272947200, "loss": 2.3968692779541017, "optimizer_updates": 9150, "effective_batch": 512, "lr": 0.00018093409014867336, "gradient_norm": 0.2621910870075226, "tokens_per_second": 1091336.2415891727, "synthetic": false, "world_size": 8} {"step": 16320, "tokens": 4278190080, "loss": 2.3903215408325194, "optimizer_updates": 9160, "effective_batch": 512, "lr": 0.00018088829733219072, "gradient_norm": 0.3797444701194763, "tokens_per_second": 1096608.763554601, "synthetic": false, "world_size": 8} {"step": 16340, "tokens": 4283432960, "loss": 2.390539360046387, "optimizer_updates": 9170, "effective_batch": 512, "lr": 0.00018084245612027833, "gradient_norm": 0.24934209883213043, "tokens_per_second": 1102338.360223008, "synthetic": false, "world_size": 8} {"step": 16360, "tokens": 4288675840, "loss": 2.395842933654785, "optimizer_updates": 9180, "effective_batch": 512, "lr": 0.000180796566544232, "gradient_norm": 0.25774216651916504, "tokens_per_second": 1080479.6900808383, "synthetic": false, "world_size": 8} {"step": 16380, "tokens": 4293918720, "loss": 2.3798120498657225, "optimizer_updates": 9190, "effective_batch": 512, "lr": 0.00018075062863538046, "gradient_norm": 0.30754271149635315, "tokens_per_second": 1076770.1650751017, "synthetic": false, "world_size": 8} {"step": 16400, "tokens": 4299161600, "loss": 2.3947261810302733, "optimizer_updates": 9200, "effective_batch": 512, "lr": 0.00018070464242508555, "gradient_norm": 0.2719357907772064, "tokens_per_second": 1095833.7353735922, "synthetic": false, "world_size": 8} {"step": 16420, "tokens": 4304404480, "loss": 2.3909526824951173, "optimizer_updates": 9210, "effective_batch": 512, "lr": 0.0001806586079447421, "gradient_norm": 0.31221815943717957, "tokens_per_second": 1088687.3348914972, "synthetic": false, "world_size": 8} {"step": 16440, "tokens": 4309647360, "loss": 2.392619514465332, "optimizer_updates": 9220, "effective_batch": 512, "lr": 0.00018061252522577777, "gradient_norm": 0.2873893976211548, "tokens_per_second": 1084530.5368279659, "synthetic": false, "world_size": 8} {"step": 16460, "tokens": 4314890240, "loss": 2.39969482421875, "optimizer_updates": 9230, "effective_batch": 512, "lr": 0.0001805663942996533, "gradient_norm": 0.3135911226272583, "tokens_per_second": 767379.7548610711, "synthetic": false, "world_size": 8} {"step": 16480, "tokens": 4320133120, "loss": 2.3956947326660156, "optimizer_updates": 9240, "effective_batch": 512, "lr": 0.00018052021519786217, "gradient_norm": 0.31436604261398315, "tokens_per_second": 1081827.5257537246, "synthetic": false, "world_size": 8} {"step": 16500, "tokens": 4325376000, "loss": 2.388929557800293, "optimizer_updates": 9250, "effective_batch": 512, "lr": 0.00018047398795193094, "gradient_norm": 0.5456836819648743, "tokens_per_second": 1084240.43543565, "synthetic": false, "world_size": 8} {"step": 16520, "tokens": 4330618880, "loss": 2.3944406509399414, "optimizer_updates": 9260, "effective_batch": 512, "lr": 0.00018042771259341888, "gradient_norm": 0.302427738904953, "tokens_per_second": 1080936.2160094886, "synthetic": false, "world_size": 8} {"step": 16540, "tokens": 4335861760, "loss": 2.389344024658203, "optimizer_updates": 9270, "effective_batch": 512, "lr": 0.00018038138915391818, "gradient_norm": 0.2745125889778137, "tokens_per_second": 1080670.9612038697, "synthetic": false, "world_size": 8} {"step": 16560, "tokens": 4341104640, "loss": 2.3955665588378907, "optimizer_updates": 9280, "effective_batch": 512, "lr": 0.00018033501766505385, "gradient_norm": 0.3516961336135864, "tokens_per_second": 1084982.6988365299, "synthetic": false, "world_size": 8} {"step": 16580, "tokens": 4346347520, "loss": 2.3860183715820313, "optimizer_updates": 9290, "effective_batch": 512, "lr": 0.00018028859815848376, "gradient_norm": 0.34400707483291626, "tokens_per_second": 1085645.6721938683, "synthetic": false, "world_size": 8} {"step": 16600, "tokens": 4351590400, "loss": 2.3843662261962892, "optimizer_updates": 9300, "effective_batch": 512, "lr": 0.0001802421306658984, "gradient_norm": 0.27917060256004333, "tokens_per_second": 1077278.9282037828, "synthetic": false, "world_size": 8} {"step": 16620, "tokens": 4356833280, "loss": 2.3914432525634766, "optimizer_updates": 9310, "effective_batch": 512, "lr": 0.00018019561521902117, "gradient_norm": 0.24257829785346985, "tokens_per_second": 1078829.2758131833, "synthetic": false, "world_size": 8} {"step": 16640, "tokens": 4362076160, "loss": 2.3848695755004883, "optimizer_updates": 9320, "effective_batch": 512, "lr": 0.00018014905184960818, "gradient_norm": 0.306650310754776, "tokens_per_second": 1085393.7611673842, "synthetic": false, "world_size": 8} {"step": 16660, "tokens": 4367319040, "loss": 2.3872049331665037, "optimizer_updates": 9330, "effective_batch": 512, "lr": 0.0001801024405894482, "gradient_norm": 0.2819781005382538, "tokens_per_second": 1081065.705683764, "synthetic": false, "world_size": 8} {"step": 16680, "tokens": 4372561920, "loss": 2.3938314437866213, "optimizer_updates": 9340, "effective_batch": 512, "lr": 0.00018005578147036271, "gradient_norm": 0.25257226824760437, "tokens_per_second": 1080330.651693217, "synthetic": false, "world_size": 8} {"step": 16700, "tokens": 4377804800, "loss": 2.3942934036254884, "optimizer_updates": 9350, "effective_batch": 512, "lr": 0.00018000907452420594, "gradient_norm": 0.3247350752353668, "tokens_per_second": 1082656.3509496409, "synthetic": false, "world_size": 8} {"step": 16720, "tokens": 4383047680, "loss": 2.3948850631713867, "optimizer_updates": 9360, "effective_batch": 512, "lr": 0.0001799623197828647, "gradient_norm": 0.2900153398513794, "tokens_per_second": 1081131.4911751733, "synthetic": false, "world_size": 8} {"step": 16740, "tokens": 4388290560, "loss": 2.4006967544555664, "optimizer_updates": 9370, "effective_batch": 512, "lr": 0.0001799155172782584, "gradient_norm": 0.32740679383277893, "tokens_per_second": 1084491.1305076743, "synthetic": false, "world_size": 8} {"step": 16760, "tokens": 4393533440, "loss": 2.3960342407226562, "optimizer_updates": 9380, "effective_batch": 512, "lr": 0.00017986866704233916, "gradient_norm": 0.2808680534362793, "tokens_per_second": 1085085.2494427187, "synthetic": false, "world_size": 8} {"step": 16780, "tokens": 4398776320, "loss": 2.3940832138061525, "optimizer_updates": 9390, "effective_batch": 512, "lr": 0.0001798217691070916, "gradient_norm": 0.2604391276836395, "tokens_per_second": 1087041.5570673328, "synthetic": false, "world_size": 8} {"step": 16800, "tokens": 4404019200, "loss": 2.372748374938965, "optimizer_updates": 9400, "effective_batch": 512, "lr": 0.00017977482350453293, "gradient_norm": 0.23870141804218292, "tokens_per_second": 1089803.7993134474, "synthetic": false, "world_size": 8} {"step": 16820, "tokens": 4409262080, "loss": 2.3818595886230467, "optimizer_updates": 9410, "effective_batch": 512, "lr": 0.0001797278302667129, "gradient_norm": 0.2912214994430542, "tokens_per_second": 1089082.974217623, "synthetic": false, "world_size": 8} {"step": 16840, "tokens": 4414504960, "loss": 2.3715667724609375, "optimizer_updates": 9420, "effective_batch": 512, "lr": 0.00017968078942571383, "gradient_norm": 0.28341954946517944, "tokens_per_second": 1078402.9783820997, "synthetic": false, "world_size": 8} {"step": 16860, "tokens": 4419747840, "loss": 2.3926849365234375, "optimizer_updates": 9430, "effective_batch": 512, "lr": 0.00017963370101365045, "gradient_norm": 0.28084126114845276, "tokens_per_second": 1072743.5969698478, "synthetic": false, "world_size": 8} {"step": 16880, "tokens": 4424990720, "loss": 2.38577938079834, "optimizer_updates": 9440, "effective_batch": 512, "lr": 0.00017958656506267005, "gradient_norm": 0.2831367552280426, "tokens_per_second": 1082610.8338160785, "synthetic": false, "world_size": 8} {"step": 16900, "tokens": 4430233600, "loss": 2.366911506652832, "optimizer_updates": 9450, "effective_batch": 512, "lr": 0.0001795393816049523, "gradient_norm": 0.33441463112831116, "tokens_per_second": 1079865.1759659855, "synthetic": false, "world_size": 8} {"step": 16920, "tokens": 4435476480, "loss": 2.3816207885742187, "optimizer_updates": 9460, "effective_batch": 512, "lr": 0.00017949215067270934, "gradient_norm": 0.3076835572719574, "tokens_per_second": 1074066.9239760845, "synthetic": false, "world_size": 8} {"step": 16940, "tokens": 4440719360, "loss": 2.376059150695801, "optimizer_updates": 9470, "effective_batch": 512, "lr": 0.0001794448722981857, "gradient_norm": 0.2803298532962799, "tokens_per_second": 1073028.5002869635, "synthetic": false, "world_size": 8} {"step": 16960, "tokens": 4445962240, "loss": 2.401753616333008, "optimizer_updates": 9480, "effective_batch": 512, "lr": 0.00017939754651365842, "gradient_norm": 0.3222559690475464, "tokens_per_second": 1079925.7134508004, "synthetic": false, "world_size": 8} {"step": 16980, "tokens": 4451205120, "loss": 2.384456825256348, "optimizer_updates": 9490, "effective_batch": 512, "lr": 0.00017935017335143672, "gradient_norm": 0.2580130696296692, "tokens_per_second": 1076147.8331746738, "synthetic": false, "world_size": 8} {"step": 17000, "tokens": 4456448000, "loss": 2.377224922180176, "optimizer_updates": 9500, "effective_batch": 512, "lr": 0.00017930275284386223, "gradient_norm": 0.3678421378135681, "tokens_per_second": 1084007.015594552, "synthetic": false, "world_size": 8} {"step": 17020, "tokens": 4461690880, "loss": 2.3916452407836912, "optimizer_updates": 9510, "effective_batch": 512, "lr": 0.00017925528502330898, "gradient_norm": 0.33958470821380615, "tokens_per_second": 842251.5800750862, "synthetic": false, "world_size": 8} {"step": 17040, "tokens": 4466933760, "loss": 2.3822963714599608, "optimizer_updates": 9520, "effective_batch": 512, "lr": 0.00017920776992218324, "gradient_norm": 0.32312822341918945, "tokens_per_second": 1078944.180190056, "synthetic": false, "world_size": 8} {"step": 17060, "tokens": 4472176640, "loss": 2.386949348449707, "optimizer_updates": 9530, "effective_batch": 512, "lr": 0.00017916020757292354, "gradient_norm": 0.2765328884124756, "tokens_per_second": 1080399.3128138208, "synthetic": false, "world_size": 8} {"step": 17080, "tokens": 4477419520, "loss": 2.3817108154296873, "optimizer_updates": 9540, "effective_batch": 512, "lr": 0.00017911259800800072, "gradient_norm": 0.2601776421070099, "tokens_per_second": 1079526.8309175784, "synthetic": false, "world_size": 8} {"step": 17100, "tokens": 4482662400, "loss": 2.391712760925293, "optimizer_updates": 9550, "effective_batch": 512, "lr": 0.00017906494125991774, "gradient_norm": 0.25751402974128723, "tokens_per_second": 976394.7616014788, "synthetic": false, "world_size": 8} {"step": 17120, "tokens": 4487905280, "loss": 2.3883487701416017, "optimizer_updates": 9560, "effective_batch": 512, "lr": 0.00017901723736120996, "gradient_norm": 0.30796292424201965, "tokens_per_second": 1073357.8234714102, "synthetic": false, "world_size": 8} {"step": 17140, "tokens": 4493148160, "loss": 2.3951562881469726, "optimizer_updates": 9570, "effective_batch": 512, "lr": 0.00017896948634444477, "gradient_norm": 0.3030487298965454, "tokens_per_second": 1076035.3024871477, "synthetic": false, "world_size": 8} {"step": 17160, "tokens": 4498391040, "loss": 2.3912380218505858, "optimizer_updates": 9580, "effective_batch": 512, "lr": 0.0001789216882422218, "gradient_norm": 0.24535885453224182, "tokens_per_second": 1092391.5704967647, "synthetic": false, "world_size": 8} {"step": 17180, "tokens": 4503633920, "loss": 2.3953060150146483, "optimizer_updates": 9590, "effective_batch": 512, "lr": 0.0001788738430871728, "gradient_norm": 0.3329929709434509, "tokens_per_second": 728748.884608889, "synthetic": false, "world_size": 8} {"step": 17200, "tokens": 4508876800, "loss": 2.3811977386474608, "optimizer_updates": 9600, "effective_batch": 512, "lr": 0.0001788259509119616, "gradient_norm": 0.27078568935394287, "tokens_per_second": 1083528.183873702, "synthetic": false, "world_size": 8} {"step": 17220, "tokens": 4514119680, "loss": 2.3897274017333983, "optimizer_updates": 9610, "effective_batch": 512, "lr": 0.00017877801174928426, "gradient_norm": 0.3170810043811798, "tokens_per_second": 1073691.3792404234, "synthetic": false, "world_size": 8} {"step": 17240, "tokens": 4519362560, "loss": 2.37987060546875, "optimizer_updates": 9620, "effective_batch": 512, "lr": 0.00017873002563186882, "gradient_norm": 0.3126865327358246, "tokens_per_second": 1077997.49699332, "synthetic": false, "world_size": 8} {"step": 17260, "tokens": 4524605440, "loss": 2.3979602813720704, "optimizer_updates": 9630, "effective_batch": 512, "lr": 0.00017868199259247537, "gradient_norm": 0.2999553382396698, "tokens_per_second": 1074552.8313888523, "synthetic": false, "world_size": 8} {"step": 17280, "tokens": 4529848320, "loss": 2.3827733993530273, "optimizer_updates": 9640, "effective_batch": 512, "lr": 0.00017863391266389605, "gradient_norm": 0.40157222747802734, "tokens_per_second": 978249.981524777, "synthetic": false, "world_size": 8} {"step": 17300, "tokens": 4535091200, "loss": 2.3804994583129884, "optimizer_updates": 9650, "effective_batch": 512, "lr": 0.00017858578587895505, "gradient_norm": 0.26501941680908203, "tokens_per_second": 1069660.2856902073, "synthetic": false, "world_size": 8} {"step": 17320, "tokens": 4540334080, "loss": 2.3922422409057615, "optimizer_updates": 9660, "effective_batch": 512, "lr": 0.00017853761227050853, "gradient_norm": 0.2518249452114105, "tokens_per_second": 1071685.7535719706, "synthetic": false, "world_size": 8} {"step": 17340, "tokens": 4545576960, "loss": 2.394455146789551, "optimizer_updates": 9670, "effective_batch": 512, "lr": 0.00017848939187144457, "gradient_norm": 0.36616307497024536, "tokens_per_second": 1076480.5165338186, "synthetic": false, "world_size": 8} {"step": 17360, "tokens": 4550819840, "loss": 2.379747772216797, "optimizer_updates": 9680, "effective_batch": 512, "lr": 0.00017844112471468324, "gradient_norm": 0.33180466294288635, "tokens_per_second": 1074587.7377227093, "synthetic": false, "world_size": 8} {"step": 17380, "tokens": 4556062720, "loss": 2.3917142868041994, "optimizer_updates": 9690, "effective_batch": 512, "lr": 0.00017839281083317652, "gradient_norm": 0.2727794051170349, "tokens_per_second": 1071582.777431324, "synthetic": false, "world_size": 8} {"step": 17400, "tokens": 4561305600, "loss": 2.3825971603393556, "optimizer_updates": 9700, "effective_batch": 512, "lr": 0.0001783444502599083, "gradient_norm": 0.3561238944530487, "tokens_per_second": 1089289.0831327569, "synthetic": false, "world_size": 8} {"step": 17420, "tokens": 4566548480, "loss": 2.393833541870117, "optimizer_updates": 9710, "effective_batch": 512, "lr": 0.0001782960430278943, "gradient_norm": 0.3059050738811493, "tokens_per_second": 775283.600149412, "synthetic": false, "world_size": 8} {"step": 17440, "tokens": 4571791360, "loss": 2.4017541885375975, "optimizer_updates": 9720, "effective_batch": 512, "lr": 0.00017824758917018224, "gradient_norm": 0.3053607642650604, "tokens_per_second": 1069316.9968578415, "synthetic": false, "world_size": 8} {"step": 17460, "tokens": 4577034240, "loss": 2.3834407806396483, "optimizer_updates": 9730, "effective_batch": 512, "lr": 0.0001781990887198514, "gradient_norm": 0.29468560218811035, "tokens_per_second": 1073330.6293884867, "synthetic": false, "world_size": 8} {"step": 17480, "tokens": 4582277120, "loss": 2.3861263275146483, "optimizer_updates": 9740, "effective_batch": 512, "lr": 0.00017815054171001313, "gradient_norm": 0.3275149166584015, "tokens_per_second": 1073130.6386769558, "synthetic": false, "world_size": 8} {"step": 17500, "tokens": 4587520000, "loss": 2.3772790908813475, "optimizer_updates": 9750, "effective_batch": 512, "lr": 0.00017810194817381044, "gradient_norm": 0.3220701515674591, "tokens_per_second": 1080223.4819039924, "synthetic": false, "world_size": 8} {"step": 17520, "tokens": 4592762880, "loss": 2.3860919952392576, "optimizer_updates": 9760, "effective_batch": 512, "lr": 0.00017805330814441817, "gradient_norm": 0.33710721135139465, "tokens_per_second": 1080908.8529603928, "synthetic": false, "world_size": 8} {"step": 17540, "tokens": 4598005760, "loss": 2.374311637878418, "optimizer_updates": 9770, "effective_batch": 512, "lr": 0.0001780046216550428, "gradient_norm": 0.30060070753097534, "tokens_per_second": 1087114.7197143922, "synthetic": false, "world_size": 8} {"step": 17560, "tokens": 4603248640, "loss": 2.3995426177978514, "optimizer_updates": 9780, "effective_batch": 512, "lr": 0.00017795588873892264, "gradient_norm": 0.3736644387245178, "tokens_per_second": 963516.4884629619, "synthetic": false, "world_size": 8} {"step": 17580, "tokens": 4608491520, "loss": 2.387821006774902, "optimizer_updates": 9790, "effective_batch": 512, "lr": 0.0001779071094293276, "gradient_norm": 0.2806302607059479, "tokens_per_second": 1074766.4615443242, "synthetic": false, "world_size": 8} {"step": 17600, "tokens": 4613734400, "loss": 2.39111442565918, "optimizer_updates": 9800, "effective_batch": 512, "lr": 0.00017785828375955934, "gradient_norm": 0.27820202708244324, "tokens_per_second": 1071775.9330265804, "synthetic": false, "world_size": 8} {"step": 17620, "tokens": 4618977280, "loss": 2.386026382446289, "optimizer_updates": 9810, "effective_batch": 512, "lr": 0.0001778094117629511, "gradient_norm": 0.2687213718891144, "tokens_per_second": 1080310.6566121813, "synthetic": false, "world_size": 8} {"step": 17640, "tokens": 4624220160, "loss": 2.3825284957885744, "optimizer_updates": 9820, "effective_batch": 512, "lr": 0.00017776049347286785, "gradient_norm": 0.24987870454788208, "tokens_per_second": 1070127.1118382555, "synthetic": false, "world_size": 8} {"step": 17660, "tokens": 4629463040, "loss": 2.3862369537353514, "optimizer_updates": 9830, "effective_batch": 512, "lr": 0.000177711528922706, "gradient_norm": 0.2552068829536438, "tokens_per_second": 1083580.5237722094, "synthetic": false, "world_size": 8} {"step": 17680, "tokens": 4634705920, "loss": 2.400862121582031, "optimizer_updates": 9840, "effective_batch": 512, "lr": 0.00017766251814589374, "gradient_norm": 0.29237568378448486, "tokens_per_second": 1072322.967654331, "synthetic": false, "world_size": 8} {"step": 17700, "tokens": 4639948800, "loss": 2.3841123580932617, "optimizer_updates": 9850, "effective_batch": 512, "lr": 0.00017761346117589066, "gradient_norm": 0.24330386519432068, "tokens_per_second": 1082006.503247271, "synthetic": false, "world_size": 8} {"step": 17720, "tokens": 4645191680, "loss": 2.374805450439453, "optimizer_updates": 9860, "effective_batch": 512, "lr": 0.00017756435804618798, "gradient_norm": 0.3079295754432678, "tokens_per_second": 1079574.5361638858, "synthetic": false, "world_size": 8} {"step": 17740, "tokens": 4650434560, "loss": 2.374683952331543, "optimizer_updates": 9870, "effective_batch": 512, "lr": 0.0001775152087903084, "gradient_norm": 0.3056707978248596, "tokens_per_second": 1079058.3961693824, "synthetic": false, "world_size": 8} {"step": 17760, "tokens": 4655677440, "loss": 2.376336097717285, "optimizer_updates": 9880, "effective_batch": 512, "lr": 0.00017746601344180606, "gradient_norm": 0.4888027012348175, "tokens_per_second": 1078497.1708825068, "synthetic": false, "world_size": 8} {"step": 17780, "tokens": 4660920320, "loss": 2.375102424621582, "optimizer_updates": 9890, "effective_batch": 512, "lr": 0.00017741677203426666, "gradient_norm": 0.28482815623283386, "tokens_per_second": 1084667.9471574803, "synthetic": false, "world_size": 8} {"step": 17800, "tokens": 4666163200, "loss": 2.3933610916137695, "optimizer_updates": 9900, "effective_batch": 512, "lr": 0.0001773674846013073, "gradient_norm": 0.26864948868751526, "tokens_per_second": 1078558.5528208488, "synthetic": false, "world_size": 8} {"step": 17820, "tokens": 4671406080, "loss": 2.3940557479858398, "optimizer_updates": 9910, "effective_batch": 512, "lr": 0.0001773181511765765, "gradient_norm": 0.24246187508106232, "tokens_per_second": 1082754.0741395936, "synthetic": false, "world_size": 8} {"step": 17840, "tokens": 4676648960, "loss": 2.3880502700805666, "optimizer_updates": 9920, "effective_batch": 512, "lr": 0.00017726877179375416, "gradient_norm": 0.28796491026878357, "tokens_per_second": 1082407.1545091341, "synthetic": false, "world_size": 8} {"step": 17860, "tokens": 4681891840, "loss": 2.3855276107788086, "optimizer_updates": 9930, "effective_batch": 512, "lr": 0.0001772193464865516, "gradient_norm": 0.25067567825317383, "tokens_per_second": 1078809.3058784038, "synthetic": false, "world_size": 8} {"step": 17880, "tokens": 4687134720, "loss": 2.382412338256836, "optimizer_updates": 9940, "effective_batch": 512, "lr": 0.00017716987528871146, "gradient_norm": 0.25398990511894226, "tokens_per_second": 1068365.3540838587, "synthetic": false, "world_size": 8} {"step": 17900, "tokens": 4692377600, "loss": 2.3902261734008787, "optimizer_updates": 9950, "effective_batch": 512, "lr": 0.00017712035823400774, "gradient_norm": 0.24775102734565735, "tokens_per_second": 1090059.313815442, "synthetic": false, "world_size": 8} {"step": 17920, "tokens": 4697620480, "loss": 2.3904302597045897, "optimizer_updates": 9960, "effective_batch": 512, "lr": 0.0001770707953562457, "gradient_norm": 0.2510029077529907, "tokens_per_second": 1080113.7477135796, "synthetic": false, "world_size": 8} {"step": 17940, "tokens": 4702863360, "loss": 2.3966724395751955, "optimizer_updates": 9970, "effective_batch": 512, "lr": 0.0001770211866892619, "gradient_norm": 0.33695876598358154, "tokens_per_second": 785389.633670553, "synthetic": false, "world_size": 8} {"step": 17960, "tokens": 4708106240, "loss": 2.385997200012207, "optimizer_updates": 9980, "effective_batch": 512, "lr": 0.0001769715322669242, "gradient_norm": 0.3085479736328125, "tokens_per_second": 1071100.9975520251, "synthetic": false, "world_size": 8} {"step": 17980, "tokens": 4713349120, "loss": 2.3976280212402346, "optimizer_updates": 9990, "effective_batch": 512, "lr": 0.00017692183212313165, "gradient_norm": 0.2460806965827942, "tokens_per_second": 1079742.8399239513, "synthetic": false, "world_size": 8} {"step": 18000, "tokens": 4718592000, "loss": 2.3856380462646483, "optimizer_updates": 10000, "effective_batch": 512, "lr": 0.00017687208629181455, "gradient_norm": 0.2781403362751007, "tokens_per_second": 1081323.9244689667, "synthetic": false, "world_size": 8} {"step": 18020, "tokens": 4723834880, "loss": 2.4056772232055663, "optimizer_updates": 10010, "effective_batch": 512, "lr": 0.00017682229480693435, "gradient_norm": 0.34862878918647766, "tokens_per_second": 842094.0863945998, "synthetic": false, "world_size": 8} {"step": 18040, "tokens": 4729077760, "loss": 2.4021575927734373, "optimizer_updates": 10020, "effective_batch": 512, "lr": 0.00017677245770248367, "gradient_norm": 0.2757125794887543, "tokens_per_second": 1084199.055650906, "synthetic": false, "world_size": 8} {"step": 18060, "tokens": 4734320640, "loss": 2.386534881591797, "optimizer_updates": 10030, "effective_batch": 512, "lr": 0.00017672257501248634, "gradient_norm": 0.3351060450077057, "tokens_per_second": 1081612.4172871439, "synthetic": false, "world_size": 8} {"step": 18080, "tokens": 4739563520, "loss": 2.395328903198242, "optimizer_updates": 10040, "effective_batch": 512, "lr": 0.00017667264677099725, "gradient_norm": 0.3226167857646942, "tokens_per_second": 768892.530569925, "synthetic": false, "world_size": 8} {"step": 18100, "tokens": 4744806400, "loss": 2.392061233520508, "optimizer_updates": 10050, "effective_batch": 512, "lr": 0.00017662267301210238, "gradient_norm": 0.48388323187828064, "tokens_per_second": 1076571.6230132822, "synthetic": false, "world_size": 8} {"step": 18120, "tokens": 4750049280, "loss": 2.3767316818237303, "optimizer_updates": 10060, "effective_batch": 512, "lr": 0.0001765726537699188, "gradient_norm": 0.300792932510376, "tokens_per_second": 1076513.4655972626, "synthetic": false, "world_size": 8} {"step": 18140, "tokens": 4755292160, "loss": 2.3847976684570313, "optimizer_updates": 10070, "effective_batch": 512, "lr": 0.0001765225890785947, "gradient_norm": 0.22597557306289673, "tokens_per_second": 1072814.0015561958, "synthetic": false, "world_size": 8} {"step": 18160, "tokens": 4760535040, "loss": 2.386759567260742, "optimizer_updates": 10080, "effective_batch": 512, "lr": 0.0001764724789723092, "gradient_norm": 0.31986311078071594, "tokens_per_second": 1069339.3065694435, "synthetic": false, "world_size": 8} {"step": 18180, "tokens": 4765777920, "loss": 2.3821998596191407, "optimizer_updates": 10090, "effective_batch": 512, "lr": 0.00017642232348527242, "gradient_norm": 0.33004140853881836, "tokens_per_second": 1068915.1045143455, "synthetic": false, "world_size": 8} {"step": 18200, "tokens": 4771020800, "loss": 2.3854894638061523, "optimizer_updates": 10100, "effective_batch": 512, "lr": 0.00017637212265172558, "gradient_norm": 0.3022213280200958, "tokens_per_second": 1064889.9461513902, "synthetic": false, "world_size": 8} {"step": 18220, "tokens": 4776263680, "loss": 2.4033533096313477, "optimizer_updates": 10110, "effective_batch": 512, "lr": 0.00017632187650594075, "gradient_norm": 0.27144384384155273, "tokens_per_second": 1060782.364760021, "synthetic": false, "world_size": 8} {"step": 18240, "tokens": 4781506560, "loss": 2.392521858215332, "optimizer_updates": 10120, "effective_batch": 512, "lr": 0.00017627158508222093, "gradient_norm": 0.2619488835334778, "tokens_per_second": 1066357.6594234768, "synthetic": false, "world_size": 8} {"step": 18260, "tokens": 4786749440, "loss": 2.389940643310547, "optimizer_updates": 10130, "effective_batch": 512, "lr": 0.00017622124841490012, "gradient_norm": 0.3206529915332794, "tokens_per_second": 1069285.50266438, "synthetic": false, "world_size": 8} {"step": 18280, "tokens": 4791992320, "loss": 2.37845401763916, "optimizer_updates": 10140, "effective_batch": 512, "lr": 0.00017617086653834316, "gradient_norm": 0.2547355592250824, "tokens_per_second": 1067377.4255470973, "synthetic": false, "world_size": 8} {"step": 18300, "tokens": 4797235200, "loss": 2.385264015197754, "optimizer_updates": 10150, "effective_batch": 512, "lr": 0.00017612043948694568, "gradient_norm": 0.28986820578575134, "tokens_per_second": 1077310.1653940736, "synthetic": false, "world_size": 8} {"step": 18320, "tokens": 4802478080, "loss": 2.391572952270508, "optimizer_updates": 10160, "effective_batch": 512, "lr": 0.0001760699672951343, "gradient_norm": 0.2487560659646988, "tokens_per_second": 1068099.4221259947, "synthetic": false, "world_size": 8} {"step": 18340, "tokens": 4807720960, "loss": 2.3838241577148436, "optimizer_updates": 10170, "effective_batch": 512, "lr": 0.0001760194499973663, "gradient_norm": 0.35152044892311096, "tokens_per_second": 1070230.7952039368, "synthetic": false, "world_size": 8} {"step": 18360, "tokens": 4812963840, "loss": 2.3884496688842773, "optimizer_updates": 10180, "effective_batch": 512, "lr": 0.0001759688876281299, "gradient_norm": 0.33860325813293457, "tokens_per_second": 1069340.3344795138, "synthetic": false, "world_size": 8} {"step": 18380, "tokens": 4818206720, "loss": 2.3888662338256834, "optimizer_updates": 10190, "effective_batch": 512, "lr": 0.00017591828022194402, "gradient_norm": 0.2847307324409485, "tokens_per_second": 1068081.740694667, "synthetic": false, "world_size": 8} {"step": 18400, "tokens": 4823449600, "loss": 2.379995918273926, "optimizer_updates": 10200, "effective_batch": 512, "lr": 0.00017586762781335825, "gradient_norm": 0.2886979877948761, "tokens_per_second": 1074439.4823817073, "synthetic": false, "world_size": 8} {"step": 18420, "tokens": 4828692480, "loss": 2.391433525085449, "optimizer_updates": 10210, "effective_batch": 512, "lr": 0.00017581693043695307, "gradient_norm": 0.29589539766311646, "tokens_per_second": 1072160.534629201, "synthetic": false, "world_size": 8} {"step": 18440, "tokens": 4833935360, "loss": 2.388055610656738, "optimizer_updates": 10220, "effective_batch": 512, "lr": 0.00017576618812733952, "gradient_norm": 0.2648415267467499, "tokens_per_second": 1076946.0003529696, "synthetic": false, "world_size": 8} {"step": 18460, "tokens": 4839178240, "loss": 2.376412010192871, "optimizer_updates": 10230, "effective_batch": 512, "lr": 0.0001757154009191594, "gradient_norm": 0.2978704869747162, "tokens_per_second": 1076667.803697346, "synthetic": false, "world_size": 8} {"step": 18480, "tokens": 4844421120, "loss": 2.385309600830078, "optimizer_updates": 10240, "effective_batch": 512, "lr": 0.0001756645688470851, "gradient_norm": 0.25920045375823975, "tokens_per_second": 1064193.5151026594, "synthetic": false, "world_size": 8} {"step": 18500, "tokens": 4849664000, "loss": 2.388240623474121, "optimizer_updates": 10250, "effective_batch": 512, "lr": 0.00017561369194581968, "gradient_norm": 0.26173168420791626, "tokens_per_second": 1070787.263971711, "synthetic": false, "world_size": 8} {"step": 18520, "tokens": 4854906880, "loss": 2.3873449325561524, "optimizer_updates": 10260, "effective_batch": 512, "lr": 0.00017556277025009682, "gradient_norm": 0.4799138009548187, "tokens_per_second": 1074820.478470138, "synthetic": false, "world_size": 8} {"step": 18540, "tokens": 4860149760, "loss": 2.379612159729004, "optimizer_updates": 10270, "effective_batch": 512, "lr": 0.00017551180379468066, "gradient_norm": 0.2534312903881073, "tokens_per_second": 1087851.8253896043, "synthetic": false, "world_size": 8} {"step": 18560, "tokens": 4865392640, "loss": 2.3968856811523436, "optimizer_updates": 10280, "effective_batch": 512, "lr": 0.00017546079261436613, "gradient_norm": 0.267630398273468, "tokens_per_second": 758308.0917479057, "synthetic": false, "world_size": 8} {"step": 18580, "tokens": 4870635520, "loss": 2.4058727264404296, "optimizer_updates": 10290, "effective_batch": 512, "lr": 0.00017540973674397845, "gradient_norm": 0.36441120505332947, "tokens_per_second": 1072092.8246026204, "synthetic": false, "world_size": 8} {"step": 18600, "tokens": 4875878400, "loss": 2.3807537078857424, "optimizer_updates": 10300, "effective_batch": 512, "lr": 0.00017535863621837347, "gradient_norm": 0.2563517093658447, "tokens_per_second": 1071436.5171246196, "synthetic": false, "world_size": 8} {"step": 18620, "tokens": 4881121280, "loss": 2.3954870223999025, "optimizer_updates": 10310, "effective_batch": 512, "lr": 0.00017530749107243758, "gradient_norm": 0.24081772565841675, "tokens_per_second": 1069917.5547251075, "synthetic": false, "world_size": 8} {"step": 18640, "tokens": 4886364160, "loss": 2.3882917404174804, "optimizer_updates": 10320, "effective_batch": 512, "lr": 0.00017525630134108746, "gradient_norm": 0.33597445487976074, "tokens_per_second": 1072821.3428611832, "synthetic": false, "world_size": 8} {"step": 18660, "tokens": 4891607040, "loss": 2.381374168395996, "optimizer_updates": 10330, "effective_batch": 512, "lr": 0.0001752050670592704, "gradient_norm": 0.2647613286972046, "tokens_per_second": 1077518.1974205847, "synthetic": false, "world_size": 8} {"step": 18680, "tokens": 4896849920, "loss": 2.3831527709960936, "optimizer_updates": 10340, "effective_batch": 512, "lr": 0.00017515378826196405, "gradient_norm": 0.2545880675315857, "tokens_per_second": 1085533.7271634713, "synthetic": false, "world_size": 8} {"step": 18700, "tokens": 4902092800, "loss": 2.375986099243164, "optimizer_updates": 10350, "effective_batch": 512, "lr": 0.00017510246498417636, "gradient_norm": 0.2472553700208664, "tokens_per_second": 1085751.9333915822, "synthetic": false, "world_size": 8} {"step": 18720, "tokens": 4907335680, "loss": 2.3862375259399413, "optimizer_updates": 10360, "effective_batch": 512, "lr": 0.0001750510972609458, "gradient_norm": 0.3211780786514282, "tokens_per_second": 1076440.2692928943, "synthetic": false, "world_size": 8} {"step": 18740, "tokens": 4912578560, "loss": 2.3885818481445313, "optimizer_updates": 10370, "effective_batch": 512, "lr": 0.00017499968512734107, "gradient_norm": 0.39771610498428345, "tokens_per_second": 1072567.1399632718, "synthetic": false, "world_size": 8} {"step": 18760, "tokens": 4917821440, "loss": 2.379191589355469, "optimizer_updates": 10380, "effective_batch": 512, "lr": 0.00017494822861846123, "gradient_norm": 0.2396448403596878, "tokens_per_second": 1076264.5449905705, "synthetic": false, "world_size": 8} {"step": 18780, "tokens": 4923064320, "loss": 2.370317268371582, "optimizer_updates": 10390, "effective_batch": 512, "lr": 0.00017489672776943566, "gradient_norm": 0.25241491198539734, "tokens_per_second": 1087477.431013076, "synthetic": false, "world_size": 8} {"step": 18800, "tokens": 4928307200, "loss": 2.3827314376831055, "optimizer_updates": 10400, "effective_batch": 512, "lr": 0.00017484518261542395, "gradient_norm": 0.3121647834777832, "tokens_per_second": 1086709.496939037, "synthetic": false, "world_size": 8} {"step": 18820, "tokens": 4933550080, "loss": 2.3929655075073244, "optimizer_updates": 10410, "effective_batch": 512, "lr": 0.00017479359319161596, "gradient_norm": 0.24359028041362762, "tokens_per_second": 1067081.0422025628, "synthetic": false, "world_size": 8} {"step": 18840, "tokens": 4938792960, "loss": 2.3890161514282227, "optimizer_updates": 10420, "effective_batch": 512, "lr": 0.0001747419595332318, "gradient_norm": 0.3750878572463989, "tokens_per_second": 1083885.1436201525, "synthetic": false, "world_size": 8} {"step": 18860, "tokens": 4944035840, "loss": 2.3932622909545898, "optimizer_updates": 10430, "effective_batch": 512, "lr": 0.00017469028167552177, "gradient_norm": 0.24364513158798218, "tokens_per_second": 1084879.9691518832, "synthetic": false, "world_size": 8} {"step": 18880, "tokens": 4949278720, "loss": 2.3842573165893555, "optimizer_updates": 10440, "effective_batch": 512, "lr": 0.0001746385596537663, "gradient_norm": 0.2805836796760559, "tokens_per_second": 1078819.4168398525, "synthetic": false, "world_size": 8} {"step": 18900, "tokens": 4954521600, "loss": 2.3882999420166016, "optimizer_updates": 10450, "effective_batch": 512, "lr": 0.00017458679350327607, "gradient_norm": 0.32170698046684265, "tokens_per_second": 1078294.230667424, "synthetic": false, "world_size": 8} {"step": 18920, "tokens": 4959764480, "loss": 2.391866111755371, "optimizer_updates": 10460, "effective_batch": 512, "lr": 0.00017453498325939175, "gradient_norm": 0.27878251671791077, "tokens_per_second": 1078704.8399596945, "synthetic": false, "world_size": 8} {"step": 18940, "tokens": 4965007360, "loss": 2.367872619628906, "optimizer_updates": 10470, "effective_batch": 512, "lr": 0.00017448312895748422, "gradient_norm": 0.24542158842086792, "tokens_per_second": 1082293.1271473658, "synthetic": false, "world_size": 8} {"step": 18960, "tokens": 4970250240, "loss": 2.3980846405029297, "optimizer_updates": 10480, "effective_batch": 512, "lr": 0.00017443123063295442, "gradient_norm": 0.2500987648963928, "tokens_per_second": 1071416.3106399893, "synthetic": false, "world_size": 8} {"step": 18980, "tokens": 4975493120, "loss": 2.3896459579467773, "optimizer_updates": 10490, "effective_batch": 512, "lr": 0.00017437928832123327, "gradient_norm": 0.3074074387550354, "tokens_per_second": 1080562.9361962427, "synthetic": false, "world_size": 8} {"step": 19000, "tokens": 4980736000, "loss": 2.3938199996948244, "optimizer_updates": 10500, "effective_batch": 512, "lr": 0.00017432730205778186, "gradient_norm": 0.25111016631126404, "tokens_per_second": 1080142.0400816922, "synthetic": false, "world_size": 8} {"step": 19020, "tokens": 4985978880, "loss": 2.382222366333008, "optimizer_updates": 10510, "effective_batch": 512, "lr": 0.00017427527187809113, "gradient_norm": 0.2635866403579712, "tokens_per_second": 835214.1136598361, "synthetic": false, "world_size": 8} {"step": 19040, "tokens": 4991221760, "loss": 2.384142303466797, "optimizer_updates": 10520, "effective_batch": 512, "lr": 0.00017422319781768215, "gradient_norm": 0.28904077410697937, "tokens_per_second": 1080481.0955894769, "synthetic": false, "world_size": 8} {"step": 19060, "tokens": 4996464640, "loss": 2.3864126205444336, "optimizer_updates": 10530, "effective_batch": 512, "lr": 0.0001741710799121058, "gradient_norm": 0.2883259356021881, "tokens_per_second": 1074490.3040146602, "synthetic": false, "world_size": 8} {"step": 19080, "tokens": 5001707520, "loss": 2.3906227111816407, "optimizer_updates": 10540, "effective_batch": 512, "lr": 0.00017411891819694303, "gradient_norm": 0.29634997248649597, "tokens_per_second": 1067799.7903316366, "synthetic": false, "world_size": 8} {"step": 19100, "tokens": 5006950400, "loss": 2.383111572265625, "optimizer_updates": 10550, "effective_batch": 512, "lr": 0.0001740667127078046, "gradient_norm": 0.2643486261367798, "tokens_per_second": 1074728.3024414985, "synthetic": false, "world_size": 8} {"step": 19120, "tokens": 5012193280, "loss": 2.3789751052856447, "optimizer_updates": 10560, "effective_batch": 512, "lr": 0.00017401446348033116, "gradient_norm": 0.29785019159317017, "tokens_per_second": 976343.2256980924, "synthetic": false, "world_size": 8} {"step": 19140, "tokens": 5017436160, "loss": 2.391374206542969, "optimizer_updates": 10570, "effective_batch": 512, "lr": 0.0001739621705501933, "gradient_norm": 0.31250807642936707, "tokens_per_second": 1076745.1962437562, "synthetic": false, "world_size": 8} {"step": 19160, "tokens": 5022679040, "loss": 2.38354434967041, "optimizer_updates": 10580, "effective_batch": 512, "lr": 0.00017390983395309138, "gradient_norm": 0.2521779239177704, "tokens_per_second": 1080527.1880855714, "synthetic": false, "world_size": 8} {"step": 19180, "tokens": 5027921920, "loss": 2.373976135253906, "optimizer_updates": 10590, "effective_batch": 512, "lr": 0.00017385745372475557, "gradient_norm": 0.3420086205005646, "tokens_per_second": 1074137.785131786, "synthetic": false, "world_size": 8} {"step": 19200, "tokens": 5033164800, "loss": 2.3922307968139647, "optimizer_updates": 10600, "effective_batch": 512, "lr": 0.00017380502990094586, "gradient_norm": 0.2426748275756836, "tokens_per_second": 1071997.7806327129, "synthetic": false, "world_size": 8} {"step": 19220, "tokens": 5038407680, "loss": 2.3757043838500977, "optimizer_updates": 10610, "effective_batch": 512, "lr": 0.00017375256251745197, "gradient_norm": 0.28654053807258606, "tokens_per_second": 1083351.1417620536, "synthetic": false, "world_size": 8} {"step": 19240, "tokens": 5043650560, "loss": 2.3881242752075194, "optimizer_updates": 10620, "effective_batch": 512, "lr": 0.00017370005161009342, "gradient_norm": 0.2630523443222046, "tokens_per_second": 1076544.3547266198, "synthetic": false, "world_size": 8} {"step": 19260, "tokens": 5048893440, "loss": 2.3763616561889647, "optimizer_updates": 10630, "effective_batch": 512, "lr": 0.00017364749721471937, "gradient_norm": 0.2631901800632477, "tokens_per_second": 1075610.5714274484, "synthetic": false, "world_size": 8} {"step": 19280, "tokens": 5054136320, "loss": 2.378889274597168, "optimizer_updates": 10640, "effective_batch": 512, "lr": 0.00017359489936720867, "gradient_norm": 0.2926936447620392, "tokens_per_second": 1078089.1973852715, "synthetic": false, "world_size": 8} {"step": 19300, "tokens": 5059379200, "loss": 2.384137725830078, "optimizer_updates": 10650, "effective_batch": 512, "lr": 0.00017354225810346988, "gradient_norm": 0.25974392890930176, "tokens_per_second": 1082742.734138141, "synthetic": false, "world_size": 8} {"step": 19320, "tokens": 5064622080, "loss": 2.380582809448242, "optimizer_updates": 10660, "effective_batch": 512, "lr": 0.00017348957345944123, "gradient_norm": 0.2906965911388397, "tokens_per_second": 1084738.9496653562, "synthetic": false, "world_size": 8} {"step": 19340, "tokens": 5069864960, "loss": 2.38070011138916, "optimizer_updates": 10670, "effective_batch": 512, "lr": 0.00017343684547109045, "gradient_norm": 0.26307156682014465, "tokens_per_second": 1077748.070464215, "synthetic": false, "world_size": 8} {"step": 19360, "tokens": 5075107840, "loss": 2.3824609756469726, "optimizer_updates": 10680, "effective_batch": 512, "lr": 0.000173384074174415, "gradient_norm": 0.2683087885379791, "tokens_per_second": 1040134.7083557432, "synthetic": false, "world_size": 8} {"step": 19380, "tokens": 5080350720, "loss": 2.3891244888305665, "optimizer_updates": 10690, "effective_batch": 512, "lr": 0.00017333125960544176, "gradient_norm": 0.3514416515827179, "tokens_per_second": 1081949.484445648, "synthetic": false, "world_size": 8} {"step": 19400, "tokens": 5085593600, "loss": 2.3929141998291015, "optimizer_updates": 10700, "effective_batch": 512, "lr": 0.00017327840180022725, "gradient_norm": 0.2691732347011566, "tokens_per_second": 1084771.9400386587, "synthetic": false, "world_size": 8} {"step": 19420, "tokens": 5090836480, "loss": 2.3888217926025392, "optimizer_updates": 10710, "effective_batch": 512, "lr": 0.0001732255007948575, "gradient_norm": 0.28454282879829407, "tokens_per_second": 981831.001289305, "synthetic": false, "world_size": 8} {"step": 19440, "tokens": 5096079360, "loss": 2.386530113220215, "optimizer_updates": 10720, "effective_batch": 512, "lr": 0.00017317255662544805, "gradient_norm": 0.2685766816139221, "tokens_per_second": 1071715.7427595546, "synthetic": false, "world_size": 8} {"step": 19460, "tokens": 5101322240, "loss": 2.3721197128295897, "optimizer_updates": 10730, "effective_batch": 512, "lr": 0.00017311956932814383, "gradient_norm": 0.2817346453666687, "tokens_per_second": 1063403.5307869217, "synthetic": false, "world_size": 8} {"step": 19480, "tokens": 5106565120, "loss": 2.3773319244384767, "optimizer_updates": 10740, "effective_batch": 512, "lr": 0.00017306653893911926, "gradient_norm": 0.2654542326927185, "tokens_per_second": 1081812.6282308782, "synthetic": false, "world_size": 8} {"step": 19500, "tokens": 5111808000, "loss": 2.3668502807617187, "optimizer_updates": 10750, "effective_batch": 512, "lr": 0.0001730134654945782, "gradient_norm": 0.2672210931777954, "tokens_per_second": 1084104.1625364856, "synthetic": false, "world_size": 8} {"step": 19520, "tokens": 5117050880, "loss": 2.383775520324707, "optimizer_updates": 10760, "effective_batch": 512, "lr": 0.00017296034903075387, "gradient_norm": 0.25125959515571594, "tokens_per_second": 1062249.8956950866, "synthetic": false, "world_size": 8} {"step": 19540, "tokens": 5122293760, "loss": 2.3941478729248047, "optimizer_updates": 10770, "effective_batch": 512, "lr": 0.0001729071895839089, "gradient_norm": 0.2736859619617462, "tokens_per_second": 1077775.251585656, "synthetic": false, "world_size": 8} {"step": 19560, "tokens": 5127536640, "loss": 2.38934383392334, "optimizer_updates": 10780, "effective_batch": 512, "lr": 0.00017285398719033517, "gradient_norm": 0.30608266592025757, "tokens_per_second": 1079374.838485095, "synthetic": false, "world_size": 8} {"step": 19580, "tokens": 5132779520, "loss": 2.3868656158447266, "optimizer_updates": 10790, "effective_batch": 512, "lr": 0.00017280074188635403, "gradient_norm": 0.23920448124408722, "tokens_per_second": 773223.5154226584, "synthetic": false, "world_size": 8} {"step": 19600, "tokens": 5138022400, "loss": 2.371054267883301, "optimizer_updates": 10800, "effective_batch": 512, "lr": 0.00017274745370831598, "gradient_norm": 0.276624470949173, "tokens_per_second": 1077101.6104983839, "synthetic": false, "world_size": 8} {"step": 19620, "tokens": 5143265280, "loss": 2.3910043716430662, "optimizer_updates": 10810, "effective_batch": 512, "lr": 0.00017269412269260088, "gradient_norm": 0.26729533076286316, "tokens_per_second": 1078637.7201965924, "synthetic": false, "world_size": 8} {"step": 19640, "tokens": 5148508160, "loss": 2.3903835296630858, "optimizer_updates": 10820, "effective_batch": 512, "lr": 0.00017264074887561777, "gradient_norm": 0.4066357910633087, "tokens_per_second": 1092856.235516845, "synthetic": false, "world_size": 8} {"step": 19660, "tokens": 5153751040, "loss": 2.383045196533203, "optimizer_updates": 10830, "effective_batch": 512, "lr": 0.000172587332293805, "gradient_norm": 0.30429399013519287, "tokens_per_second": 1087652.070716941, "synthetic": false, "world_size": 8} {"step": 19680, "tokens": 5158993920, "loss": 2.379221725463867, "optimizer_updates": 10840, "effective_batch": 512, "lr": 0.00017253387298363002, "gradient_norm": 0.24697847664356232, "tokens_per_second": 737567.6842514228, "synthetic": false, "world_size": 8} {"step": 19700, "tokens": 5164236800, "loss": 2.3759286880493162, "optimizer_updates": 10850, "effective_batch": 512, "lr": 0.0001724803709815895, "gradient_norm": 0.3190629482269287, "tokens_per_second": 1095836.647225328, "synthetic": false, "world_size": 8} {"step": 19720, "tokens": 5169479680, "loss": 2.3815404891967775, "optimizer_updates": 10860, "effective_batch": 512, "lr": 0.00017242682632420927, "gradient_norm": 0.2859245836734772, "tokens_per_second": 1095052.7601330134, "synthetic": false, "world_size": 8} {"step": 19740, "tokens": 5174722560, "loss": 2.3867321014404297, "optimizer_updates": 10870, "effective_batch": 512, "lr": 0.00017237323904804424, "gradient_norm": 0.27255013585090637, "tokens_per_second": 1054643.9924966544, "synthetic": false, "world_size": 8} {"step": 19760, "tokens": 5179965440, "loss": 2.386788749694824, "optimizer_updates": 10880, "effective_batch": 512, "lr": 0.00017231960918967845, "gradient_norm": 0.36786869168281555, "tokens_per_second": 1094132.627814935, "synthetic": false, "world_size": 8} {"step": 19780, "tokens": 5185208320, "loss": 2.3832902908325195, "optimizer_updates": 10890, "effective_batch": 512, "lr": 0.00017226593678572498, "gradient_norm": 0.28830090165138245, "tokens_per_second": 1098525.130699424, "synthetic": false, "world_size": 8} {"step": 19800, "tokens": 5190451200, "loss": 2.3859413146972654, "optimizer_updates": 10900, "effective_batch": 512, "lr": 0.00017221222187282598, "gradient_norm": 0.24694617092609406, "tokens_per_second": 1083847.8966596473, "synthetic": false, "world_size": 8} {"step": 19820, "tokens": 5195694080, "loss": 2.38079833984375, "optimizer_updates": 10910, "effective_batch": 512, "lr": 0.0001721584644876526, "gradient_norm": 0.28534141182899475, "tokens_per_second": 1100336.880516979, "synthetic": false, "world_size": 8} {"step": 19840, "tokens": 5200936960, "loss": 2.385426902770996, "optimizer_updates": 10920, "effective_batch": 512, "lr": 0.00017210466466690503, "gradient_norm": 0.2561454772949219, "tokens_per_second": 1083133.4269955275, "synthetic": false, "world_size": 8} {"step": 19860, "tokens": 5206179840, "loss": 2.3748847961425783, "optimizer_updates": 10930, "effective_batch": 512, "lr": 0.00017205082244731236, "gradient_norm": 0.319109708070755, "tokens_per_second": 1001334.3107125045, "synthetic": false, "world_size": 8} {"step": 19880, "tokens": 5211422720, "loss": 2.385259246826172, "optimizer_updates": 10940, "effective_batch": 512, "lr": 0.00017199693786563273, "gradient_norm": 0.2790383994579315, "tokens_per_second": 1095591.0807713757, "synthetic": false, "world_size": 8} {"step": 19900, "tokens": 5216665600, "loss": 2.3998594284057617, "optimizer_updates": 10950, "effective_batch": 512, "lr": 0.00017194301095865304, "gradient_norm": 0.23286116123199463, "tokens_per_second": 1096875.0326261644, "synthetic": false, "world_size": 8} {"step": 19920, "tokens": 5221908480, "loss": 2.3849199295043944, "optimizer_updates": 10960, "effective_batch": 512, "lr": 0.00017188904176318925, "gradient_norm": 0.241264209151268, "tokens_per_second": 1095619.1993521876, "synthetic": false, "world_size": 8} {"step": 19940, "tokens": 5227151360, "loss": 2.377307891845703, "optimizer_updates": 10970, "effective_batch": 512, "lr": 0.0001718350303160861, "gradient_norm": 0.2838045358657837, "tokens_per_second": 1089983.5086213616, "synthetic": false, "world_size": 8} {"step": 19960, "tokens": 5232394240, "loss": 2.3824178695678713, "optimizer_updates": 10980, "effective_batch": 512, "lr": 0.0001717809766542172, "gradient_norm": 0.2783464789390564, "tokens_per_second": 1093743.1821471744, "synthetic": false, "world_size": 8} {"step": 19980, "tokens": 5237637120, "loss": 2.391627311706543, "optimizer_updates": 10990, "effective_batch": 512, "lr": 0.000171726880814485, "gradient_norm": 0.2577689588069916, "tokens_per_second": 1093281.9978907334, "synthetic": false, "world_size": 8} {"step": 20000, "tokens": 5242880000, "loss": 2.3853118896484373, "optimizer_updates": 11000, "effective_batch": 512, "lr": 0.00017167274283382068, "gradient_norm": 0.3962107002735138, "tokens_per_second": 1081536.8829901214, "synthetic": false, "world_size": 8} {"step": 20020, "tokens": 5248122880, "loss": 2.385233688354492, "optimizer_updates": 11010, "effective_batch": 512, "lr": 0.00017161856274918426, "gradient_norm": 0.24028714001178741, "tokens_per_second": 762154.5213309181, "synthetic": false, "world_size": 8} {"step": 20040, "tokens": 5253365760, "loss": 2.382913017272949, "optimizer_updates": 11020, "effective_batch": 512, "lr": 0.00017156434059756445, "gradient_norm": 0.2841578722000122, "tokens_per_second": 1098474.5997696107, "synthetic": false, "world_size": 8} {"step": 20060, "tokens": 5258608640, "loss": 2.3794898986816406, "optimizer_updates": 11030, "effective_batch": 512, "lr": 0.00017151007641597873, "gradient_norm": 0.264026015996933, "tokens_per_second": 1099263.0792678194, "synthetic": false, "world_size": 8} {"step": 20080, "tokens": 5263851520, "loss": 2.3824541091918947, "optimizer_updates": 11040, "effective_batch": 512, "lr": 0.00017145577024147321, "gradient_norm": 0.2907159924507141, "tokens_per_second": 1092654.6182594218, "synthetic": false, "world_size": 8} {"step": 20100, "tokens": 5269094400, "loss": 2.3833280563354493, "optimizer_updates": 11050, "effective_batch": 512, "lr": 0.00017140142211112278, "gradient_norm": 0.2817089855670929, "tokens_per_second": 1090416.5264884012, "synthetic": false, "world_size": 8} {"step": 20120, "tokens": 5274337280, "loss": 2.3972572326660155, "optimizer_updates": 11060, "effective_batch": 512, "lr": 0.00017134703206203082, "gradient_norm": 0.35694921016693115, "tokens_per_second": 1088957.2728905356, "synthetic": false, "world_size": 8} {"step": 20140, "tokens": 5279580160, "loss": 2.380095100402832, "optimizer_updates": 11070, "effective_batch": 512, "lr": 0.00017129260013132945, "gradient_norm": 0.35293036699295044, "tokens_per_second": 1091131.0906103281, "synthetic": false, "world_size": 8} {"step": 20160, "tokens": 5284823040, "loss": 2.3945430755615233, "optimizer_updates": 11080, "effective_batch": 512, "lr": 0.00017123812635617936, "gradient_norm": 0.30366113781929016, "tokens_per_second": 1092731.8881848913, "synthetic": false, "world_size": 8} {"step": 20180, "tokens": 5290065920, "loss": 2.378276824951172, "optimizer_updates": 11090, "effective_batch": 512, "lr": 0.00017118361077376974, "gradient_norm": 0.34202852845191956, "tokens_per_second": 1085258.9508807606, "synthetic": false, "world_size": 8} {"step": 20200, "tokens": 5295308800, "loss": 2.3772396087646483, "optimizer_updates": 11100, "effective_batch": 512, "lr": 0.0001711290534213184, "gradient_norm": 0.2831333875656128, "tokens_per_second": 786214.9772627124, "synthetic": false, "world_size": 8} {"step": 20220, "tokens": 5300551680, "loss": 2.3786556243896486, "optimizer_updates": 11110, "effective_batch": 512, "lr": 0.00017107445433607165, "gradient_norm": 0.28069064021110535, "tokens_per_second": 1091022.5207169272, "synthetic": false, "world_size": 8} {"step": 20240, "tokens": 5305794560, "loss": 2.380240821838379, "optimizer_updates": 11120, "effective_batch": 512, "lr": 0.0001710198135553042, "gradient_norm": 0.25132590532302856, "tokens_per_second": 1098599.6570003163, "synthetic": false, "world_size": 8} {"step": 20260, "tokens": 5311037440, "loss": 2.371603775024414, "optimizer_updates": 11130, "effective_batch": 512, "lr": 0.0001709651311163194, "gradient_norm": 0.26969316601753235, "tokens_per_second": 1096985.252982005, "synthetic": false, "world_size": 8} {"step": 20280, "tokens": 5316280320, "loss": 2.372129440307617, "optimizer_updates": 11140, "effective_batch": 512, "lr": 0.0001709104070564489, "gradient_norm": 0.298501193523407, "tokens_per_second": 1094457.0715388572, "synthetic": false, "world_size": 8} {"step": 20300, "tokens": 5321523200, "loss": 2.378250312805176, "optimizer_updates": 11150, "effective_batch": 512, "lr": 0.0001708556414130528, "gradient_norm": 0.2600558400154114, "tokens_per_second": 1076882.5201832044, "synthetic": false, "world_size": 8} {"step": 20320, "tokens": 5326766080, "loss": 2.3986520767211914, "optimizer_updates": 11160, "effective_batch": 512, "lr": 0.00017080083422351961, "gradient_norm": 0.24481292068958282, "tokens_per_second": 1094843.6613227238, "synthetic": false, "world_size": 8} {"step": 20340, "tokens": 5332008960, "loss": 2.3974796295166017, "optimizer_updates": 11170, "effective_batch": 512, "lr": 0.00017074598552526616, "gradient_norm": 0.3662129044532776, "tokens_per_second": 1095123.5199674976, "synthetic": false, "world_size": 8} {"step": 20360, "tokens": 5337251840, "loss": 2.3885498046875, "optimizer_updates": 11180, "effective_batch": 512, "lr": 0.0001706910953557377, "gradient_norm": 0.2623741626739502, "tokens_per_second": 1098224.9856437342, "synthetic": false, "world_size": 8} {"step": 20380, "tokens": 5342494720, "loss": 2.3895450592041017, "optimizer_updates": 11190, "effective_batch": 512, "lr": 0.0001706361637524077, "gradient_norm": 0.31526342034339905, "tokens_per_second": 1095358.9999964605, "synthetic": false, "world_size": 8} {"step": 20400, "tokens": 5347737600, "loss": 2.392243003845215, "optimizer_updates": 11200, "effective_batch": 512, "lr": 0.00017058119075277797, "gradient_norm": 0.26657137274742126, "tokens_per_second": 1099346.5770448453, "synthetic": false, "world_size": 8} {"step": 20420, "tokens": 5352980480, "loss": 2.3769880294799806, "optimizer_updates": 11210, "effective_batch": 512, "lr": 0.0001705261763943786, "gradient_norm": 0.2817787826061249, "tokens_per_second": 1104613.377294458, "synthetic": false, "world_size": 8} {"step": 20440, "tokens": 5358223360, "loss": 2.3859603881835936, "optimizer_updates": 11220, "effective_batch": 512, "lr": 0.00017047112071476783, "gradient_norm": 0.32184669375419617, "tokens_per_second": 1095195.9811937085, "synthetic": false, "world_size": 8} {"step": 20460, "tokens": 5363466240, "loss": 2.3702457427978514, "optimizer_updates": 11230, "effective_batch": 512, "lr": 0.00017041602375153216, "gradient_norm": 0.27680695056915283, "tokens_per_second": 1089574.0400064613, "synthetic": false, "world_size": 8} {"step": 20480, "tokens": 5368709120, "loss": 2.3906700134277346, "optimizer_updates": 11240, "effective_batch": 512, "lr": 0.00017036088554228633, "gradient_norm": 0.35117223858833313, "tokens_per_second": 1089094.794700205, "synthetic": false, "world_size": 8} {"step": 20500, "tokens": 5373952000, "loss": 2.3821437835693358, "optimizer_updates": 11250, "effective_batch": 512, "lr": 0.00017030570612467315, "gradient_norm": 0.2580946385860443, "tokens_per_second": 1101897.065684084, "synthetic": false, "world_size": 8} {"step": 20520, "tokens": 5379194880, "loss": 2.3914684295654296, "optimizer_updates": 11260, "effective_batch": 512, "lr": 0.00017025048553636363, "gradient_norm": 0.2743726372718811, "tokens_per_second": 1090892.7324906678, "synthetic": false, "world_size": 8} {"step": 20540, "tokens": 5384437760, "loss": 2.3822765350341797, "optimizer_updates": 11270, "effective_batch": 512, "lr": 0.00017019522381505684, "gradient_norm": 0.3355204463005066, "tokens_per_second": 1091962.635825329, "synthetic": false, "world_size": 8} {"step": 20560, "tokens": 5389680640, "loss": 2.389047050476074, "optimizer_updates": 11280, "effective_batch": 512, "lr": 0.00017013992099847996, "gradient_norm": 0.25852108001708984, "tokens_per_second": 1091301.0189551555, "synthetic": false, "world_size": 8} {"step": 20580, "tokens": 5394923520, "loss": 2.3704095840454102, "optimizer_updates": 11290, "effective_batch": 512, "lr": 0.00017008457712438814, "gradient_norm": 0.29543396830558777, "tokens_per_second": 1088699.6307790608, "synthetic": false, "world_size": 8} {"step": 20600, "tokens": 5400166400, "loss": 2.392543983459473, "optimizer_updates": 11300, "effective_batch": 512, "lr": 0.00017002919223056475, "gradient_norm": 0.30455076694488525, "tokens_per_second": 1085927.0915113385, "synthetic": false, "world_size": 8} {"step": 20620, "tokens": 5405409280, "loss": 2.3922054290771486, "optimizer_updates": 11310, "effective_batch": 512, "lr": 0.00016997376635482099, "gradient_norm": 0.27739888429641724, "tokens_per_second": 1092055.0286628054, "synthetic": false, "world_size": 8} {"step": 20640, "tokens": 5410652160, "loss": 2.3682151794433595, "optimizer_updates": 11320, "effective_batch": 512, "lr": 0.0001699182995349961, "gradient_norm": 0.29283851385116577, "tokens_per_second": 1093013.516905237, "synthetic": false, "world_size": 8} {"step": 20660, "tokens": 5415895040, "loss": 2.3726924896240233, "optimizer_updates": 11330, "effective_batch": 512, "lr": 0.00016986279180895725, "gradient_norm": 0.27790793776512146, "tokens_per_second": 1092025.3674960309, "synthetic": false, "world_size": 8} {"step": 20680, "tokens": 5421137920, "loss": 2.389101028442383, "optimizer_updates": 11340, "effective_batch": 512, "lr": 0.00016980724321459962, "gradient_norm": 0.3681933581829071, "tokens_per_second": 722439.1910298535, "synthetic": false, "world_size": 8} {"step": 20700, "tokens": 5426380800, "loss": 2.3754377365112305, "optimizer_updates": 11350, "effective_batch": 512, "lr": 0.00016975165378984615, "gradient_norm": 0.29515719413757324, "tokens_per_second": 1090435.9208481524, "synthetic": false, "world_size": 8} {"step": 20720, "tokens": 5431623680, "loss": 2.3887969970703127, "optimizer_updates": 11360, "effective_batch": 512, "lr": 0.00016969602357264776, "gradient_norm": 0.26841315627098083, "tokens_per_second": 1100171.2042374485, "synthetic": false, "world_size": 8} {"step": 20740, "tokens": 5436866560, "loss": 2.3818397521972656, "optimizer_updates": 11370, "effective_batch": 512, "lr": 0.00016964035260098322, "gradient_norm": 0.41200366616249084, "tokens_per_second": 1096817.4339495706, "synthetic": false, "world_size": 8} {"step": 20760, "tokens": 5442109440, "loss": 2.3953214645385743, "optimizer_updates": 11380, "effective_batch": 512, "lr": 0.00016958464091285907, "gradient_norm": 0.29096174240112305, "tokens_per_second": 1099096.3490325587, "synthetic": false, "world_size": 8} {"step": 20780, "tokens": 5447352320, "loss": 2.387054443359375, "optimizer_updates": 11390, "effective_batch": 512, "lr": 0.00016952888854630967, "gradient_norm": 0.2852810323238373, "tokens_per_second": 1087971.2868950842, "synthetic": false, "world_size": 8} {"step": 20800, "tokens": 5452595200, "loss": 2.380679702758789, "optimizer_updates": 11400, "effective_batch": 512, "lr": 0.00016947309553939715, "gradient_norm": 0.31388092041015625, "tokens_per_second": 1091918.9061886987, "synthetic": false, "world_size": 8} {"step": 20820, "tokens": 5457838080, "loss": 2.376672554016113, "optimizer_updates": 11410, "effective_batch": 512, "lr": 0.0001694172619302114, "gradient_norm": 0.3485110104084015, "tokens_per_second": 1086806.2004628603, "synthetic": false, "world_size": 8} {"step": 20840, "tokens": 5463080960, "loss": 2.3744060516357424, "optimizer_updates": 11420, "effective_batch": 512, "lr": 0.00016936138775687, "gradient_norm": 0.3422110080718994, "tokens_per_second": 1101084.4193143332, "synthetic": false, "world_size": 8} {"step": 20860, "tokens": 5468323840, "loss": 2.3856456756591795, "optimizer_updates": 11430, "effective_batch": 512, "lr": 0.00016930547305751823, "gradient_norm": 0.28251609206199646, "tokens_per_second": 1091494.9431474733, "synthetic": false, "world_size": 8} {"step": 20880, "tokens": 5473566720, "loss": 2.381697082519531, "optimizer_updates": 11440, "effective_batch": 512, "lr": 0.0001692495178703291, "gradient_norm": 0.268396258354187, "tokens_per_second": 1101440.2876893163, "synthetic": false, "world_size": 8} {"step": 20900, "tokens": 5478809600, "loss": 2.3887603759765623, "optimizer_updates": 11450, "effective_batch": 512, "lr": 0.00016919352223350315, "gradient_norm": 0.25938311219215393, "tokens_per_second": 1102465.8747621572, "synthetic": false, "world_size": 8} {"step": 20920, "tokens": 5484052480, "loss": 2.3851242065429688, "optimizer_updates": 11460, "effective_batch": 512, "lr": 0.00016913748618526862, "gradient_norm": 0.2738424837589264, "tokens_per_second": 1100679.2362639562, "synthetic": false, "world_size": 8} {"step": 20940, "tokens": 5489295360, "loss": 2.3837163925170897, "optimizer_updates": 11470, "effective_batch": 512, "lr": 0.0001690814097638813, "gradient_norm": 0.29986944794654846, "tokens_per_second": 1099657.47070716, "synthetic": false, "world_size": 8} {"step": 20960, "tokens": 5494538240, "loss": 2.3886770248413085, "optimizer_updates": 11480, "effective_batch": 512, "lr": 0.00016902529300762457, "gradient_norm": 0.324886679649353, "tokens_per_second": 1104726.670729983, "synthetic": false, "world_size": 8} {"step": 20980, "tokens": 5499781120, "loss": 2.385679244995117, "optimizer_updates": 11490, "effective_batch": 512, "lr": 0.00016896913595480933, "gradient_norm": 0.23798421025276184, "tokens_per_second": 1102640.4801332266, "synthetic": false, "world_size": 8} {"step": 21000, "tokens": 5505024000, "loss": 2.3943668365478517, "optimizer_updates": 11500, "effective_batch": 512, "lr": 0.00016891293864377397, "gradient_norm": 0.29434382915496826, "tokens_per_second": 1104859.4616569325, "synthetic": false, "world_size": 8} {"step": 21020, "tokens": 5510266880, "loss": 2.384499740600586, "optimizer_updates": 11510, "effective_batch": 512, "lr": 0.00016885670111288438, "gradient_norm": 0.2789576053619385, "tokens_per_second": 851333.0986436296, "synthetic": false, "world_size": 8} {"step": 21040, "tokens": 5515509760, "loss": 2.392416572570801, "optimizer_updates": 11520, "effective_batch": 512, "lr": 0.00016880042340053396, "gradient_norm": 0.248048797249794, "tokens_per_second": 1094872.8419978, "synthetic": false, "world_size": 8} {"step": 21060, "tokens": 5520752640, "loss": 2.3828145980834963, "optimizer_updates": 11530, "effective_batch": 512, "lr": 0.00016874410554514348, "gradient_norm": 0.2821904122829437, "tokens_per_second": 1095728.4350727503, "synthetic": false, "world_size": 8} {"step": 21080, "tokens": 5525995520, "loss": 2.404978370666504, "optimizer_updates": 11540, "effective_batch": 512, "lr": 0.0001686877475851611, "gradient_norm": 0.2523784935474396, "tokens_per_second": 1099096.761923342, "synthetic": false, "world_size": 8} {"step": 21100, "tokens": 5531238400, "loss": 2.3893011093139647, "optimizer_updates": 11550, "effective_batch": 512, "lr": 0.0001686313495590624, "gradient_norm": 0.25626224279403687, "tokens_per_second": 1097378.294311837, "synthetic": false, "world_size": 8} {"step": 21120, "tokens": 5536481280, "loss": 2.3861135482788085, "optimizer_updates": 11560, "effective_batch": 512, "lr": 0.0001685749115053503, "gradient_norm": 0.3119368553161621, "tokens_per_second": 1103532.603875426, "synthetic": false, "world_size": 8} {"step": 21140, "tokens": 5541724160, "loss": 2.3905990600585936, "optimizer_updates": 11570, "effective_batch": 512, "lr": 0.0001685184334625551, "gradient_norm": 0.3243556022644043, "tokens_per_second": 1096822.7789174283, "synthetic": false, "world_size": 8} {"step": 21160, "tokens": 5546967040, "loss": 2.3816431045532225, "optimizer_updates": 11580, "effective_batch": 512, "lr": 0.00016846191546923429, "gradient_norm": 0.2396714836359024, "tokens_per_second": 982857.3857882081, "synthetic": false, "world_size": 8} {"step": 21180, "tokens": 5552209920, "loss": 2.399068832397461, "optimizer_updates": 11590, "effective_batch": 512, "lr": 0.00016840535756397273, "gradient_norm": 0.3450362980365753, "tokens_per_second": 1089226.2271260025, "synthetic": false, "world_size": 8} {"step": 21200, "tokens": 5557452800, "loss": 2.388639450073242, "optimizer_updates": 11600, "effective_batch": 512, "lr": 0.0001683487597853825, "gradient_norm": 0.2418551743030548, "tokens_per_second": 1098773.8811890013, "synthetic": false, "world_size": 8} {"step": 21220, "tokens": 5562695680, "loss": 2.377992057800293, "optimizer_updates": 11610, "effective_batch": 512, "lr": 0.00016829212217210285, "gradient_norm": 0.2552295923233032, "tokens_per_second": 1097515.244545154, "synthetic": false, "world_size": 8} {"step": 21240, "tokens": 5567938560, "loss": 2.3826765060424804, "optimizer_updates": 11620, "effective_batch": 512, "lr": 0.00016823544476280032, "gradient_norm": 0.24468518793582916, "tokens_per_second": 1093652.3789080835, "synthetic": false, "world_size": 8} {"step": 21260, "tokens": 5573181440, "loss": 2.3843788146972655, "optimizer_updates": 11630, "effective_batch": 512, "lr": 0.0001681787275961685, "gradient_norm": 0.32962891459465027, "tokens_per_second": 1096614.8925236189, "synthetic": false, "world_size": 8} {"step": 21280, "tokens": 5578424320, "loss": 2.3737251281738283, "optimizer_updates": 11640, "effective_batch": 512, "lr": 0.0001681219707109283, "gradient_norm": 0.2516344487667084, "tokens_per_second": 1095007.6112446024, "synthetic": false, "world_size": 8} {"step": 21300, "tokens": 5583667200, "loss": 2.389479064941406, "optimizer_updates": 11650, "effective_batch": 512, "lr": 0.0001680651741458276, "gradient_norm": 0.2622676193714142, "tokens_per_second": 1104657.8096256675, "synthetic": false, "world_size": 8} {"step": 21320, "tokens": 5588910080, "loss": 2.3931203842163087, "optimizer_updates": 11660, "effective_batch": 512, "lr": 0.0001680083379396413, "gradient_norm": 0.23255713284015656, "tokens_per_second": 1099899.0672492916, "synthetic": false, "world_size": 8} {"step": 21340, "tokens": 5594152960, "loss": 2.3868064880371094, "optimizer_updates": 11670, "effective_batch": 512, "lr": 0.0001679514621311716, "gradient_norm": 0.28914472460746765, "tokens_per_second": 1104336.9592060363, "synthetic": false, "world_size": 8} {"step": 21360, "tokens": 5599395840, "loss": 2.386363220214844, "optimizer_updates": 11680, "effective_batch": 512, "lr": 0.00016789454675924755, "gradient_norm": 0.35685476660728455, "tokens_per_second": 1100923.6901867706, "synthetic": false, "world_size": 8} {"step": 21380, "tokens": 5604638720, "loss": 2.383377265930176, "optimizer_updates": 11690, "effective_batch": 512, "lr": 0.00016783759186272528, "gradient_norm": 0.322916179895401, "tokens_per_second": 1099517.4989471138, "synthetic": false, "world_size": 8} {"step": 21400, "tokens": 5609881600, "loss": 2.380846405029297, "optimizer_updates": 11700, "effective_batch": 512, "lr": 0.00016778059748048785, "gradient_norm": 0.3113756775856018, "tokens_per_second": 1100497.9955048629, "synthetic": false, "world_size": 8} {"step": 21420, "tokens": 5615124480, "loss": 2.377914237976074, "optimizer_updates": 11710, "effective_batch": 512, "lr": 0.0001677235636514454, "gradient_norm": 0.2811338007450104, "tokens_per_second": 1088439.1165441005, "synthetic": false, "world_size": 8} {"step": 21440, "tokens": 5620367360, "loss": 2.3853790283203127, "optimizer_updates": 11720, "effective_batch": 512, "lr": 0.00016766649041453482, "gradient_norm": 0.25903505086898804, "tokens_per_second": 1102396.8833125401, "synthetic": false, "world_size": 8} {"step": 21460, "tokens": 5625610240, "loss": 2.3736621856689455, "optimizer_updates": 11730, "effective_batch": 512, "lr": 0.00016760937780872006, "gradient_norm": 0.25196582078933716, "tokens_per_second": 1101804.81049665, "synthetic": false, "world_size": 8} {"step": 21480, "tokens": 5630853120, "loss": 2.3812084197998047, "optimizer_updates": 11740, "effective_batch": 512, "lr": 0.00016755222587299184, "gradient_norm": 0.34784069657325745, "tokens_per_second": 1094427.9475164728, "synthetic": false, "world_size": 8} {"step": 21500, "tokens": 5636096000, "loss": 2.3869869232177736, "optimizer_updates": 11750, "effective_batch": 512, "lr": 0.00016749503464636781, "gradient_norm": 0.2617642879486084, "tokens_per_second": 1091982.867147147, "synthetic": false, "world_size": 8} {"step": 21520, "tokens": 5641338880, "loss": 2.3814220428466797, "optimizer_updates": 11760, "effective_batch": 512, "lr": 0.00016743780416789248, "gradient_norm": 0.27023765444755554, "tokens_per_second": 1093086.7757555617, "synthetic": false, "world_size": 8} {"step": 21540, "tokens": 5646581760, "loss": 2.3926795959472655, "optimizer_updates": 11770, "effective_batch": 512, "lr": 0.00016738053447663695, "gradient_norm": 0.2431952953338623, "tokens_per_second": 1102446.1901548868, "synthetic": false, "world_size": 8} {"step": 21560, "tokens": 5651824640, "loss": 2.3786808013916017, "optimizer_updates": 11780, "effective_batch": 512, "lr": 0.00016732322561169934, "gradient_norm": 0.26840755343437195, "tokens_per_second": 1091655.1076050894, "synthetic": false, "world_size": 8} {"step": 21580, "tokens": 5657067520, "loss": 2.384441375732422, "optimizer_updates": 11790, "effective_batch": 512, "lr": 0.00016726587761220436, "gradient_norm": 0.2902525067329407, "tokens_per_second": 1089889.26442041, "synthetic": false, "world_size": 8} {"step": 21600, "tokens": 5662310400, "loss": 2.3926464080810548, "optimizer_updates": 11800, "effective_batch": 512, "lr": 0.00016720849051730347, "gradient_norm": 0.31890544295310974, "tokens_per_second": 1000297.0190674638, "synthetic": false, "world_size": 8} {"step": 21620, "tokens": 5667553280, "loss": 2.3715133666992188, "optimizer_updates": 11810, "effective_batch": 512, "lr": 0.00016715106436617484, "gradient_norm": 0.3217931091785431, "tokens_per_second": 1094083.0151920328, "synthetic": false, "world_size": 8} {"step": 21640, "tokens": 5672796160, "loss": 2.385234069824219, "optimizer_updates": 11820, "effective_batch": 512, "lr": 0.0001670935991980233, "gradient_norm": 0.3094388544559479, "tokens_per_second": 1100536.705467553, "synthetic": false, "world_size": 8} {"step": 21660, "tokens": 5678039040, "loss": 2.3712846755981447, "optimizer_updates": 11830, "effective_batch": 512, "lr": 0.00016703609505208032, "gradient_norm": 0.2420376092195511, "tokens_per_second": 1097279.0166368524, "synthetic": false, "world_size": 8} {"step": 21680, "tokens": 5683281920, "loss": 2.3766195297241213, "optimizer_updates": 11840, "effective_batch": 512, "lr": 0.00016697855196760397, "gradient_norm": 0.2607910931110382, "tokens_per_second": 1078503.5225908419, "synthetic": false, "world_size": 8} {"step": 21700, "tokens": 5688524800, "loss": 2.3862983703613283, "optimizer_updates": 11850, "effective_batch": 512, "lr": 0.00016692096998387887, "gradient_norm": 0.23610146343708038, "tokens_per_second": 1088044.3132773857, "synthetic": false, "world_size": 8} {"step": 21720, "tokens": 5693767680, "loss": 2.3842094421386717, "optimizer_updates": 11860, "effective_batch": 512, "lr": 0.00016686334914021628, "gradient_norm": 0.3085198998451233, "tokens_per_second": 1098814.6784639703, "synthetic": false, "world_size": 8} {"step": 21740, "tokens": 5699010560, "loss": 2.375920295715332, "optimizer_updates": 11870, "effective_batch": 512, "lr": 0.0001668056894759539, "gradient_norm": 0.3155631721019745, "tokens_per_second": 1080827.8037176384, "synthetic": false, "world_size": 8} {"step": 21760, "tokens": 5704253440, "loss": 2.3887977600097656, "optimizer_updates": 11880, "effective_batch": 512, "lr": 0.00016674799103045602, "gradient_norm": 0.29238399863243103, "tokens_per_second": 1090313.4537063085, "synthetic": false, "world_size": 8} {"step": 21780, "tokens": 5709496320, "loss": 2.3803335189819337, "optimizer_updates": 11890, "effective_batch": 512, "lr": 0.0001666902538431133, "gradient_norm": 0.26844388246536255, "tokens_per_second": 1093518.436597197, "synthetic": false, "world_size": 8} {"step": 21800, "tokens": 5714739200, "loss": 2.382689094543457, "optimizer_updates": 11900, "effective_batch": 512, "lr": 0.00016663247795334297, "gradient_norm": 0.23271718621253967, "tokens_per_second": 1095154.0601967603, "synthetic": false, "world_size": 8} {"step": 21820, "tokens": 5719982080, "loss": 2.393645477294922, "optimizer_updates": 11910, "effective_batch": 512, "lr": 0.0001665746634005886, "gradient_norm": 0.38238421082496643, "tokens_per_second": 1097863.8816151547, "synthetic": false, "world_size": 8} {"step": 21840, "tokens": 5725224960, "loss": 2.376242446899414, "optimizer_updates": 11920, "effective_batch": 512, "lr": 0.00016651681022432013, "gradient_norm": 0.35963037610054016, "tokens_per_second": 1100184.5707908901, "synthetic": false, "world_size": 8} {"step": 21860, "tokens": 5730467840, "loss": 2.382660484313965, "optimizer_updates": 11930, "effective_batch": 512, "lr": 0.000166458918464034, "gradient_norm": 0.3793601393699646, "tokens_per_second": 1098325.244278447, "synthetic": false, "world_size": 8} {"step": 21880, "tokens": 5735710720, "loss": 2.388206672668457, "optimizer_updates": 11940, "effective_batch": 512, "lr": 0.0001664009881592528, "gradient_norm": 0.2776537835597992, "tokens_per_second": 1102404.009212094, "synthetic": false, "world_size": 8} {"step": 21900, "tokens": 5740953600, "loss": 2.387678527832031, "optimizer_updates": 11950, "effective_batch": 512, "lr": 0.00016634301934952565, "gradient_norm": 0.28615182638168335, "tokens_per_second": 1095610.1682854553, "synthetic": false, "world_size": 8} {"step": 21920, "tokens": 5746196480, "loss": 2.374820518493652, "optimizer_updates": 11960, "effective_batch": 512, "lr": 0.00016628501207442779, "gradient_norm": 0.2868155539035797, "tokens_per_second": 1092793.839538866, "synthetic": false, "world_size": 8} {"step": 21940, "tokens": 5751439360, "loss": 2.3707853317260743, "optimizer_updates": 11970, "effective_batch": 512, "lr": 0.0001662269663735608, "gradient_norm": 0.3300882577896118, "tokens_per_second": 1098648.8429875153, "synthetic": false, "world_size": 8} {"step": 21960, "tokens": 5756682240, "loss": 2.385780143737793, "optimizer_updates": 11980, "effective_batch": 512, "lr": 0.00016616888228655242, "gradient_norm": 0.25351962447166443, "tokens_per_second": 1098623.8487532418, "synthetic": false, "world_size": 8} {"step": 21980, "tokens": 5761925120, "loss": 2.3697824478149414, "optimizer_updates": 11990, "effective_batch": 512, "lr": 0.00016611075985305672, "gradient_norm": 0.27145621180534363, "tokens_per_second": 1093072.2586410472, "synthetic": false, "world_size": 8} {"step": 22000, "tokens": 5767168000, "loss": 2.3804304122924806, "optimizer_updates": 12000, "effective_batch": 512, "lr": 0.00016605259911275382, "gradient_norm": 0.3102031648159027, "tokens_per_second": 805880.7742825989, "synthetic": false, "world_size": 8} {"step": 22020, "tokens": 5772410880, "loss": 2.3854442596435548, "optimizer_updates": 12010, "effective_batch": 512, "lr": 0.00016599440010535007, "gradient_norm": 0.2449035942554474, "tokens_per_second": 716853.8561511325, "synthetic": false, "world_size": 8} {"step": 22040, "tokens": 5777653760, "loss": 2.3768474578857424, "optimizer_updates": 12020, "effective_batch": 512, "lr": 0.00016593616287057794, "gradient_norm": 0.3547620475292206, "tokens_per_second": 1098055.9454106756, "synthetic": false, "world_size": 8} {"step": 22060, "tokens": 5782896640, "loss": 2.3879474639892577, "optimizer_updates": 12030, "effective_batch": 512, "lr": 0.00016587788744819594, "gradient_norm": 0.2905674874782562, "tokens_per_second": 1099855.9709841376, "synthetic": false, "world_size": 8} {"step": 22080, "tokens": 5788139520, "loss": 2.385283279418945, "optimizer_updates": 12040, "effective_batch": 512, "lr": 0.00016581957387798874, "gradient_norm": 0.26567378640174866, "tokens_per_second": 1098258.6079865554, "synthetic": false, "world_size": 8} {"step": 22100, "tokens": 5793382400, "loss": 2.384194755554199, "optimizer_updates": 12050, "effective_batch": 512, "lr": 0.00016576122219976694, "gradient_norm": 0.3511340022087097, "tokens_per_second": 1090269.02102416, "synthetic": false, "world_size": 8} {"step": 22120, "tokens": 5798625280, "loss": 2.381221389770508, "optimizer_updates": 12060, "effective_batch": 512, "lr": 0.0001657028324533673, "gradient_norm": 0.2649453580379486, "tokens_per_second": 955484.9190085027, "synthetic": false, "world_size": 8} {"step": 22140, "tokens": 5803868160, "loss": 2.370270538330078, "optimizer_updates": 12070, "effective_batch": 512, "lr": 0.00016564440467865246, "gradient_norm": 0.293628454208374, "tokens_per_second": 1069201.4055352802, "synthetic": false, "world_size": 8} {"step": 22160, "tokens": 5809111040, "loss": 2.3869535446166994, "optimizer_updates": 12080, "effective_batch": 512, "lr": 0.00016558593891551103, "gradient_norm": 0.30953824520111084, "tokens_per_second": 1079214.7571628608, "synthetic": false, "world_size": 8} {"step": 22180, "tokens": 5814353920, "loss": 2.3838275909423827, "optimizer_updates": 12090, "effective_batch": 512, "lr": 0.00016552743520385763, "gradient_norm": 0.27676263451576233, "tokens_per_second": 983891.3534392165, "synthetic": false, "world_size": 8} {"step": 22200, "tokens": 5819596800, "loss": 2.384697151184082, "optimizer_updates": 12100, "effective_batch": 512, "lr": 0.00016546889358363265, "gradient_norm": 0.2703225910663605, "tokens_per_second": 1090238.0464238748, "synthetic": false, "world_size": 8} {"step": 22220, "tokens": 5824839680, "loss": 2.3884830474853516, "optimizer_updates": 12110, "effective_batch": 512, "lr": 0.0001654103140948025, "gradient_norm": 0.2794162929058075, "tokens_per_second": 1083972.8422293167, "synthetic": false, "world_size": 8} {"step": 22240, "tokens": 5830082560, "loss": 2.358400344848633, "optimizer_updates": 12120, "effective_batch": 512, "lr": 0.0001653516967773594, "gradient_norm": 0.24040162563323975, "tokens_per_second": 1085514.7414587808, "synthetic": false, "world_size": 8} {"step": 22260, "tokens": 5835325440, "loss": 2.3775306701660157, "optimizer_updates": 12130, "effective_batch": 512, "lr": 0.00016529304167132137, "gradient_norm": 0.2654668390750885, "tokens_per_second": 1090376.175623053, "synthetic": false, "world_size": 8} {"step": 22280, "tokens": 5840568320, "loss": 2.3823476791381837, "optimizer_updates": 12140, "effective_batch": 512, "lr": 0.00016523434881673222, "gradient_norm": 0.2923986613750458, "tokens_per_second": 1085418.8522870042, "synthetic": false, "world_size": 8} {"step": 22300, "tokens": 5845811200, "loss": 2.389678192138672, "optimizer_updates": 12150, "effective_batch": 512, "lr": 0.00016517561825366158, "gradient_norm": 0.297477662563324, "tokens_per_second": 1091776.7696192872, "synthetic": false, "world_size": 8} {"step": 22320, "tokens": 5851054080, "loss": 2.3838815689086914, "optimizer_updates": 12160, "effective_batch": 512, "lr": 0.0001651168500222048, "gradient_norm": 0.31466126441955566, "tokens_per_second": 1097163.3411656676, "synthetic": false, "world_size": 8} {"step": 22340, "tokens": 5856296960, "loss": 2.374641227722168, "optimizer_updates": 12170, "effective_batch": 512, "lr": 0.00016505804416248293, "gradient_norm": 0.2601832151412964, "tokens_per_second": 1093621.4346333633, "synthetic": false, "world_size": 8} {"step": 22360, "tokens": 5861539840, "loss": 2.3800315856933594, "optimizer_updates": 12180, "effective_batch": 512, "lr": 0.0001649992007146427, "gradient_norm": 0.24333389103412628, "tokens_per_second": 1081535.6523626014, "synthetic": false, "world_size": 8} {"step": 22380, "tokens": 5866782720, "loss": 2.3858417510986327, "optimizer_updates": 12190, "effective_batch": 512, "lr": 0.00016494031971885656, "gradient_norm": 0.2727367877960205, "tokens_per_second": 960179.8746619665, "synthetic": false, "world_size": 8} {"step": 22400, "tokens": 5872025600, "loss": 2.3976612091064453, "optimizer_updates": 12200, "effective_batch": 512, "lr": 0.00016488140121532254, "gradient_norm": 0.2941474914550781, "tokens_per_second": 1090706.6178582255, "synthetic": false, "world_size": 8} {"step": 22420, "tokens": 5877268480, "loss": 2.3859203338623045, "optimizer_updates": 12210, "effective_batch": 512, "lr": 0.0001648224452442643, "gradient_norm": 0.36749541759490967, "tokens_per_second": 1092396.8608098554, "synthetic": false, "world_size": 8} {"step": 22440, "tokens": 5882511360, "loss": 2.397617721557617, "optimizer_updates": 12220, "effective_batch": 512, "lr": 0.00016476345184593104, "gradient_norm": 0.2535862624645233, "tokens_per_second": 1098443.1187340291, "synthetic": false, "world_size": 8} {"step": 22460, "tokens": 5887754240, "loss": 2.386447525024414, "optimizer_updates": 12230, "effective_batch": 512, "lr": 0.00016470442106059763, "gradient_norm": 0.2378258854150772, "tokens_per_second": 1086763.5356514284, "synthetic": false, "world_size": 8} {"step": 22480, "tokens": 5892997120, "loss": 2.3783506393432616, "optimizer_updates": 12240, "effective_batch": 512, "lr": 0.00016464535292856427, "gradient_norm": 0.28313446044921875, "tokens_per_second": 1086185.8873757974, "synthetic": false, "world_size": 8} {"step": 22500, "tokens": 5898240000, "loss": 2.3868154525756835, "optimizer_updates": 12250, "effective_batch": 512, "lr": 0.00016458624749015683, "gradient_norm": 0.28559166193008423, "tokens_per_second": 1092718.0168032532, "synthetic": false, "world_size": 8} {"step": 22520, "tokens": 5903482880, "loss": 2.378449821472168, "optimizer_updates": 12260, "effective_batch": 512, "lr": 0.00016452710478572657, "gradient_norm": 0.288324773311615, "tokens_per_second": 1091410.688959146, "synthetic": false, "world_size": 8} {"step": 22540, "tokens": 5908725760, "loss": 2.3708518981933593, "optimizer_updates": 12270, "effective_batch": 512, "lr": 0.0001644679248556502, "gradient_norm": 0.325411319732666, "tokens_per_second": 1093616.7144111863, "synthetic": false, "world_size": 8} {"step": 22560, "tokens": 5913968640, "loss": 2.382139205932617, "optimizer_updates": 12280, "effective_batch": 512, "lr": 0.00016440870774032983, "gradient_norm": 0.28988030552864075, "tokens_per_second": 1094220.3884968753, "synthetic": false, "world_size": 8} {"step": 22580, "tokens": 5919211520, "loss": 2.369047737121582, "optimizer_updates": 12290, "effective_batch": 512, "lr": 0.000164349453480193, "gradient_norm": 0.3130106031894684, "tokens_per_second": 1087172.7195627876, "synthetic": false, "world_size": 8} {"step": 22600, "tokens": 5924454400, "loss": 2.384299659729004, "optimizer_updates": 12300, "effective_batch": 512, "lr": 0.00016429016211569263, "gradient_norm": 0.31984663009643555, "tokens_per_second": 1089652.1113647046, "synthetic": false, "world_size": 8} {"step": 22620, "tokens": 5929697280, "loss": 2.389872741699219, "optimizer_updates": 12310, "effective_batch": 512, "lr": 0.00016423083368730684, "gradient_norm": 0.28875091671943665, "tokens_per_second": 1086321.0234947493, "synthetic": false, "world_size": 8} {"step": 22640, "tokens": 5934940160, "loss": 2.3883892059326173, "optimizer_updates": 12320, "effective_batch": 512, "lr": 0.0001641714682355392, "gradient_norm": 0.27098917961120605, "tokens_per_second": 1088287.211597591, "synthetic": false, "world_size": 8} {"step": 22660, "tokens": 5940183040, "loss": 2.389792060852051, "optimizer_updates": 12330, "effective_batch": 512, "lr": 0.00016411206580091846, "gradient_norm": 0.2464304268360138, "tokens_per_second": 1088033.6626547473, "synthetic": false, "world_size": 8} {"step": 22680, "tokens": 5945425920, "loss": 2.3763359069824217, "optimizer_updates": 12340, "effective_batch": 512, "lr": 0.00016405262642399867, "gradient_norm": 0.25770920515060425, "tokens_per_second": 1094655.6765069326, "synthetic": false, "world_size": 8} {"step": 22700, "tokens": 5950668800, "loss": 2.374276351928711, "optimizer_updates": 12350, "effective_batch": 512, "lr": 0.00016399315014535906, "gradient_norm": 0.3250492513179779, "tokens_per_second": 1086682.7020945228, "synthetic": false, "world_size": 8} {"step": 22720, "tokens": 5955911680, "loss": 2.3881557464599608, "optimizer_updates": 12360, "effective_batch": 512, "lr": 0.0001639336370056041, "gradient_norm": 0.2758305072784424, "tokens_per_second": 1094157.8523921228, "synthetic": false, "world_size": 8} {"step": 22740, "tokens": 5961154560, "loss": 2.382310676574707, "optimizer_updates": 12370, "effective_batch": 512, "lr": 0.00016387408704536343, "gradient_norm": 0.26629742980003357, "tokens_per_second": 1091824.1726245948, "synthetic": false, "world_size": 8} {"step": 22760, "tokens": 5966397440, "loss": 2.388276481628418, "optimizer_updates": 12380, "effective_batch": 512, "lr": 0.00016381450030529174, "gradient_norm": 0.2499651163816452, "tokens_per_second": 1098385.5628165524, "synthetic": false, "world_size": 8} {"step": 22780, "tokens": 5971640320, "loss": 2.3732269287109373, "optimizer_updates": 12390, "effective_batch": 512, "lr": 0.0001637548768260689, "gradient_norm": 0.3536262512207031, "tokens_per_second": 1093923.3917576857, "synthetic": false, "world_size": 8} {"step": 22800, "tokens": 5976883200, "loss": 2.387894630432129, "optimizer_updates": 12400, "effective_batch": 512, "lr": 0.00016369521664839987, "gradient_norm": 0.2635982036590576, "tokens_per_second": 1099518.3765532228, "synthetic": false, "world_size": 8} {"step": 22820, "tokens": 5982126080, "loss": 2.3755495071411135, "optimizer_updates": 12410, "effective_batch": 512, "lr": 0.00016363551981301463, "gradient_norm": 0.25670579075813293, "tokens_per_second": 773099.7437484702, "synthetic": false, "world_size": 8} {"step": 22840, "tokens": 5987368960, "loss": 2.397482490539551, "optimizer_updates": 12420, "effective_batch": 512, "lr": 0.0001635757863606682, "gradient_norm": 0.2728120982646942, "tokens_per_second": 1081589.088944107, "synthetic": false, "world_size": 8} {"step": 22860, "tokens": 5992611840, "loss": 2.377358245849609, "optimizer_updates": 12430, "effective_batch": 512, "lr": 0.00016351601633214066, "gradient_norm": 0.3983992636203766, "tokens_per_second": 1095363.5439587936, "synthetic": false, "world_size": 8} {"step": 22880, "tokens": 5997854720, "loss": 2.3849365234375, "optimizer_updates": 12440, "effective_batch": 512, "lr": 0.0001634562097682369, "gradient_norm": 0.24389521777629852, "tokens_per_second": 1081003.7400458197, "synthetic": false, "world_size": 8} {"step": 22900, "tokens": 6003097600, "loss": 2.386016082763672, "optimizer_updates": 12450, "effective_batch": 512, "lr": 0.00016339636670978692, "gradient_norm": 0.30685076117515564, "tokens_per_second": 1093376.91119198, "synthetic": false, "world_size": 8} {"step": 22920, "tokens": 6008340480, "loss": 2.380712127685547, "optimizer_updates": 12460, "effective_batch": 512, "lr": 0.00016333648719764552, "gradient_norm": 0.26831746101379395, "tokens_per_second": 1087530.2481420315, "synthetic": false, "world_size": 8} {"step": 22940, "tokens": 6013583360, "loss": 2.3736791610717773, "optimizer_updates": 12470, "effective_batch": 512, "lr": 0.0001632765712726925, "gradient_norm": 0.2764693796634674, "tokens_per_second": 1090900.3029082469, "synthetic": false, "world_size": 8} {"step": 22960, "tokens": 6018826240, "loss": 2.377066802978516, "optimizer_updates": 12480, "effective_batch": 512, "lr": 0.00016321661897583239, "gradient_norm": 0.3114791810512543, "tokens_per_second": 1095723.1421932185, "synthetic": false, "world_size": 8} {"step": 22980, "tokens": 6024069120, "loss": 2.37784366607666, "optimizer_updates": 12490, "effective_batch": 512, "lr": 0.00016315663034799463, "gradient_norm": 0.2859714925289154, "tokens_per_second": 1096591.3740250221, "synthetic": false, "world_size": 8} {"step": 23000, "tokens": 6029312000, "loss": 2.3778474807739256, "optimizer_updates": 12500, "effective_batch": 512, "lr": 0.00016309660543013343, "gradient_norm": 0.3322562277317047, "tokens_per_second": 1095852.7230298012, "synthetic": false, "world_size": 8} {"step": 23020, "tokens": 6034554880, "loss": 2.376664733886719, "optimizer_updates": 12510, "effective_batch": 512, "lr": 0.00016303654426322786, "gradient_norm": 0.3513305187225342, "tokens_per_second": 863063.8374203413, "synthetic": false, "world_size": 8} {"step": 23040, "tokens": 6039797760, "loss": 2.375288200378418, "optimizer_updates": 12520, "effective_batch": 512, "lr": 0.0001629764468882816, "gradient_norm": 0.300491601228714, "tokens_per_second": 1088045.5287419744, "synthetic": false, "world_size": 8} {"step": 23060, "tokens": 6045040640, "loss": 2.3928955078125, "optimizer_updates": 12530, "effective_batch": 512, "lr": 0.00016291631334632316, "gradient_norm": 0.286703497171402, "tokens_per_second": 1090253.140612104, "synthetic": false, "world_size": 8} {"step": 23080, "tokens": 6050283520, "loss": 2.3894399642944335, "optimizer_updates": 12540, "effective_batch": 512, "lr": 0.00016285614367840567, "gradient_norm": 0.31988683342933655, "tokens_per_second": 1090904.054332567, "synthetic": false, "world_size": 8} {"step": 23100, "tokens": 6055526400, "loss": 2.3794708251953125, "optimizer_updates": 12550, "effective_batch": 512, "lr": 0.00016279593792560697, "gradient_norm": 0.28841230273246765, "tokens_per_second": 1088530.3504164359, "synthetic": false, "world_size": 8} {"step": 23120, "tokens": 6060769280, "loss": 2.393189239501953, "optimizer_updates": 12560, "effective_batch": 512, "lr": 0.0001627356961290295, "gradient_norm": 0.27399590611457825, "tokens_per_second": 1093036.839076057, "synthetic": false, "world_size": 8} {"step": 23140, "tokens": 6066012160, "loss": 2.3684621810913087, "optimizer_updates": 12570, "effective_batch": 512, "lr": 0.00016267541832980036, "gradient_norm": 0.28470608592033386, "tokens_per_second": 1078162.7068314767, "synthetic": false, "world_size": 8} {"step": 23160, "tokens": 6071255040, "loss": 2.3737682342529296, "optimizer_updates": 12580, "effective_batch": 512, "lr": 0.00016261510456907116, "gradient_norm": 0.295373797416687, "tokens_per_second": 1096922.277663376, "synthetic": false, "world_size": 8} {"step": 23180, "tokens": 6076497920, "loss": 2.3799440383911135, "optimizer_updates": 12590, "effective_batch": 512, "lr": 0.00016255475488801812, "gradient_norm": 0.2519923448562622, "tokens_per_second": 1093957.2892480174, "synthetic": false, "world_size": 8} {"step": 23200, "tokens": 6081740800, "loss": 2.3741619110107424, "optimizer_updates": 12600, "effective_batch": 512, "lr": 0.00016249436932784194, "gradient_norm": 0.24518075585365295, "tokens_per_second": 1086172.684392586, "synthetic": false, "world_size": 8} {"step": 23220, "tokens": 6086983680, "loss": 2.3850475311279298, "optimizer_updates": 12610, "effective_batch": 512, "lr": 0.00016243394792976782, "gradient_norm": 0.24658386409282684, "tokens_per_second": 985617.9113728874, "synthetic": false, "world_size": 8} {"step": 23240, "tokens": 6092226560, "loss": 2.3866817474365236, "optimizer_updates": 12620, "effective_batch": 512, "lr": 0.00016237349073504548, "gradient_norm": 0.34865909814834595, "tokens_per_second": 1081811.4340321345, "synthetic": false, "world_size": 8} {"step": 23260, "tokens": 6097469440, "loss": 2.373993492126465, "optimizer_updates": 12630, "effective_batch": 512, "lr": 0.00016231299778494902, "gradient_norm": 0.25755804777145386, "tokens_per_second": 1083330.130617213, "synthetic": false, "world_size": 8} {"step": 23280, "tokens": 6102712320, "loss": 2.3811695098876955, "optimizer_updates": 12640, "effective_batch": 512, "lr": 0.00016225246912077696, "gradient_norm": 0.2670632004737854, "tokens_per_second": 1079502.0866038662, "synthetic": false, "world_size": 8} {"step": 23300, "tokens": 6107955200, "loss": 2.3741931915283203, "optimizer_updates": 12650, "effective_batch": 512, "lr": 0.0001621919047838522, "gradient_norm": 0.36500126123428345, "tokens_per_second": 1083631.0641879311, "synthetic": false, "world_size": 8} {"step": 23320, "tokens": 6113198080, "loss": 2.391251564025879, "optimizer_updates": 12660, "effective_batch": 512, "lr": 0.00016213130481552206, "gradient_norm": 0.2976001501083374, "tokens_per_second": 1078337.8168702838, "synthetic": false, "world_size": 8} {"step": 23340, "tokens": 6118440960, "loss": 2.3732666015625, "optimizer_updates": 12670, "effective_batch": 512, "lr": 0.00016207066925715805, "gradient_norm": 0.2804773151874542, "tokens_per_second": 1076408.4953271702, "synthetic": false, "world_size": 8} {"step": 23360, "tokens": 6123683840, "loss": 2.3828462600708007, "optimizer_updates": 12680, "effective_batch": 512, "lr": 0.0001620099981501561, "gradient_norm": 0.3122577667236328, "tokens_per_second": 1078702.641631682, "synthetic": false, "world_size": 8} {"step": 23380, "tokens": 6128926720, "loss": 2.380055236816406, "optimizer_updates": 12690, "effective_batch": 512, "lr": 0.00016194929153593636, "gradient_norm": 0.2533998489379883, "tokens_per_second": 1078235.2836261338, "synthetic": false, "world_size": 8} {"step": 23400, "tokens": 6134169600, "loss": 2.3846323013305666, "optimizer_updates": 12700, "effective_batch": 512, "lr": 0.00016188854945594323, "gradient_norm": 0.2651866674423218, "tokens_per_second": 1080593.7407725488, "synthetic": false, "world_size": 8} {"step": 23420, "tokens": 6139412480, "loss": 2.370939254760742, "optimizer_updates": 12710, "effective_batch": 512, "lr": 0.00016182777195164534, "gradient_norm": 0.29849156737327576, "tokens_per_second": 1079023.7040000567, "synthetic": false, "world_size": 8} {"step": 23440, "tokens": 6144655360, "loss": 2.3954553604125977, "optimizer_updates": 12720, "effective_batch": 512, "lr": 0.0001617669590645354, "gradient_norm": 0.3541782796382904, "tokens_per_second": 1079277.545442844, "synthetic": false, "world_size": 8} {"step": 23460, "tokens": 6149898240, "loss": 2.378382682800293, "optimizer_updates": 12730, "effective_batch": 512, "lr": 0.00016170611083613046, "gradient_norm": 0.23067858815193176, "tokens_per_second": 1083663.2465111623, "synthetic": false, "world_size": 8} {"step": 23480, "tokens": 6155141120, "loss": 2.3845409393310546, "optimizer_updates": 12740, "effective_batch": 512, "lr": 0.00016164522730797155, "gradient_norm": 0.2960678040981293, "tokens_per_second": 1082820.953299226, "synthetic": false, "world_size": 8} {"step": 23500, "tokens": 6160384000, "loss": 2.3749414443969727, "optimizer_updates": 12750, "effective_batch": 512, "lr": 0.00016158430852162382, "gradient_norm": 0.2843666672706604, "tokens_per_second": 1079331.79856278, "synthetic": false, "world_size": 8} {"step": 23520, "tokens": 6165626880, "loss": 2.3801734924316404, "optimizer_updates": 12760, "effective_batch": 512, "lr": 0.00016152335451867655, "gradient_norm": 0.26033759117126465, "tokens_per_second": 1079453.5565350256, "synthetic": false, "world_size": 8} {"step": 23540, "tokens": 6170869760, "loss": 2.403354263305664, "optimizer_updates": 12770, "effective_batch": 512, "lr": 0.00016146236534074303, "gradient_norm": 0.33120712637901306, "tokens_per_second": 1069889.8476192462, "synthetic": false, "world_size": 8} {"step": 23560, "tokens": 6176112640, "loss": 2.3965606689453125, "optimizer_updates": 12780, "effective_batch": 512, "lr": 0.00016140134102946054, "gradient_norm": 0.23874695599079132, "tokens_per_second": 1072767.4911639164, "synthetic": false, "world_size": 8} {"step": 23580, "tokens": 6181355520, "loss": 2.3831150054931642, "optimizer_updates": 12790, "effective_batch": 512, "lr": 0.00016134028162649044, "gradient_norm": 0.24849644303321838, "tokens_per_second": 1074190.231495792, "synthetic": false, "world_size": 8} {"step": 23600, "tokens": 6186598400, "loss": 2.390009307861328, "optimizer_updates": 12800, "effective_batch": 512, "lr": 0.00016127918717351783, "gradient_norm": 0.27106207609176636, "tokens_per_second": 1088190.871343847, "synthetic": false, "world_size": 8} {"step": 23620, "tokens": 6191841280, "loss": 2.3971635818481447, "optimizer_updates": 12810, "effective_batch": 512, "lr": 0.00016121805771225202, "gradient_norm": 0.2478054314851761, "tokens_per_second": 1080839.5263536351, "synthetic": false, "world_size": 8} {"step": 23640, "tokens": 6197084160, "loss": 2.3696094512939454, "optimizer_updates": 12820, "effective_batch": 512, "lr": 0.00016115689328442603, "gradient_norm": 0.3306799530982971, "tokens_per_second": 1083860.7000918295, "synthetic": false, "world_size": 8} {"step": 23660, "tokens": 6202327040, "loss": 2.389729881286621, "optimizer_updates": 12830, "effective_batch": 512, "lr": 0.0001610956939317968, "gradient_norm": 0.29703643918037415, "tokens_per_second": 1082565.9649043304, "synthetic": false, "world_size": 8} {"step": 23680, "tokens": 6207569920, "loss": 2.3729623794555663, "optimizer_updates": 12840, "effective_batch": 512, "lr": 0.0001610344596961451, "gradient_norm": 0.2551829516887665, "tokens_per_second": 1087812.5389215434, "synthetic": false, "world_size": 8} {"step": 23700, "tokens": 6212812800, "loss": 2.3749555587768554, "optimizer_updates": 12850, "effective_batch": 512, "lr": 0.00016097319061927565, "gradient_norm": 0.25545749068260193, "tokens_per_second": 1083298.7573124073, "synthetic": false, "world_size": 8} {"step": 23720, "tokens": 6218055680, "loss": 2.399373245239258, "optimizer_updates": 12860, "effective_batch": 512, "lr": 0.0001609118867430167, "gradient_norm": 0.24898500740528107, "tokens_per_second": 1047575.6300229415, "synthetic": false, "world_size": 8} {"step": 23740, "tokens": 6223298560, "loss": 2.37933406829834, "optimizer_updates": 12870, "effective_batch": 512, "lr": 0.00016085054810922043, "gradient_norm": 0.28570806980133057, "tokens_per_second": 1078799.5271468684, "synthetic": false, "world_size": 8} {"step": 23760, "tokens": 6228541440, "loss": 2.3757076263427734, "optimizer_updates": 12880, "effective_batch": 512, "lr": 0.00016078917475976275, "gradient_norm": 0.2596036493778229, "tokens_per_second": 1080486.6786729614, "synthetic": false, "world_size": 8} {"step": 23780, "tokens": 6233784320, "loss": 2.372756576538086, "optimizer_updates": 12890, "effective_batch": 512, "lr": 0.00016072776673654323, "gradient_norm": 0.2747496962547302, "tokens_per_second": 979037.2147195784, "synthetic": false, "world_size": 8} {"step": 23800, "tokens": 6239027200, "loss": 2.374691200256348, "optimizer_updates": 12900, "effective_batch": 512, "lr": 0.00016066632408148513, "gradient_norm": 0.32135283946990967, "tokens_per_second": 1081135.9395072022, "synthetic": false, "world_size": 8} {"step": 23820, "tokens": 6244270080, "loss": 2.383082962036133, "optimizer_updates": 12910, "effective_batch": 512, "lr": 0.00016060484683653529, "gradient_norm": 0.41000330448150635, "tokens_per_second": 1080708.282628002, "synthetic": false, "world_size": 8} {"step": 23840, "tokens": 6249512960, "loss": 2.381010627746582, "optimizer_updates": 12920, "effective_batch": 512, "lr": 0.00016054333504366425, "gradient_norm": 0.28243231773376465, "tokens_per_second": 1082655.2355964885, "synthetic": false, "world_size": 8} {"step": 23860, "tokens": 6254755840, "loss": 2.374878692626953, "optimizer_updates": 12930, "effective_batch": 512, "lr": 0.00016048178874486608, "gradient_norm": 0.25066977739334106, "tokens_per_second": 1081049.0682166978, "synthetic": false, "world_size": 8} {"step": 23880, "tokens": 6259998720, "loss": 2.382304382324219, "optimizer_updates": 12940, "effective_batch": 512, "lr": 0.00016042020798215847, "gradient_norm": 0.24854321777820587, "tokens_per_second": 1077950.6996313662, "synthetic": false, "world_size": 8} {"step": 23900, "tokens": 6265241600, "loss": 2.387076759338379, "optimizer_updates": 12950, "effective_batch": 512, "lr": 0.00016035859279758255, "gradient_norm": 0.31117498874664307, "tokens_per_second": 1083026.6664842418, "synthetic": false, "world_size": 8} {"step": 23920, "tokens": 6270484480, "loss": 2.380350875854492, "optimizer_updates": 12960, "effective_batch": 512, "lr": 0.00016029694323320306, "gradient_norm": 0.2677043080329895, "tokens_per_second": 1076913.4952862326, "synthetic": false, "world_size": 8} {"step": 23940, "tokens": 6275727360, "loss": 2.370991897583008, "optimizer_updates": 12970, "effective_batch": 512, "lr": 0.00016023525933110807, "gradient_norm": 0.2946583032608032, "tokens_per_second": 1078570.563091062, "synthetic": false, "world_size": 8} {"step": 23960, "tokens": 6280970240, "loss": 2.382214164733887, "optimizer_updates": 12980, "effective_batch": 512, "lr": 0.00016017354113340924, "gradient_norm": 0.23436687886714935, "tokens_per_second": 1080366.6414854801, "synthetic": false, "world_size": 8} {"step": 23980, "tokens": 6286213120, "loss": 2.392795181274414, "optimizer_updates": 12990, "effective_batch": 512, "lr": 0.00016011178868224156, "gradient_norm": 0.22698745131492615, "tokens_per_second": 1075752.2243520303, "synthetic": false, "world_size": 8} {"step": 24000, "tokens": 6291456000, "loss": 2.390952491760254, "optimizer_updates": 13000, "effective_batch": 512, "lr": 0.00016005000201976336, "gradient_norm": 0.2788717448711395, "tokens_per_second": 1086355.2491701192, "synthetic": false, "world_size": 8} {"step": 24020, "tokens": 6296698880, "loss": 2.3788280487060547, "optimizer_updates": 13010, "effective_batch": 512, "lr": 0.00015998818118815642, "gradient_norm": 0.3506242334842682, "tokens_per_second": 845915.9297015499, "synthetic": false, "world_size": 8} {"step": 24040, "tokens": 6301941760, "loss": 2.3831975936889647, "optimizer_updates": 13020, "effective_batch": 512, "lr": 0.00015992632622962585, "gradient_norm": 0.3995550572872162, "tokens_per_second": 1082813.3684643707, "synthetic": false, "world_size": 8} {"step": 24060, "tokens": 6307184640, "loss": 2.3772825241088866, "optimizer_updates": 13030, "effective_batch": 512, "lr": 0.0001598644371864, "gradient_norm": 0.282657265663147, "tokens_per_second": 1075888.5764967473, "synthetic": false, "world_size": 8} {"step": 24080, "tokens": 6312427520, "loss": 2.3849746704101564, "optimizer_updates": 13040, "effective_batch": 512, "lr": 0.00015980251410073048, "gradient_norm": 0.27303841710090637, "tokens_per_second": 1084930.2902786452, "synthetic": false, "world_size": 8} {"step": 24100, "tokens": 6317670400, "loss": 2.381468963623047, "optimizer_updates": 13050, "effective_batch": 512, "lr": 0.00015974055701489218, "gradient_norm": 0.24330851435661316, "tokens_per_second": 1088600.3516159935, "synthetic": false, "world_size": 8} {"step": 24120, "tokens": 6322913280, "loss": 2.379280662536621, "optimizer_updates": 13060, "effective_batch": 512, "lr": 0.00015967856597118323, "gradient_norm": 0.2856258153915405, "tokens_per_second": 1076503.593221019, "synthetic": false, "world_size": 8} {"step": 24140, "tokens": 6328156160, "loss": 2.3811717987060548, "optimizer_updates": 13070, "effective_batch": 512, "lr": 0.00015961654101192486, "gradient_norm": 0.30728620290756226, "tokens_per_second": 1090031.0332329168, "synthetic": false, "world_size": 8} {"step": 24160, "tokens": 6333399040, "loss": 2.3936309814453125, "optimizer_updates": 13080, "effective_batch": 512, "lr": 0.00015955448217946154, "gradient_norm": 0.3102059066295624, "tokens_per_second": 1038288.0816283802, "synthetic": false, "world_size": 8} {"step": 24180, "tokens": 6338641920, "loss": 2.3802120208740236, "optimizer_updates": 13090, "effective_batch": 512, "lr": 0.0001594923895161608, "gradient_norm": 0.24805213510990143, "tokens_per_second": 1087773.8878769889, "synthetic": false, "world_size": 8} {"step": 24200, "tokens": 6343884800, "loss": 2.3938507080078124, "optimizer_updates": 13100, "effective_batch": 512, "lr": 0.0001594302630644133, "gradient_norm": 0.2829267680644989, "tokens_per_second": 1088441.3553935408, "synthetic": false, "world_size": 8} {"step": 24220, "tokens": 6349127680, "loss": 2.39091796875, "optimizer_updates": 13110, "effective_batch": 512, "lr": 0.00015936810286663276, "gradient_norm": 0.23335975408554077, "tokens_per_second": 1082154.2048157877, "synthetic": false, "world_size": 8} {"step": 24240, "tokens": 6354370560, "loss": 2.3709325790405273, "optimizer_updates": 13120, "effective_batch": 512, "lr": 0.00015930590896525595, "gradient_norm": 0.29765334725379944, "tokens_per_second": 948463.3108386195, "synthetic": false, "world_size": 8} {"step": 24260, "tokens": 6359613440, "loss": 2.37978515625, "optimizer_updates": 13130, "effective_batch": 512, "lr": 0.00015924368140274257, "gradient_norm": 0.23795536160469055, "tokens_per_second": 1084735.5024185535, "synthetic": false, "world_size": 8} {"step": 24280, "tokens": 6364856320, "loss": 2.382674789428711, "optimizer_updates": 13140, "effective_batch": 512, "lr": 0.00015918142022157547, "gradient_norm": 0.2591831088066101, "tokens_per_second": 1001128.3889751772, "synthetic": false, "world_size": 8} {"step": 24300, "tokens": 6370099200, "loss": 2.3856666564941404, "optimizer_updates": 13150, "effective_batch": 512, "lr": 0.00015911912546426028, "gradient_norm": 0.2540940046310425, "tokens_per_second": 1081413.5473701851, "synthetic": false, "world_size": 8} {"step": 24320, "tokens": 6375342080, "loss": 2.3834501266479493, "optimizer_updates": 13160, "effective_batch": 512, "lr": 0.00015905679717332564, "gradient_norm": 0.3589262366294861, "tokens_per_second": 1086293.5046093552, "synthetic": false, "world_size": 8} {"step": 24340, "tokens": 6380584960, "loss": 2.382427978515625, "optimizer_updates": 13170, "effective_batch": 512, "lr": 0.00015899443539132307, "gradient_norm": 0.30001336336135864, "tokens_per_second": 1087811.8496147075, "synthetic": false, "world_size": 8} {"step": 24360, "tokens": 6385827840, "loss": 2.3708932876586912, "optimizer_updates": 13180, "effective_batch": 512, "lr": 0.00015893204016082695, "gradient_norm": 0.24052764475345612, "tokens_per_second": 1081543.6012460564, "synthetic": false, "world_size": 8} {"step": 24380, "tokens": 6391070720, "loss": 2.379183769226074, "optimizer_updates": 13190, "effective_batch": 512, "lr": 0.00015886961152443448, "gradient_norm": 0.2778993844985962, "tokens_per_second": 1082519.1969776093, "synthetic": false, "world_size": 8} {"step": 24400, "tokens": 6396313600, "loss": 2.378599739074707, "optimizer_updates": 13200, "effective_batch": 512, "lr": 0.00015880714952476568, "gradient_norm": 0.3056209683418274, "tokens_per_second": 1084486.440067349, "synthetic": false, "world_size": 8} {"step": 24420, "tokens": 6401556480, "loss": 2.3701862335205077, "optimizer_updates": 13210, "effective_batch": 512, "lr": 0.00015874465420446336, "gradient_norm": 0.27924299240112305, "tokens_per_second": 1087943.8753529435, "synthetic": false, "world_size": 8} {"step": 24440, "tokens": 6406799360, "loss": 2.3811672210693358, "optimizer_updates": 13220, "effective_batch": 512, "lr": 0.00015868212560619309, "gradient_norm": 0.2503054738044739, "tokens_per_second": 723545.8861357179, "synthetic": false, "world_size": 8} {"step": 24460, "tokens": 6412042240, "loss": 2.3861774444580077, "optimizer_updates": 13230, "effective_batch": 512, "lr": 0.00015861956377264305, "gradient_norm": 0.28355324268341064, "tokens_per_second": 1087337.1890860095, "synthetic": false, "world_size": 8} {"step": 24480, "tokens": 6417285120, "loss": 2.382333183288574, "optimizer_updates": 13240, "effective_batch": 512, "lr": 0.00015855696874652431, "gradient_norm": 0.3138468265533447, "tokens_per_second": 1087950.770055083, "synthetic": false, "world_size": 8} {"step": 24500, "tokens": 6422528000, "loss": 2.387357711791992, "optimizer_updates": 13250, "effective_batch": 512, "lr": 0.0001584943405705704, "gradient_norm": 0.3908713757991791, "tokens_per_second": 990674.6868415322, "synthetic": false, "world_size": 8} {"step": 24520, "tokens": 6427770880, "loss": 2.3870601654052734, "optimizer_updates": 13260, "effective_batch": 512, "lr": 0.00015843167928753757, "gradient_norm": 0.2559897005558014, "tokens_per_second": 767867.1933922196, "synthetic": false, "world_size": 8} {"step": 24540, "tokens": 6433013760, "loss": 2.3792516708374025, "optimizer_updates": 13270, "effective_batch": 512, "lr": 0.0001583689849402047, "gradient_norm": 0.2845333218574524, "tokens_per_second": 1082327.2268851264, "synthetic": false, "world_size": 8} {"step": 24560, "tokens": 6438256640, "loss": 2.3818058013916015, "optimizer_updates": 13280, "effective_batch": 512, "lr": 0.0001583062575713732, "gradient_norm": 0.2986023426055908, "tokens_per_second": 1082662.554118676, "synthetic": false, "world_size": 8} {"step": 24580, "tokens": 6443499520, "loss": 2.3918184280395507, "optimizer_updates": 13290, "effective_batch": 512, "lr": 0.00015824349722386706, "gradient_norm": 0.41996636986732483, "tokens_per_second": 1077950.652208968, "synthetic": false, "world_size": 8} {"step": 24600, "tokens": 6448742400, "loss": 2.3753843307495117, "optimizer_updates": 13300, "effective_batch": 512, "lr": 0.00015818070394053272, "gradient_norm": 0.25405341386795044, "tokens_per_second": 1079995.195619655, "synthetic": false, "world_size": 8} {"step": 24620, "tokens": 6453985280, "loss": 2.393680191040039, "optimizer_updates": 13310, "effective_batch": 512, "lr": 0.00015811787776423916, "gradient_norm": 0.25651898980140686, "tokens_per_second": 1078383.7579270056, "synthetic": false, "world_size": 8} {"step": 24640, "tokens": 6459228160, "loss": 2.377617073059082, "optimizer_updates": 13320, "effective_batch": 512, "lr": 0.0001580550187378778, "gradient_norm": 0.26442041993141174, "tokens_per_second": 1091245.6122640339, "synthetic": false, "world_size": 8} {"step": 24660, "tokens": 6464471040, "loss": 2.3776817321777344, "optimizer_updates": 13330, "effective_batch": 512, "lr": 0.00015799212690436254, "gradient_norm": 0.2689844071865082, "tokens_per_second": 1084959.5899524335, "synthetic": false, "world_size": 8} {"step": 24680, "tokens": 6469713920, "loss": 2.3774513244628905, "optimizer_updates": 13340, "effective_batch": 512, "lr": 0.0001579292023066295, "gradient_norm": 0.27222391963005066, "tokens_per_second": 1071811.3408033587, "synthetic": false, "world_size": 8} {"step": 24700, "tokens": 6474956800, "loss": 2.3872821807861326, "optimizer_updates": 13350, "effective_batch": 512, "lr": 0.0001578662449876374, "gradient_norm": 0.2927784323692322, "tokens_per_second": 1074568.62441085, "synthetic": false, "world_size": 8} {"step": 24720, "tokens": 6480199680, "loss": 2.379772758483887, "optimizer_updates": 13360, "effective_batch": 512, "lr": 0.00015780325499036715, "gradient_norm": 0.36159375309944153, "tokens_per_second": 1074969.9427599828, "synthetic": false, "world_size": 8} {"step": 24740, "tokens": 6485442560, "loss": 2.369604301452637, "optimizer_updates": 13370, "effective_batch": 512, "lr": 0.00015774023235782205, "gradient_norm": 0.2786611318588257, "tokens_per_second": 1074585.1810523535, "synthetic": false, "world_size": 8} {"step": 24760, "tokens": 6490685440, "loss": 2.3947475433349608, "optimizer_updates": 13380, "effective_batch": 512, "lr": 0.00015767717713302757, "gradient_norm": 0.2742551565170288, "tokens_per_second": 1088033.9340580064, "synthetic": false, "world_size": 8} {"step": 24780, "tokens": 6495928320, "loss": 2.378977584838867, "optimizer_updates": 13390, "effective_batch": 512, "lr": 0.00015761408935903155, "gradient_norm": 0.23727518320083618, "tokens_per_second": 1090596.1183342622, "synthetic": false, "world_size": 8} {"step": 24800, "tokens": 6501171200, "loss": 2.377634048461914, "optimizer_updates": 13400, "effective_batch": 512, "lr": 0.00015755096907890404, "gradient_norm": 0.2887742817401886, "tokens_per_second": 1081809.2208150208, "synthetic": false, "world_size": 8} {"step": 24820, "tokens": 6506414080, "loss": 2.373428153991699, "optimizer_updates": 13410, "effective_batch": 512, "lr": 0.00015748781633573717, "gradient_norm": 0.3002287745475769, "tokens_per_second": 1084878.0403455687, "synthetic": false, "world_size": 8} {"step": 24840, "tokens": 6511656960, "loss": 2.3834659576416017, "optimizer_updates": 13420, "effective_batch": 512, "lr": 0.00015742463117264537, "gradient_norm": 0.25097110867500305, "tokens_per_second": 1079827.3747607667, "synthetic": false, "world_size": 8} {"step": 24860, "tokens": 6516899840, "loss": 2.384903907775879, "optimizer_updates": 13430, "effective_batch": 512, "lr": 0.0001573614136327651, "gradient_norm": 0.25785622000694275, "tokens_per_second": 1079952.1362513048, "synthetic": false, "world_size": 8} {"step": 24880, "tokens": 6522142720, "loss": 2.3724237442016602, "optimizer_updates": 13440, "effective_batch": 512, "lr": 0.00015729816375925496, "gradient_norm": 0.2969362139701843, "tokens_per_second": 1080281.7443861763, "synthetic": false, "world_size": 8} {"step": 24900, "tokens": 6527385600, "loss": 2.3773021697998047, "optimizer_updates": 13450, "effective_batch": 512, "lr": 0.00015723488159529567, "gradient_norm": 0.2520125210285187, "tokens_per_second": 1085588.5636773608, "synthetic": false, "world_size": 8} {"step": 24920, "tokens": 6532628480, "loss": 2.372911834716797, "optimizer_updates": 13460, "effective_batch": 512, "lr": 0.0001571715671840899, "gradient_norm": 0.2831595540046692, "tokens_per_second": 1086438.2896631605, "synthetic": false, "world_size": 8} {"step": 24940, "tokens": 6537871360, "loss": 2.3775882720947266, "optimizer_updates": 13470, "effective_batch": 512, "lr": 0.00015710822056886245, "gradient_norm": 0.25628241896629333, "tokens_per_second": 976624.9266186007, "synthetic": false, "world_size": 8} {"step": 24960, "tokens": 6543114240, "loss": 2.381181526184082, "optimizer_updates": 13480, "effective_batch": 512, "lr": 0.00015704484179286, "gradient_norm": 0.26771190762519836, "tokens_per_second": 1069133.8066799946, "synthetic": false, "world_size": 8} {"step": 24980, "tokens": 6548357120, "loss": 2.3789016723632814, "optimizer_updates": 13490, "effective_batch": 512, "lr": 0.00015698143089935127, "gradient_norm": 0.2942209839820862, "tokens_per_second": 1064849.9032269018, "synthetic": false, "world_size": 8} {"step": 25000, "tokens": 6553600000, "loss": 2.379862594604492, "optimizer_updates": 13500, "effective_batch": 512, "lr": 0.0001569179879316268, "gradient_norm": 0.34670743346214294, "tokens_per_second": 1071312.592485364, "synthetic": false, "world_size": 8} {"step": 25020, "tokens": 6558842880, "loss": 2.3902286529541015, "optimizer_updates": 13510, "effective_batch": 512, "lr": 0.0001568545129329992, "gradient_norm": 0.41595688462257385, "tokens_per_second": 835823.1919752632, "synthetic": false, "world_size": 8} {"step": 25040, "tokens": 6564085760, "loss": 2.3764476776123047, "optimizer_updates": 13520, "effective_batch": 512, "lr": 0.0001567910059468027, "gradient_norm": 0.265776127576828, "tokens_per_second": 1063872.3660233775, "synthetic": false, "world_size": 8} {"step": 25060, "tokens": 6569328640, "loss": 2.3900278091430662, "optimizer_updates": 13530, "effective_batch": 512, "lr": 0.00015672746701639363, "gradient_norm": 0.2860790491104126, "tokens_per_second": 1056037.9010822452, "synthetic": false, "world_size": 8} {"step": 25080, "tokens": 6574571520, "loss": 2.3950199127197265, "optimizer_updates": 13540, "effective_batch": 512, "lr": 0.00015666389618515, "gradient_norm": 0.2485220730304718, "tokens_per_second": 1063150.8297883472, "synthetic": false, "world_size": 8} {"step": 25100, "tokens": 6579814400, "loss": 2.375339889526367, "optimizer_updates": 13550, "effective_batch": 512, "lr": 0.00015660029349647155, "gradient_norm": 0.3904989957809448, "tokens_per_second": 1061789.4029683538, "synthetic": false, "world_size": 8} {"step": 25120, "tokens": 6585057280, "loss": 2.3949348449707033, "optimizer_updates": 13560, "effective_batch": 512, "lr": 0.00015653665899377983, "gradient_norm": 0.2718851864337921, "tokens_per_second": 1064476.0340325024, "synthetic": false, "world_size": 8} {"step": 25140, "tokens": 6590300160, "loss": 2.384984588623047, "optimizer_updates": 13570, "effective_batch": 512, "lr": 0.00015647299272051812, "gradient_norm": 0.3148800730705261, "tokens_per_second": 1071696.5314599203, "synthetic": false, "world_size": 8} {"step": 25160, "tokens": 6595543040, "loss": 2.385976028442383, "optimizer_updates": 13580, "effective_batch": 512, "lr": 0.0001564092947201514, "gradient_norm": 0.3963993787765503, "tokens_per_second": 1072370.0521351732, "synthetic": false, "world_size": 8} {"step": 25180, "tokens": 6600785920, "loss": 2.373534393310547, "optimizer_updates": 13590, "effective_batch": 512, "lr": 0.00015634556503616627, "gradient_norm": 0.40569761395454407, "tokens_per_second": 1062109.4982207243, "synthetic": false, "world_size": 8} {"step": 25200, "tokens": 6606028800, "loss": 2.3783538818359373, "optimizer_updates": 13600, "effective_batch": 512, "lr": 0.00015628180371207097, "gradient_norm": 0.293160617351532, "tokens_per_second": 1069450.8768891918, "synthetic": false, "world_size": 8} {"step": 25220, "tokens": 6611271680, "loss": 2.3743682861328126, "optimizer_updates": 13610, "effective_batch": 512, "lr": 0.00015621801079139533, "gradient_norm": 0.3351580500602722, "tokens_per_second": 1064948.1709035886, "synthetic": false, "world_size": 8} {"step": 25240, "tokens": 6616514560, "loss": 2.3941570281982423, "optimizer_updates": 13620, "effective_batch": 512, "lr": 0.00015615418631769078, "gradient_norm": 0.2635977268218994, "tokens_per_second": 1080052.1703503476, "synthetic": false, "world_size": 8} {"step": 25260, "tokens": 6621757440, "loss": 2.3818435668945312, "optimizer_updates": 13630, "effective_batch": 512, "lr": 0.0001560903303345303, "gradient_norm": 0.26713505387306213, "tokens_per_second": 969758.0346123981, "synthetic": false, "world_size": 8} {"step": 25280, "tokens": 6627000320, "loss": 2.3872777938842775, "optimizer_updates": 13640, "effective_batch": 512, "lr": 0.00015602644288550835, "gradient_norm": 0.2699551582336426, "tokens_per_second": 1063982.5565899955, "synthetic": false, "world_size": 8} {"step": 25300, "tokens": 6632243200, "loss": 2.3722591400146484, "optimizer_updates": 13650, "effective_batch": 512, "lr": 0.00015596252401424088, "gradient_norm": 0.2637849748134613, "tokens_per_second": 1066994.6713775394, "synthetic": false, "world_size": 8} {"step": 25320, "tokens": 6637486080, "loss": 2.3810455322265627, "optimizer_updates": 13660, "effective_batch": 512, "lr": 0.00015589857376436525, "gradient_norm": 0.2668640911579132, "tokens_per_second": 1068100.5568840727, "synthetic": false, "world_size": 8} {"step": 25340, "tokens": 6642728960, "loss": 2.376813507080078, "optimizer_updates": 13670, "effective_batch": 512, "lr": 0.00015583459217954033, "gradient_norm": 0.2763596773147583, "tokens_per_second": 1068654.0372764172, "synthetic": false, "world_size": 8} {"step": 25360, "tokens": 6647971840, "loss": 2.376287078857422, "optimizer_updates": 13680, "effective_batch": 512, "lr": 0.00015577057930344634, "gradient_norm": 0.2341226190328598, "tokens_per_second": 1076119.2341290337, "synthetic": false, "world_size": 8} {"step": 25380, "tokens": 6653214720, "loss": 2.3801753997802733, "optimizer_updates": 13690, "effective_batch": 512, "lr": 0.00015570653517978488, "gradient_norm": 0.24286234378814697, "tokens_per_second": 1069731.8776775294, "synthetic": false, "world_size": 8} {"step": 25400, "tokens": 6658457600, "loss": 2.3673301696777345, "optimizer_updates": 13700, "effective_batch": 512, "lr": 0.00015564245985227879, "gradient_norm": 0.23056787252426147, "tokens_per_second": 1067529.27187088, "synthetic": false, "world_size": 8} {"step": 25420, "tokens": 6663700480, "loss": 2.3726837158203127, "optimizer_updates": 13710, "effective_batch": 512, "lr": 0.00015557835336467237, "gradient_norm": 0.284898579120636, "tokens_per_second": 1063657.1173410935, "synthetic": false, "world_size": 8} {"step": 25440, "tokens": 6668943360, "loss": 2.379994773864746, "optimizer_updates": 13720, "effective_batch": 512, "lr": 0.00015551421576073105, "gradient_norm": 0.27676260471343994, "tokens_per_second": 1071656.7368723762, "synthetic": false, "world_size": 8} {"step": 25460, "tokens": 6674186240, "loss": 2.3831903457641603, "optimizer_updates": 13730, "effective_batch": 512, "lr": 0.00015545004708424157, "gradient_norm": 0.29257282614707947, "tokens_per_second": 1075369.1378011415, "synthetic": false, "world_size": 8} {"step": 25480, "tokens": 6679429120, "loss": 2.367061996459961, "optimizer_updates": 13740, "effective_batch": 512, "lr": 0.00015538584737901192, "gradient_norm": 0.26726576685905457, "tokens_per_second": 1069546.0697870837, "synthetic": false, "world_size": 8} {"step": 25500, "tokens": 6684672000, "loss": 2.381433296203613, "optimizer_updates": 13750, "effective_batch": 512, "lr": 0.00015532161668887118, "gradient_norm": 0.2714992165565491, "tokens_per_second": 1071745.3116725492, "synthetic": false, "world_size": 8} {"step": 25520, "tokens": 6689914880, "loss": 2.3654769897460937, "optimizer_updates": 13760, "effective_batch": 512, "lr": 0.00015525735505766966, "gradient_norm": 0.23307888209819794, "tokens_per_second": 1069926.9582109407, "synthetic": false, "world_size": 8} {"step": 25540, "tokens": 6695157760, "loss": 2.373285484313965, "optimizer_updates": 13770, "effective_batch": 512, "lr": 0.00015519306252927874, "gradient_norm": 0.24923431873321533, "tokens_per_second": 1075513.6023613994, "synthetic": false, "world_size": 8} {"step": 25560, "tokens": 6700400640, "loss": 2.38013916015625, "optimizer_updates": 13780, "effective_batch": 512, "lr": 0.00015512873914759094, "gradient_norm": 0.24025960266590118, "tokens_per_second": 1069333.218901174, "synthetic": false, "world_size": 8} {"step": 25580, "tokens": 6705643520, "loss": 2.3840925216674806, "optimizer_updates": 13790, "effective_batch": 512, "lr": 0.00015506438495651985, "gradient_norm": 0.2400406152009964, "tokens_per_second": 1071680.0985471068, "synthetic": false, "world_size": 8} {"step": 25600, "tokens": 6710886400, "loss": 2.389146423339844, "optimizer_updates": 13800, "effective_batch": 512, "lr": 0.000155, "gradient_norm": 0.2635638415813446, "tokens_per_second": 1063578.6133907905, "synthetic": false, "world_size": 8} {"step": 25620, "tokens": 6716129280, "loss": 2.3833866119384766, "optimizer_updates": 13810, "effective_batch": 512, "lr": 0.00015493558432198707, "gradient_norm": 0.3001745045185089, "tokens_per_second": 1068774.4476445133, "synthetic": false, "world_size": 8} {"step": 25640, "tokens": 6721372160, "loss": 2.38431339263916, "optimizer_updates": 13820, "effective_batch": 512, "lr": 0.00015487113796645754, "gradient_norm": 0.2894328236579895, "tokens_per_second": 1075769.777698189, "synthetic": false, "world_size": 8} {"step": 25660, "tokens": 6726615040, "loss": 2.3858591079711915, "optimizer_updates": 13830, "effective_batch": 512, "lr": 0.000154806660977409, "gradient_norm": 0.25921159982681274, "tokens_per_second": 1073007.6337768254, "synthetic": false, "world_size": 8} {"step": 25680, "tokens": 6731857920, "loss": 2.3861766815185548, "optimizer_updates": 13840, "effective_batch": 512, "lr": 0.00015474215339885983, "gradient_norm": 0.23720084130764008, "tokens_per_second": 1076605.647889774, "synthetic": false, "world_size": 8} {"step": 25700, "tokens": 6737100800, "loss": 2.3755672454833983, "optimizer_updates": 13850, "effective_batch": 512, "lr": 0.0001546776152748494, "gradient_norm": 0.3088222146034241, "tokens_per_second": 1066137.7263984454, "synthetic": false, "world_size": 8} {"step": 25720, "tokens": 6742343680, "loss": 2.3882875442504883, "optimizer_updates": 13860, "effective_batch": 512, "lr": 0.00015461304664943782, "gradient_norm": 0.2567524015903473, "tokens_per_second": 1074527.4659942489, "synthetic": false, "world_size": 8} {"step": 25740, "tokens": 6747586560, "loss": 2.393422317504883, "optimizer_updates": 13870, "effective_batch": 512, "lr": 0.00015454844756670612, "gradient_norm": 0.2644828259944916, "tokens_per_second": 1070122.6319902202, "synthetic": false, "world_size": 8} {"step": 25760, "tokens": 6752829440, "loss": 2.390714645385742, "optimizer_updates": 13880, "effective_batch": 512, "lr": 0.0001544838180707561, "gradient_norm": 0.25384366512298584, "tokens_per_second": 1073948.2076741362, "synthetic": false, "world_size": 8} {"step": 25780, "tokens": 6758072320, "loss": 2.3923450469970704, "optimizer_updates": 13890, "effective_batch": 512, "lr": 0.00015441915820571024, "gradient_norm": 0.30283892154693604, "tokens_per_second": 1064068.6944084086, "synthetic": false, "world_size": 8} {"step": 25800, "tokens": 6763315200, "loss": 2.386439323425293, "optimizer_updates": 13900, "effective_batch": 512, "lr": 0.00015435446801571187, "gradient_norm": 0.25922325253486633, "tokens_per_second": 1074497.7039650353, "synthetic": false, "world_size": 8} {"step": 25820, "tokens": 6768558080, "loss": 2.3835285186767576, "optimizer_updates": 13910, "effective_batch": 512, "lr": 0.000154289747544925, "gradient_norm": 0.3513871431350708, "tokens_per_second": 1080928.5251901322, "synthetic": false, "world_size": 8} {"step": 25840, "tokens": 6773800960, "loss": 2.4005126953125, "optimizer_updates": 13920, "effective_batch": 512, "lr": 0.00015422499683753418, "gradient_norm": 0.25431403517723083, "tokens_per_second": 1074466.6410901952, "synthetic": false, "world_size": 8} {"step": 25860, "tokens": 6779043840, "loss": 2.3825698852539063, "optimizer_updates": 13930, "effective_batch": 512, "lr": 0.0001541602159377448, "gradient_norm": 0.2766357958316803, "tokens_per_second": 1077439.8416955397, "synthetic": false, "world_size": 8} {"step": 25880, "tokens": 6784286720, "loss": 2.3900829315185548, "optimizer_updates": 13940, "effective_batch": 512, "lr": 0.00015409540488978276, "gradient_norm": 0.3267805576324463, "tokens_per_second": 1071453.1057104324, "synthetic": false, "world_size": 8} {"step": 25900, "tokens": 6789529600, "loss": 2.3683528900146484, "optimizer_updates": 13950, "effective_batch": 512, "lr": 0.00015403056373789454, "gradient_norm": 0.3444024622440338, "tokens_per_second": 1081355.176791724, "synthetic": false, "world_size": 8} {"step": 25920, "tokens": 6794772480, "loss": 2.380055046081543, "optimizer_updates": 13960, "effective_batch": 512, "lr": 0.0001539656925263472, "gradient_norm": 0.2809763252735138, "tokens_per_second": 975882.402160744, "synthetic": false, "world_size": 8} {"step": 25940, "tokens": 6800015360, "loss": 2.377056884765625, "optimizer_updates": 13970, "effective_batch": 512, "lr": 0.00015390079129942824, "gradient_norm": 0.2411881983280182, "tokens_per_second": 1066834.0297307211, "synthetic": false, "world_size": 8} {"step": 25960, "tokens": 6805258240, "loss": 2.3785329818725587, "optimizer_updates": 13980, "effective_batch": 512, "lr": 0.0001538358601014458, "gradient_norm": 0.24281543493270874, "tokens_per_second": 1067813.6051771764, "synthetic": false, "world_size": 8} {"step": 25980, "tokens": 6810501120, "loss": 2.389063835144043, "optimizer_updates": 13990, "effective_batch": 512, "lr": 0.00015377089897672836, "gradient_norm": 0.25976699590682983, "tokens_per_second": 1071217.7542179346, "synthetic": false, "world_size": 8} {"step": 26000, "tokens": 6815744000, "loss": 2.3952621459960937, "optimizer_updates": 14000, "effective_batch": 512, "lr": 0.00015370590796962488, "gradient_norm": 0.2853952944278717, "tokens_per_second": 1066439.8286442277, "synthetic": false, "world_size": 8} {"step": 26020, "tokens": 6820986880, "loss": 2.384778594970703, "optimizer_updates": 14010, "effective_batch": 512, "lr": 0.00015364088712450471, "gradient_norm": 0.2532549798488617, "tokens_per_second": 843527.5809731841, "synthetic": false, "world_size": 8} {"step": 26040, "tokens": 6826229760, "loss": 2.3814783096313477, "optimizer_updates": 14020, "effective_batch": 512, "lr": 0.00015357583648575754, "gradient_norm": 0.44564151763916016, "tokens_per_second": 1067034.0168701431, "synthetic": false, "world_size": 8} {"step": 26060, "tokens": 6831472640, "loss": 2.383022689819336, "optimizer_updates": 14030, "effective_batch": 512, "lr": 0.0001535107560977935, "gradient_norm": 0.31642866134643555, "tokens_per_second": 1068405.6283341895, "synthetic": false, "world_size": 8} {"step": 26080, "tokens": 6836715520, "loss": 2.3819671630859376, "optimizer_updates": 14040, "effective_batch": 512, "lr": 0.0001534456460050429, "gradient_norm": 0.24481385946273804, "tokens_per_second": 1073543.9415757428, "synthetic": false, "world_size": 8} {"step": 26100, "tokens": 6841958400, "loss": 2.3597238540649412, "optimizer_updates": 14050, "effective_batch": 512, "lr": 0.0001533805062519564, "gradient_norm": 0.2555376887321472, "tokens_per_second": 1066192.1517221786, "synthetic": false, "world_size": 8} {"step": 26120, "tokens": 6847201280, "loss": 2.379055976867676, "optimizer_updates": 14060, "effective_batch": 512, "lr": 0.00015331533688300492, "gradient_norm": 0.2999279499053955, "tokens_per_second": 1071528.2294081375, "synthetic": false, "world_size": 8} {"step": 26140, "tokens": 6852444160, "loss": 2.3854061126708985, "optimizer_updates": 14070, "effective_batch": 512, "lr": 0.00015325013794267956, "gradient_norm": 0.23481018841266632, "tokens_per_second": 1071484.6433930278, "synthetic": false, "world_size": 8} {"step": 26160, "tokens": 6857687040, "loss": 2.387721824645996, "optimizer_updates": 14080, "effective_batch": 512, "lr": 0.00015318490947549164, "gradient_norm": 0.2583558261394501, "tokens_per_second": 1071576.7159001473, "synthetic": false, "world_size": 8} {"step": 26180, "tokens": 6862929920, "loss": 2.383423614501953, "optimizer_updates": 14090, "effective_batch": 512, "lr": 0.0001531196515259726, "gradient_norm": 0.2597600817680359, "tokens_per_second": 1069924.34728844, "synthetic": false, "world_size": 8} {"step": 26200, "tokens": 6868172800, "loss": 2.400905418395996, "optimizer_updates": 14100, "effective_batch": 512, "lr": 0.0001530543641386741, "gradient_norm": 0.4160501956939697, "tokens_per_second": 1077977.6130313587, "synthetic": false, "world_size": 8} {"step": 26220, "tokens": 6873415680, "loss": 2.3777229309082033, "optimizer_updates": 14110, "effective_batch": 512, "lr": 0.00015298904735816776, "gradient_norm": 0.26248911023139954, "tokens_per_second": 1069423.6882268793, "synthetic": false, "world_size": 8} {"step": 26240, "tokens": 6878658560, "loss": 2.390496826171875, "optimizer_updates": 14120, "effective_batch": 512, "lr": 0.00015292370122904533, "gradient_norm": 0.2720513343811035, "tokens_per_second": 1071859.3068722957, "synthetic": false, "world_size": 8} {"step": 26260, "tokens": 6883901440, "loss": 2.386962890625, "optimizer_updates": 14130, "effective_batch": 512, "lr": 0.00015285832579591864, "gradient_norm": 0.35329121351242065, "tokens_per_second": 1079029.768586254, "synthetic": false, "world_size": 8} {"step": 26280, "tokens": 6889144320, "loss": 2.3767677307128907, "optimizer_updates": 14140, "effective_batch": 512, "lr": 0.00015279292110341946, "gradient_norm": 0.31970497965812683, "tokens_per_second": 1070981.7530662315, "synthetic": false, "world_size": 8} {"step": 26300, "tokens": 6894387200, "loss": 2.372477722167969, "optimizer_updates": 14150, "effective_batch": 512, "lr": 0.0001527274871961996, "gradient_norm": 0.3400143086910248, "tokens_per_second": 1076630.6062858, "synthetic": false, "world_size": 8} {"step": 26320, "tokens": 6899630080, "loss": 2.3780237197875977, "optimizer_updates": 14160, "effective_batch": 512, "lr": 0.00015266202411893078, "gradient_norm": 0.40550199151039124, "tokens_per_second": 740817.5761858567, "synthetic": false, "world_size": 8} {"step": 26340, "tokens": 6904872960, "loss": 2.378231239318848, "optimizer_updates": 14170, "effective_batch": 512, "lr": 0.00015259653191630458, "gradient_norm": 0.2612719237804413, "tokens_per_second": 1071708.1994698248, "synthetic": false, "world_size": 8} {"step": 26360, "tokens": 6910115840, "loss": 2.3918075561523438, "optimizer_updates": 14180, "effective_batch": 512, "lr": 0.00015253101063303256, "gradient_norm": 0.2390097826719284, "tokens_per_second": 1070097.7144783584, "synthetic": false, "world_size": 8} {"step": 26380, "tokens": 6915358720, "loss": 2.3641639709472657, "optimizer_updates": 14190, "effective_batch": 512, "lr": 0.0001524654603138461, "gradient_norm": 0.2864585816860199, "tokens_per_second": 1069135.2366837913, "synthetic": false, "world_size": 8} {"step": 26400, "tokens": 6920601600, "loss": 2.3747846603393556, "optimizer_updates": 14200, "effective_batch": 512, "lr": 0.00015239988100349634, "gradient_norm": 0.28388288617134094, "tokens_per_second": 1066830.335227499, "synthetic": false, "world_size": 8} {"step": 26420, "tokens": 6925844480, "loss": 2.392680549621582, "optimizer_updates": 14210, "effective_batch": 512, "lr": 0.0001523342727467543, "gradient_norm": 0.2686314284801483, "tokens_per_second": 1065445.7136003287, "synthetic": false, "world_size": 8} {"step": 26440, "tokens": 6931087360, "loss": 2.3777229309082033, "optimizer_updates": 14220, "effective_batch": 512, "lr": 0.00015226863558841076, "gradient_norm": 0.3283853530883789, "tokens_per_second": 1066135.7312078383, "synthetic": false, "world_size": 8} {"step": 26460, "tokens": 6936330240, "loss": 2.3735206604003904, "optimizer_updates": 14230, "effective_batch": 512, "lr": 0.00015220296957327612, "gradient_norm": 0.27142560482025146, "tokens_per_second": 1069134.6887884834, "synthetic": false, "world_size": 8} {"step": 26480, "tokens": 6941573120, "loss": 2.3915264129638674, "optimizer_updates": 14240, "effective_batch": 512, "lr": 0.0001521372747461806, "gradient_norm": 0.24985262751579285, "tokens_per_second": 1072318.877534511, "synthetic": false, "world_size": 8} {"step": 26500, "tokens": 6946816000, "loss": 2.3819768905639647, "optimizer_updates": 14250, "effective_batch": 512, "lr": 0.00015207155115197406, "gradient_norm": 0.2659706175327301, "tokens_per_second": 1069744.566546681, "synthetic": false, "world_size": 8} {"step": 26520, "tokens": 6952058880, "loss": 2.377005958557129, "optimizer_updates": 14260, "effective_batch": 512, "lr": 0.00015200579883552597, "gradient_norm": 0.298783540725708, "tokens_per_second": 1075297.1582403823, "synthetic": false, "world_size": 8} {"step": 26540, "tokens": 6957301760, "loss": 2.3826526641845702, "optimizer_updates": 14270, "effective_batch": 512, "lr": 0.00015194001784172548, "gradient_norm": 0.26161330938339233, "tokens_per_second": 1079212.9270932334, "synthetic": false, "world_size": 8} {"step": 26560, "tokens": 6962544640, "loss": 2.369195747375488, "optimizer_updates": 14280, "effective_batch": 512, "lr": 0.00015187420821548116, "gradient_norm": 0.25066593289375305, "tokens_per_second": 786721.1974202521, "synthetic": false, "world_size": 8} {"step": 26580, "tokens": 6967787520, "loss": 2.3843482971191405, "optimizer_updates": 14290, "effective_batch": 512, "lr": 0.0001518083700017213, "gradient_norm": 0.27941763401031494, "tokens_per_second": 1069576.4414078176, "synthetic": false, "world_size": 8} {"step": 26600, "tokens": 6973030400, "loss": 2.3777942657470703, "optimizer_updates": 14300, "effective_batch": 512, "lr": 0.00015174250324539364, "gradient_norm": 0.3383748233318329, "tokens_per_second": 1067402.5926728651, "synthetic": false, "world_size": 8} {"step": 26620, "tokens": 6978273280, "loss": 2.38016357421875, "optimizer_updates": 14310, "effective_batch": 512, "lr": 0.0001516766079914654, "gradient_norm": 0.3025858998298645, "tokens_per_second": 1074121.8890029916, "synthetic": false, "world_size": 8} {"step": 26640, "tokens": 6983516160, "loss": 2.381052780151367, "optimizer_updates": 14320, "effective_batch": 512, "lr": 0.00015161068428492323, "gradient_norm": 0.3928671181201935, "tokens_per_second": 1076102.2142796994, "synthetic": false, "world_size": 8} {"step": 26660, "tokens": 6988759040, "loss": 2.373021125793457, "optimizer_updates": 14330, "effective_batch": 512, "lr": 0.00015154473217077327, "gradient_norm": 0.2686448097229004, "tokens_per_second": 786956.410990433, "synthetic": false, "world_size": 8} {"step": 26680, "tokens": 6994001920, "loss": 2.3791072845458983, "optimizer_updates": 14340, "effective_batch": 512, "lr": 0.000151478751694041, "gradient_norm": 0.2745599150657654, "tokens_per_second": 1065629.7990150447, "synthetic": false, "world_size": 8} {"step": 26700, "tokens": 6999244800, "loss": 2.390220069885254, "optimizer_updates": 14350, "effective_batch": 512, "lr": 0.0001514127428997713, "gradient_norm": 0.26965972781181335, "tokens_per_second": 1074153.724874567, "synthetic": false, "world_size": 8} {"step": 26720, "tokens": 7004487680, "loss": 2.3856910705566405, "optimizer_updates": 14360, "effective_batch": 512, "lr": 0.0001513467058330283, "gradient_norm": 0.35772112011909485, "tokens_per_second": 1067631.8078124116, "synthetic": false, "world_size": 8} {"step": 26740, "tokens": 7009730560, "loss": 2.366288948059082, "optimizer_updates": 14370, "effective_batch": 512, "lr": 0.00015128064053889558, "gradient_norm": 0.24450944364070892, "tokens_per_second": 1077619.3381941796, "synthetic": false, "world_size": 8} {"step": 26760, "tokens": 7014973440, "loss": 2.3836643218994142, "optimizer_updates": 14380, "effective_batch": 512, "lr": 0.00015121454706247585, "gradient_norm": 0.28694579005241394, "tokens_per_second": 1077177.112788415, "synthetic": false, "world_size": 8} {"step": 26780, "tokens": 7020216320, "loss": 2.3737049102783203, "optimizer_updates": 14390, "effective_batch": 512, "lr": 0.00015114842544889116, "gradient_norm": 0.35269591212272644, "tokens_per_second": 1074410.6426936344, "synthetic": false, "world_size": 8} {"step": 26800, "tokens": 7025459200, "loss": 2.3855770111083983, "optimizer_updates": 14400, "effective_batch": 512, "lr": 0.00015108227574328267, "gradient_norm": 0.2502255439758301, "tokens_per_second": 979832.595515951, "synthetic": false, "world_size": 8} {"step": 26820, "tokens": 7030702080, "loss": 2.3673704147338865, "optimizer_updates": 14410, "effective_batch": 512, "lr": 0.00015101609799081085, "gradient_norm": 0.3001258075237274, "tokens_per_second": 861105.8742475039, "synthetic": false, "world_size": 8} {"step": 26840, "tokens": 7035944960, "loss": 2.36575870513916, "optimizer_updates": 14420, "effective_batch": 512, "lr": 0.0001509498922366552, "gradient_norm": 0.25445085763931274, "tokens_per_second": 899987.4164279983, "synthetic": false, "world_size": 8} {"step": 26860, "tokens": 7041187840, "loss": 2.371258354187012, "optimizer_updates": 14430, "effective_batch": 512, "lr": 0.00015088365852601438, "gradient_norm": 0.26785901188850403, "tokens_per_second": 1073089.305042973, "synthetic": false, "world_size": 8} {"step": 26880, "tokens": 7046430720, "loss": 2.3748003005981446, "optimizer_updates": 14440, "effective_batch": 512, "lr": 0.00015081739690410607, "gradient_norm": 0.3078063726425171, "tokens_per_second": 1068594.14183681, "synthetic": false, "world_size": 8} {"step": 26900, "tokens": 7051673600, "loss": 2.3708803176879885, "optimizer_updates": 14450, "effective_batch": 512, "lr": 0.00015075110741616718, "gradient_norm": 0.23649729788303375, "tokens_per_second": 1064347.9338494288, "synthetic": false, "world_size": 8} {"step": 26920, "tokens": 7056916480, "loss": 2.395219612121582, "optimizer_updates": 14460, "effective_batch": 512, "lr": 0.00015068479010745347, "gradient_norm": 0.32353606820106506, "tokens_per_second": 1064354.4235768435, "synthetic": false, "world_size": 8} {"step": 26940, "tokens": 7062159360, "loss": 2.398436737060547, "optimizer_updates": 14470, "effective_batch": 512, "lr": 0.00015061844502323976, "gradient_norm": 0.2722906768321991, "tokens_per_second": 1072421.236012886, "synthetic": false, "world_size": 8} {"step": 26960, "tokens": 7067402240, "loss": 2.3795473098754885, "optimizer_updates": 14480, "effective_batch": 512, "lr": 0.00015055207220881985, "gradient_norm": 0.24522808194160461, "tokens_per_second": 1074109.497453399, "synthetic": false, "world_size": 8} {"step": 26980, "tokens": 7072645120, "loss": 2.3767343521118165, "optimizer_updates": 14490, "effective_batch": 512, "lr": 0.00015048567170950644, "gradient_norm": 0.2643493711948395, "tokens_per_second": 1074743.3723013585, "synthetic": false, "world_size": 8} {"step": 27000, "tokens": 7077888000, "loss": 2.381186676025391, "optimizer_updates": 14500, "effective_batch": 512, "lr": 0.00015041924357063114, "gradient_norm": 0.26935458183288574, "tokens_per_second": 1073509.996073584, "synthetic": false, "world_size": 8} {"step": 27020, "tokens": 7083130880, "loss": 2.3666542053222654, "optimizer_updates": 14510, "effective_batch": 512, "lr": 0.00015035278783754444, "gradient_norm": 0.2900293469429016, "tokens_per_second": 647018.0674674193, "synthetic": false, "world_size": 8} {"step": 27040, "tokens": 7088373760, "loss": 2.3712812423706056, "optimizer_updates": 14520, "effective_batch": 512, "lr": 0.00015028630455561563, "gradient_norm": 0.2549345791339874, "tokens_per_second": 1077199.3203024366, "synthetic": false, "world_size": 8} {"step": 27060, "tokens": 7093616640, "loss": 2.3755369186401367, "optimizer_updates": 14530, "effective_batch": 512, "lr": 0.00015021979377023286, "gradient_norm": 0.24954357743263245, "tokens_per_second": 1063814.5621248477, "synthetic": false, "world_size": 8} {"step": 27080, "tokens": 7098859520, "loss": 2.3774059295654295, "optimizer_updates": 14540, "effective_batch": 512, "lr": 0.00015015325552680302, "gradient_norm": 0.3293229639530182, "tokens_per_second": 1064254.7171268307, "synthetic": false, "world_size": 8} {"step": 27100, "tokens": 7104102400, "loss": 2.3746946334838865, "optimizer_updates": 14550, "effective_batch": 512, "lr": 0.00015008668987075176, "gradient_norm": 0.3671530783176422, "tokens_per_second": 1068481.3600608665, "synthetic": false, "world_size": 8} {"step": 27120, "tokens": 7109345280, "loss": 2.37684326171875, "optimizer_updates": 14560, "effective_batch": 512, "lr": 0.00015002009684752347, "gradient_norm": 0.32135769724845886, "tokens_per_second": 1071385.8227933513, "synthetic": false, "world_size": 8} {"step": 27140, "tokens": 7114588160, "loss": 2.367025947570801, "optimizer_updates": 14570, "effective_batch": 512, "lr": 0.00014995347650258116, "gradient_norm": 0.2882402539253235, "tokens_per_second": 1068608.811450206, "synthetic": false, "world_size": 8} {"step": 27160, "tokens": 7119831040, "loss": 2.394240951538086, "optimizer_updates": 14580, "effective_batch": 512, "lr": 0.00014988682888140658, "gradient_norm": 0.2936928868293762, "tokens_per_second": 1063930.8947432975, "synthetic": false, "world_size": 8} {"step": 27180, "tokens": 7125073920, "loss": 2.3653459548950195, "optimizer_updates": 14590, "effective_batch": 512, "lr": 0.00014982015402949998, "gradient_norm": 0.3084121644496918, "tokens_per_second": 1074394.1259807828, "synthetic": false, "world_size": 8} {"step": 27200, "tokens": 7130316800, "loss": 2.384583282470703, "optimizer_updates": 14600, "effective_batch": 512, "lr": 0.00014975345199238032, "gradient_norm": 0.26104819774627686, "tokens_per_second": 1072592.7325629285, "synthetic": false, "world_size": 8} {"step": 27220, "tokens": 7135559680, "loss": 2.3856178283691407, "optimizer_updates": 14610, "effective_batch": 512, "lr": 0.00014968672281558506, "gradient_norm": 0.277515709400177, "tokens_per_second": 1069693.2351897627, "synthetic": false, "world_size": 8} {"step": 27240, "tokens": 7140802560, "loss": 2.384870147705078, "optimizer_updates": 14620, "effective_batch": 512, "lr": 0.00014961996654467018, "gradient_norm": 0.2766651511192322, "tokens_per_second": 1065534.0290448354, "synthetic": false, "world_size": 8} {"step": 27260, "tokens": 7146045440, "loss": 2.3828622817993166, "optimizer_updates": 14630, "effective_batch": 512, "lr": 0.00014955318322521023, "gradient_norm": 0.2799217104911804, "tokens_per_second": 1075267.2893769683, "synthetic": false, "world_size": 8} {"step": 27280, "tokens": 7151288320, "loss": 2.3766607284545898, "optimizer_updates": 14640, "effective_batch": 512, "lr": 0.0001494863729027981, "gradient_norm": 0.25944098830223083, "tokens_per_second": 971815.9608416359, "synthetic": false, "world_size": 8} {"step": 27300, "tokens": 7156531200, "loss": 2.3890398025512694, "optimizer_updates": 14650, "effective_batch": 512, "lr": 0.00014941953562304524, "gradient_norm": 0.2683790922164917, "tokens_per_second": 1071232.4707792073, "synthetic": false, "world_size": 8} {"step": 27320, "tokens": 7161774080, "loss": 2.3801631927490234, "optimizer_updates": 14660, "effective_batch": 512, "lr": 0.00014935267143158142, "gradient_norm": 0.319760262966156, "tokens_per_second": 1082414.3007869988, "synthetic": false, "world_size": 8} {"step": 27340, "tokens": 7167016960, "loss": 2.3716291427612304, "optimizer_updates": 14670, "effective_batch": 512, "lr": 0.00014928578037405482, "gradient_norm": 0.2758520543575287, "tokens_per_second": 1071059.5516658311, "synthetic": false, "world_size": 8} {"step": 27360, "tokens": 7172259840, "loss": 2.3766557693481447, "optimizer_updates": 14680, "effective_batch": 512, "lr": 0.000149218862496132, "gradient_norm": 0.24076615273952484, "tokens_per_second": 1070978.9678828306, "synthetic": false, "world_size": 8} {"step": 27380, "tokens": 7177502720, "loss": 2.376873779296875, "optimizer_updates": 14690, "effective_batch": 512, "lr": 0.0001491519178434977, "gradient_norm": 0.26846960186958313, "tokens_per_second": 1069571.598278556, "synthetic": false, "world_size": 8} {"step": 27400, "tokens": 7182745600, "loss": 2.3819671630859376, "optimizer_updates": 14700, "effective_batch": 512, "lr": 0.0001490849464618551, "gradient_norm": 0.28883227705955505, "tokens_per_second": 1074635.5369267373, "synthetic": false, "world_size": 8} {"step": 27420, "tokens": 7187988480, "loss": 2.3804677963256835, "optimizer_updates": 14710, "effective_batch": 512, "lr": 0.00014901794839692551, "gradient_norm": 0.2894366979598999, "tokens_per_second": 1072522.2833263385, "synthetic": false, "world_size": 8} {"step": 27440, "tokens": 7193231360, "loss": 2.3722854614257813, "optimizer_updates": 14720, "effective_batch": 512, "lr": 0.0001489509236944485, "gradient_norm": 0.2971363365650177, "tokens_per_second": 1074514.9937376648, "synthetic": false, "world_size": 8} {"step": 27460, "tokens": 7198474240, "loss": 2.3711994171142576, "optimizer_updates": 14730, "effective_batch": 512, "lr": 0.00014888387240018184, "gradient_norm": 0.27005910873413086, "tokens_per_second": 1064961.6107202095, "synthetic": false, "world_size": 8} {"step": 27480, "tokens": 7203717120, "loss": 2.3727169036865234, "optimizer_updates": 14740, "effective_batch": 512, "lr": 0.00014881679455990145, "gradient_norm": 0.2446555197238922, "tokens_per_second": 1079616.441624726, "synthetic": false, "world_size": 8} {"step": 27500, "tokens": 7208960000, "loss": 2.3741172790527343, "optimizer_updates": 14750, "effective_batch": 512, "lr": 0.00014874969021940135, "gradient_norm": 0.2494899481534958, "tokens_per_second": 1071911.87942067, "synthetic": false, "world_size": 8} {"step": 27520, "tokens": 7214202880, "loss": 2.3809309005737305, "optimizer_updates": 14760, "effective_batch": 512, "lr": 0.00014868255942449362, "gradient_norm": 0.23453973233699799, "tokens_per_second": 1068185.3651645759, "synthetic": false, "world_size": 8} {"step": 27540, "tokens": 7219445760, "loss": 2.3665212631225585, "optimizer_updates": 14770, "effective_batch": 512, "lr": 0.00014861540222100853, "gradient_norm": 0.27438661456108093, "tokens_per_second": 1069352.404674229, "synthetic": false, "world_size": 8} {"step": 27560, "tokens": 7224688640, "loss": 2.375644874572754, "optimizer_updates": 14780, "effective_batch": 512, "lr": 0.00014854821865479422, "gradient_norm": 0.25689423084259033, "tokens_per_second": 1083381.405473327, "synthetic": false, "world_size": 8} {"step": 27580, "tokens": 7229931520, "loss": 2.3705514907836913, "optimizer_updates": 14790, "effective_batch": 512, "lr": 0.0001484810087717169, "gradient_norm": 0.2562420666217804, "tokens_per_second": 1068525.479060961, "synthetic": false, "world_size": 8} {"step": 27600, "tokens": 7235174400, "loss": 2.391910362243652, "optimizer_updates": 14800, "effective_batch": 512, "lr": 0.00014841377261766076, "gradient_norm": 0.31594812870025635, "tokens_per_second": 1066455.8975455235, "synthetic": false, "world_size": 8} {"step": 27620, "tokens": 7240417280, "loss": 2.3727935791015624, "optimizer_updates": 14810, "effective_batch": 512, "lr": 0.00014834651023852796, "gradient_norm": 0.2778869867324829, "tokens_per_second": 1072965.7736377795, "synthetic": false, "world_size": 8} {"step": 27640, "tokens": 7245660160, "loss": 2.3767168045043947, "optimizer_updates": 14820, "effective_batch": 512, "lr": 0.00014827922168023848, "gradient_norm": 0.2855622470378876, "tokens_per_second": 1073218.6292785385, "synthetic": false, "world_size": 8} {"step": 27660, "tokens": 7250903040, "loss": 2.378446578979492, "optimizer_updates": 14830, "effective_batch": 512, "lr": 0.00014821190698873022, "gradient_norm": 0.3316967189311981, "tokens_per_second": 1070241.4416046035, "synthetic": false, "world_size": 8} {"step": 27680, "tokens": 7256145920, "loss": 2.387447738647461, "optimizer_updates": 14840, "effective_batch": 512, "lr": 0.00014814456620995887, "gradient_norm": 0.2868758738040924, "tokens_per_second": 1067983.6603160235, "synthetic": false, "world_size": 8} {"step": 27700, "tokens": 7261388800, "loss": 2.3778049468994142, "optimizer_updates": 14850, "effective_batch": 512, "lr": 0.000148077199389898, "gradient_norm": 0.25078290700912476, "tokens_per_second": 1067158.5437751962, "synthetic": false, "world_size": 8} {"step": 27720, "tokens": 7266631680, "loss": 2.3728294372558594, "optimizer_updates": 14860, "effective_batch": 512, "lr": 0.0001480098065745389, "gradient_norm": 0.24676483869552612, "tokens_per_second": 1069915.3237437517, "synthetic": false, "world_size": 8} {"step": 27740, "tokens": 7271874560, "loss": 2.3754388809204103, "optimizer_updates": 14870, "effective_batch": 512, "lr": 0.0001479423878098907, "gradient_norm": 0.2588956356048584, "tokens_per_second": 1068514.2197552198, "synthetic": false, "world_size": 8} {"step": 27760, "tokens": 7277117440, "loss": 2.3828266143798826, "optimizer_updates": 14880, "effective_batch": 512, "lr": 0.0001478749431419801, "gradient_norm": 0.2894452214241028, "tokens_per_second": 1075541.9423927134, "synthetic": false, "world_size": 8} {"step": 27780, "tokens": 7282360320, "loss": 2.370829963684082, "optimizer_updates": 14890, "effective_batch": 512, "lr": 0.00014780747261685165, "gradient_norm": 0.280341774225235, "tokens_per_second": 1076944.7009089065, "synthetic": false, "world_size": 8} {"step": 27800, "tokens": 7287603200, "loss": 2.3932125091552736, "optimizer_updates": 14900, "effective_batch": 512, "lr": 0.00014773997628056738, "gradient_norm": 0.25182121992111206, "tokens_per_second": 1075685.0365092, "synthetic": false, "world_size": 8} {"step": 27820, "tokens": 7292846080, "loss": 2.354367256164551, "optimizer_updates": 14910, "effective_batch": 512, "lr": 0.0001476724541792071, "gradient_norm": 0.4173802435398102, "tokens_per_second": 1068959.9956006848, "synthetic": false, "world_size": 8} {"step": 27840, "tokens": 7298088960, "loss": 2.3785354614257814, "optimizer_updates": 14920, "effective_batch": 512, "lr": 0.0001476049063588681, "gradient_norm": 0.24326330423355103, "tokens_per_second": 1071660.4131893427, "synthetic": false, "world_size": 8} {"step": 27860, "tokens": 7303331840, "loss": 2.382524871826172, "optimizer_updates": 14930, "effective_batch": 512, "lr": 0.00014753733286566525, "gradient_norm": 0.35452187061309814, "tokens_per_second": 1072032.5560459134, "synthetic": false, "world_size": 8} {"step": 27880, "tokens": 7308574720, "loss": 2.3764005661010743, "optimizer_updates": 14940, "effective_batch": 512, "lr": 0.000147469733745731, "gradient_norm": 0.30407461524009705, "tokens_per_second": 1073347.4269675435, "synthetic": false, "world_size": 8} {"step": 27900, "tokens": 7313817600, "loss": 2.3730281829833983, "optimizer_updates": 14950, "effective_batch": 512, "lr": 0.00014740210904521528, "gradient_norm": 0.2463032454252243, "tokens_per_second": 1076392.915553984, "synthetic": false, "world_size": 8} {"step": 27920, "tokens": 7319060480, "loss": 2.388607978820801, "optimizer_updates": 14960, "effective_batch": 512, "lr": 0.0001473344588102854, "gradient_norm": 0.2930000424385071, "tokens_per_second": 1071742.0758007423, "synthetic": false, "world_size": 8} {"step": 27940, "tokens": 7324303360, "loss": 2.3856000900268555, "optimizer_updates": 14970, "effective_batch": 512, "lr": 0.00014726678308712616, "gradient_norm": 0.26201531291007996, "tokens_per_second": 1066018.187247352, "synthetic": false, "world_size": 8} {"step": 27960, "tokens": 7329546240, "loss": 2.366441345214844, "optimizer_updates": 14980, "effective_batch": 512, "lr": 0.00014719908192193984, "gradient_norm": 0.28132304549217224, "tokens_per_second": 1069887.446894682, "synthetic": false, "world_size": 8} {"step": 27980, "tokens": 7334789120, "loss": 2.381563186645508, "optimizer_updates": 14990, "effective_batch": 512, "lr": 0.000147131355360946, "gradient_norm": 0.3504731357097626, "tokens_per_second": 1080861.5475721098, "synthetic": false, "world_size": 8} {"step": 28000, "tokens": 7340032000, "loss": 2.3620073318481447, "optimizer_updates": 15000, "effective_batch": 512, "lr": 0.00014706360345038147, "gradient_norm": 0.26986488699913025, "tokens_per_second": 1079249.5735809708, "synthetic": false, "world_size": 8} {"step": 28020, "tokens": 7345274880, "loss": 2.3772327423095705, "optimizer_updates": 15010, "effective_batch": 512, "lr": 0.00014699582623650055, "gradient_norm": 0.29835039377212524, "tokens_per_second": 838110.1587697008, "synthetic": false, "world_size": 8} {"step": 28040, "tokens": 7350517760, "loss": 2.3807668685913086, "optimizer_updates": 15020, "effective_batch": 512, "lr": 0.0001469280237655747, "gradient_norm": 0.30259791016578674, "tokens_per_second": 754522.2486284951, "synthetic": false, "world_size": 8} {"step": 28060, "tokens": 7355760640, "loss": 2.3895477294921874, "optimizer_updates": 15030, "effective_batch": 512, "lr": 0.00014686019608389268, "gradient_norm": 0.29871219396591187, "tokens_per_second": 1073027.7729603974, "synthetic": false, "world_size": 8} {"step": 28080, "tokens": 7361003520, "loss": 2.3777273178100584, "optimizer_updates": 15040, "effective_batch": 512, "lr": 0.00014679234323776045, "gradient_norm": 0.2952297627925873, "tokens_per_second": 1075277.8671075706, "synthetic": false, "world_size": 8} {"step": 28100, "tokens": 7366246400, "loss": 2.3797065734863283, "optimizer_updates": 15050, "effective_batch": 512, "lr": 0.00014672446527350108, "gradient_norm": 0.27796289324760437, "tokens_per_second": 1042183.7103563991, "synthetic": false, "world_size": 8} {"step": 28120, "tokens": 7371489280, "loss": 2.3676742553710937, "optimizer_updates": 15060, "effective_batch": 512, "lr": 0.0001466565622374549, "gradient_norm": 0.25160345435142517, "tokens_per_second": 1078476.1489916677, "synthetic": false, "world_size": 8} {"step": 28140, "tokens": 7376732160, "loss": 2.3816661834716797, "optimizer_updates": 15070, "effective_batch": 512, "lr": 0.00014658863417597927, "gradient_norm": 0.2784183919429779, "tokens_per_second": 1069695.3478373515, "synthetic": false, "world_size": 8} {"step": 28160, "tokens": 7381975040, "loss": 2.3860446929931642, "optimizer_updates": 15080, "effective_batch": 512, "lr": 0.00014652068113544866, "gradient_norm": 0.30631890892982483, "tokens_per_second": 1083737.1038447074, "synthetic": false, "world_size": 8} {"step": 28180, "tokens": 7387217920, "loss": 2.374037170410156, "optimizer_updates": 15090, "effective_batch": 512, "lr": 0.00014645270316225465, "gradient_norm": 0.24662286043167114, "tokens_per_second": 1062282.822007736, "synthetic": false, "world_size": 8} {"step": 28200, "tokens": 7392460800, "loss": 2.36440372467041, "optimizer_updates": 15100, "effective_batch": 512, "lr": 0.00014638470030280574, "gradient_norm": 0.3281681537628174, "tokens_per_second": 1072624.585378704, "synthetic": false, "world_size": 8} {"step": 28220, "tokens": 7397703680, "loss": 2.3787120819091796, "optimizer_updates": 15110, "effective_batch": 512, "lr": 0.0001463166726035275, "gradient_norm": 0.26505839824676514, "tokens_per_second": 1075489.4334560505, "synthetic": false, "world_size": 8} {"step": 28240, "tokens": 7402946560, "loss": 2.3748615264892576, "optimizer_updates": 15120, "effective_batch": 512, "lr": 0.0001462486201108624, "gradient_norm": 0.31639283895492554, "tokens_per_second": 1072548.0247451, "synthetic": false, "world_size": 8} {"step": 28260, "tokens": 7408189440, "loss": 2.374714469909668, "optimizer_updates": 15130, "effective_batch": 512, "lr": 0.00014618054287126992, "gradient_norm": 0.35037335753440857, "tokens_per_second": 1070639.8052737657, "synthetic": false, "world_size": 8} {"step": 28280, "tokens": 7413432320, "loss": 2.3911094665527344, "optimizer_updates": 15140, "effective_batch": 512, "lr": 0.00014611244093122635, "gradient_norm": 0.24453531205654144, "tokens_per_second": 1074011.9649840423, "synthetic": false, "world_size": 8} {"step": 28300, "tokens": 7418675200, "loss": 2.373008155822754, "optimizer_updates": 15150, "effective_batch": 512, "lr": 0.00014604431433722486, "gradient_norm": 0.2581664025783539, "tokens_per_second": 1071395.5899782402, "synthetic": false, "world_size": 8} {"step": 28320, "tokens": 7423918080, "loss": 2.380125045776367, "optimizer_updates": 15160, "effective_batch": 512, "lr": 0.00014597616313577548, "gradient_norm": 0.27666398882865906, "tokens_per_second": 1075501.7171962229, "synthetic": false, "world_size": 8} {"step": 28340, "tokens": 7429160960, "loss": 2.382958984375, "optimizer_updates": 15170, "effective_batch": 512, "lr": 0.000145907987373405, "gradient_norm": 0.2517957091331482, "tokens_per_second": 1068188.8033359454, "synthetic": false, "world_size": 8} {"step": 28360, "tokens": 7434403840, "loss": 2.3767356872558594, "optimizer_updates": 15180, "effective_batch": 512, "lr": 0.00014583978709665707, "gradient_norm": 0.2885657250881195, "tokens_per_second": 1075828.242644005, "synthetic": false, "world_size": 8} {"step": 28380, "tokens": 7439646720, "loss": 2.388449859619141, "optimizer_updates": 15190, "effective_batch": 512, "lr": 0.00014577156235209192, "gradient_norm": 0.23266001045703888, "tokens_per_second": 775959.8194688937, "synthetic": false, "world_size": 8} {"step": 28400, "tokens": 7444889600, "loss": 2.3799259185791017, "optimizer_updates": 15200, "effective_batch": 512, "lr": 0.00014570331318628665, "gradient_norm": 0.2502347528934479, "tokens_per_second": 1078458.8098375204, "synthetic": false, "world_size": 8} {"step": 28420, "tokens": 7450132480, "loss": 2.3806886672973633, "optimizer_updates": 15210, "effective_batch": 512, "lr": 0.00014563503964583493, "gradient_norm": 0.2627863585948944, "tokens_per_second": 1077644.042143594, "synthetic": false, "world_size": 8} {"step": 28440, "tokens": 7455375360, "loss": 2.371321678161621, "optimizer_updates": 15220, "effective_batch": 512, "lr": 0.0001455667417773471, "gradient_norm": 0.28248265385627747, "tokens_per_second": 1082162.0401635894, "synthetic": false, "world_size": 8} {"step": 28460, "tokens": 7460618240, "loss": 2.3607864379882812, "optimizer_updates": 15230, "effective_batch": 512, "lr": 0.00014549841962745, "gradient_norm": 0.25964677333831787, "tokens_per_second": 1069675.5694724543, "synthetic": false, "world_size": 8} {"step": 28480, "tokens": 7465861120, "loss": 2.3643238067626955, "optimizer_updates": 15240, "effective_batch": 512, "lr": 0.00014543007324278735, "gradient_norm": 0.2939208447933197, "tokens_per_second": 1075744.432521825, "synthetic": false, "world_size": 8} {"step": 28500, "tokens": 7471104000, "loss": 2.3764579772949217, "optimizer_updates": 15250, "effective_batch": 512, "lr": 0.00014536170267001903, "gradient_norm": 0.299029678106308, "tokens_per_second": 1075082.8567467043, "synthetic": false, "world_size": 8} {"step": 28520, "tokens": 7476346880, "loss": 2.3685720443725584, "optimizer_updates": 15260, "effective_batch": 512, "lr": 0.00014529330795582174, "gradient_norm": 0.25725293159484863, "tokens_per_second": 1079840.8102359413, "synthetic": false, "world_size": 8} {"step": 28540, "tokens": 7481589760, "loss": 2.3856584548950197, "optimizer_updates": 15270, "effective_batch": 512, "lr": 0.0001452248891468885, "gradient_norm": 0.25938880443573, "tokens_per_second": 1082104.8316502322, "synthetic": false, "world_size": 8} {"step": 28560, "tokens": 7486832640, "loss": 2.3650928497314454, "optimizer_updates": 15280, "effective_batch": 512, "lr": 0.0001451564462899288, "gradient_norm": 0.29153430461883545, "tokens_per_second": 1074275.737328473, "synthetic": false, "world_size": 8} {"step": 28580, "tokens": 7492075520, "loss": 2.3813861846923827, "optimizer_updates": 15290, "effective_batch": 512, "lr": 0.00014508797943166865, "gradient_norm": 0.2816341817378998, "tokens_per_second": 1074654.9876520599, "synthetic": false, "world_size": 8} {"step": 28600, "tokens": 7497318400, "loss": 2.376017951965332, "optimizer_updates": 15300, "effective_batch": 512, "lr": 0.00014501948861885024, "gradient_norm": 0.2643103301525116, "tokens_per_second": 999928.3887646962, "synthetic": false, "world_size": 8} {"step": 28620, "tokens": 7502561280, "loss": 2.383203125, "optimizer_updates": 15310, "effective_batch": 512, "lr": 0.00014495097389823232, "gradient_norm": 0.36045411229133606, "tokens_per_second": 1068728.1629023966, "synthetic": false, "world_size": 8} {"step": 28640, "tokens": 7507804160, "loss": 2.376011276245117, "optimizer_updates": 15320, "effective_batch": 512, "lr": 0.0001448824353165899, "gradient_norm": 0.24670395255088806, "tokens_per_second": 1078518.2551932957, "synthetic": false, "world_size": 8} {"step": 28660, "tokens": 7513047040, "loss": 2.374651336669922, "optimizer_updates": 15330, "effective_batch": 512, "lr": 0.00014481387292071416, "gradient_norm": 0.2422993928194046, "tokens_per_second": 1072422.5798006346, "synthetic": false, "world_size": 8} {"step": 28680, "tokens": 7518289920, "loss": 2.3798089981079102, "optimizer_updates": 15340, "effective_batch": 512, "lr": 0.0001447452867574127, "gradient_norm": 0.3688446581363678, "tokens_per_second": 1078141.0543993707, "synthetic": false, "world_size": 8} {"step": 28700, "tokens": 7523532800, "loss": 2.3825653076171873, "optimizer_updates": 15350, "effective_batch": 512, "lr": 0.0001446766768735093, "gradient_norm": 0.245265394449234, "tokens_per_second": 1074653.9655775991, "synthetic": false, "world_size": 8} {"step": 28720, "tokens": 7528775680, "loss": 2.3819253921508787, "optimizer_updates": 15360, "effective_batch": 512, "lr": 0.0001446080433158439, "gradient_norm": 0.3033246695995331, "tokens_per_second": 1079847.39154467, "synthetic": false, "world_size": 8} {"step": 28740, "tokens": 7534018560, "loss": 2.3688787460327148, "optimizer_updates": 15370, "effective_batch": 512, "lr": 0.00014453938613127258, "gradient_norm": 0.24540771543979645, "tokens_per_second": 1073984.7975740675, "synthetic": false, "world_size": 8} {"step": 28760, "tokens": 7539261440, "loss": 2.394547462463379, "optimizer_updates": 15380, "effective_batch": 512, "lr": 0.0001444707053666677, "gradient_norm": 0.23780827224254608, "tokens_per_second": 1075137.63348852, "synthetic": false, "world_size": 8} {"step": 28780, "tokens": 7544504320, "loss": 2.372318649291992, "optimizer_updates": 15390, "effective_batch": 512, "lr": 0.00014440200106891746, "gradient_norm": 0.256277859210968, "tokens_per_second": 691117.6717273275, "synthetic": false, "world_size": 8} {"step": 28800, "tokens": 7549747200, "loss": 2.3693065643310547, "optimizer_updates": 15400, "effective_batch": 512, "lr": 0.00014433327328492636, "gradient_norm": 0.23376555740833282, "tokens_per_second": 1077406.946166724, "synthetic": false, "world_size": 8} {"step": 28820, "tokens": 7554990080, "loss": 2.3819265365600586, "optimizer_updates": 15410, "effective_batch": 512, "lr": 0.00014426452206161484, "gradient_norm": 0.24914787709712982, "tokens_per_second": 1068860.8741605785, "synthetic": false, "world_size": 8} {"step": 28840, "tokens": 7560232960, "loss": 2.3781896591186524, "optimizer_updates": 15420, "effective_batch": 512, "lr": 0.00014419574744591935, "gradient_norm": 0.2506735622882843, "tokens_per_second": 1073027.7661598513, "synthetic": false, "world_size": 8} {"step": 28860, "tokens": 7565475840, "loss": 2.380521774291992, "optimizer_updates": 15430, "effective_batch": 512, "lr": 0.0001441269494847923, "gradient_norm": 0.25542151927948, "tokens_per_second": 1072930.4010452349, "synthetic": false, "world_size": 8} {"step": 28880, "tokens": 7570718720, "loss": 2.37481689453125, "optimizer_updates": 15440, "effective_batch": 512, "lr": 0.00014405812822520204, "gradient_norm": 0.23842386901378632, "tokens_per_second": 1069182.4824880615, "synthetic": false, "world_size": 8} {"step": 28900, "tokens": 7575961600, "loss": 2.3985622406005858, "optimizer_updates": 15450, "effective_batch": 512, "lr": 0.00014398928371413286, "gradient_norm": 0.28387558460235596, "tokens_per_second": 1066204.8118329882, "synthetic": false, "world_size": 8} {"step": 28920, "tokens": 7581204480, "loss": 2.3801170349121095, "optimizer_updates": 15460, "effective_batch": 512, "lr": 0.00014392041599858488, "gradient_norm": 0.23875759541988373, "tokens_per_second": 1071537.045166836, "synthetic": false, "world_size": 8} {"step": 28940, "tokens": 7586447360, "loss": 2.370983123779297, "optimizer_updates": 15470, "effective_batch": 512, "lr": 0.00014385152512557406, "gradient_norm": 0.26748228073120117, "tokens_per_second": 1071570.396896701, "synthetic": false, "world_size": 8} {"step": 28960, "tokens": 7591690240, "loss": 2.3823251724243164, "optimizer_updates": 15480, "effective_batch": 512, "lr": 0.00014378261114213225, "gradient_norm": 0.31906992197036743, "tokens_per_second": 1079228.6352376933, "synthetic": false, "world_size": 8} {"step": 28980, "tokens": 7596933120, "loss": 2.3787862777709963, "optimizer_updates": 15490, "effective_batch": 512, "lr": 0.00014371367409530693, "gradient_norm": 0.2562933564186096, "tokens_per_second": 1070435.5958783568, "synthetic": false, "world_size": 8} {"step": 29000, "tokens": 7602176000, "loss": 2.368790054321289, "optimizer_updates": 15500, "effective_batch": 512, "lr": 0.00014364471403216148, "gradient_norm": 0.2484302967786789, "tokens_per_second": 1074604.5570570282, "synthetic": false, "world_size": 8} {"step": 29020, "tokens": 7607418880, "loss": 2.3929792404174806, "optimizer_updates": 15510, "effective_batch": 512, "lr": 0.00014357573099977488, "gradient_norm": 0.28639429807662964, "tokens_per_second": 837891.934561819, "synthetic": false, "world_size": 8} {"step": 29040, "tokens": 7612661760, "loss": 2.375164794921875, "optimizer_updates": 15520, "effective_batch": 512, "lr": 0.00014350672504524187, "gradient_norm": 0.23432666063308716, "tokens_per_second": 1077771.681863384, "synthetic": false, "world_size": 8} {"step": 29060, "tokens": 7617904640, "loss": 2.381761169433594, "optimizer_updates": 15530, "effective_batch": 512, "lr": 0.00014343769621567282, "gradient_norm": 0.3306180536746979, "tokens_per_second": 796693.6887381036, "synthetic": false, "world_size": 8} {"step": 29080, "tokens": 7623147520, "loss": 2.3864131927490235, "optimizer_updates": 15540, "effective_batch": 512, "lr": 0.00014336864455819363, "gradient_norm": 0.26792770624160767, "tokens_per_second": 1079158.5819696402, "synthetic": false, "world_size": 8} {"step": 29100, "tokens": 7628390400, "loss": 2.3806480407714843, "optimizer_updates": 15550, "effective_batch": 512, "lr": 0.00014329957011994593, "gradient_norm": 0.30386456847190857, "tokens_per_second": 963624.2116021147, "synthetic": false, "world_size": 8} {"step": 29120, "tokens": 7633633280, "loss": 2.3810503005981447, "optimizer_updates": 15560, "effective_batch": 512, "lr": 0.00014323047294808678, "gradient_norm": 0.30129122734069824, "tokens_per_second": 1079422.5278150183, "synthetic": false, "world_size": 8} {"step": 29140, "tokens": 7638876160, "loss": 2.385896110534668, "optimizer_updates": 15570, "effective_batch": 512, "lr": 0.0001431613530897888, "gradient_norm": 0.29482102394104004, "tokens_per_second": 1077324.9232159487, "synthetic": false, "world_size": 8} {"step": 29160, "tokens": 7644119040, "loss": 2.3679292678833006, "optimizer_updates": 15580, "effective_batch": 512, "lr": 0.00014309221059224017, "gradient_norm": 0.27362945675849915, "tokens_per_second": 1069460.6015883503, "synthetic": false, "world_size": 8} {"step": 29180, "tokens": 7649361920, "loss": 2.3774662017822266, "optimizer_updates": 15590, "effective_batch": 512, "lr": 0.0001430230455026444, "gradient_norm": 0.293391615152359, "tokens_per_second": 1080253.5700068201, "synthetic": false, "world_size": 8} {"step": 29200, "tokens": 7654604800, "loss": 2.359139633178711, "optimizer_updates": 15600, "effective_batch": 512, "lr": 0.00014295385786822052, "gradient_norm": 0.23413047194480896, "tokens_per_second": 772180.6454360095, "synthetic": false, "world_size": 8} {"step": 29220, "tokens": 7659847680, "loss": 2.3818368911743164, "optimizer_updates": 15610, "effective_batch": 512, "lr": 0.00014288464773620291, "gradient_norm": 0.2903554439544678, "tokens_per_second": 1069813.135723527, "synthetic": false, "world_size": 8} {"step": 29240, "tokens": 7665090560, "loss": 2.3832849502563476, "optimizer_updates": 15620, "effective_batch": 512, "lr": 0.0001428154151538413, "gradient_norm": 0.25366461277008057, "tokens_per_second": 1068021.2627647978, "synthetic": false, "world_size": 8} {"step": 29260, "tokens": 7670333440, "loss": 2.385029602050781, "optimizer_updates": 15630, "effective_batch": 512, "lr": 0.0001427461601684008, "gradient_norm": 0.24361476302146912, "tokens_per_second": 1075222.6335134315, "synthetic": false, "world_size": 8} {"step": 29280, "tokens": 7675576320, "loss": 2.3849227905273436, "optimizer_updates": 15640, "effective_batch": 512, "lr": 0.00014267688282716177, "gradient_norm": 0.30687642097473145, "tokens_per_second": 967793.8685620587, "synthetic": false, "world_size": 8} {"step": 29300, "tokens": 7680819200, "loss": 2.367340850830078, "optimizer_updates": 15650, "effective_batch": 512, "lr": 0.0001426075831774198, "gradient_norm": 0.2677168548107147, "tokens_per_second": 1072575.0903166158, "synthetic": false, "world_size": 8} {"step": 29320, "tokens": 7686062080, "loss": 2.3941137313842775, "optimizer_updates": 15660, "effective_batch": 512, "lr": 0.00014253826126648574, "gradient_norm": 0.2652772068977356, "tokens_per_second": 1076295.5753511682, "synthetic": false, "world_size": 8} {"step": 29340, "tokens": 7691304960, "loss": 2.3752090454101564, "optimizer_updates": 15670, "effective_batch": 512, "lr": 0.00014246891714168574, "gradient_norm": 0.3735366463661194, "tokens_per_second": 1066276.5448613355, "synthetic": false, "world_size": 8} {"step": 29360, "tokens": 7696547840, "loss": 2.371957206726074, "optimizer_updates": 15680, "effective_batch": 512, "lr": 0.00014239955085036096, "gradient_norm": 0.2409086972475052, "tokens_per_second": 1069794.609478487, "synthetic": false, "world_size": 8} {"step": 29380, "tokens": 7701790720, "loss": 2.3727636337280273, "optimizer_updates": 15690, "effective_batch": 512, "lr": 0.00014233016243986776, "gradient_norm": 0.28392645716667175, "tokens_per_second": 1073869.0708219588, "synthetic": false, "world_size": 8} {"step": 29400, "tokens": 7707033600, "loss": 2.3779485702514647, "optimizer_updates": 15700, "effective_batch": 512, "lr": 0.0001422607519575776, "gradient_norm": 0.35926303267478943, "tokens_per_second": 1074496.7654042144, "synthetic": false, "world_size": 8} {"step": 29420, "tokens": 7712276480, "loss": 2.3827703475952147, "optimizer_updates": 15710, "effective_batch": 512, "lr": 0.000142191319450877, "gradient_norm": 0.3231789171695709, "tokens_per_second": 1079538.5673483817, "synthetic": false, "world_size": 8} {"step": 29440, "tokens": 7717519360, "loss": 2.3753843307495117, "optimizer_updates": 15720, "effective_batch": 512, "lr": 0.00014212186496716754, "gradient_norm": 0.25421833992004395, "tokens_per_second": 1070225.324624828, "synthetic": false, "world_size": 8} {"step": 29460, "tokens": 7722762240, "loss": 2.372531700134277, "optimizer_updates": 15730, "effective_batch": 512, "lr": 0.00014205238855386577, "gradient_norm": 0.2649569511413574, "tokens_per_second": 1071817.8195505713, "synthetic": false, "world_size": 8} {"step": 29480, "tokens": 7728005120, "loss": 2.368216133117676, "optimizer_updates": 15740, "effective_batch": 512, "lr": 0.0001419828902584032, "gradient_norm": 0.29206931591033936, "tokens_per_second": 1068361.3995050483, "synthetic": false, "world_size": 8} {"step": 29500, "tokens": 7733248000, "loss": 2.376700019836426, "optimizer_updates": 15750, "effective_batch": 512, "lr": 0.0001419133701282264, "gradient_norm": 0.29530322551727295, "tokens_per_second": 1074225.633065623, "synthetic": false, "world_size": 8} {"step": 29520, "tokens": 7738490880, "loss": 2.389487457275391, "optimizer_updates": 15760, "effective_batch": 512, "lr": 0.00014184382821079666, "gradient_norm": 0.30688562989234924, "tokens_per_second": 1073887.6111131331, "synthetic": false, "world_size": 8} {"step": 29540, "tokens": 7743733760, "loss": 2.391900062561035, "optimizer_updates": 15770, "effective_batch": 512, "lr": 0.00014177426455359027, "gradient_norm": 0.32446062564849854, "tokens_per_second": 1074048.5719847423, "synthetic": false, "world_size": 8} {"step": 29560, "tokens": 7748976640, "loss": 2.3702970504760743, "optimizer_updates": 15780, "effective_batch": 512, "lr": 0.0001417046792040983, "gradient_norm": 0.28080838918685913, "tokens_per_second": 1074645.5938308453, "synthetic": false, "world_size": 8} {"step": 29580, "tokens": 7754219520, "loss": 2.379977798461914, "optimizer_updates": 15790, "effective_batch": 512, "lr": 0.0001416350722098267, "gradient_norm": 0.2513454854488373, "tokens_per_second": 1069718.1818647971, "synthetic": false, "world_size": 8} {"step": 29600, "tokens": 7759462400, "loss": 2.3841789245605467, "optimizer_updates": 15800, "effective_batch": 512, "lr": 0.00014156544361829614, "gradient_norm": 0.2658766806125641, "tokens_per_second": 1076350.585331288, "synthetic": false, "world_size": 8} {"step": 29620, "tokens": 7764705280, "loss": 2.376515197753906, "optimizer_updates": 15810, "effective_batch": 512, "lr": 0.00014149579347704202, "gradient_norm": 0.2506219148635864, "tokens_per_second": 1077737.1561231236, "synthetic": false, "world_size": 8} {"step": 29640, "tokens": 7769948160, "loss": 2.3624170303344725, "optimizer_updates": 15820, "effective_batch": 512, "lr": 0.00014142612183361454, "gradient_norm": 0.2609058618545532, "tokens_per_second": 1082488.269361293, "synthetic": false, "world_size": 8} {"step": 29660, "tokens": 7775191040, "loss": 2.387579154968262, "optimizer_updates": 15830, "effective_batch": 512, "lr": 0.00014135642873557846, "gradient_norm": 0.2706654369831085, "tokens_per_second": 1069811.2740968463, "synthetic": false, "world_size": 8} {"step": 29680, "tokens": 7780433920, "loss": 2.373651885986328, "optimizer_updates": 15840, "effective_batch": 512, "lr": 0.00014128671423051326, "gradient_norm": 0.3487296998500824, "tokens_per_second": 1076083.692189594, "synthetic": false, "world_size": 8} {"step": 29700, "tokens": 7785676800, "loss": 2.3726276397705077, "optimizer_updates": 15850, "effective_batch": 512, "lr": 0.0001412169783660131, "gradient_norm": 0.2428494393825531, "tokens_per_second": 1072854.2369050353, "synthetic": false, "world_size": 8} {"step": 29720, "tokens": 7790919680, "loss": 2.37701530456543, "optimizer_updates": 15860, "effective_batch": 512, "lr": 0.00014114722118968652, "gradient_norm": 0.3124772906303406, "tokens_per_second": 1082291.3952374351, "synthetic": false, "world_size": 8} {"step": 29740, "tokens": 7796162560, "loss": 2.3832065582275392, "optimizer_updates": 15870, "effective_batch": 512, "lr": 0.0001410774427491568, "gradient_norm": 0.27354589104652405, "tokens_per_second": 1077790.0764218946, "synthetic": false, "world_size": 8} {"step": 29760, "tokens": 7801405440, "loss": 2.367147445678711, "optimizer_updates": 15880, "effective_batch": 512, "lr": 0.00014100764309206166, "gradient_norm": 0.2811966836452484, "tokens_per_second": 1071675.7256976012, "synthetic": false, "world_size": 8} {"step": 29780, "tokens": 7806648320, "loss": 2.381454658508301, "optimizer_updates": 15890, "effective_batch": 512, "lr": 0.0001409378222660533, "gradient_norm": 0.29070061445236206, "tokens_per_second": 1080267.1587617947, "synthetic": false, "world_size": 8} {"step": 29800, "tokens": 7811891200, "loss": 2.3858407974243163, "optimizer_updates": 15900, "effective_batch": 512, "lr": 0.00014086798031879845, "gradient_norm": 0.2754094898700714, "tokens_per_second": 1082937.7159704273, "synthetic": false, "world_size": 8} {"step": 29820, "tokens": 7817134080, "loss": 2.3823198318481444, "optimizer_updates": 15910, "effective_batch": 512, "lr": 0.00014079811729797814, "gradient_norm": 0.2557956576347351, "tokens_per_second": 1072894.455770018, "synthetic": false, "world_size": 8} {"step": 29840, "tokens": 7822376960, "loss": 2.376359748840332, "optimizer_updates": 15920, "effective_batch": 512, "lr": 0.00014072823325128784, "gradient_norm": 0.3454165458679199, "tokens_per_second": 1078465.2540407947, "synthetic": false, "world_size": 8} {"step": 29860, "tokens": 7827619840, "loss": 2.3723045349121095, "optimizer_updates": 15930, "effective_batch": 512, "lr": 0.00014065832822643742, "gradient_norm": 0.2635701894760132, "tokens_per_second": 1078057.4709807413, "synthetic": false, "world_size": 8} {"step": 29880, "tokens": 7832862720, "loss": 2.378449249267578, "optimizer_updates": 15940, "effective_batch": 512, "lr": 0.000140588402271151, "gradient_norm": 0.2418481856584549, "tokens_per_second": 1073022.1881049103, "synthetic": false, "world_size": 8} {"step": 29900, "tokens": 7838105600, "loss": 2.380930709838867, "optimizer_updates": 15950, "effective_batch": 512, "lr": 0.000140518455433167, "gradient_norm": 0.2796184718608856, "tokens_per_second": 1081466.515027558, "synthetic": false, "world_size": 8} {"step": 29920, "tokens": 7843348480, "loss": 2.388351821899414, "optimizer_updates": 15960, "effective_batch": 512, "lr": 0.00014044848776023817, "gradient_norm": 0.26859891414642334, "tokens_per_second": 1076863.895365204, "synthetic": false, "world_size": 8} {"step": 29940, "tokens": 7848591360, "loss": 2.364837646484375, "optimizer_updates": 15970, "effective_batch": 512, "lr": 0.00014037849930013135, "gradient_norm": 0.25077953934669495, "tokens_per_second": 1072855.6764440837, "synthetic": false, "world_size": 8} {"step": 29960, "tokens": 7853834240, "loss": 2.3857955932617188, "optimizer_updates": 15980, "effective_batch": 512, "lr": 0.00014030849010062774, "gradient_norm": 0.27629920840263367, "tokens_per_second": 1076699.199184711, "synthetic": false, "world_size": 8} {"step": 29980, "tokens": 7859077120, "loss": 2.3650577545166014, "optimizer_updates": 15990, "effective_batch": 512, "lr": 0.00014023846020952256, "gradient_norm": 0.2607179284095764, "tokens_per_second": 1069230.8249763835, "synthetic": false, "world_size": 8} {"step": 30000, "tokens": 7864320000, "loss": 2.364699363708496, "optimizer_updates": 16000, "effective_batch": 512, "lr": 0.0001401684096746252, "gradient_norm": 0.2330038994550705, "tokens_per_second": 1078015.6640812603, "synthetic": false, "world_size": 8} {"step": 30020, "tokens": 7869562880, "loss": 2.371944808959961, "optimizer_updates": 16010, "effective_batch": 512, "lr": 0.0001400983385437592, "gradient_norm": 0.274183452129364, "tokens_per_second": 842955.6535965597, "synthetic": false, "world_size": 8} {"step": 30040, "tokens": 7874805760, "loss": 2.364120674133301, "optimizer_updates": 16020, "effective_batch": 512, "lr": 0.00014002824686476205, "gradient_norm": 0.3742165267467499, "tokens_per_second": 1069024.8041989738, "synthetic": false, "world_size": 8} {"step": 30060, "tokens": 7880048640, "loss": 2.381740951538086, "optimizer_updates": 16030, "effective_batch": 512, "lr": 0.00013995813468548534, "gradient_norm": 0.24662593007087708, "tokens_per_second": 1082212.2504130239, "synthetic": false, "world_size": 8} {"step": 30080, "tokens": 7885291520, "loss": 2.3685617446899414, "optimizer_updates": 16040, "effective_batch": 512, "lr": 0.00013988800205379467, "gradient_norm": 0.2475585639476776, "tokens_per_second": 1077528.7020772998, "synthetic": false, "world_size": 8} {"step": 30100, "tokens": 7890534400, "loss": 2.3736072540283204, "optimizer_updates": 16050, "effective_batch": 512, "lr": 0.00013981784901756955, "gradient_norm": 0.3031986653804779, "tokens_per_second": 1067828.396697627, "synthetic": false, "world_size": 8} {"step": 30120, "tokens": 7895777280, "loss": 2.3735029220581056, "optimizer_updates": 16060, "effective_batch": 512, "lr": 0.00013974767562470347, "gradient_norm": 0.24151045083999634, "tokens_per_second": 1077728.3401548488, "synthetic": false, "world_size": 8} {"step": 30140, "tokens": 7901020160, "loss": 2.3735233306884767, "optimizer_updates": 16070, "effective_batch": 512, "lr": 0.00013967748192310382, "gradient_norm": 0.294533371925354, "tokens_per_second": 1073756.7601949659, "synthetic": false, "world_size": 8} {"step": 30160, "tokens": 7906263040, "loss": 2.373509407043457, "optimizer_updates": 16080, "effective_batch": 512, "lr": 0.00013960726796069176, "gradient_norm": 0.2386631816625595, "tokens_per_second": 1080629.6380514037, "synthetic": false, "world_size": 8} {"step": 30180, "tokens": 7911505920, "loss": 2.367238235473633, "optimizer_updates": 16090, "effective_batch": 512, "lr": 0.0001395370337854024, "gradient_norm": 0.25457167625427246, "tokens_per_second": 986783.5274847371, "synthetic": false, "world_size": 8} {"step": 30200, "tokens": 7916748800, "loss": 2.3805124282836916, "optimizer_updates": 16100, "effective_batch": 512, "lr": 0.00013946677944518457, "gradient_norm": 0.23219817876815796, "tokens_per_second": 1074743.4465516862, "synthetic": false, "world_size": 8} {"step": 30220, "tokens": 7921991680, "loss": 2.368550491333008, "optimizer_updates": 16110, "effective_batch": 512, "lr": 0.0001393965049880009, "gradient_norm": 0.2887788414955139, "tokens_per_second": 1067540.9025573854, "synthetic": false, "world_size": 8} {"step": 30240, "tokens": 7927234560, "loss": 2.3812625885009764, "optimizer_updates": 16120, "effective_batch": 512, "lr": 0.0001393262104618278, "gradient_norm": 0.25552886724472046, "tokens_per_second": 1067604.590488299, "synthetic": false, "world_size": 8} {"step": 30260, "tokens": 7932477440, "loss": 2.3931676864624025, "optimizer_updates": 16130, "effective_batch": 512, "lr": 0.00013925589591465528, "gradient_norm": 0.25305336713790894, "tokens_per_second": 1080140.9301102587, "synthetic": false, "world_size": 8} {"step": 30280, "tokens": 7937720320, "loss": 2.3782018661499023, "optimizer_updates": 16140, "effective_batch": 512, "lr": 0.0001391855613944871, "gradient_norm": 0.2923227548599243, "tokens_per_second": 195335.8398190254, "synthetic": false, "world_size": 8} {"step": 30300, "tokens": 7942963200, "loss": 2.3681705474853514, "optimizer_updates": 16150, "effective_batch": 512, "lr": 0.0001391152069493406, "gradient_norm": 0.2625177204608917, "tokens_per_second": 163791.59127745236, "synthetic": false, "world_size": 8} {"step": 30320, "tokens": 7948206080, "loss": 2.3804622650146485, "optimizer_updates": 16160, "effective_batch": 512, "lr": 0.0001390448326272468, "gradient_norm": 0.24180153012275696, "tokens_per_second": 676471.9450342994, "synthetic": false, "world_size": 8} {"step": 30340, "tokens": 7953448960, "loss": 2.3812114715576174, "optimizer_updates": 16170, "effective_batch": 512, "lr": 0.00013897443847625017, "gradient_norm": 0.25317832827568054, "tokens_per_second": 1144437.1774836085, "synthetic": false, "world_size": 8} {"step": 30360, "tokens": 7958691840, "loss": 2.372645950317383, "optimizer_updates": 16180, "effective_batch": 512, "lr": 0.00013890402454440882, "gradient_norm": 0.28083521127700806, "tokens_per_second": 1139798.6137603545, "synthetic": false, "world_size": 8} {"step": 30380, "tokens": 7963934720, "loss": 2.3903631210327148, "optimizer_updates": 16190, "effective_batch": 512, "lr": 0.00013883359087979436, "gradient_norm": 0.4050294756889343, "tokens_per_second": 1140924.3627284158, "synthetic": false, "world_size": 8} {"step": 30400, "tokens": 7969177600, "loss": 2.3859052658081055, "optimizer_updates": 16200, "effective_batch": 512, "lr": 0.0001387631375304918, "gradient_norm": 0.275480180978775, "tokens_per_second": 1136244.4819541182, "synthetic": false, "world_size": 8} {"step": 30420, "tokens": 7974420480, "loss": 2.384588050842285, "optimizer_updates": 16210, "effective_batch": 512, "lr": 0.0001386926645445996, "gradient_norm": 0.25837522745132446, "tokens_per_second": 1145861.6990075072, "synthetic": false, "world_size": 8} {"step": 30440, "tokens": 7979663360, "loss": 2.3849294662475584, "optimizer_updates": 16220, "effective_batch": 512, "lr": 0.00013862217197022973, "gradient_norm": 0.2913464605808258, "tokens_per_second": 1140008.6485475076, "synthetic": false, "world_size": 8} {"step": 30460, "tokens": 7984906240, "loss": 2.375989532470703, "optimizer_updates": 16230, "effective_batch": 512, "lr": 0.00013855165985550744, "gradient_norm": 0.25326254963874817, "tokens_per_second": 1137673.3263740349, "synthetic": false, "world_size": 8} {"step": 30480, "tokens": 7990149120, "loss": 2.3815608978271485, "optimizer_updates": 16240, "effective_batch": 512, "lr": 0.0001384811282485713, "gradient_norm": 0.2522198557853699, "tokens_per_second": 1137264.200302885, "synthetic": false, "world_size": 8} {"step": 30500, "tokens": 7995392000, "loss": 2.3718494415283202, "optimizer_updates": 16250, "effective_batch": 512, "lr": 0.0001384105771975733, "gradient_norm": 0.2693573236465454, "tokens_per_second": 1137435.4057819427, "synthetic": false, "world_size": 8} {"step": 30520, "tokens": 8000634880, "loss": 2.374729347229004, "optimizer_updates": 16260, "effective_batch": 512, "lr": 0.00013834000675067856, "gradient_norm": 0.26392656564712524, "tokens_per_second": 1134287.7822872335, "synthetic": false, "world_size": 8} {"step": 30540, "tokens": 8005877760, "loss": 2.373422622680664, "optimizer_updates": 16270, "effective_batch": 512, "lr": 0.00013826941695606554, "gradient_norm": 0.3381890654563904, "tokens_per_second": 1149136.7093529813, "synthetic": false, "world_size": 8} {"step": 30560, "tokens": 8011120640, "loss": 2.37969856262207, "optimizer_updates": 16280, "effective_batch": 512, "lr": 0.0001381988078619259, "gradient_norm": 0.3612661361694336, "tokens_per_second": 1139303.6829404298, "synthetic": false, "world_size": 8} {"step": 30580, "tokens": 8016363520, "loss": 2.3853586196899412, "optimizer_updates": 16290, "effective_batch": 512, "lr": 0.00013812817951646441, "gradient_norm": 0.25210919976234436, "tokens_per_second": 1135799.169774095, "synthetic": false, "world_size": 8} {"step": 30600, "tokens": 8021606400, "loss": 2.369931221008301, "optimizer_updates": 16300, "effective_batch": 512, "lr": 0.0001380575319678991, "gradient_norm": 0.3081798553466797, "tokens_per_second": 1132847.57156069, "synthetic": false, "world_size": 8} {"step": 30620, "tokens": 8026849280, "loss": 2.3604623794555666, "optimizer_updates": 16310, "effective_batch": 512, "lr": 0.00013798686526446095, "gradient_norm": 0.3241172432899475, "tokens_per_second": 1126161.244665682, "synthetic": false, "world_size": 8} {"step": 30640, "tokens": 8032092160, "loss": 2.3802846908569335, "optimizer_updates": 16320, "effective_batch": 512, "lr": 0.0001379161794543942, "gradient_norm": 0.32174718379974365, "tokens_per_second": 1130491.0502848323, "synthetic": false, "world_size": 8} {"step": 30660, "tokens": 8037335040, "loss": 2.3751199722290037, "optimizer_updates": 16330, "effective_batch": 512, "lr": 0.000137845474585956, "gradient_norm": 0.2344965934753418, "tokens_per_second": 1133702.429501999, "synthetic": false, "world_size": 8} {"step": 30680, "tokens": 8042577920, "loss": 2.3755008697509767, "optimizer_updates": 16340, "effective_batch": 512, "lr": 0.00013777475070741652, "gradient_norm": 0.29063162207603455, "tokens_per_second": 1124426.338451873, "synthetic": false, "world_size": 8} {"step": 30700, "tokens": 8047820800, "loss": 2.3735103607177734, "optimizer_updates": 16350, "effective_batch": 512, "lr": 0.00013770400786705902, "gradient_norm": 0.2660069465637207, "tokens_per_second": 1142014.139705892, "synthetic": false, "world_size": 8} {"step": 30720, "tokens": 8053063680, "loss": 2.3833303451538086, "optimizer_updates": 16360, "effective_batch": 512, "lr": 0.00013763324611317955, "gradient_norm": 0.2584936022758484, "tokens_per_second": 1133865.6116799978, "synthetic": false, "world_size": 8} {"step": 30740, "tokens": 8058306560, "loss": 2.377463531494141, "optimizer_updates": 16370, "effective_batch": 512, "lr": 0.0001375624654940872, "gradient_norm": 0.25450992584228516, "tokens_per_second": 1139014.9116005348, "synthetic": false, "world_size": 8} {"step": 30760, "tokens": 8063549440, "loss": 2.3638357162475585, "optimizer_updates": 16380, "effective_batch": 512, "lr": 0.00013749166605810386, "gradient_norm": 0.2583954930305481, "tokens_per_second": 1134248.8725596243, "synthetic": false, "world_size": 8} {"step": 30780, "tokens": 8068792320, "loss": 2.3753822326660154, "optimizer_updates": 16390, "effective_batch": 512, "lr": 0.0001374208478535643, "gradient_norm": 0.27321112155914307, "tokens_per_second": 1126446.2506496224, "synthetic": false, "world_size": 8} {"step": 30800, "tokens": 8074035200, "loss": 2.384075164794922, "optimizer_updates": 16400, "effective_batch": 512, "lr": 0.0001373500109288161, "gradient_norm": 0.27873852849006653, "tokens_per_second": 1126481.7686677282, "synthetic": false, "world_size": 8} {"step": 30820, "tokens": 8079278080, "loss": 2.377226638793945, "optimizer_updates": 16410, "effective_batch": 512, "lr": 0.00013727915533221963, "gradient_norm": 0.2678193747997284, "tokens_per_second": 1126459.0069445071, "synthetic": false, "world_size": 8} {"step": 30840, "tokens": 8084520960, "loss": 2.3773530960083007, "optimizer_updates": 16420, "effective_batch": 512, "lr": 0.00013720828111214796, "gradient_norm": 0.24186018109321594, "tokens_per_second": 1126361.6289438263, "synthetic": false, "world_size": 8} {"step": 30860, "tokens": 8089763840, "loss": 2.374608612060547, "optimizer_updates": 16430, "effective_batch": 512, "lr": 0.00013713738831698695, "gradient_norm": 0.31608572602272034, "tokens_per_second": 1141875.60756669, "synthetic": false, "world_size": 8} {"step": 30880, "tokens": 8095006720, "loss": 2.369350051879883, "optimizer_updates": 16440, "effective_batch": 512, "lr": 0.00013706647699513507, "gradient_norm": 0.25010445713996887, "tokens_per_second": 1138009.2354583892, "synthetic": false, "world_size": 8} {"step": 30900, "tokens": 8100249600, "loss": 2.374636650085449, "optimizer_updates": 16450, "effective_batch": 512, "lr": 0.0001369955471950035, "gradient_norm": 0.2668735682964325, "tokens_per_second": 1129390.4789849177, "synthetic": false, "world_size": 8} {"step": 30920, "tokens": 8105492480, "loss": 2.378800392150879, "optimizer_updates": 16460, "effective_batch": 512, "lr": 0.00013692459896501595, "gradient_norm": 0.23543581366539001, "tokens_per_second": 1124341.27323669, "synthetic": false, "world_size": 8} {"step": 30940, "tokens": 8110735360, "loss": 2.3718624114990234, "optimizer_updates": 16470, "effective_batch": 512, "lr": 0.00013685363235360883, "gradient_norm": 0.3153543770313263, "tokens_per_second": 1118242.8817609863, "synthetic": false, "world_size": 8} {"step": 30960, "tokens": 8115978240, "loss": 2.3778736114501955, "optimizer_updates": 16480, "effective_batch": 512, "lr": 0.000136782647409231, "gradient_norm": 0.2677372395992279, "tokens_per_second": 1128599.253321157, "synthetic": false, "world_size": 8} {"step": 30980, "tokens": 8121221120, "loss": 2.3768840789794923, "optimizer_updates": 16490, "effective_batch": 512, "lr": 0.0001367116441803439, "gradient_norm": 0.2546823024749756, "tokens_per_second": 1122235.8761173896, "synthetic": false, "world_size": 8} {"step": 31000, "tokens": 8126464000, "loss": 2.3760324478149415, "optimizer_updates": 16500, "effective_batch": 512, "lr": 0.00013664062271542135, "gradient_norm": 0.23459534347057343, "tokens_per_second": 1118449.2630987922, "synthetic": false, "world_size": 8} {"step": 31020, "tokens": 8131706880, "loss": 2.3715959548950196, "optimizer_updates": 16510, "effective_batch": 512, "lr": 0.00013656958306294977, "gradient_norm": 0.2665960490703583, "tokens_per_second": 835783.7414014312, "synthetic": false, "world_size": 8} {"step": 31040, "tokens": 8136949760, "loss": 2.3705907821655274, "optimizer_updates": 16520, "effective_batch": 512, "lr": 0.00013649852527142787, "gradient_norm": 0.30858486890792847, "tokens_per_second": 1129105.8240926831, "synthetic": false, "world_size": 8} {"step": 31060, "tokens": 8142192640, "loss": 2.391610527038574, "optimizer_updates": 16530, "effective_batch": 512, "lr": 0.0001364274493893668, "gradient_norm": 0.24987806379795074, "tokens_per_second": 1023149.8496103899, "synthetic": false, "world_size": 8} {"step": 31080, "tokens": 8147435520, "loss": 2.381041717529297, "optimizer_updates": 16540, "effective_batch": 512, "lr": 0.00013635635546529012, "gradient_norm": 0.2578899562358856, "tokens_per_second": 974469.3076599097, "synthetic": false, "world_size": 8} {"step": 31100, "tokens": 8152678400, "loss": 2.377119445800781, "optimizer_updates": 16550, "effective_batch": 512, "lr": 0.00013628524354773356, "gradient_norm": 0.27606895565986633, "tokens_per_second": 1124776.7281410196, "synthetic": false, "world_size": 8} {"step": 31120, "tokens": 8157921280, "loss": 2.374174118041992, "optimizer_updates": 16560, "effective_batch": 512, "lr": 0.00013621411368524528, "gradient_norm": 0.3106916546821594, "tokens_per_second": 1127805.7334495895, "synthetic": false, "world_size": 8} {"step": 31140, "tokens": 8163164160, "loss": 2.3647098541259766, "optimizer_updates": 16570, "effective_batch": 512, "lr": 0.00013614296592638557, "gradient_norm": 0.30980801582336426, "tokens_per_second": 1116352.4439240915, "synthetic": false, "world_size": 8} {"step": 31160, "tokens": 8168407040, "loss": 2.3646625518798827, "optimizer_updates": 16580, "effective_batch": 512, "lr": 0.00013607180031972703, "gradient_norm": 0.30391445755958557, "tokens_per_second": 1120921.7009662616, "synthetic": false, "world_size": 8} {"step": 31180, "tokens": 8173649920, "loss": 2.3843704223632813, "optimizer_updates": 16590, "effective_batch": 512, "lr": 0.00013600061691385436, "gradient_norm": 0.24839894473552704, "tokens_per_second": 1129798.7812864846, "synthetic": false, "world_size": 8} {"step": 31200, "tokens": 8178892800, "loss": 2.3832172393798827, "optimizer_updates": 16600, "effective_batch": 512, "lr": 0.0001359294157573645, "gradient_norm": 0.2748558223247528, "tokens_per_second": 1125482.5924442082, "synthetic": false, "world_size": 8} {"step": 31220, "tokens": 8184135680, "loss": 2.3764076232910156, "optimizer_updates": 16610, "effective_batch": 512, "lr": 0.00013585819689886647, "gradient_norm": 0.2872788906097412, "tokens_per_second": 1125985.6303243325, "synthetic": false, "world_size": 8} {"step": 31240, "tokens": 8189378560, "loss": 2.3801368713378905, "optimizer_updates": 16620, "effective_batch": 512, "lr": 0.00013578696038698138, "gradient_norm": 0.32436519861221313, "tokens_per_second": 1123593.8795338783, "synthetic": false, "world_size": 8} {"step": 31260, "tokens": 8194621440, "loss": 2.3900615692138674, "optimizer_updates": 16630, "effective_batch": 512, "lr": 0.00013571570627034238, "gradient_norm": 0.23856818675994873, "tokens_per_second": 1127989.9339833285, "synthetic": false, "world_size": 8} {"step": 31280, "tokens": 8199864320, "loss": 2.38002986907959, "optimizer_updates": 16640, "effective_batch": 512, "lr": 0.00013564443459759465, "gradient_norm": 0.31917840242385864, "tokens_per_second": 1022114.2883610044, "synthetic": false, "world_size": 8} {"step": 31300, "tokens": 8205107200, "loss": 2.3759937286376953, "optimizer_updates": 16650, "effective_batch": 512, "lr": 0.00013557314541739533, "gradient_norm": 0.2511475384235382, "tokens_per_second": 1124922.4424118693, "synthetic": false, "world_size": 8} {"step": 31320, "tokens": 8210350080, "loss": 2.370849609375, "optimizer_updates": 16660, "effective_batch": 512, "lr": 0.0001355018387784135, "gradient_norm": 0.2354373335838318, "tokens_per_second": 1132371.0069960016, "synthetic": false, "world_size": 8} {"step": 31340, "tokens": 8215592960, "loss": 2.3811981201171877, "optimizer_updates": 16670, "effective_batch": 512, "lr": 0.00013543051472933025, "gradient_norm": 0.2895144522190094, "tokens_per_second": 1122950.5577183317, "synthetic": false, "world_size": 8} {"step": 31360, "tokens": 8220835840, "loss": 2.3807662963867187, "optimizer_updates": 16680, "effective_batch": 512, "lr": 0.0001353591733188385, "gradient_norm": 0.26796263456344604, "tokens_per_second": 1119783.06439071, "synthetic": false, "world_size": 8} {"step": 31380, "tokens": 8226078720, "loss": 2.3654151916503907, "optimizer_updates": 16690, "effective_batch": 512, "lr": 0.000135287814595643, "gradient_norm": 0.2747383713722229, "tokens_per_second": 1124407.373330217, "synthetic": false, "world_size": 8} {"step": 31400, "tokens": 8231321600, "loss": 2.3708993911743166, "optimizer_updates": 16700, "effective_batch": 512, "lr": 0.0001352164386084603, "gradient_norm": 0.3738430440425873, "tokens_per_second": 1125207.2795099928, "synthetic": false, "world_size": 8} {"step": 31420, "tokens": 8236564480, "loss": 2.3720001220703124, "optimizer_updates": 16710, "effective_batch": 512, "lr": 0.00013514504540601885, "gradient_norm": 0.24933728575706482, "tokens_per_second": 1128004.8101794166, "synthetic": false, "world_size": 8} {"step": 31440, "tokens": 8241807360, "loss": 2.3710941314697265, "optimizer_updates": 16720, "effective_batch": 512, "lr": 0.00013507363503705876, "gradient_norm": 0.24579370021820068, "tokens_per_second": 1126358.9613362653, "synthetic": false, "world_size": 8} {"step": 31460, "tokens": 8247050240, "loss": 2.382391357421875, "optimizer_updates": 16730, "effective_batch": 512, "lr": 0.00013500220755033183, "gradient_norm": 0.26447048783302307, "tokens_per_second": 1130677.6345698445, "synthetic": false, "world_size": 8} {"step": 31480, "tokens": 8252293120, "loss": 2.371080207824707, "optimizer_updates": 16740, "effective_batch": 512, "lr": 0.00013493076299460162, "gradient_norm": 0.2929672598838806, "tokens_per_second": 1127036.319681847, "synthetic": false, "world_size": 8} {"step": 31500, "tokens": 8257536000, "loss": 2.3910825729370115, "optimizer_updates": 16750, "effective_batch": 512, "lr": 0.00013485930141864333, "gradient_norm": 0.2399936467409134, "tokens_per_second": 1133313.7055065962, "synthetic": false, "world_size": 8} {"step": 31520, "tokens": 8262778880, "loss": 2.3774463653564455, "optimizer_updates": 16760, "effective_batch": 512, "lr": 0.00013478782287124376, "gradient_norm": 0.2976531684398651, "tokens_per_second": 1126434.4021911717, "synthetic": false, "world_size": 8} {"step": 31540, "tokens": 8268021760, "loss": 2.3674510955810546, "optimizer_updates": 16770, "effective_batch": 512, "lr": 0.00013471632740120129, "gradient_norm": 0.2773440182209015, "tokens_per_second": 1137366.1901886426, "synthetic": false, "world_size": 8} {"step": 31560, "tokens": 8273264640, "loss": 2.375560760498047, "optimizer_updates": 16780, "effective_batch": 512, "lr": 0.0001346448150573259, "gradient_norm": 0.3054230809211731, "tokens_per_second": 1129109.9124086034, "synthetic": false, "world_size": 8} {"step": 31580, "tokens": 8278507520, "loss": 2.378832244873047, "optimizer_updates": 16790, "effective_batch": 512, "lr": 0.00013457328588843903, "gradient_norm": 0.28254684805870056, "tokens_per_second": 1137352.2197405961, "synthetic": false, "world_size": 8} {"step": 31600, "tokens": 8283750400, "loss": 2.3775056838989257, "optimizer_updates": 16800, "effective_batch": 512, "lr": 0.00013450173994337367, "gradient_norm": 0.24896477162837982, "tokens_per_second": 1130161.376962541, "synthetic": false, "world_size": 8} {"step": 31620, "tokens": 8288993280, "loss": 2.37825870513916, "optimizer_updates": 16810, "effective_batch": 512, "lr": 0.00013443017727097416, "gradient_norm": 0.24760916829109192, "tokens_per_second": 1130019.559088654, "synthetic": false, "world_size": 8} {"step": 31640, "tokens": 8294236160, "loss": 2.3790754318237304, "optimizer_updates": 16820, "effective_batch": 512, "lr": 0.00013435859792009636, "gradient_norm": 0.28653717041015625, "tokens_per_second": 1130509.7407114669, "synthetic": false, "world_size": 8} {"step": 31660, "tokens": 8299479040, "loss": 2.374314308166504, "optimizer_updates": 16830, "effective_batch": 512, "lr": 0.00013428700193960746, "gradient_norm": 0.2403525859117508, "tokens_per_second": 1127256.7815187809, "synthetic": false, "world_size": 8} {"step": 31680, "tokens": 8304721920, "loss": 2.3700761795043945, "optimizer_updates": 16840, "effective_batch": 512, "lr": 0.00013421538937838606, "gradient_norm": 0.2441941797733307, "tokens_per_second": 1121945.3605900411, "synthetic": false, "world_size": 8} {"step": 31700, "tokens": 8309964800, "loss": 2.3750436782836912, "optimizer_updates": 16850, "effective_batch": 512, "lr": 0.00013414376028532206, "gradient_norm": 0.26518934965133667, "tokens_per_second": 1118953.4354671456, "synthetic": false, "world_size": 8} {"step": 31720, "tokens": 8315207680, "loss": 2.381695365905762, "optimizer_updates": 16860, "effective_batch": 512, "lr": 0.0001340721147093166, "gradient_norm": 0.33545270562171936, "tokens_per_second": 1124174.0304942394, "synthetic": false, "world_size": 8} {"step": 31740, "tokens": 8320450560, "loss": 2.3836271286010744, "optimizer_updates": 16870, "effective_batch": 512, "lr": 0.00013400045269928206, "gradient_norm": 0.24081139266490936, "tokens_per_second": 1117833.7227694392, "synthetic": false, "world_size": 8} {"step": 31760, "tokens": 8325693440, "loss": 2.380121421813965, "optimizer_updates": 16880, "effective_batch": 512, "lr": 0.0001339287743041422, "gradient_norm": 0.284149706363678, "tokens_per_second": 1126099.0195046864, "synthetic": false, "world_size": 8} {"step": 31780, "tokens": 8330936320, "loss": 2.3809368133544924, "optimizer_updates": 16890, "effective_batch": 512, "lr": 0.00013385707957283172, "gradient_norm": 0.26855137944221497, "tokens_per_second": 1128901.3725484337, "synthetic": false, "world_size": 8} {"step": 31800, "tokens": 8336179200, "loss": 2.379059982299805, "optimizer_updates": 16900, "effective_batch": 512, "lr": 0.00013378536855429668, "gradient_norm": 0.34278109669685364, "tokens_per_second": 1136588.4487179562, "synthetic": false, "world_size": 8} {"step": 31820, "tokens": 8341422080, "loss": 2.3696266174316407, "optimizer_updates": 16910, "effective_batch": 512, "lr": 0.00013371364129749415, "gradient_norm": 0.2659999430179596, "tokens_per_second": 772002.6112034473, "synthetic": false, "world_size": 8} {"step": 31840, "tokens": 8346664960, "loss": 2.3715192794799806, "optimizer_updates": 16920, "effective_batch": 512, "lr": 0.00013364189785139232, "gradient_norm": 0.27292871475219727, "tokens_per_second": 1122342.1487299225, "synthetic": false, "world_size": 8} {"step": 31860, "tokens": 8351907840, "loss": 2.3843421936035156, "optimizer_updates": 16930, "effective_batch": 512, "lr": 0.00013357013826497047, "gradient_norm": 0.30627456307411194, "tokens_per_second": 1123271.5145141927, "synthetic": false, "world_size": 8} {"step": 31880, "tokens": 8357150720, "loss": 2.379502296447754, "optimizer_updates": 16940, "effective_batch": 512, "lr": 0.0001334983625872188, "gradient_norm": 0.2523215115070343, "tokens_per_second": 1118859.4765098994, "synthetic": false, "world_size": 8} {"step": 31900, "tokens": 8362393600, "loss": 2.372562789916992, "optimizer_updates": 16950, "effective_batch": 512, "lr": 0.0001334265708671386, "gradient_norm": 0.26046261191368103, "tokens_per_second": 1113544.906321066, "synthetic": false, "world_size": 8} {"step": 31920, "tokens": 8367636480, "loss": 2.371775436401367, "optimizer_updates": 16960, "effective_batch": 512, "lr": 0.00013335476315374205, "gradient_norm": 0.26927924156188965, "tokens_per_second": 1119394.5738492457, "synthetic": false, "world_size": 8} {"step": 31940, "tokens": 8372879360, "loss": 2.377518653869629, "optimizer_updates": 16970, "effective_batch": 512, "lr": 0.00013328293949605225, "gradient_norm": 0.3732645809650421, "tokens_per_second": 1113260.7836653285, "synthetic": false, "world_size": 8} {"step": 31960, "tokens": 8378122240, "loss": 2.3735193252563476, "optimizer_updates": 16980, "effective_batch": 512, "lr": 0.00013321109994310321, "gradient_norm": 0.2960633635520935, "tokens_per_second": 1115239.0703614727, "synthetic": false, "world_size": 8} {"step": 31980, "tokens": 8383365120, "loss": 2.386347007751465, "optimizer_updates": 16990, "effective_batch": 512, "lr": 0.0001331392445439398, "gradient_norm": 0.2657430171966553, "tokens_per_second": 1118335.504612959, "synthetic": false, "world_size": 8} {"step": 32000, "tokens": 8388608000, "loss": 2.3908803939819334, "optimizer_updates": 17000, "effective_batch": 512, "lr": 0.00013306737334761766, "gradient_norm": 0.24602754414081573, "tokens_per_second": 1116645.5305779653, "synthetic": false, "world_size": 8} {"step": 32020, "tokens": 8393850880, "loss": 2.3755573272705077, "optimizer_updates": 17010, "effective_batch": 512, "lr": 0.00013299548640320326, "gradient_norm": 0.24747203290462494, "tokens_per_second": 826822.2595669206, "synthetic": false, "world_size": 8} {"step": 32040, "tokens": 8399093760, "loss": 2.3645130157470704, "optimizer_updates": 17020, "effective_batch": 512, "lr": 0.00013292358375977382, "gradient_norm": 0.3176897168159485, "tokens_per_second": 1119244.2783222226, "synthetic": false, "world_size": 8} {"step": 32060, "tokens": 8404336640, "loss": 2.3776758193969725, "optimizer_updates": 17030, "effective_batch": 512, "lr": 0.00013285166546641726, "gradient_norm": 0.2401863932609558, "tokens_per_second": 1120959.1986058264, "synthetic": false, "world_size": 8} {"step": 32080, "tokens": 8409579520, "loss": 2.3567987442016602, "optimizer_updates": 17040, "effective_batch": 512, "lr": 0.00013277973157223215, "gradient_norm": 0.26752904057502747, "tokens_per_second": 1122576.2429918165, "synthetic": false, "world_size": 8} {"step": 32100, "tokens": 8414822400, "loss": 2.384122848510742, "optimizer_updates": 17050, "effective_batch": 512, "lr": 0.0001327077821263278, "gradient_norm": 0.25903695821762085, "tokens_per_second": 1133367.3507992972, "synthetic": false, "world_size": 8} {"step": 32120, "tokens": 8420065280, "loss": 2.38212890625, "optimizer_updates": 17060, "effective_batch": 512, "lr": 0.00013263581717782406, "gradient_norm": 0.24695178866386414, "tokens_per_second": 854933.2490713848, "synthetic": false, "world_size": 8} {"step": 32140, "tokens": 8425308160, "loss": 2.373722457885742, "optimizer_updates": 17070, "effective_batch": 512, "lr": 0.00013256383677585137, "gradient_norm": 0.2680824398994446, "tokens_per_second": 1135361.1318044825, "synthetic": false, "world_size": 8} {"step": 32160, "tokens": 8430551040, "loss": 2.3759391784667967, "optimizer_updates": 17080, "effective_batch": 512, "lr": 0.00013249184096955077, "gradient_norm": 0.2354927361011505, "tokens_per_second": 1016935.1222885816, "synthetic": false, "world_size": 8} {"step": 32180, "tokens": 8435793920, "loss": 2.3819114685058596, "optimizer_updates": 17090, "effective_batch": 512, "lr": 0.00013241982980807378, "gradient_norm": 0.26321014761924744, "tokens_per_second": 1138793.5465373378, "synthetic": false, "world_size": 8} {"step": 32200, "tokens": 8441036800, "loss": 2.3629478454589843, "optimizer_updates": 17100, "effective_batch": 512, "lr": 0.0001323478033405824, "gradient_norm": 0.2671872079372406, "tokens_per_second": 1127925.1263534036, "synthetic": false, "world_size": 8} {"step": 32220, "tokens": 8446279680, "loss": 2.373116302490234, "optimizer_updates": 17110, "effective_batch": 512, "lr": 0.00013227576161624907, "gradient_norm": 0.4118867516517639, "tokens_per_second": 1127672.6871875874, "synthetic": false, "world_size": 8} {"step": 32240, "tokens": 8451522560, "loss": 2.3775583267211915, "optimizer_updates": 17120, "effective_batch": 512, "lr": 0.00013220370468425676, "gradient_norm": 0.41770660877227783, "tokens_per_second": 1127344.8713235427, "synthetic": false, "world_size": 8} {"step": 32260, "tokens": 8456765440, "loss": 2.379953956604004, "optimizer_updates": 17130, "effective_batch": 512, "lr": 0.0001321316325937986, "gradient_norm": 0.25394129753112793, "tokens_per_second": 1138297.8311702777, "synthetic": false, "world_size": 8} {"step": 32280, "tokens": 8462008320, "loss": 2.375600242614746, "optimizer_updates": 17140, "effective_batch": 512, "lr": 0.00013205954539407825, "gradient_norm": 0.25703927874565125, "tokens_per_second": 1128394.2973905972, "synthetic": false, "world_size": 8} {"step": 32300, "tokens": 8467251200, "loss": 2.3814413070678713, "optimizer_updates": 17150, "effective_batch": 512, "lr": 0.00013198744313430962, "gradient_norm": 0.2865300178527832, "tokens_per_second": 1130648.4553022464, "synthetic": false, "world_size": 8} {"step": 32320, "tokens": 8472494080, "loss": 2.377651405334473, "optimizer_updates": 17160, "effective_batch": 512, "lr": 0.00013191532586371695, "gradient_norm": 0.2682807743549347, "tokens_per_second": 1135651.7384118047, "synthetic": false, "world_size": 8} {"step": 32340, "tokens": 8477736960, "loss": 2.3697765350341795, "optimizer_updates": 17170, "effective_batch": 512, "lr": 0.00013184319363153464, "gradient_norm": 0.24291586875915527, "tokens_per_second": 1122490.3519397748, "synthetic": false, "world_size": 8} {"step": 32360, "tokens": 8482979840, "loss": 2.374390411376953, "optimizer_updates": 17180, "effective_batch": 512, "lr": 0.0001317710464870074, "gradient_norm": 0.23484130203723907, "tokens_per_second": 1129599.8448268434, "synthetic": false, "world_size": 8} {"step": 32380, "tokens": 8488222720, "loss": 2.3600318908691404, "optimizer_updates": 17190, "effective_batch": 512, "lr": 0.00013169888447939, "gradient_norm": 0.2810969352722168, "tokens_per_second": 1133088.0157515022, "synthetic": false, "world_size": 8} {"step": 32400, "tokens": 8493465600, "loss": 2.3667205810546874, "optimizer_updates": 17200, "effective_batch": 512, "lr": 0.00013162670765794754, "gradient_norm": 0.2922378182411194, "tokens_per_second": 1127014.2271704494, "synthetic": false, "world_size": 8} {"step": 32420, "tokens": 8498708480, "loss": 2.3832542419433596, "optimizer_updates": 17210, "effective_batch": 512, "lr": 0.00013155451607195503, "gradient_norm": 0.24628548324108124, "tokens_per_second": 1136642.7777916975, "synthetic": false, "world_size": 8} {"step": 32440, "tokens": 8503951360, "loss": 2.3714262008666993, "optimizer_updates": 17220, "effective_batch": 512, "lr": 0.0001314823097706977, "gradient_norm": 0.3375786244869232, "tokens_per_second": 1129835.3106693635, "synthetic": false, "world_size": 8} {"step": 32460, "tokens": 8509194240, "loss": 2.376801300048828, "optimizer_updates": 17230, "effective_batch": 512, "lr": 0.00013141008880347078, "gradient_norm": 0.2751549780368805, "tokens_per_second": 780630.2298249846, "synthetic": false, "world_size": 8} {"step": 32480, "tokens": 8514437120, "loss": 2.3792585372924804, "optimizer_updates": 17240, "effective_batch": 512, "lr": 0.0001313378532195795, "gradient_norm": 0.29308629035949707, "tokens_per_second": 1141498.2771277446, "synthetic": false, "world_size": 8} {"step": 32500, "tokens": 8519680000, "loss": 2.3747573852539063, "optimizer_updates": 17250, "effective_batch": 512, "lr": 0.0001312656030683391, "gradient_norm": 0.2588198781013489, "tokens_per_second": 1135819.696605312, "synthetic": false, "world_size": 8} {"step": 32520, "tokens": 8524922880, "loss": 2.3784934997558596, "optimizer_updates": 17260, "effective_batch": 512, "lr": 0.0001311933383990747, "gradient_norm": 0.239423930644989, "tokens_per_second": 1127258.9940887564, "synthetic": false, "world_size": 8} {"step": 32540, "tokens": 8530165760, "loss": 2.3631057739257812, "optimizer_updates": 17270, "effective_batch": 512, "lr": 0.00013112105926112145, "gradient_norm": 0.29633963108062744, "tokens_per_second": 1132050.2814000444, "synthetic": false, "world_size": 8} {"step": 32560, "tokens": 8535408640, "loss": 2.376649856567383, "optimizer_updates": 17280, "effective_batch": 512, "lr": 0.00013104876570382425, "gradient_norm": 0.24375830590724945, "tokens_per_second": 1139734.9205548814, "synthetic": false, "world_size": 8} {"step": 32580, "tokens": 8540651520, "loss": 2.3765033721923827, "optimizer_updates": 17290, "effective_batch": 512, "lr": 0.0001309764577765379, "gradient_norm": 0.2776404321193695, "tokens_per_second": 1134277.2801638069, "synthetic": false, "world_size": 8} {"step": 32600, "tokens": 8545894400, "loss": 2.3766136169433594, "optimizer_updates": 17300, "effective_batch": 512, "lr": 0.00013090413552862708, "gradient_norm": 0.3295792043209076, "tokens_per_second": 1132346.9183605753, "synthetic": false, "world_size": 8} {"step": 32620, "tokens": 8551137280, "loss": 2.3747041702270506, "optimizer_updates": 17310, "effective_batch": 512, "lr": 0.0001308317990094661, "gradient_norm": 0.2641009986400604, "tokens_per_second": 1135080.698186067, "synthetic": false, "world_size": 8} {"step": 32640, "tokens": 8556380160, "loss": 2.3729885101318358, "optimizer_updates": 17320, "effective_batch": 512, "lr": 0.00013075944826843912, "gradient_norm": 0.28674113750457764, "tokens_per_second": 1130159.4382380168, "synthetic": false, "world_size": 8} {"step": 32660, "tokens": 8561623040, "loss": 2.3751649856567383, "optimizer_updates": 17330, "effective_batch": 512, "lr": 0.00013068708335493997, "gradient_norm": 0.25701531767845154, "tokens_per_second": 1131670.9314784154, "synthetic": false, "world_size": 8} {"step": 32680, "tokens": 8566865920, "loss": 2.36317138671875, "optimizer_updates": 17340, "effective_batch": 512, "lr": 0.00013061470431837216, "gradient_norm": 0.24900628626346588, "tokens_per_second": 1125374.0991181892, "synthetic": false, "world_size": 8} {"step": 32700, "tokens": 8572108800, "loss": 2.3722848892211914, "optimizer_updates": 17350, "effective_batch": 512, "lr": 0.00013054231120814892, "gradient_norm": 0.2777458429336548, "tokens_per_second": 1139786.8970345054, "synthetic": false, "world_size": 8} {"step": 32720, "tokens": 8577351680, "loss": 2.3807239532470703, "optimizer_updates": 17360, "effective_batch": 512, "lr": 0.00013046990407369292, "gradient_norm": 0.244584321975708, "tokens_per_second": 1127227.7870373384, "synthetic": false, "world_size": 8} {"step": 32740, "tokens": 8582594560, "loss": 2.3715787887573243, "optimizer_updates": 17370, "effective_batch": 512, "lr": 0.00013039748296443652, "gradient_norm": 0.27435004711151123, "tokens_per_second": 1132884.826314185, "synthetic": false, "world_size": 8} {"step": 32760, "tokens": 8587837440, "loss": 2.3855239868164064, "optimizer_updates": 17380, "effective_batch": 512, "lr": 0.00013032504792982163, "gradient_norm": 0.25279560685157776, "tokens_per_second": 1134429.0836894196, "synthetic": false, "world_size": 8} {"step": 32780, "tokens": 8593080320, "loss": 2.3632362365722654, "optimizer_updates": 17390, "effective_batch": 512, "lr": 0.00013025259901929963, "gradient_norm": 0.24935603141784668, "tokens_per_second": 1135228.6543548778, "synthetic": false, "world_size": 8} {"step": 32800, "tokens": 8598323200, "loss": 2.381647491455078, "optimizer_updates": 17400, "effective_batch": 512, "lr": 0.00013018013628233137, "gradient_norm": 0.2742180824279785, "tokens_per_second": 1133776.0581053605, "synthetic": false, "world_size": 8} {"step": 32820, "tokens": 8603566080, "loss": 2.376825141906738, "optimizer_updates": 17410, "effective_batch": 512, "lr": 0.00013010765976838713, "gradient_norm": 0.3176853060722351, "tokens_per_second": 1127304.2823670327, "synthetic": false, "world_size": 8} {"step": 32840, "tokens": 8608808960, "loss": 2.3651988983154295, "optimizer_updates": 17420, "effective_batch": 512, "lr": 0.00013003516952694668, "gradient_norm": 0.27966931462287903, "tokens_per_second": 752012.9038514821, "synthetic": false, "world_size": 8} {"step": 32860, "tokens": 8614051840, "loss": 2.3717954635620115, "optimizer_updates": 17430, "effective_batch": 512, "lr": 0.00012996266560749904, "gradient_norm": 0.24469053745269775, "tokens_per_second": 1136179.488836366, "synthetic": false, "world_size": 8} {"step": 32880, "tokens": 8619294720, "loss": 2.3710079193115234, "optimizer_updates": 17440, "effective_batch": 512, "lr": 0.00012989014805954262, "gradient_norm": 0.2989058792591095, "tokens_per_second": 1139286.2790932788, "synthetic": false, "world_size": 8} {"step": 32900, "tokens": 8624537600, "loss": 2.3834392547607424, "optimizer_updates": 17450, "effective_batch": 512, "lr": 0.00012981761693258518, "gradient_norm": 0.269832044839859, "tokens_per_second": 1130239.9724180868, "synthetic": false, "world_size": 8} {"step": 32920, "tokens": 8629780480, "loss": 2.3743600845336914, "optimizer_updates": 17460, "effective_batch": 512, "lr": 0.0001297450722761437, "gradient_norm": 0.3260565400123596, "tokens_per_second": 1129269.1961100418, "synthetic": false, "world_size": 8} {"step": 32940, "tokens": 8635023360, "loss": 2.369784355163574, "optimizer_updates": 17470, "effective_batch": 512, "lr": 0.00012967251413974437, "gradient_norm": 0.2581599950790405, "tokens_per_second": 1130569.1679073176, "synthetic": false, "world_size": 8} {"step": 32960, "tokens": 8640266240, "loss": 2.388128662109375, "optimizer_updates": 17480, "effective_batch": 512, "lr": 0.00012959994257292264, "gradient_norm": 0.2608296573162079, "tokens_per_second": 1123502.8193998106, "synthetic": false, "world_size": 8} {"step": 32980, "tokens": 8645509120, "loss": 2.3843088150024414, "optimizer_updates": 17490, "effective_batch": 512, "lr": 0.0001295273576252231, "gradient_norm": 0.26087749004364014, "tokens_per_second": 1135512.9865357417, "synthetic": false, "world_size": 8} {"step": 33000, "tokens": 8650752000, "loss": 2.3686330795288084, "optimizer_updates": 17500, "effective_batch": 512, "lr": 0.0001294547593461995, "gradient_norm": 0.2661280632019043, "tokens_per_second": 1134423.2007240797, "synthetic": false, "world_size": 8} {"step": 33020, "tokens": 8655994880, "loss": 2.373219871520996, "optimizer_updates": 17510, "effective_batch": 512, "lr": 0.00012938214778541473, "gradient_norm": 0.2797888517379761, "tokens_per_second": 833627.8289556653, "synthetic": false, "world_size": 8} {"step": 33040, "tokens": 8661237760, "loss": 2.3592269897460936, "optimizer_updates": 17520, "effective_batch": 512, "lr": 0.00012930952299244057, "gradient_norm": 0.29010722041130066, "tokens_per_second": 1129725.3794202683, "synthetic": false, "world_size": 8} {"step": 33060, "tokens": 8666480640, "loss": 2.3642915725708007, "optimizer_updates": 17530, "effective_batch": 512, "lr": 0.00012923688501685802, "gradient_norm": 0.28794166445732117, "tokens_per_second": 1132731.7929403663, "synthetic": false, "world_size": 8} {"step": 33080, "tokens": 8671723520, "loss": 2.382774543762207, "optimizer_updates": 17540, "effective_batch": 512, "lr": 0.000129164233908257, "gradient_norm": 0.227791428565979, "tokens_per_second": 1132380.445366035, "synthetic": false, "world_size": 8} {"step": 33100, "tokens": 8676966400, "loss": 2.380699348449707, "optimizer_updates": 17550, "effective_batch": 512, "lr": 0.00012909156971623641, "gradient_norm": 0.29128673672676086, "tokens_per_second": 1131085.8206949625, "synthetic": false, "world_size": 8} {"step": 33120, "tokens": 8682209280, "loss": 2.372427749633789, "optimizer_updates": 17560, "effective_batch": 512, "lr": 0.00012901889249040412, "gradient_norm": 0.26517775654792786, "tokens_per_second": 1126056.336759085, "synthetic": false, "world_size": 8} {"step": 33140, "tokens": 8687452160, "loss": 2.374314308166504, "optimizer_updates": 17570, "effective_batch": 512, "lr": 0.0001289462022803768, "gradient_norm": 0.24393565952777863, "tokens_per_second": 1123056.930338108, "synthetic": false, "world_size": 8} {"step": 33160, "tokens": 8692695040, "loss": 2.3859352111816405, "optimizer_updates": 17580, "effective_batch": 512, "lr": 0.0001288734991357801, "gradient_norm": 0.24456606805324554, "tokens_per_second": 1121375.4912138507, "synthetic": false, "world_size": 8} {"step": 33180, "tokens": 8697937920, "loss": 2.3794445037841796, "optimizer_updates": 17590, "effective_batch": 512, "lr": 0.00012880078310624845, "gradient_norm": 0.3090325593948364, "tokens_per_second": 1130533.4194859955, "synthetic": false, "world_size": 8} {"step": 33200, "tokens": 8703180800, "loss": 2.3574138641357423, "optimizer_updates": 17600, "effective_batch": 512, "lr": 0.000128728054241425, "gradient_norm": 0.2651181221008301, "tokens_per_second": 1123057.1980710225, "synthetic": false, "world_size": 8} {"step": 33220, "tokens": 8708423680, "loss": 2.3860618591308596, "optimizer_updates": 17610, "effective_batch": 512, "lr": 0.0001286553125909618, "gradient_norm": 0.2695035934448242, "tokens_per_second": 1121727.5733531483, "synthetic": false, "world_size": 8} {"step": 33240, "tokens": 8713666560, "loss": 2.376844596862793, "optimizer_updates": 17620, "effective_batch": 512, "lr": 0.00012858255820451952, "gradient_norm": 0.27700912952423096, "tokens_per_second": 1136106.360435865, "synthetic": false, "world_size": 8} {"step": 33260, "tokens": 8718909440, "loss": 2.364795112609863, "optimizer_updates": 17630, "effective_batch": 512, "lr": 0.0001285097911317676, "gradient_norm": 0.2736104726791382, "tokens_per_second": 1132203.311385893, "synthetic": false, "world_size": 8} {"step": 33280, "tokens": 8724152320, "loss": 2.372550392150879, "optimizer_updates": 17640, "effective_batch": 512, "lr": 0.00012843701142238413, "gradient_norm": 0.2513261139392853, "tokens_per_second": 1132202.3497741318, "synthetic": false, "world_size": 8} {"step": 33300, "tokens": 8729395200, "loss": 2.3878456115722657, "optimizer_updates": 17650, "effective_batch": 512, "lr": 0.00012836421912605577, "gradient_norm": 0.29080092906951904, "tokens_per_second": 1022915.6706187174, "synthetic": false, "world_size": 8} {"step": 33320, "tokens": 8734638080, "loss": 2.365371894836426, "optimizer_updates": 17660, "effective_batch": 512, "lr": 0.0001282914142924778, "gradient_norm": 0.3962095379829407, "tokens_per_second": 1137071.7243446743, "synthetic": false, "world_size": 8} {"step": 33340, "tokens": 8739880960, "loss": 2.3698970794677736, "optimizer_updates": 17670, "effective_batch": 512, "lr": 0.00012821859697135412, "gradient_norm": 0.31173163652420044, "tokens_per_second": 1130938.9038313373, "synthetic": false, "world_size": 8} {"step": 33360, "tokens": 8745123840, "loss": 2.3772300720214843, "optimizer_updates": 17680, "effective_batch": 512, "lr": 0.00012814576721239705, "gradient_norm": 0.30067527294158936, "tokens_per_second": 1133984.7422918663, "synthetic": false, "world_size": 8} {"step": 33380, "tokens": 8750366720, "loss": 2.3810943603515624, "optimizer_updates": 17690, "effective_batch": 512, "lr": 0.00012807292506532747, "gradient_norm": 0.36490172147750854, "tokens_per_second": 1135195.8578269011, "synthetic": false, "world_size": 8} {"step": 33400, "tokens": 8755609600, "loss": 2.374947738647461, "optimizer_updates": 17700, "effective_batch": 512, "lr": 0.00012800007057987473, "gradient_norm": 0.2797301411628723, "tokens_per_second": 1124300.9624411913, "synthetic": false, "world_size": 8} {"step": 33420, "tokens": 8760852480, "loss": 2.3773033142089846, "optimizer_updates": 17710, "effective_batch": 512, "lr": 0.00012792720380577655, "gradient_norm": 0.3005470633506775, "tokens_per_second": 1131280.2641834577, "synthetic": false, "world_size": 8} {"step": 33440, "tokens": 8766095360, "loss": 2.374804878234863, "optimizer_updates": 17720, "effective_batch": 512, "lr": 0.00012785432479277904, "gradient_norm": 0.249874085187912, "tokens_per_second": 1125545.2122041387, "synthetic": false, "world_size": 8} {"step": 33460, "tokens": 8771338240, "loss": 2.369176483154297, "optimizer_updates": 17730, "effective_batch": 512, "lr": 0.00012778143359063674, "gradient_norm": 0.24643519520759583, "tokens_per_second": 1018235.8403006837, "synthetic": false, "world_size": 8} {"step": 33480, "tokens": 8776581120, "loss": 2.3594566345214845, "optimizer_updates": 17740, "effective_batch": 512, "lr": 0.00012770853024911244, "gradient_norm": 0.2953055202960968, "tokens_per_second": 1137251.5607645009, "synthetic": false, "world_size": 8} {"step": 33500, "tokens": 8781824000, "loss": 2.3747987747192383, "optimizer_updates": 17750, "effective_batch": 512, "lr": 0.00012763561481797728, "gradient_norm": 0.31645700335502625, "tokens_per_second": 1133577.5193227197, "synthetic": false, "world_size": 8} {"step": 33520, "tokens": 8787066880, "loss": 2.3810344696044923, "optimizer_updates": 17760, "effective_batch": 512, "lr": 0.00012756268734701056, "gradient_norm": 0.2751360535621643, "tokens_per_second": 1133454.365881362, "synthetic": false, "world_size": 8} {"step": 33540, "tokens": 8792309760, "loss": 2.372492790222168, "optimizer_updates": 17770, "effective_batch": 512, "lr": 0.00012748974788599985, "gradient_norm": 0.2750723361968994, "tokens_per_second": 1123634.325284095, "synthetic": false, "world_size": 8} {"step": 33560, "tokens": 8797552640, "loss": 2.384381103515625, "optimizer_updates": 17780, "effective_batch": 512, "lr": 0.00012741679648474097, "gradient_norm": 0.27836722135543823, "tokens_per_second": 1133246.81036765, "synthetic": false, "world_size": 8} {"step": 33580, "tokens": 8802795520, "loss": 2.363244819641113, "optimizer_updates": 17790, "effective_batch": 512, "lr": 0.00012734383319303773, "gradient_norm": 0.26934605836868286, "tokens_per_second": 1133204.250519612, "synthetic": false, "world_size": 8} {"step": 33600, "tokens": 8808038400, "loss": 2.372713088989258, "optimizer_updates": 17800, "effective_batch": 512, "lr": 0.00012727085806070226, "gradient_norm": 0.26595595479011536, "tokens_per_second": 1136034.5416500324, "synthetic": false, "world_size": 8} {"step": 33620, "tokens": 8813281280, "loss": 2.373442459106445, "optimizer_updates": 17810, "effective_batch": 512, "lr": 0.00012719787113755462, "gradient_norm": 0.32146063446998596, "tokens_per_second": 1133801.4896922826, "synthetic": false, "world_size": 8} {"step": 33640, "tokens": 8818524160, "loss": 2.3755468368530273, "optimizer_updates": 17820, "effective_batch": 512, "lr": 0.000127124872473423, "gradient_norm": 0.2615416944026947, "tokens_per_second": 1134429.9089239582, "synthetic": false, "world_size": 8} {"step": 33660, "tokens": 8823767040, "loss": 2.3735702514648436, "optimizer_updates": 17830, "effective_batch": 512, "lr": 0.00012705186211814354, "gradient_norm": 0.33336567878723145, "tokens_per_second": 1133122.9497667358, "synthetic": false, "world_size": 8} {"step": 33680, "tokens": 8829009920, "loss": 2.3681161880493162, "optimizer_updates": 17840, "effective_batch": 512, "lr": 0.0001269788401215604, "gradient_norm": 0.30819639563560486, "tokens_per_second": 1132737.107228942, "synthetic": false, "world_size": 8} {"step": 33700, "tokens": 8834252800, "loss": 2.3650508880615235, "optimizer_updates": 17850, "effective_batch": 512, "lr": 0.00012690580653352572, "gradient_norm": 0.2980627119541168, "tokens_per_second": 1128143.2547052498, "synthetic": false, "world_size": 8} {"step": 33720, "tokens": 8839495680, "loss": 2.3643550872802734, "optimizer_updates": 17860, "effective_batch": 512, "lr": 0.00012683276140389952, "gradient_norm": 0.3028213679790497, "tokens_per_second": 1127682.1902476668, "synthetic": false, "world_size": 8} {"step": 33740, "tokens": 8844738560, "loss": 2.3723638534545897, "optimizer_updates": 17870, "effective_batch": 512, "lr": 0.00012675970478254965, "gradient_norm": 0.3224159777164459, "tokens_per_second": 1121060.3808531933, "synthetic": false, "world_size": 8} {"step": 33760, "tokens": 8849981440, "loss": 2.3745891571044924, "optimizer_updates": 17880, "effective_batch": 512, "lr": 0.00012668663671935193, "gradient_norm": 0.29609692096710205, "tokens_per_second": 1139646.7403138087, "synthetic": false, "world_size": 8} {"step": 33780, "tokens": 8855224320, "loss": 2.3781293869018554, "optimizer_updates": 17890, "effective_batch": 512, "lr": 0.00012661355726418982, "gradient_norm": 0.32728761434555054, "tokens_per_second": 1136612.0025910968, "synthetic": false, "world_size": 8} {"step": 33800, "tokens": 8860467200, "loss": 2.3758846282958985, "optimizer_updates": 17900, "effective_batch": 512, "lr": 0.00012654046646695476, "gradient_norm": 0.26286715269088745, "tokens_per_second": 1128524.335721301, "synthetic": false, "world_size": 8} {"step": 33820, "tokens": 8865710080, "loss": 2.3740392684936524, "optimizer_updates": 17910, "effective_batch": 512, "lr": 0.00012646736437754572, "gradient_norm": 0.2745605409145355, "tokens_per_second": 1130525.7614312107, "synthetic": false, "world_size": 8} {"step": 33840, "tokens": 8870952960, "loss": 2.37414493560791, "optimizer_updates": 17920, "effective_batch": 512, "lr": 0.00012639425104586955, "gradient_norm": 0.26995521783828735, "tokens_per_second": 1137051.2370953038, "synthetic": false, "world_size": 8} {"step": 33860, "tokens": 8876195840, "loss": 2.373486328125, "optimizer_updates": 17930, "effective_batch": 512, "lr": 0.0001263211265218407, "gradient_norm": 0.29742416739463806, "tokens_per_second": 1141091.30161224, "synthetic": false, "world_size": 8} {"step": 33880, "tokens": 8881438720, "loss": 2.370937728881836, "optimizer_updates": 17940, "effective_batch": 512, "lr": 0.0001262479908553813, "gradient_norm": 0.32381805777549744, "tokens_per_second": 1132136.4181680148, "synthetic": false, "world_size": 8} {"step": 33900, "tokens": 8886681600, "loss": 2.375530242919922, "optimizer_updates": 17950, "effective_batch": 512, "lr": 0.00012617484409642096, "gradient_norm": 0.25651678442955017, "tokens_per_second": 1133993.9039426935, "synthetic": false, "world_size": 8} {"step": 33920, "tokens": 8891924480, "loss": 2.3790971755981447, "optimizer_updates": 17960, "effective_batch": 512, "lr": 0.00012610168629489704, "gradient_norm": 0.2823539078235626, "tokens_per_second": 1137604.8892401683, "synthetic": false, "world_size": 8} {"step": 33940, "tokens": 8897167360, "loss": 2.3799739837646485, "optimizer_updates": 17970, "effective_batch": 512, "lr": 0.0001260285175007544, "gradient_norm": 0.3199448883533478, "tokens_per_second": 1131735.552907246, "synthetic": false, "world_size": 8} {"step": 33960, "tokens": 8902410240, "loss": 2.3769702911376953, "optimizer_updates": 17980, "effective_batch": 512, "lr": 0.00012595533776394525, "gradient_norm": 0.2537387013435364, "tokens_per_second": 1132228.6749412385, "synthetic": false, "world_size": 8} {"step": 33980, "tokens": 8907653120, "loss": 2.385873222351074, "optimizer_updates": 17990, "effective_batch": 512, "lr": 0.0001258821471344295, "gradient_norm": 0.2600449025630951, "tokens_per_second": 1131372.1421579455, "synthetic": false, "world_size": 8} {"step": 34000, "tokens": 8912896000, "loss": 2.3697063446044924, "optimizer_updates": 18000, "effective_batch": 512, "lr": 0.00012580894566217429, "gradient_norm": 0.2483130544424057, "tokens_per_second": 1130339.6371797232, "synthetic": false, "world_size": 8} {"step": 34020, "tokens": 8918138880, "loss": 2.371449661254883, "optimizer_updates": 18010, "effective_batch": 512, "lr": 0.00012573573339715431, "gradient_norm": 0.33324211835861206, "tokens_per_second": 838557.0616125099, "synthetic": false, "world_size": 8} {"step": 34040, "tokens": 8923381760, "loss": 2.3803855895996096, "optimizer_updates": 18020, "effective_batch": 512, "lr": 0.00012566251038935151, "gradient_norm": 0.2839726507663727, "tokens_per_second": 998524.1939279606, "synthetic": false, "world_size": 8} {"step": 34060, "tokens": 8928624640, "loss": 2.3765417098999024, "optimizer_updates": 18030, "effective_batch": 512, "lr": 0.00012558927668875527, "gradient_norm": 0.2808029055595398, "tokens_per_second": 846947.0670948452, "synthetic": false, "world_size": 8} {"step": 34080, "tokens": 8933867520, "loss": 2.370253562927246, "optimizer_updates": 18040, "effective_batch": 512, "lr": 0.00012551603234536225, "gradient_norm": 0.2580486238002777, "tokens_per_second": 1140620.0053177124, "synthetic": false, "world_size": 8} {"step": 34100, "tokens": 8939110400, "loss": 2.3713783264160155, "optimizer_updates": 18050, "effective_batch": 512, "lr": 0.00012544277740917628, "gradient_norm": 0.24940375983715057, "tokens_per_second": 1129843.8336749645, "synthetic": false, "world_size": 8} {"step": 34120, "tokens": 8944353280, "loss": 2.3569828033447267, "optimizer_updates": 18060, "effective_batch": 512, "lr": 0.00012536951193020855, "gradient_norm": 0.24764186143875122, "tokens_per_second": 1128742.5767897803, "synthetic": false, "world_size": 8} {"step": 34140, "tokens": 8949596160, "loss": 2.3790117263793946, "optimizer_updates": 18070, "effective_batch": 512, "lr": 0.0001252962359584774, "gradient_norm": 0.3096657991409302, "tokens_per_second": 1140898.8079787686, "synthetic": false, "world_size": 8} {"step": 34160, "tokens": 8954839040, "loss": 2.3747886657714843, "optimizer_updates": 18080, "effective_batch": 512, "lr": 0.00012522294954400828, "gradient_norm": 0.2569124698638916, "tokens_per_second": 1137118.819160532, "synthetic": false, "world_size": 8} {"step": 34180, "tokens": 8960081920, "loss": 2.3684150695800783, "optimizer_updates": 18090, "effective_batch": 512, "lr": 0.0001251496527368338, "gradient_norm": 0.2708224058151245, "tokens_per_second": 1138334.346437167, "synthetic": false, "world_size": 8} {"step": 34200, "tokens": 8965324800, "loss": 2.3805620193481447, "optimizer_updates": 18100, "effective_batch": 512, "lr": 0.00012507634558699373, "gradient_norm": 0.3246094882488251, "tokens_per_second": 1124936.7789731754, "synthetic": false, "world_size": 8} {"step": 34220, "tokens": 8970567680, "loss": 2.379084014892578, "optimizer_updates": 18110, "effective_batch": 512, "lr": 0.00012500302814453485, "gradient_norm": 0.27572712302207947, "tokens_per_second": 1138980.896568921, "synthetic": false, "world_size": 8} {"step": 34240, "tokens": 8975810560, "loss": 2.3824743270874023, "optimizer_updates": 18120, "effective_batch": 512, "lr": 0.00012492970045951092, "gradient_norm": 0.29398614168167114, "tokens_per_second": 1124179.4552128862, "synthetic": false, "world_size": 8} {"step": 34260, "tokens": 8981053440, "loss": 2.375857925415039, "optimizer_updates": 18130, "effective_batch": 512, "lr": 0.0001248563625819828, "gradient_norm": 0.28519687056541443, "tokens_per_second": 1135231.58932029, "synthetic": false, "world_size": 8} {"step": 34280, "tokens": 8986296320, "loss": 2.3783140182495117, "optimizer_updates": 18140, "effective_batch": 512, "lr": 0.0001247830145620182, "gradient_norm": 0.2629398703575134, "tokens_per_second": 1136056.5485566629, "synthetic": false, "world_size": 8} {"step": 34300, "tokens": 8991539200, "loss": 2.3627750396728517, "optimizer_updates": 18150, "effective_batch": 512, "lr": 0.0001247096564496918, "gradient_norm": 0.2757818102836609, "tokens_per_second": 774269.5002079546, "synthetic": false, "world_size": 8} {"step": 34320, "tokens": 8996782080, "loss": 2.3815645217895507, "optimizer_updates": 18160, "effective_batch": 512, "lr": 0.00012463628829508522, "gradient_norm": 0.2740399241447449, "tokens_per_second": 787407.7064236482, "synthetic": false, "world_size": 8} {"step": 34340, "tokens": 9002024960, "loss": 2.363454055786133, "optimizer_updates": 18170, "effective_batch": 512, "lr": 0.00012456291014828683, "gradient_norm": 0.3644605875015259, "tokens_per_second": 1138696.62635854, "synthetic": false, "world_size": 8} {"step": 34360, "tokens": 9007267840, "loss": 2.3727209091186525, "optimizer_updates": 18180, "effective_batch": 512, "lr": 0.00012448952205939193, "gradient_norm": 0.2993478775024414, "tokens_per_second": 1135820.7682122716, "synthetic": false, "world_size": 8} {"step": 34380, "tokens": 9012510720, "loss": 2.3727474212646484, "optimizer_updates": 18190, "effective_batch": 512, "lr": 0.00012441612407850251, "gradient_norm": 0.24100522696971893, "tokens_per_second": 1135418.3879995274, "synthetic": false, "world_size": 8} {"step": 34400, "tokens": 9017753600, "loss": 2.366465377807617, "optimizer_updates": 18200, "effective_batch": 512, "lr": 0.00012434271625572741, "gradient_norm": 0.23765495419502258, "tokens_per_second": 1135558.5154524394, "synthetic": false, "world_size": 8} {"step": 34420, "tokens": 9022996480, "loss": 2.364254379272461, "optimizer_updates": 18210, "effective_batch": 512, "lr": 0.00012426929864118208, "gradient_norm": 0.330899178981781, "tokens_per_second": 1130296.9990509257, "synthetic": false, "world_size": 8} {"step": 34440, "tokens": 9028239360, "loss": 2.3759307861328125, "optimizer_updates": 18220, "effective_batch": 512, "lr": 0.00012419587128498878, "gradient_norm": 0.24216347932815552, "tokens_per_second": 1120091.4178624914, "synthetic": false, "world_size": 8} {"step": 34460, "tokens": 9033482240, "loss": 2.3688451766967775, "optimizer_updates": 18230, "effective_batch": 512, "lr": 0.00012412243423727632, "gradient_norm": 0.27457839250564575, "tokens_per_second": 1126963.7740844027, "synthetic": false, "world_size": 8} {"step": 34480, "tokens": 9038725120, "loss": 2.3744503021240235, "optimizer_updates": 18240, "effective_batch": 512, "lr": 0.00012404898754818014, "gradient_norm": 0.25768330693244934, "tokens_per_second": 1029471.5633414619, "synthetic": false, "world_size": 8} {"step": 34500, "tokens": 9043968000, "loss": 2.374395751953125, "optimizer_updates": 18250, "effective_batch": 512, "lr": 0.00012397553126784235, "gradient_norm": 0.232496440410614, "tokens_per_second": 1134155.357454865, "synthetic": false, "world_size": 8} {"step": 34520, "tokens": 9049210880, "loss": 2.3673738479614257, "optimizer_updates": 18260, "effective_batch": 512, "lr": 0.00012390206544641145, "gradient_norm": 0.2409428507089615, "tokens_per_second": 1131548.1098842025, "synthetic": false, "world_size": 8} {"step": 34540, "tokens": 9054453760, "loss": 2.3796175003051756, "optimizer_updates": 18270, "effective_batch": 512, "lr": 0.0001238285901340426, "gradient_norm": 0.2912396192550659, "tokens_per_second": 1129541.9381901978, "synthetic": false, "world_size": 8} {"step": 34560, "tokens": 9059696640, "loss": 2.380691337585449, "optimizer_updates": 18280, "effective_batch": 512, "lr": 0.0001237551053808974, "gradient_norm": 0.2640444338321686, "tokens_per_second": 1122774.0239902553, "synthetic": false, "world_size": 8} {"step": 34580, "tokens": 9064939520, "loss": 2.3586332321166994, "optimizer_updates": 18290, "effective_batch": 512, "lr": 0.00012368161123714382, "gradient_norm": 0.23651307821273804, "tokens_per_second": 1127461.7651662116, "synthetic": false, "world_size": 8} {"step": 34600, "tokens": 9070182400, "loss": 2.3760313034057616, "optimizer_updates": 18300, "effective_batch": 512, "lr": 0.0001236081077529564, "gradient_norm": 0.28370633721351624, "tokens_per_second": 1129679.6203780624, "synthetic": false, "world_size": 8} {"step": 34620, "tokens": 9075425280, "loss": 2.3518404006958007, "optimizer_updates": 18310, "effective_batch": 512, "lr": 0.00012353459497851585, "gradient_norm": 0.3225480020046234, "tokens_per_second": 1128689.8835649707, "synthetic": false, "world_size": 8} {"step": 34640, "tokens": 9080668160, "loss": 2.3742034912109373, "optimizer_updates": 18320, "effective_batch": 512, "lr": 0.00012346107296400938, "gradient_norm": 0.23078152537345886, "tokens_per_second": 1125256.3483189577, "synthetic": false, "world_size": 8} {"step": 34660, "tokens": 9085911040, "loss": 2.358470916748047, "optimizer_updates": 18330, "effective_batch": 512, "lr": 0.00012338754175963046, "gradient_norm": 0.2695421278476715, "tokens_per_second": 1124130.722735323, "synthetic": false, "world_size": 8} {"step": 34680, "tokens": 9091153920, "loss": 2.376520538330078, "optimizer_updates": 18340, "effective_batch": 512, "lr": 0.00012331400141557883, "gradient_norm": 0.3490309715270996, "tokens_per_second": 1132333.0655354003, "synthetic": false, "world_size": 8} {"step": 34700, "tokens": 9096396800, "loss": 2.374059867858887, "optimizer_updates": 18350, "effective_batch": 512, "lr": 0.00012324045198206047, "gradient_norm": 0.2733682096004486, "tokens_per_second": 1126997.6265359195, "synthetic": false, "world_size": 8} {"step": 34720, "tokens": 9101639680, "loss": 2.3839797973632812, "optimizer_updates": 18360, "effective_batch": 512, "lr": 0.00012316689350928757, "gradient_norm": 0.2595454752445221, "tokens_per_second": 1133259.361528593, "synthetic": false, "world_size": 8} {"step": 34740, "tokens": 9106882560, "loss": 2.3714799880981445, "optimizer_updates": 18370, "effective_batch": 512, "lr": 0.00012309332604747847, "gradient_norm": 0.25009170174598694, "tokens_per_second": 1126902.782000123, "synthetic": false, "world_size": 8} {"step": 34760, "tokens": 9112125440, "loss": 2.3663434982299805, "optimizer_updates": 18380, "effective_batch": 512, "lr": 0.0001230197496468577, "gradient_norm": 0.25078314542770386, "tokens_per_second": 1135792.1023554904, "synthetic": false, "world_size": 8} {"step": 34780, "tokens": 9117368320, "loss": 2.369159126281738, "optimizer_updates": 18390, "effective_batch": 512, "lr": 0.00012294616435765582, "gradient_norm": 0.24953584372997284, "tokens_per_second": 1130470.2329741463, "synthetic": false, "world_size": 8} {"step": 34800, "tokens": 9122611200, "loss": 2.3780485153198243, "optimizer_updates": 18400, "effective_batch": 512, "lr": 0.0001228725702301095, "gradient_norm": 0.27717673778533936, "tokens_per_second": 1146275.976579974, "synthetic": false, "world_size": 8} {"step": 34820, "tokens": 9127854080, "loss": 2.3738981246948243, "optimizer_updates": 18410, "effective_batch": 512, "lr": 0.00012279896731446144, "gradient_norm": 0.2369535267353058, "tokens_per_second": 1133993.956395755, "synthetic": false, "world_size": 8} {"step": 34840, "tokens": 9133096960, "loss": 2.379886245727539, "optimizer_updates": 18420, "effective_batch": 512, "lr": 0.0001227253556609604, "gradient_norm": 0.2598063051700592, "tokens_per_second": 1138562.958294545, "synthetic": false, "world_size": 8} {"step": 34860, "tokens": 9138339840, "loss": 2.3870065689086912, "optimizer_updates": 18430, "effective_batch": 512, "lr": 0.00012265173531986092, "gradient_norm": 0.3536163568496704, "tokens_per_second": 1026317.5488873807, "synthetic": false, "world_size": 8} {"step": 34880, "tokens": 9143582720, "loss": 2.3692304611206056, "optimizer_updates": 18440, "effective_batch": 512, "lr": 0.00012257810634142374, "gradient_norm": 0.24090087413787842, "tokens_per_second": 1119075.2561325247, "synthetic": false, "world_size": 8} {"step": 34900, "tokens": 9148825600, "loss": 2.375127983093262, "optimizer_updates": 18450, "effective_batch": 512, "lr": 0.00012250446877591523, "gradient_norm": 0.27595219016075134, "tokens_per_second": 1133417.4311311494, "synthetic": false, "world_size": 8} {"step": 34920, "tokens": 9154068480, "loss": 2.3664451599121095, "optimizer_updates": 18460, "effective_batch": 512, "lr": 0.00012243082267360787, "gradient_norm": 0.23020656406879425, "tokens_per_second": 1132192.3862414726, "synthetic": false, "world_size": 8} {"step": 34940, "tokens": 9159311360, "loss": 2.366486740112305, "optimizer_updates": 18470, "effective_batch": 512, "lr": 0.0001223571680847797, "gradient_norm": 0.2712145447731018, "tokens_per_second": 1125473.758668526, "synthetic": false, "world_size": 8} {"step": 34960, "tokens": 9164554240, "loss": 2.3689910888671877, "optimizer_updates": 18480, "effective_batch": 512, "lr": 0.0001222835050597148, "gradient_norm": 0.2637591063976288, "tokens_per_second": 1124742.2957528655, "synthetic": false, "world_size": 8} {"step": 34980, "tokens": 9169797120, "loss": 2.3663158416748047, "optimizer_updates": 18490, "effective_batch": 512, "lr": 0.00012220983364870285, "gradient_norm": 0.25271472334861755, "tokens_per_second": 1133559.1390634137, "synthetic": false, "world_size": 8} {"step": 35000, "tokens": 9175040000, "loss": 2.363481903076172, "optimizer_updates": 18500, "effective_batch": 512, "lr": 0.00012213615390203934, "gradient_norm": 0.28075945377349854, "tokens_per_second": 1134078.3754498432, "synthetic": false, "world_size": 8} {"step": 35020, "tokens": 9180282880, "loss": 2.375926208496094, "optimizer_updates": 18510, "effective_batch": 512, "lr": 0.0001220624658700254, "gradient_norm": 0.2865281403064728, "tokens_per_second": 829294.7597038868, "synthetic": false, "world_size": 8} {"step": 35040, "tokens": 9185525760, "loss": 2.3618194580078127, "optimizer_updates": 18520, "effective_batch": 512, "lr": 0.00012198876960296787, "gradient_norm": 0.3100717067718506, "tokens_per_second": 1140457.0256331724, "synthetic": false, "world_size": 8} {"step": 35060, "tokens": 9190768640, "loss": 2.3738189697265626, "optimizer_updates": 18530, "effective_batch": 512, "lr": 0.00012191506515117917, "gradient_norm": 0.27869662642478943, "tokens_per_second": 1131142.2259838379, "synthetic": false, "world_size": 8} {"step": 35080, "tokens": 9196011520, "loss": 2.366758918762207, "optimizer_updates": 18540, "effective_batch": 512, "lr": 0.00012184135256497734, "gradient_norm": 0.3332412540912628, "tokens_per_second": 1122961.192891892, "synthetic": false, "world_size": 8} {"step": 35100, "tokens": 9201254400, "loss": 2.37146110534668, "optimizer_updates": 18550, "effective_batch": 512, "lr": 0.00012176763189468587, "gradient_norm": 0.2724047899246216, "tokens_per_second": 1123311.854741516, "synthetic": false, "world_size": 8} {"step": 35120, "tokens": 9206497280, "loss": 2.374740409851074, "optimizer_updates": 18560, "effective_batch": 512, "lr": 0.00012169390319063394, "gradient_norm": 0.25175970792770386, "tokens_per_second": 1128321.9195167453, "synthetic": false, "world_size": 8} {"step": 35140, "tokens": 9211740160, "loss": 2.3872753143310548, "optimizer_updates": 18570, "effective_batch": 512, "lr": 0.00012162016650315605, "gradient_norm": 0.2879091799259186, "tokens_per_second": 1130274.5200168246, "synthetic": false, "world_size": 8} {"step": 35160, "tokens": 9216983040, "loss": 2.3845003128051756, "optimizer_updates": 18580, "effective_batch": 512, "lr": 0.00012154642188259229, "gradient_norm": 0.24383772909641266, "tokens_per_second": 1138469.8100488721, "synthetic": false, "world_size": 8} {"step": 35180, "tokens": 9222225920, "loss": 2.377678871154785, "optimizer_updates": 18590, "effective_batch": 512, "lr": 0.00012147266937928807, "gradient_norm": 0.2371632605791092, "tokens_per_second": 1138253.8045045966, "synthetic": false, "world_size": 8} {"step": 35200, "tokens": 9227468800, "loss": 2.3603273391723634, "optimizer_updates": 18600, "effective_batch": 512, "lr": 0.00012139890904359422, "gradient_norm": 0.25448179244995117, "tokens_per_second": 1128769.9141221538, "synthetic": false, "world_size": 8} {"step": 35220, "tokens": 9232711680, "loss": 2.3903783798217773, "optimizer_updates": 18610, "effective_batch": 512, "lr": 0.00012132514092586692, "gradient_norm": 0.2590031921863556, "tokens_per_second": 1131946.9202164493, "synthetic": false, "world_size": 8} {"step": 35240, "tokens": 9237954560, "loss": 2.368256759643555, "optimizer_updates": 18620, "effective_batch": 512, "lr": 0.00012125136507646763, "gradient_norm": 0.2651349604129791, "tokens_per_second": 1135276.5123185066, "synthetic": false, "world_size": 8} {"step": 35260, "tokens": 9243197440, "loss": 2.3949981689453126, "optimizer_updates": 18630, "effective_batch": 512, "lr": 0.0001211775815457631, "gradient_norm": 0.26640141010284424, "tokens_per_second": 1131660.475339489, "synthetic": false, "world_size": 8} {"step": 35280, "tokens": 9248440320, "loss": 2.37258243560791, "optimizer_updates": 18640, "effective_batch": 512, "lr": 0.00012110379038412539, "gradient_norm": 0.2975984513759613, "tokens_per_second": 1130311.4573863773, "synthetic": false, "world_size": 8} {"step": 35300, "tokens": 9253683200, "loss": 2.374473762512207, "optimizer_updates": 18650, "effective_batch": 512, "lr": 0.00012102999164193166, "gradient_norm": 0.2474246323108673, "tokens_per_second": 1131977.892253497, "synthetic": false, "world_size": 8} {"step": 35320, "tokens": 9258926080, "loss": 2.3755842208862306, "optimizer_updates": 18660, "effective_batch": 512, "lr": 0.00012095618536956433, "gradient_norm": 0.26668792963027954, "tokens_per_second": 1125556.5234091303, "synthetic": false, "world_size": 8} {"step": 35340, "tokens": 9264168960, "loss": 2.368381118774414, "optimizer_updates": 18670, "effective_batch": 512, "lr": 0.00012088237161741091, "gradient_norm": 0.26152294874191284, "tokens_per_second": 1126327.195762137, "synthetic": false, "world_size": 8} {"step": 35360, "tokens": 9269411840, "loss": 2.358829307556152, "optimizer_updates": 18680, "effective_batch": 512, "lr": 0.00012080855043586407, "gradient_norm": 0.30024605989456177, "tokens_per_second": 802733.7086823154, "synthetic": false, "world_size": 8} {"step": 35380, "tokens": 9274654720, "loss": 2.3698284149169924, "optimizer_updates": 18690, "effective_batch": 512, "lr": 0.00012073472187532148, "gradient_norm": 0.30295342206954956, "tokens_per_second": 1139891.0147636482, "synthetic": false, "world_size": 8} {"step": 35400, "tokens": 9279897600, "loss": 2.372694206237793, "optimizer_updates": 18700, "effective_batch": 512, "lr": 0.00012066088598618593, "gradient_norm": 0.2795424461364746, "tokens_per_second": 1130556.4417255663, "synthetic": false, "world_size": 8} {"step": 35420, "tokens": 9285140480, "loss": 2.3721250534057616, "optimizer_updates": 18710, "effective_batch": 512, "lr": 0.00012058704281886511, "gradient_norm": 0.27360671758651733, "tokens_per_second": 1121508.732066875, "synthetic": false, "world_size": 8} {"step": 35440, "tokens": 9290383360, "loss": 2.387790298461914, "optimizer_updates": 18720, "effective_batch": 512, "lr": 0.00012051319242377178, "gradient_norm": 0.25468412041664124, "tokens_per_second": 1132847.3933755257, "synthetic": false, "world_size": 8} {"step": 35460, "tokens": 9295626240, "loss": 2.3833429336547853, "optimizer_updates": 18730, "effective_batch": 512, "lr": 0.00012043933485132362, "gradient_norm": 0.23807093501091003, "tokens_per_second": 1140053.386907845, "synthetic": false, "world_size": 8} {"step": 35480, "tokens": 9300869120, "loss": 2.3595666885375977, "optimizer_updates": 18740, "effective_batch": 512, "lr": 0.00012036547015194312, "gradient_norm": 0.23136959969997406, "tokens_per_second": 1138282.8624053937, "synthetic": false, "world_size": 8} {"step": 35500, "tokens": 9306112000, "loss": 2.3704879760742186, "optimizer_updates": 18750, "effective_batch": 512, "lr": 0.00012029159837605775, "gradient_norm": 0.278270423412323, "tokens_per_second": 1140410.4048137374, "synthetic": false, "world_size": 8} {"step": 35520, "tokens": 9311354880, "loss": 2.3712226867675783, "optimizer_updates": 18760, "effective_batch": 512, "lr": 0.00012021771957409973, "gradient_norm": 0.2529810965061188, "tokens_per_second": 1131374.039144034, "synthetic": false, "world_size": 8} {"step": 35540, "tokens": 9316597760, "loss": 2.375199890136719, "optimizer_updates": 18770, "effective_batch": 512, "lr": 0.00012014383379650614, "gradient_norm": 0.2662651836872101, "tokens_per_second": 1141365.0904854503, "synthetic": false, "world_size": 8} {"step": 35560, "tokens": 9321840640, "loss": 2.364352226257324, "optimizer_updates": 18780, "effective_batch": 512, "lr": 0.00012006994109371876, "gradient_norm": 0.3230094611644745, "tokens_per_second": 761650.6448170756, "synthetic": false, "world_size": 8} {"step": 35580, "tokens": 9327083520, "loss": 2.354623794555664, "optimizer_updates": 18790, "effective_batch": 512, "lr": 0.00011999604151618411, "gradient_norm": 0.27747082710266113, "tokens_per_second": 1147271.8903642995, "synthetic": false, "world_size": 8} {"step": 35600, "tokens": 9332326400, "loss": 2.3683956146240233, "optimizer_updates": 18800, "effective_batch": 512, "lr": 0.00011992213511435346, "gradient_norm": 0.34266427159309387, "tokens_per_second": 1134881.8987901832, "synthetic": false, "world_size": 8} {"step": 35620, "tokens": 9337569280, "loss": 2.378757095336914, "optimizer_updates": 18810, "effective_batch": 512, "lr": 0.00011984822193868268, "gradient_norm": 0.25071051716804504, "tokens_per_second": 1128950.227340189, "synthetic": false, "world_size": 8} {"step": 35640, "tokens": 9342812160, "loss": 2.3711997985839846, "optimizer_updates": 18820, "effective_batch": 512, "lr": 0.00011977430203963229, "gradient_norm": 0.2444542646408081, "tokens_per_second": 1015516.8254596753, "synthetic": false, "world_size": 8} {"step": 35660, "tokens": 9348055040, "loss": 2.3712677001953124, "optimizer_updates": 18830, "effective_batch": 512, "lr": 0.0001197003754676674, "gradient_norm": 0.25796929001808167, "tokens_per_second": 1132829.9301620654, "synthetic": false, "world_size": 8} {"step": 35680, "tokens": 9353297920, "loss": 2.3694108963012694, "optimizer_updates": 18840, "effective_batch": 512, "lr": 0.00011962644227325763, "gradient_norm": 0.3247254490852356, "tokens_per_second": 1138254.6197780082, "synthetic": false, "world_size": 8} {"step": 35700, "tokens": 9358540800, "loss": 2.370576858520508, "optimizer_updates": 18850, "effective_batch": 512, "lr": 0.00011955250250687722, "gradient_norm": 0.277584046125412, "tokens_per_second": 1120324.9544587566, "synthetic": false, "world_size": 8} {"step": 35720, "tokens": 9363783680, "loss": 2.3711172103881837, "optimizer_updates": 18860, "effective_batch": 512, "lr": 0.00011947855621900483, "gradient_norm": 0.26042282581329346, "tokens_per_second": 1135360.321443523, "synthetic": false, "world_size": 8} {"step": 35740, "tokens": 9369026560, "loss": 2.3786832809448244, "optimizer_updates": 18870, "effective_batch": 512, "lr": 0.00011940460346012352, "gradient_norm": 0.3126824200153351, "tokens_per_second": 1138506.8520549615, "synthetic": false, "world_size": 8} {"step": 35760, "tokens": 9374269440, "loss": 2.3653303146362306, "optimizer_updates": 18880, "effective_batch": 512, "lr": 0.00011933064428072087, "gradient_norm": 0.24717333912849426, "tokens_per_second": 1129991.8353389886, "synthetic": false, "world_size": 8} {"step": 35780, "tokens": 9379512320, "loss": 2.373762512207031, "optimizer_updates": 18890, "effective_batch": 512, "lr": 0.00011925667873128878, "gradient_norm": 0.26023873686790466, "tokens_per_second": 1134240.0201579744, "synthetic": false, "world_size": 8} {"step": 35800, "tokens": 9384755200, "loss": 2.3715986251831054, "optimizer_updates": 18900, "effective_batch": 512, "lr": 0.00011918270686232356, "gradient_norm": 0.2533959150314331, "tokens_per_second": 1125208.764630904, "synthetic": false, "world_size": 8} {"step": 35820, "tokens": 9389998080, "loss": 2.3700420379638674, "optimizer_updates": 18910, "effective_batch": 512, "lr": 0.00011910872872432574, "gradient_norm": 0.30446532368659973, "tokens_per_second": 1136276.5306146487, "synthetic": false, "world_size": 8} {"step": 35840, "tokens": 9395240960, "loss": 2.3666738510131835, "optimizer_updates": 18920, "effective_batch": 512, "lr": 0.00011903474436780024, "gradient_norm": 0.2826949954032898, "tokens_per_second": 1085694.177662457, "synthetic": false, "world_size": 8} {"step": 35860, "tokens": 9400483840, "loss": 2.365366554260254, "optimizer_updates": 18930, "effective_batch": 512, "lr": 0.00011896075384325613, "gradient_norm": 0.4107462763786316, "tokens_per_second": 1129705.4710175518, "synthetic": false, "world_size": 8} {"step": 35880, "tokens": 9405726720, "loss": 2.364446830749512, "optimizer_updates": 18940, "effective_batch": 512, "lr": 0.00011888675720120674, "gradient_norm": 0.2728526294231415, "tokens_per_second": 1136636.9935628525, "synthetic": false, "world_size": 8} {"step": 35900, "tokens": 9410969600, "loss": 2.363242340087891, "optimizer_updates": 18950, "effective_batch": 512, "lr": 0.00011881275449216956, "gradient_norm": 0.2861751616001129, "tokens_per_second": 1132669.5130125969, "synthetic": false, "world_size": 8} {"step": 35920, "tokens": 9416212480, "loss": 2.365169906616211, "optimizer_updates": 18960, "effective_batch": 512, "lr": 0.00011873874576666624, "gradient_norm": 0.33762380480766296, "tokens_per_second": 1134310.7510463013, "synthetic": false, "world_size": 8} {"step": 35940, "tokens": 9421455360, "loss": 2.3596038818359375, "optimizer_updates": 18970, "effective_batch": 512, "lr": 0.00011866473107522252, "gradient_norm": 0.24710850417613983, "tokens_per_second": 1129509.074004943, "synthetic": false, "world_size": 8} {"step": 35960, "tokens": 9426698240, "loss": 2.366705322265625, "optimizer_updates": 18980, "effective_batch": 512, "lr": 0.00011859071046836822, "gradient_norm": 0.2905915379524231, "tokens_per_second": 1129246.0688626848, "synthetic": false, "world_size": 8} {"step": 35980, "tokens": 9431941120, "loss": 2.3763126373291015, "optimizer_updates": 18990, "effective_batch": 512, "lr": 0.00011851668399663719, "gradient_norm": 0.24736237525939941, "tokens_per_second": 1135151.2186614869, "synthetic": false, "world_size": 8} {"step": 36000, "tokens": 9437184000, "loss": 2.3709625244140624, "optimizer_updates": 19000, "effective_batch": 512, "lr": 0.00011844265171056731, "gradient_norm": 0.3286150395870209, "tokens_per_second": 1130018.9626372303, "synthetic": false, "world_size": 8} {"step": 36020, "tokens": 9442426880, "loss": 2.3475830078125, "optimizer_updates": 19010, "effective_batch": 512, "lr": 0.00011836861366070041, "gradient_norm": 0.2397996485233307, "tokens_per_second": 833438.6065740457, "synthetic": false, "world_size": 8} {"step": 36040, "tokens": 9447669760, "loss": 2.3693572998046877, "optimizer_updates": 19020, "effective_batch": 512, "lr": 0.00011829456989758221, "gradient_norm": 0.2683403491973877, "tokens_per_second": 1123823.7260930566, "synthetic": false, "world_size": 8} {"step": 36060, "tokens": 9452912640, "loss": 2.3778102874755858, "optimizer_updates": 19030, "effective_batch": 512, "lr": 0.00011822052047176243, "gradient_norm": 0.2919800877571106, "tokens_per_second": 1131782.3166863304, "synthetic": false, "world_size": 8} {"step": 36080, "tokens": 9458155520, "loss": 2.3652374267578127, "optimizer_updates": 19040, "effective_batch": 512, "lr": 0.00011814646543379456, "gradient_norm": 0.2521074414253235, "tokens_per_second": 1131178.663610579, "synthetic": false, "world_size": 8} {"step": 36100, "tokens": 9463398400, "loss": 2.357752227783203, "optimizer_updates": 19050, "effective_batch": 512, "lr": 0.000118072404834236, "gradient_norm": 0.3007381856441498, "tokens_per_second": 1127763.4056419681, "synthetic": false, "world_size": 8} {"step": 36120, "tokens": 9468641280, "loss": 2.378508758544922, "optimizer_updates": 19060, "effective_batch": 512, "lr": 0.00011799833872364788, "gradient_norm": 0.2855830490589142, "tokens_per_second": 1133253.6898473622, "synthetic": false, "world_size": 8} {"step": 36140, "tokens": 9473884160, "loss": 2.368669319152832, "optimizer_updates": 19070, "effective_batch": 512, "lr": 0.00011792426715259515, "gradient_norm": 0.2903555631637573, "tokens_per_second": 1128445.2978790728, "synthetic": false, "world_size": 8} {"step": 36160, "tokens": 9479127040, "loss": 2.361592102050781, "optimizer_updates": 19080, "effective_batch": 512, "lr": 0.00011785019017164642, "gradient_norm": 0.28125500679016113, "tokens_per_second": 1138900.564670696, "synthetic": false, "world_size": 8} {"step": 36180, "tokens": 9484369920, "loss": 2.361870002746582, "optimizer_updates": 19090, "effective_batch": 512, "lr": 0.00011777610783137407, "gradient_norm": 0.2609920799732208, "tokens_per_second": 1126524.7056356503, "synthetic": false, "world_size": 8} {"step": 36200, "tokens": 9489612800, "loss": 2.3608013153076173, "optimizer_updates": 19100, "effective_batch": 512, "lr": 0.00011770202018235413, "gradient_norm": 0.2483130246400833, "tokens_per_second": 1131967.2728475677, "synthetic": false, "world_size": 8} {"step": 36220, "tokens": 9494855680, "loss": 2.373168182373047, "optimizer_updates": 19110, "effective_batch": 512, "lr": 0.00011762792727516615, "gradient_norm": 0.2558262050151825, "tokens_per_second": 1135901.7231660546, "synthetic": false, "world_size": 8} {"step": 36240, "tokens": 9500098560, "loss": 2.3802318572998047, "optimizer_updates": 19120, "effective_batch": 512, "lr": 0.00011755382916039338, "gradient_norm": 0.23269537091255188, "tokens_per_second": 1130829.1436414747, "synthetic": false, "world_size": 8} {"step": 36260, "tokens": 9505341440, "loss": 2.3648971557617187, "optimizer_updates": 19130, "effective_batch": 512, "lr": 0.00011747972588862261, "gradient_norm": 0.2556396424770355, "tokens_per_second": 1120393.151005187, "synthetic": false, "world_size": 8} {"step": 36280, "tokens": 9510584320, "loss": 2.3753427505493163, "optimizer_updates": 19140, "effective_batch": 512, "lr": 0.00011740561751044411, "gradient_norm": 0.25322481989860535, "tokens_per_second": 802114.0910445411, "synthetic": false, "world_size": 8} {"step": 36300, "tokens": 9515827200, "loss": 2.3770544052124025, "optimizer_updates": 19150, "effective_batch": 512, "lr": 0.00011733150407645165, "gradient_norm": 0.2866501808166504, "tokens_per_second": 1130616.3692991391, "synthetic": false, "world_size": 8} {"step": 36320, "tokens": 9521070080, "loss": 2.365582275390625, "optimizer_updates": 19160, "effective_batch": 512, "lr": 0.00011725738563724251, "gradient_norm": 0.2483401745557785, "tokens_per_second": 1131498.9318035152, "synthetic": false, "world_size": 8} {"step": 36340, "tokens": 9526312960, "loss": 2.369871711730957, "optimizer_updates": 19170, "effective_batch": 512, "lr": 0.0001171832622434173, "gradient_norm": 0.2927192449569702, "tokens_per_second": 1126347.4213148956, "synthetic": false, "world_size": 8} {"step": 36360, "tokens": 9531555840, "loss": 2.3719364166259767, "optimizer_updates": 19180, "effective_batch": 512, "lr": 0.00011710913394558006, "gradient_norm": 0.26232317090034485, "tokens_per_second": 1123696.6085199218, "synthetic": false, "world_size": 8} {"step": 36380, "tokens": 9536798720, "loss": 2.360958480834961, "optimizer_updates": 19190, "effective_batch": 512, "lr": 0.00011703500079433814, "gradient_norm": 0.2577444314956665, "tokens_per_second": 1122228.136745593, "synthetic": false, "world_size": 8} {"step": 36400, "tokens": 9542041600, "loss": 2.352811813354492, "optimizer_updates": 19200, "effective_batch": 512, "lr": 0.00011696086284030226, "gradient_norm": 0.2600822150707245, "tokens_per_second": 1128550.1079771067, "synthetic": false, "world_size": 8} {"step": 36420, "tokens": 9547284480, "loss": 2.3690120697021486, "optimizer_updates": 19210, "effective_batch": 512, "lr": 0.0001168867201340864, "gradient_norm": 0.2536280155181885, "tokens_per_second": 1036430.6205334653, "synthetic": false, "world_size": 8} {"step": 36440, "tokens": 9552527360, "loss": 2.358871269226074, "optimizer_updates": 19220, "effective_batch": 512, "lr": 0.00011681257272630772, "gradient_norm": 0.2392161339521408, "tokens_per_second": 1120992.7209908725, "synthetic": false, "world_size": 8} {"step": 36460, "tokens": 9557770240, "loss": 2.3614519119262694, "optimizer_updates": 19230, "effective_batch": 512, "lr": 0.00011673842066758671, "gradient_norm": 0.2536605894565582, "tokens_per_second": 1129081.4603004083, "synthetic": false, "world_size": 8} {"step": 36480, "tokens": 9563013120, "loss": 2.3778514862060547, "optimizer_updates": 19240, "effective_batch": 512, "lr": 0.00011666426400854692, "gradient_norm": 0.2850542664527893, "tokens_per_second": 1128752.957689801, "synthetic": false, "world_size": 8} {"step": 36500, "tokens": 9568256000, "loss": 2.3693521499633787, "optimizer_updates": 19250, "effective_batch": 512, "lr": 0.00011659010279981515, "gradient_norm": 0.25014951825141907, "tokens_per_second": 1130536.3933405846, "synthetic": false, "world_size": 8} {"step": 36520, "tokens": 9573498880, "loss": 2.3756216049194334, "optimizer_updates": 19260, "effective_batch": 512, "lr": 0.00011651593709202116, "gradient_norm": 0.2929541766643524, "tokens_per_second": 789904.7205621119, "synthetic": false, "world_size": 8} {"step": 36540, "tokens": 9578741760, "loss": 2.366056442260742, "optimizer_updates": 19270, "effective_batch": 512, "lr": 0.00011644176693579794, "gradient_norm": 0.25164496898651123, "tokens_per_second": 1134338.3364476238, "synthetic": false, "world_size": 8} {"step": 36560, "tokens": 9583984640, "loss": 2.3624073028564454, "optimizer_updates": 19280, "effective_batch": 512, "lr": 0.0001163675923817814, "gradient_norm": 0.3682306706905365, "tokens_per_second": 1134904.5838286728, "synthetic": false, "world_size": 8} {"step": 36580, "tokens": 9589227520, "loss": 2.384337615966797, "optimizer_updates": 19290, "effective_batch": 512, "lr": 0.00011629341348061052, "gradient_norm": 0.2507685422897339, "tokens_per_second": 1130821.8730495903, "synthetic": false, "world_size": 8} {"step": 36600, "tokens": 9594470400, "loss": 2.353371810913086, "optimizer_updates": 19300, "effective_batch": 512, "lr": 0.0001162192302829272, "gradient_norm": 0.26586705446243286, "tokens_per_second": 1137726.8694203037, "synthetic": false, "world_size": 8} {"step": 36620, "tokens": 9599713280, "loss": 2.3730133056640623, "optimizer_updates": 19310, "effective_batch": 512, "lr": 0.00011614504283937634, "gradient_norm": 0.26752540469169617, "tokens_per_second": 1133309.073945136, "synthetic": false, "world_size": 8} {"step": 36640, "tokens": 9604956160, "loss": 2.367720031738281, "optimizer_updates": 19320, "effective_batch": 512, "lr": 0.00011607085120060567, "gradient_norm": 0.26355668902397156, "tokens_per_second": 1126889.8368833736, "synthetic": false, "world_size": 8} {"step": 36660, "tokens": 9610199040, "loss": 2.3738948822021486, "optimizer_updates": 19330, "effective_batch": 512, "lr": 0.00011599665541726582, "gradient_norm": 0.2984245717525482, "tokens_per_second": 1131555.265744968, "synthetic": false, "world_size": 8} {"step": 36680, "tokens": 9615441920, "loss": 2.360527229309082, "optimizer_updates": 19340, "effective_batch": 512, "lr": 0.00011592245554001022, "gradient_norm": 0.294773131608963, "tokens_per_second": 1135509.9069935037, "synthetic": false, "world_size": 8} {"step": 36700, "tokens": 9620684800, "loss": 2.3764604568481444, "optimizer_updates": 19350, "effective_batch": 512, "lr": 0.00011584825161949513, "gradient_norm": 0.342130184173584, "tokens_per_second": 1133584.626346059, "synthetic": false, "world_size": 8} {"step": 36720, "tokens": 9625927680, "loss": 2.356815147399902, "optimizer_updates": 19360, "effective_batch": 512, "lr": 0.00011577404370637956, "gradient_norm": 0.2607582211494446, "tokens_per_second": 1124415.7292970882, "synthetic": false, "world_size": 8} {"step": 36740, "tokens": 9631170560, "loss": 2.357566261291504, "optimizer_updates": 19370, "effective_batch": 512, "lr": 0.00011569983185132519, "gradient_norm": 0.23831312358379364, "tokens_per_second": 1135071.7457987058, "synthetic": false, "world_size": 8} {"step": 36760, "tokens": 9636413440, "loss": 2.3605518341064453, "optimizer_updates": 19380, "effective_batch": 512, "lr": 0.00011562561610499652, "gradient_norm": 0.2666003704071045, "tokens_per_second": 1136676.6673975966, "synthetic": false, "world_size": 8} {"step": 36780, "tokens": 9641656320, "loss": 2.368440628051758, "optimizer_updates": 19390, "effective_batch": 512, "lr": 0.0001155513965180606, "gradient_norm": 0.29344671964645386, "tokens_per_second": 1121982.4316645684, "synthetic": false, "world_size": 8} {"step": 36800, "tokens": 9646899200, "loss": 2.3658470153808593, "optimizer_updates": 19400, "effective_batch": 512, "lr": 0.00011547717314118712, "gradient_norm": 0.2453562468290329, "tokens_per_second": 1131433.1136170712, "synthetic": false, "world_size": 8} {"step": 36820, "tokens": 9652142080, "loss": 2.3754091262817383, "optimizer_updates": 19410, "effective_batch": 512, "lr": 0.0001154029460250484, "gradient_norm": 0.233866348862648, "tokens_per_second": 1138733.7865787272, "synthetic": false, "world_size": 8} {"step": 36840, "tokens": 9657384960, "loss": 2.366464614868164, "optimizer_updates": 19420, "effective_batch": 512, "lr": 0.00011532871522031923, "gradient_norm": 0.29501092433929443, "tokens_per_second": 1136975.0368779341, "synthetic": false, "world_size": 8} {"step": 36860, "tokens": 9662627840, "loss": 2.365494155883789, "optimizer_updates": 19430, "effective_batch": 512, "lr": 0.00011525448077767698, "gradient_norm": 0.27066510915756226, "tokens_per_second": 834815.5715790349, "synthetic": false, "world_size": 8} {"step": 36880, "tokens": 9667870720, "loss": 2.3711015701293947, "optimizer_updates": 19440, "effective_batch": 512, "lr": 0.00011518024274780152, "gradient_norm": 0.2571379542350769, "tokens_per_second": 1142699.8594650442, "synthetic": false, "world_size": 8} {"step": 36900, "tokens": 9673113600, "loss": 2.3751686096191404, "optimizer_updates": 19450, "effective_batch": 512, "lr": 0.00011510600118137513, "gradient_norm": 0.2611970007419586, "tokens_per_second": 1139192.798877328, "synthetic": false, "world_size": 8} {"step": 36920, "tokens": 9678356480, "loss": 2.3708002090454103, "optimizer_updates": 19460, "effective_batch": 512, "lr": 0.00011503175612908251, "gradient_norm": 0.27244848012924194, "tokens_per_second": 1127238.1124431158, "synthetic": false, "world_size": 8} {"step": 36940, "tokens": 9683599360, "loss": 2.369215393066406, "optimizer_updates": 19470, "effective_batch": 512, "lr": 0.00011495750764161076, "gradient_norm": 0.2675636112689972, "tokens_per_second": 1126984.9275566405, "synthetic": false, "world_size": 8} {"step": 36960, "tokens": 9688842240, "loss": 2.369069480895996, "optimizer_updates": 19480, "effective_batch": 512, "lr": 0.00011488325576964928, "gradient_norm": 0.2544878125190735, "tokens_per_second": 1136481.5911609374, "synthetic": false, "world_size": 8} {"step": 36980, "tokens": 9694085120, "loss": 2.3506914138793946, "optimizer_updates": 19490, "effective_batch": 512, "lr": 0.00011480900056388985, "gradient_norm": 0.25087839365005493, "tokens_per_second": 1128885.7908788838, "synthetic": false, "world_size": 8} {"step": 37000, "tokens": 9699328000, "loss": 2.3803661346435545, "optimizer_updates": 19500, "effective_batch": 512, "lr": 0.00011473474207502647, "gradient_norm": 0.2927579879760742, "tokens_per_second": 1131096.1412509233, "synthetic": false, "world_size": 8} {"step": 37020, "tokens": 9704570880, "loss": 2.358236312866211, "optimizer_updates": 19510, "effective_batch": 512, "lr": 0.00011466048035375539, "gradient_norm": 0.25739338994026184, "tokens_per_second": 831052.485621843, "synthetic": false, "world_size": 8} {"step": 37040, "tokens": 9709813760, "loss": 2.3693328857421876, "optimizer_updates": 19520, "effective_batch": 512, "lr": 0.00011458621545077508, "gradient_norm": 0.2364991456270218, "tokens_per_second": 1128764.2556880033, "synthetic": false, "world_size": 8} {"step": 37060, "tokens": 9715056640, "loss": 2.361102294921875, "optimizer_updates": 19530, "effective_batch": 512, "lr": 0.00011451194741678618, "gradient_norm": 0.292048841714859, "tokens_per_second": 1122752.7770287544, "synthetic": false, "world_size": 8} {"step": 37080, "tokens": 9720299520, "loss": 2.372390556335449, "optimizer_updates": 19540, "effective_batch": 512, "lr": 0.00011443767630249147, "gradient_norm": 0.2626434862613678, "tokens_per_second": 1137705.6109766646, "synthetic": false, "world_size": 8} {"step": 37100, "tokens": 9725542400, "loss": 2.3795753479003907, "optimizer_updates": 19550, "effective_batch": 512, "lr": 0.00011436340215859583, "gradient_norm": 0.3015546500682831, "tokens_per_second": 1132854.9962298314, "synthetic": false, "world_size": 8} {"step": 37120, "tokens": 9730785280, "loss": 2.370090103149414, "optimizer_updates": 19560, "effective_batch": 512, "lr": 0.00011428912503580619, "gradient_norm": 0.2779040038585663, "tokens_per_second": 1124770.1179441751, "synthetic": false, "world_size": 8} {"step": 37140, "tokens": 9736028160, "loss": 2.3620107650756834, "optimizer_updates": 19570, "effective_batch": 512, "lr": 0.0001142148449848316, "gradient_norm": 0.24454495310783386, "tokens_per_second": 1130839.1007145406, "synthetic": false, "world_size": 8} {"step": 37160, "tokens": 9741271040, "loss": 2.368125152587891, "optimizer_updates": 19580, "effective_batch": 512, "lr": 0.00011414056205638291, "gradient_norm": 0.2545897364616394, "tokens_per_second": 1121210.935577534, "synthetic": false, "world_size": 8} {"step": 37180, "tokens": 9746513920, "loss": 2.3791528701782227, "optimizer_updates": 19590, "effective_batch": 512, "lr": 0.00011406627630117316, "gradient_norm": 0.23780785501003265, "tokens_per_second": 1128298.4974390736, "synthetic": false, "world_size": 8} {"step": 37200, "tokens": 9751756800, "loss": 2.3709463119506835, "optimizer_updates": 19600, "effective_batch": 512, "lr": 0.00011399198776991721, "gradient_norm": 0.27970755100250244, "tokens_per_second": 1126209.0707722784, "synthetic": false, "world_size": 8} {"step": 37220, "tokens": 9756999680, "loss": 2.3697139739990236, "optimizer_updates": 19610, "effective_batch": 512, "lr": 0.00011391769651333182, "gradient_norm": 0.2628844082355499, "tokens_per_second": 1128174.2466408648, "synthetic": false, "world_size": 8} {"step": 37240, "tokens": 9762242560, "loss": 2.3652877807617188, "optimizer_updates": 19620, "effective_batch": 512, "lr": 0.00011384340258213561, "gradient_norm": 0.27365899085998535, "tokens_per_second": 1130535.3300072637, "synthetic": false, "world_size": 8} {"step": 37260, "tokens": 9767485440, "loss": 2.367873191833496, "optimizer_updates": 19630, "effective_batch": 512, "lr": 0.00011376910602704905, "gradient_norm": 0.31442543864250183, "tokens_per_second": 793340.8674901753, "synthetic": false, "world_size": 8} {"step": 37280, "tokens": 9772728320, "loss": 2.3743783950805666, "optimizer_updates": 19640, "effective_batch": 512, "lr": 0.0001136948068987944, "gradient_norm": 0.2330000102519989, "tokens_per_second": 1141512.821841045, "synthetic": false, "world_size": 8} {"step": 37300, "tokens": 9777971200, "loss": 2.3482574462890624, "optimizer_updates": 19650, "effective_batch": 512, "lr": 0.00011362050524809563, "gradient_norm": 0.24036206305027008, "tokens_per_second": 1137232.7291425199, "synthetic": false, "world_size": 8} {"step": 37320, "tokens": 9783214080, "loss": 2.3760799407958983, "optimizer_updates": 19660, "effective_batch": 512, "lr": 0.00011354620112567846, "gradient_norm": 0.2790513336658478, "tokens_per_second": 1132055.440925606, "synthetic": false, "world_size": 8} {"step": 37340, "tokens": 9788456960, "loss": 2.3746891021728516, "optimizer_updates": 19670, "effective_batch": 512, "lr": 0.00011347189458227035, "gradient_norm": 0.3080624043941498, "tokens_per_second": 1133301.0984999088, "synthetic": false, "world_size": 8} {"step": 37360, "tokens": 9793699840, "loss": 2.37194938659668, "optimizer_updates": 19680, "effective_batch": 512, "lr": 0.00011339758566860031, "gradient_norm": 0.2991059124469757, "tokens_per_second": 1134075.9873856313, "synthetic": false, "world_size": 8} {"step": 37380, "tokens": 9798942720, "loss": 2.3618473052978515, "optimizer_updates": 19690, "effective_batch": 512, "lr": 0.00011332327443539907, "gradient_norm": 0.2476319670677185, "tokens_per_second": 1134381.640765879, "synthetic": false, "world_size": 8} {"step": 37400, "tokens": 9804185600, "loss": 2.357425308227539, "optimizer_updates": 19700, "effective_batch": 512, "lr": 0.00011324896093339889, "gradient_norm": 0.24427591264247894, "tokens_per_second": 1129257.3735631134, "synthetic": false, "world_size": 8} {"step": 37420, "tokens": 9809428480, "loss": 2.3530303955078127, "optimizer_updates": 19710, "effective_batch": 512, "lr": 0.00011317464521333358, "gradient_norm": 0.24442505836486816, "tokens_per_second": 1142102.9760132148, "synthetic": false, "world_size": 8} {"step": 37440, "tokens": 9814671360, "loss": 2.362545394897461, "optimizer_updates": 19720, "effective_batch": 512, "lr": 0.00011310032732593845, "gradient_norm": 0.26248466968536377, "tokens_per_second": 1133103.4944944365, "synthetic": false, "world_size": 8} {"step": 37460, "tokens": 9819914240, "loss": 2.364068794250488, "optimizer_updates": 19730, "effective_batch": 512, "lr": 0.00011302600732195035, "gradient_norm": 0.26680514216423035, "tokens_per_second": 1132798.4106812875, "synthetic": false, "world_size": 8} {"step": 37480, "tokens": 9825157120, "loss": 2.367284965515137, "optimizer_updates": 19740, "effective_batch": 512, "lr": 0.0001129516852521075, "gradient_norm": 0.2953875660896301, "tokens_per_second": 1133115.2088649846, "synthetic": false, "world_size": 8} {"step": 37500, "tokens": 9830400000, "loss": 2.3662765502929686, "optimizer_updates": 19750, "effective_batch": 512, "lr": 0.00011287736116714957, "gradient_norm": 0.2850736379623413, "tokens_per_second": 1128813.6019229244, "synthetic": false, "world_size": 8} {"step": 37520, "tokens": 9835642880, "loss": 2.363043785095215, "optimizer_updates": 19760, "effective_batch": 512, "lr": 0.00011280303511781761, "gradient_norm": 0.2884190082550049, "tokens_per_second": 1120538.7046774346, "synthetic": false, "world_size": 8} {"step": 37540, "tokens": 9840885760, "loss": 2.361563873291016, "optimizer_updates": 19770, "effective_batch": 512, "lr": 0.00011272870715485402, "gradient_norm": 0.28966742753982544, "tokens_per_second": 1119078.2514594037, "synthetic": false, "world_size": 8} {"step": 37560, "tokens": 9846128640, "loss": 2.364139175415039, "optimizer_updates": 19780, "effective_batch": 512, "lr": 0.00011265437732900247, "gradient_norm": 0.2712879478931427, "tokens_per_second": 1116454.3646044862, "synthetic": false, "world_size": 8} {"step": 37580, "tokens": 9851371520, "loss": 2.3580629348754885, "optimizer_updates": 19790, "effective_batch": 512, "lr": 0.00011258004569100791, "gradient_norm": 0.275539755821228, "tokens_per_second": 1119634.6737491847, "synthetic": false, "world_size": 8} {"step": 37600, "tokens": 9856614400, "loss": 2.370446968078613, "optimizer_updates": 19800, "effective_batch": 512, "lr": 0.00011250571229161655, "gradient_norm": 0.273318886756897, "tokens_per_second": 1118730.5410766802, "synthetic": false, "world_size": 8} {"step": 37620, "tokens": 9861857280, "loss": 2.3731693267822265, "optimizer_updates": 19810, "effective_batch": 512, "lr": 0.00011243137718157582, "gradient_norm": 0.24496084451675415, "tokens_per_second": 1122631.8111599584, "synthetic": false, "world_size": 8} {"step": 37640, "tokens": 9867100160, "loss": 2.360727310180664, "optimizer_updates": 19820, "effective_batch": 512, "lr": 0.00011235704041163421, "gradient_norm": 0.26861855387687683, "tokens_per_second": 1127205.1138757344, "synthetic": false, "world_size": 8} {"step": 37660, "tokens": 9872343040, "loss": 2.3539173126220705, "optimizer_updates": 19830, "effective_batch": 512, "lr": 0.00011228270203254151, "gradient_norm": 0.26598525047302246, "tokens_per_second": 1127561.2334355789, "synthetic": false, "world_size": 8} {"step": 37680, "tokens": 9877585920, "loss": 2.3758920669555663, "optimizer_updates": 19840, "effective_batch": 512, "lr": 0.00011220836209504846, "gradient_norm": 0.25434401631355286, "tokens_per_second": 1114542.9045080706, "synthetic": false, "world_size": 8} {"step": 37700, "tokens": 9882828800, "loss": 2.363572120666504, "optimizer_updates": 19850, "effective_batch": 512, "lr": 0.00011213402064990696, "gradient_norm": 0.2802751064300537, "tokens_per_second": 1121719.6043483606, "synthetic": false, "world_size": 8} {"step": 37720, "tokens": 9888071680, "loss": 2.3698116302490235, "optimizer_updates": 19860, "effective_batch": 512, "lr": 0.00011205967774786989, "gradient_norm": 0.2608720362186432, "tokens_per_second": 1126670.9123939013, "synthetic": false, "world_size": 8} {"step": 37740, "tokens": 9893314560, "loss": 2.3788238525390626, "optimizer_updates": 19870, "effective_batch": 512, "lr": 0.00011198533343969113, "gradient_norm": 0.303178071975708, "tokens_per_second": 1122401.916464879, "synthetic": false, "world_size": 8} {"step": 37760, "tokens": 9898557440, "loss": 2.359814262390137, "optimizer_updates": 19880, "effective_batch": 512, "lr": 0.00011191098777612556, "gradient_norm": 0.34337756037712097, "tokens_per_second": 1123027.2453187716, "synthetic": false, "world_size": 8} {"step": 37780, "tokens": 9903800320, "loss": 2.3646112442016602, "optimizer_updates": 19890, "effective_batch": 512, "lr": 0.0001118366408079289, "gradient_norm": 0.269414484500885, "tokens_per_second": 1143236.8627900847, "synthetic": false, "world_size": 8} {"step": 37800, "tokens": 9909043200, "loss": 2.3691274642944338, "optimizer_updates": 19900, "effective_batch": 512, "lr": 0.00011176229258585784, "gradient_norm": 0.25495144724845886, "tokens_per_second": 1024832.1777414375, "synthetic": false, "world_size": 8} {"step": 37820, "tokens": 9914286080, "loss": 2.3670230865478517, "optimizer_updates": 19910, "effective_batch": 512, "lr": 0.00011168794316066991, "gradient_norm": 0.28762638568878174, "tokens_per_second": 1022263.2235079209, "synthetic": false, "world_size": 8} {"step": 37840, "tokens": 9919528960, "loss": 2.3690420150756837, "optimizer_updates": 19920, "effective_batch": 512, "lr": 0.00011161359258312343, "gradient_norm": 0.3115898370742798, "tokens_per_second": 1140169.5625529632, "synthetic": false, "world_size": 8} {"step": 37860, "tokens": 9924771840, "loss": 2.3724884033203124, "optimizer_updates": 19930, "effective_batch": 512, "lr": 0.00011153924090397754, "gradient_norm": 0.271064817905426, "tokens_per_second": 794787.3952977071, "synthetic": false, "world_size": 8} {"step": 37880, "tokens": 9930014720, "loss": 2.380668830871582, "optimizer_updates": 19940, "effective_batch": 512, "lr": 0.00011146488817399213, "gradient_norm": 0.2814572751522064, "tokens_per_second": 1125551.0266567525, "synthetic": false, "world_size": 8} {"step": 37900, "tokens": 9935257600, "loss": 2.3741172790527343, "optimizer_updates": 19950, "effective_batch": 512, "lr": 0.0001113905344439278, "gradient_norm": 0.24645574390888214, "tokens_per_second": 1121579.8996818594, "synthetic": false, "world_size": 8} {"step": 37920, "tokens": 9940500480, "loss": 2.364615249633789, "optimizer_updates": 19960, "effective_batch": 512, "lr": 0.00011131617976454578, "gradient_norm": 0.2919613718986511, "tokens_per_second": 1118665.7821949094, "synthetic": false, "world_size": 8} {"step": 37940, "tokens": 9945743360, "loss": 2.383283805847168, "optimizer_updates": 19970, "effective_batch": 512, "lr": 0.00011124182418660808, "gradient_norm": 0.25676774978637695, "tokens_per_second": 1118508.55967578, "synthetic": false, "world_size": 8} {"step": 37960, "tokens": 9950986240, "loss": 2.3699420928955077, "optimizer_updates": 19980, "effective_batch": 512, "lr": 0.00011116746776087717, "gradient_norm": 0.24178624153137207, "tokens_per_second": 1113998.3049309007, "synthetic": false, "world_size": 8} {"step": 37980, "tokens": 9956229120, "loss": 2.3808177947998046, "optimizer_updates": 19990, "effective_batch": 512, "lr": 0.0001110931105381162, "gradient_norm": 0.2557596266269684, "tokens_per_second": 1113913.716741006, "synthetic": false, "world_size": 8} {"step": 38000, "tokens": 9961472000, "loss": 2.365030288696289, "optimizer_updates": 20000, "effective_batch": 512, "lr": 0.00011101875256908885, "gradient_norm": 0.26975417137145996, "tokens_per_second": 1128441.8237231688, "synthetic": false, "world_size": 8} {"step": 38020, "tokens": 9966714880, "loss": 2.367335319519043, "optimizer_updates": 20010, "effective_batch": 512, "lr": 0.00011094439390455924, "gradient_norm": 0.2561686336994171, "tokens_per_second": 829237.1708022419, "synthetic": false, "world_size": 8} {"step": 38040, "tokens": 9971957760, "loss": 2.384019660949707, "optimizer_updates": 20020, "effective_batch": 512, "lr": 0.00011087003459529206, "gradient_norm": 0.23606404662132263, "tokens_per_second": 1125151.5205504647, "synthetic": false, "world_size": 8} {"step": 38060, "tokens": 9977200640, "loss": 2.362149238586426, "optimizer_updates": 20030, "effective_batch": 512, "lr": 0.00011079567469205243, "gradient_norm": 0.2515629529953003, "tokens_per_second": 1126686.9194290699, "synthetic": false, "world_size": 8} {"step": 38080, "tokens": 9982443520, "loss": 2.365857696533203, "optimizer_updates": 20040, "effective_batch": 512, "lr": 0.00011072131424560579, "gradient_norm": 0.2687815725803375, "tokens_per_second": 1130895.096238847, "synthetic": false, "world_size": 8} {"step": 38100, "tokens": 9987686400, "loss": 2.3604944229125975, "optimizer_updates": 20050, "effective_batch": 512, "lr": 0.00011064695330671803, "gradient_norm": 0.31071674823760986, "tokens_per_second": 1126338.2518971164, "synthetic": false, "world_size": 8} {"step": 38120, "tokens": 9992929280, "loss": 2.370697021484375, "optimizer_updates": 20060, "effective_batch": 512, "lr": 0.00011057259192615535, "gradient_norm": 0.25202661752700806, "tokens_per_second": 1125905.4587387363, "synthetic": false, "world_size": 8} {"step": 38140, "tokens": 9998172160, "loss": 2.3662082672119142, "optimizer_updates": 20070, "effective_batch": 512, "lr": 0.00011049823015468424, "gradient_norm": 0.28340667486190796, "tokens_per_second": 1133228.8513349474, "synthetic": false, "world_size": 8} {"step": 38160, "tokens": 10003415040, "loss": 2.3644634246826173, "optimizer_updates": 20080, "effective_batch": 512, "lr": 0.00011042386804307147, "gradient_norm": 0.23719345033168793, "tokens_per_second": 1127149.812258457, "synthetic": false, "world_size": 8} {"step": 38180, "tokens": 10008657920, "loss": 2.364754486083984, "optimizer_updates": 20090, "effective_batch": 512, "lr": 0.00011034950564208408, "gradient_norm": 0.2735931873321533, "tokens_per_second": 1131260.6172708329, "synthetic": false, "world_size": 8} {"step": 38200, "tokens": 10013900800, "loss": 2.3697444915771486, "optimizer_updates": 20100, "effective_batch": 512, "lr": 0.00011027514300248921, "gradient_norm": 0.25128260254859924, "tokens_per_second": 1131168.4850269123, "synthetic": false, "world_size": 8} {"step": 38220, "tokens": 10019143680, "loss": 2.370011901855469, "optimizer_updates": 20110, "effective_batch": 512, "lr": 0.00011020078017505428, "gradient_norm": 0.2720721364021301, "tokens_per_second": 1121660.5367518908, "synthetic": false, "world_size": 8} {"step": 38240, "tokens": 10024386560, "loss": 2.373256874084473, "optimizer_updates": 20120, "effective_batch": 512, "lr": 0.00011012641721054676, "gradient_norm": 0.30830952525138855, "tokens_per_second": 1136052.1126322781, "synthetic": false, "world_size": 8} {"step": 38260, "tokens": 10029629440, "loss": 2.3785776138305663, "optimizer_updates": 20130, "effective_batch": 512, "lr": 0.0001100520541597342, "gradient_norm": 0.2516096532344818, "tokens_per_second": 1134759.3437938693, "synthetic": false, "world_size": 8} {"step": 38280, "tokens": 10034872320, "loss": 2.37000732421875, "optimizer_updates": 20140, "effective_batch": 512, "lr": 0.00010997769107338429, "gradient_norm": 0.2915671467781067, "tokens_per_second": 1122781.482381781, "synthetic": false, "world_size": 8} {"step": 38300, "tokens": 10040115200, "loss": 2.3589809417724608, "optimizer_updates": 20150, "effective_batch": 512, "lr": 0.00010990332800226468, "gradient_norm": 0.26175203919410706, "tokens_per_second": 1130768.6523405476, "synthetic": false, "world_size": 8} {"step": 38320, "tokens": 10045358080, "loss": 2.3777584075927733, "optimizer_updates": 20160, "effective_batch": 512, "lr": 0.00010982896499714303, "gradient_norm": 0.26581957936286926, "tokens_per_second": 1122611.1738794958, "synthetic": false, "world_size": 8} {"step": 38340, "tokens": 10050600960, "loss": 2.375206184387207, "optimizer_updates": 20170, "effective_batch": 512, "lr": 0.00010975460210878694, "gradient_norm": 0.3032861053943634, "tokens_per_second": 1141114.194340142, "synthetic": false, "world_size": 8} {"step": 38360, "tokens": 10055843840, "loss": 2.371210479736328, "optimizer_updates": 20180, "effective_batch": 512, "lr": 0.00010968023938796395, "gradient_norm": 0.27555736899375916, "tokens_per_second": 1134500.0203523682, "synthetic": false, "world_size": 8} {"step": 38380, "tokens": 10061086720, "loss": 2.371189498901367, "optimizer_updates": 20190, "effective_batch": 512, "lr": 0.0001096058768854415, "gradient_norm": 0.25799453258514404, "tokens_per_second": 1134795.6650432956, "synthetic": false, "world_size": 8} {"step": 38400, "tokens": 10066329600, "loss": 2.363150978088379, "optimizer_updates": 20200, "effective_batch": 512, "lr": 0.00010953151465198684, "gradient_norm": 0.2809860110282898, "tokens_per_second": 1130555.3388485257, "synthetic": false, "world_size": 8} {"step": 38420, "tokens": 10071572480, "loss": 2.356416702270508, "optimizer_updates": 20210, "effective_batch": 512, "lr": 0.00010945715273836706, "gradient_norm": 0.257229208946228, "tokens_per_second": 1126029.835681314, "synthetic": false, "world_size": 8} {"step": 38440, "tokens": 10076815360, "loss": 2.380143737792969, "optimizer_updates": 20220, "effective_batch": 512, "lr": 0.000109382791195349, "gradient_norm": 0.30891653895378113, "tokens_per_second": 1125129.4907944365, "synthetic": false, "world_size": 8} {"step": 38460, "tokens": 10082058240, "loss": 2.373482322692871, "optimizer_updates": 20230, "effective_batch": 512, "lr": 0.0001093084300736993, "gradient_norm": 0.2637783885002136, "tokens_per_second": 1130867.7119839082, "synthetic": false, "world_size": 8} {"step": 38480, "tokens": 10087301120, "loss": 2.3672613143920898, "optimizer_updates": 20240, "effective_batch": 512, "lr": 0.00010923406942418427, "gradient_norm": 0.257565975189209, "tokens_per_second": 1133045.651949382, "synthetic": false, "world_size": 8} {"step": 38500, "tokens": 10092544000, "loss": 2.385692596435547, "optimizer_updates": 20250, "effective_batch": 512, "lr": 0.00010915970929756995, "gradient_norm": 0.24879232048988342, "tokens_per_second": 1020417.5157946651, "synthetic": false, "world_size": 8} {"step": 38520, "tokens": 10097786880, "loss": 2.3653974533081055, "optimizer_updates": 20260, "effective_batch": 512, "lr": 0.00010908534974462195, "gradient_norm": 0.2899490296840668, "tokens_per_second": 1135593.5636011695, "synthetic": false, "world_size": 8} {"step": 38540, "tokens": 10103029760, "loss": 2.363572692871094, "optimizer_updates": 20270, "effective_batch": 512, "lr": 0.00010901099081610555, "gradient_norm": 0.2641279995441437, "tokens_per_second": 1030664.8331952705, "synthetic": false, "world_size": 8} {"step": 38560, "tokens": 10108272640, "loss": 2.3725908279418944, "optimizer_updates": 20280, "effective_batch": 512, "lr": 0.00010893663256278559, "gradient_norm": 0.2657594084739685, "tokens_per_second": 1138338.577270077, "synthetic": false, "world_size": 8} {"step": 38580, "tokens": 10113515520, "loss": 2.3652725219726562, "optimizer_updates": 20290, "effective_batch": 512, "lr": 0.0001088622750354264, "gradient_norm": 0.2523190975189209, "tokens_per_second": 1130816.6181716486, "synthetic": false, "world_size": 8} {"step": 38600, "tokens": 10118758400, "loss": 2.3667924880981444, "optimizer_updates": 20300, "effective_batch": 512, "lr": 0.00010878791828479186, "gradient_norm": 0.23611369729042053, "tokens_per_second": 1133568.583754455, "synthetic": false, "world_size": 8} {"step": 38620, "tokens": 10124001280, "loss": 2.3732986450195312, "optimizer_updates": 20310, "effective_batch": 512, "lr": 0.00010871356236164532, "gradient_norm": 0.24732820689678192, "tokens_per_second": 1124684.9946409818, "synthetic": false, "world_size": 8} {"step": 38640, "tokens": 10129244160, "loss": 2.3561397552490235, "optimizer_updates": 20320, "effective_batch": 512, "lr": 0.00010863920731674957, "gradient_norm": 0.26143208146095276, "tokens_per_second": 1124968.9631889635, "synthetic": false, "world_size": 8} {"step": 38660, "tokens": 10134487040, "loss": 2.3670494079589846, "optimizer_updates": 20330, "effective_batch": 512, "lr": 0.00010856485320086677, "gradient_norm": 0.2542332410812378, "tokens_per_second": 1128436.8982006612, "synthetic": false, "world_size": 8} {"step": 38680, "tokens": 10139729920, "loss": 2.3698728561401365, "optimizer_updates": 20340, "effective_batch": 512, "lr": 0.00010849050006475847, "gradient_norm": 0.3195083737373352, "tokens_per_second": 1123803.0310026275, "synthetic": false, "world_size": 8} {"step": 38700, "tokens": 10144972800, "loss": 2.37072868347168, "optimizer_updates": 20350, "effective_batch": 512, "lr": 0.00010841614795918554, "gradient_norm": 0.27383196353912354, "tokens_per_second": 1135758.8520458273, "synthetic": false, "world_size": 8} {"step": 38720, "tokens": 10150215680, "loss": 2.364552307128906, "optimizer_updates": 20360, "effective_batch": 512, "lr": 0.00010834179693490819, "gradient_norm": 0.2496119737625122, "tokens_per_second": 753165.2415160404, "synthetic": false, "world_size": 8} {"step": 38740, "tokens": 10155458560, "loss": 2.3715309143066405, "optimizer_updates": 20370, "effective_batch": 512, "lr": 0.00010826744704268579, "gradient_norm": 0.27309006452560425, "tokens_per_second": 1133193.5950610898, "synthetic": false, "world_size": 8} {"step": 38760, "tokens": 10160701440, "loss": 2.3716087341308594, "optimizer_updates": 20380, "effective_batch": 512, "lr": 0.00010819309833327703, "gradient_norm": 0.29110100865364075, "tokens_per_second": 1130972.7671443676, "synthetic": false, "world_size": 8} {"step": 38780, "tokens": 10165944320, "loss": 2.365732955932617, "optimizer_updates": 20390, "effective_batch": 512, "lr": 0.00010811875085743975, "gradient_norm": 0.26663562655448914, "tokens_per_second": 1129738.3301106254, "synthetic": false, "world_size": 8} {"step": 38800, "tokens": 10171187200, "loss": 2.3770204544067384, "optimizer_updates": 20400, "effective_batch": 512, "lr": 0.000108044404665931, "gradient_norm": 0.24885064363479614, "tokens_per_second": 1125459.0790960372, "synthetic": false, "world_size": 8} {"step": 38820, "tokens": 10176430080, "loss": 2.3697908401489256, "optimizer_updates": 20410, "effective_batch": 512, "lr": 0.00010797005980950687, "gradient_norm": 0.24923349916934967, "tokens_per_second": 1133333.200625555, "synthetic": false, "world_size": 8} {"step": 38840, "tokens": 10181672960, "loss": 2.3625839233398436, "optimizer_updates": 20420, "effective_batch": 512, "lr": 0.0001078957163389226, "gradient_norm": 0.24264107644557953, "tokens_per_second": 1137703.5668141579, "synthetic": false, "world_size": 8} {"step": 38860, "tokens": 10186915840, "loss": 2.3608537673950196, "optimizer_updates": 20430, "effective_batch": 512, "lr": 0.00010782137430493246, "gradient_norm": 0.23993384838104248, "tokens_per_second": 1131418.2659841774, "synthetic": false, "world_size": 8} {"step": 38880, "tokens": 10192158720, "loss": 2.3677993774414063, "optimizer_updates": 20440, "effective_batch": 512, "lr": 0.00010774703375828978, "gradient_norm": 0.31400275230407715, "tokens_per_second": 1133587.082475888, "synthetic": false, "world_size": 8} {"step": 38900, "tokens": 10197401600, "loss": 2.3689548492431642, "optimizer_updates": 20450, "effective_batch": 512, "lr": 0.00010767269474974677, "gradient_norm": 0.28061264753341675, "tokens_per_second": 1126660.7508749706, "synthetic": false, "world_size": 8} {"step": 38920, "tokens": 10202644480, "loss": 2.3804288864135743, "optimizer_updates": 20460, "effective_batch": 512, "lr": 0.0001075983573300547, "gradient_norm": 0.2862382233142853, "tokens_per_second": 1130773.9747992833, "synthetic": false, "world_size": 8} {"step": 38940, "tokens": 10207887360, "loss": 2.361102294921875, "optimizer_updates": 20470, "effective_batch": 512, "lr": 0.00010752402154996373, "gradient_norm": 0.2548040747642517, "tokens_per_second": 1133498.2475086988, "synthetic": false, "world_size": 8} {"step": 38960, "tokens": 10213130240, "loss": 2.3605432510375977, "optimizer_updates": 20480, "effective_batch": 512, "lr": 0.00010744968746022286, "gradient_norm": 0.2741275727748871, "tokens_per_second": 1127494.9089748312, "synthetic": false, "world_size": 8} {"step": 38980, "tokens": 10218373120, "loss": 2.3702472686767577, "optimizer_updates": 20490, "effective_batch": 512, "lr": 0.00010737535511157996, "gradient_norm": 0.29752323031425476, "tokens_per_second": 1132891.8772049265, "synthetic": false, "world_size": 8} {"step": 39000, "tokens": 10223616000, "loss": 2.3714370727539062, "optimizer_updates": 20500, "effective_batch": 512, "lr": 0.00010730102455478175, "gradient_norm": 0.2517430782318115, "tokens_per_second": 1126683.8931265674, "synthetic": false, "world_size": 8} {"step": 39020, "tokens": 10228858880, "loss": 2.3758081436157226, "optimizer_updates": 20510, "effective_batch": 512, "lr": 0.00010722669584057367, "gradient_norm": 0.25994113087654114, "tokens_per_second": 834788.6399663156, "synthetic": false, "world_size": 8} {"step": 39040, "tokens": 10234101760, "loss": 2.375930595397949, "optimizer_updates": 20520, "effective_batch": 512, "lr": 0.0001071523690196999, "gradient_norm": 0.30347928404808044, "tokens_per_second": 1132434.8841321429, "synthetic": false, "world_size": 8} {"step": 39060, "tokens": 10239344640, "loss": 2.369440460205078, "optimizer_updates": 20530, "effective_batch": 512, "lr": 0.00010707804414290337, "gradient_norm": 0.2492474466562271, "tokens_per_second": 1122445.2439727683, "synthetic": false, "world_size": 8} {"step": 39080, "tokens": 10244587520, "loss": 2.3616260528564452, "optimizer_updates": 20540, "effective_batch": 512, "lr": 0.00010700372126092565, "gradient_norm": 0.25129014253616333, "tokens_per_second": 1135649.5429164085, "synthetic": false, "world_size": 8} {"step": 39100, "tokens": 10249830400, "loss": 2.3695430755615234, "optimizer_updates": 20550, "effective_batch": 512, "lr": 0.00010692940042450697, "gradient_norm": 0.25507497787475586, "tokens_per_second": 1130799.2448541743, "synthetic": false, "world_size": 8} {"step": 39120, "tokens": 10255073280, "loss": 2.363670539855957, "optimizer_updates": 20560, "effective_batch": 512, "lr": 0.00010685508168438615, "gradient_norm": 0.2515936493873596, "tokens_per_second": 1127248.2492235445, "synthetic": false, "world_size": 8} {"step": 39140, "tokens": 10260316160, "loss": 2.3641183853149412, "optimizer_updates": 20570, "effective_batch": 512, "lr": 0.00010678076509130058, "gradient_norm": 0.2748219668865204, "tokens_per_second": 1135085.8008620131, "synthetic": false, "world_size": 8} {"step": 39160, "tokens": 10265559040, "loss": 2.375415802001953, "optimizer_updates": 20580, "effective_batch": 512, "lr": 0.00010670645069598619, "gradient_norm": 0.26035481691360474, "tokens_per_second": 1127972.2372892832, "synthetic": false, "world_size": 8} {"step": 39180, "tokens": 10270801920, "loss": 2.3743566513061523, "optimizer_updates": 20590, "effective_batch": 512, "lr": 0.00010663213854917741, "gradient_norm": 0.35170871019363403, "tokens_per_second": 1138380.099930251, "synthetic": false, "world_size": 8} {"step": 39200, "tokens": 10276044800, "loss": 2.360439491271973, "optimizer_updates": 20600, "effective_batch": 512, "lr": 0.00010655782870160715, "gradient_norm": 0.3108239769935608, "tokens_per_second": 1126311.291112496, "synthetic": false, "world_size": 8} {"step": 39220, "tokens": 10281287680, "loss": 2.363425064086914, "optimizer_updates": 20610, "effective_batch": 512, "lr": 0.00010648352120400669, "gradient_norm": 0.32935044169425964, "tokens_per_second": 1132367.2985608988, "synthetic": false, "world_size": 8} {"step": 39240, "tokens": 10286530560, "loss": 2.370417022705078, "optimizer_updates": 20620, "effective_batch": 512, "lr": 0.00010640921610710577, "gradient_norm": 0.23519426584243774, "tokens_per_second": 817311.3254458588, "synthetic": false, "world_size": 8} {"step": 39260, "tokens": 10291773440, "loss": 2.3708051681518554, "optimizer_updates": 20630, "effective_batch": 512, "lr": 0.00010633491346163245, "gradient_norm": 0.26945117115974426, "tokens_per_second": 1134477.2032214045, "synthetic": false, "world_size": 8} {"step": 39280, "tokens": 10297016320, "loss": 2.3613183975219725, "optimizer_updates": 20640, "effective_batch": 512, "lr": 0.00010626061331831317, "gradient_norm": 0.26263076066970825, "tokens_per_second": 1132904.269461317, "synthetic": false, "world_size": 8} {"step": 39300, "tokens": 10302259200, "loss": 2.379159164428711, "optimizer_updates": 20650, "effective_batch": 512, "lr": 0.00010618631572787259, "gradient_norm": 0.24957707524299622, "tokens_per_second": 1129353.8939934894, "synthetic": false, "world_size": 8} {"step": 39320, "tokens": 10307502080, "loss": 2.374357223510742, "optimizer_updates": 20660, "effective_batch": 512, "lr": 0.00010611202074103368, "gradient_norm": 0.2605741322040558, "tokens_per_second": 1130106.516653664, "synthetic": false, "world_size": 8} {"step": 39340, "tokens": 10312744960, "loss": 2.362558364868164, "optimizer_updates": 20670, "effective_batch": 512, "lr": 0.00010603772840851763, "gradient_norm": 0.29207608103752136, "tokens_per_second": 1133601.431674132, "synthetic": false, "world_size": 8} {"step": 39360, "tokens": 10317987840, "loss": 2.3745353698730467, "optimizer_updates": 20680, "effective_batch": 512, "lr": 0.00010596343878104378, "gradient_norm": 0.25130534172058105, "tokens_per_second": 1135133.6076988329, "synthetic": false, "world_size": 8} {"step": 39380, "tokens": 10323230720, "loss": 2.3509136199951173, "optimizer_updates": 20690, "effective_batch": 512, "lr": 0.00010588915190932967, "gradient_norm": 0.24529002606868744, "tokens_per_second": 1132445.330382191, "synthetic": false, "world_size": 8} {"step": 39400, "tokens": 10328473600, "loss": 2.3634653091430664, "optimizer_updates": 20700, "effective_batch": 512, "lr": 0.0001058148678440909, "gradient_norm": 0.2585007846355438, "tokens_per_second": 1134560.6303841237, "synthetic": false, "world_size": 8} {"step": 39420, "tokens": 10333716480, "loss": 2.370578956604004, "optimizer_updates": 20710, "effective_batch": 512, "lr": 0.00010574058663604123, "gradient_norm": 0.2468833178281784, "tokens_per_second": 1126603.5543281205, "synthetic": false, "world_size": 8} {"step": 39440, "tokens": 10338959360, "loss": 2.368060302734375, "optimizer_updates": 20720, "effective_batch": 512, "lr": 0.00010566630833589241, "gradient_norm": 0.23626506328582764, "tokens_per_second": 1139112.5967339121, "synthetic": false, "world_size": 8} {"step": 39460, "tokens": 10344202240, "loss": 2.370127487182617, "optimizer_updates": 20730, "effective_batch": 512, "lr": 0.00010559203299435423, "gradient_norm": 0.24253840744495392, "tokens_per_second": 1135143.819684521, "synthetic": false, "world_size": 8} {"step": 39480, "tokens": 10349445120, "loss": 2.377802276611328, "optimizer_updates": 20740, "effective_batch": 512, "lr": 0.00010551776066213444, "gradient_norm": 0.23655225336551666, "tokens_per_second": 1143621.1592102954, "synthetic": false, "world_size": 8} {"step": 39500, "tokens": 10354688000, "loss": 2.372045135498047, "optimizer_updates": 20750, "effective_batch": 512, "lr": 0.00010544349138993879, "gradient_norm": 0.2566276788711548, "tokens_per_second": 1131007.410086146, "synthetic": false, "world_size": 8} {"step": 39520, "tokens": 10359930880, "loss": 2.3662500381469727, "optimizer_updates": 20760, "effective_batch": 512, "lr": 0.00010536922522847086, "gradient_norm": 0.2524525225162506, "tokens_per_second": 1139693.430058251, "synthetic": false, "world_size": 8} {"step": 39540, "tokens": 10365173760, "loss": 2.3705806732177734, "optimizer_updates": 20770, "effective_batch": 512, "lr": 0.00010529496222843214, "gradient_norm": 0.24960215389728546, "tokens_per_second": 1129374.5587648158, "synthetic": false, "world_size": 8} {"step": 39560, "tokens": 10370416640, "loss": 2.3652992248535156, "optimizer_updates": 20780, "effective_batch": 512, "lr": 0.00010522070244052201, "gradient_norm": 0.25415053963661194, "tokens_per_second": 1135797.6196430482, "synthetic": false, "world_size": 8} {"step": 39580, "tokens": 10375659520, "loss": 2.375071334838867, "optimizer_updates": 20790, "effective_batch": 512, "lr": 0.00010514644591543758, "gradient_norm": 0.2672865688800812, "tokens_per_second": 1140651.6848336775, "synthetic": false, "world_size": 8} {"step": 39600, "tokens": 10380902400, "loss": 2.365983581542969, "optimizer_updates": 20800, "effective_batch": 512, "lr": 0.00010507219270387377, "gradient_norm": 0.31036967039108276, "tokens_per_second": 1131844.915953635, "synthetic": false, "world_size": 8} {"step": 39620, "tokens": 10386145280, "loss": 2.375738525390625, "optimizer_updates": 20810, "effective_batch": 512, "lr": 0.00010499794285652327, "gradient_norm": 0.282857209444046, "tokens_per_second": 1139691.8189511679, "synthetic": false, "world_size": 8} {"step": 39640, "tokens": 10391388160, "loss": 2.369830513000488, "optimizer_updates": 20820, "effective_batch": 512, "lr": 0.0001049236964240764, "gradient_norm": 0.2353392392396927, "tokens_per_second": 1136779.9945501955, "synthetic": false, "world_size": 8} {"step": 39660, "tokens": 10396631040, "loss": 2.342733383178711, "optimizer_updates": 20830, "effective_batch": 512, "lr": 0.00010484945345722122, "gradient_norm": 0.34339216351509094, "tokens_per_second": 805171.4563173245, "synthetic": false, "world_size": 8} {"step": 39680, "tokens": 10401873920, "loss": 2.3770782470703127, "optimizer_updates": 20840, "effective_batch": 512, "lr": 0.00010477521400664339, "gradient_norm": 0.269986093044281, "tokens_per_second": 1139680.0633516405, "synthetic": false, "world_size": 8} {"step": 39700, "tokens": 10407116800, "loss": 2.371202087402344, "optimizer_updates": 20850, "effective_batch": 512, "lr": 0.00010470097812302615, "gradient_norm": 0.25579044222831726, "tokens_per_second": 1137557.8195517058, "synthetic": false, "world_size": 8} {"step": 39720, "tokens": 10412359680, "loss": 2.360932540893555, "optimizer_updates": 20860, "effective_batch": 512, "lr": 0.00010462674585705033, "gradient_norm": 0.2559202015399933, "tokens_per_second": 1131626.8302122776, "synthetic": false, "world_size": 8} {"step": 39740, "tokens": 10417602560, "loss": 2.350109100341797, "optimizer_updates": 20870, "effective_batch": 512, "lr": 0.00010455251725939429, "gradient_norm": 0.28461840748786926, "tokens_per_second": 1134298.6941416524, "synthetic": false, "world_size": 8} {"step": 39760, "tokens": 10422845440, "loss": 2.373348617553711, "optimizer_updates": 20880, "effective_batch": 512, "lr": 0.00010447829238073388, "gradient_norm": 0.24596086144447327, "tokens_per_second": 1137284.2933826207, "synthetic": false, "world_size": 8} {"step": 39780, "tokens": 10428088320, "loss": 2.3642091751098633, "optimizer_updates": 20890, "effective_batch": 512, "lr": 0.0001044040712717424, "gradient_norm": 0.2510587275028229, "tokens_per_second": 1129973.7845195925, "synthetic": false, "world_size": 8} {"step": 39800, "tokens": 10433331200, "loss": 2.362164115905762, "optimizer_updates": 20900, "effective_batch": 512, "lr": 0.00010432985398309063, "gradient_norm": 0.26478809118270874, "tokens_per_second": 1145311.534401363, "synthetic": false, "world_size": 8} {"step": 39820, "tokens": 10438574080, "loss": 2.3627395629882812, "optimizer_updates": 20910, "effective_batch": 512, "lr": 0.0001042556405654467, "gradient_norm": 0.26706910133361816, "tokens_per_second": 1134317.9789467321, "synthetic": false, "world_size": 8} {"step": 39840, "tokens": 10443816960, "loss": 2.364583396911621, "optimizer_updates": 20920, "effective_batch": 512, "lr": 0.00010418143106947606, "gradient_norm": 0.2581913471221924, "tokens_per_second": 1138459.0580712133, "synthetic": false, "world_size": 8} {"step": 39860, "tokens": 10449059840, "loss": 2.378282928466797, "optimizer_updates": 20930, "effective_batch": 512, "lr": 0.00010410722554584155, "gradient_norm": 0.3251381814479828, "tokens_per_second": 1140934.0125235443, "synthetic": false, "world_size": 8} {"step": 39880, "tokens": 10454302720, "loss": 2.367229461669922, "optimizer_updates": 20940, "effective_batch": 512, "lr": 0.00010403302404520325, "gradient_norm": 0.2592490017414093, "tokens_per_second": 1134667.1596402584, "synthetic": false, "world_size": 8} {"step": 39900, "tokens": 10459545600, "loss": 2.3646371841430662, "optimizer_updates": 20950, "effective_batch": 512, "lr": 0.00010395882661821852, "gradient_norm": 0.25142398476600647, "tokens_per_second": 1142543.4485122706, "synthetic": false, "world_size": 8} {"step": 39920, "tokens": 10464788480, "loss": 2.357777786254883, "optimizer_updates": 20960, "effective_batch": 512, "lr": 0.00010388463331554193, "gradient_norm": 0.26840662956237793, "tokens_per_second": 1132598.028725315, "synthetic": false, "world_size": 8} {"step": 39940, "tokens": 10470031360, "loss": 2.360274314880371, "optimizer_updates": 20970, "effective_batch": 512, "lr": 0.00010381044418782524, "gradient_norm": 0.28674840927124023, "tokens_per_second": 1129505.2226798183, "synthetic": false, "world_size": 8} {"step": 39960, "tokens": 10475274240, "loss": 2.3725559234619142, "optimizer_updates": 20980, "effective_batch": 512, "lr": 0.00010373625928571737, "gradient_norm": 0.2717914879322052, "tokens_per_second": 1129660.0295323413, "synthetic": false, "world_size": 8} {"step": 39980, "tokens": 10480517120, "loss": 2.373524856567383, "optimizer_updates": 20990, "effective_batch": 512, "lr": 0.00010366207865986435, "gradient_norm": 0.26022765040397644, "tokens_per_second": 1125375.6999205404, "synthetic": false, "world_size": 8} {"step": 40000, "tokens": 10485760000, "loss": 2.3636585235595704, "optimizer_updates": 21000, "effective_batch": 512, "lr": 0.00010358790236090923, "gradient_norm": 0.26145249605178833, "tokens_per_second": 775123.2703397109, "synthetic": false, "world_size": 8} {"step": 40020, "tokens": 10491002880, "loss": 2.367279052734375, "optimizer_updates": 21010, "effective_batch": 512, "lr": 0.0001035137304394922, "gradient_norm": 0.28571757674217224, "tokens_per_second": 760163.1746539964, "synthetic": false, "world_size": 8} {"step": 40040, "tokens": 10496245760, "loss": 2.3704401016235352, "optimizer_updates": 21020, "effective_batch": 512, "lr": 0.00010343956294625039, "gradient_norm": 0.31201764941215515, "tokens_per_second": 1134511.0519241118, "synthetic": false, "world_size": 8} {"step": 40060, "tokens": 10501488640, "loss": 2.350683403015137, "optimizer_updates": 21030, "effective_batch": 512, "lr": 0.00010336539993181797, "gradient_norm": 0.25154995918273926, "tokens_per_second": 1137758.5921932962, "synthetic": false, "world_size": 8} {"step": 40080, "tokens": 10506731520, "loss": 2.358768653869629, "optimizer_updates": 21040, "effective_batch": 512, "lr": 0.000103291241446826, "gradient_norm": 0.25973525643348694, "tokens_per_second": 1136877.3664363804, "synthetic": false, "world_size": 8} {"step": 40100, "tokens": 10511974400, "loss": 2.370225715637207, "optimizer_updates": 21050, "effective_batch": 512, "lr": 0.00010321708754190246, "gradient_norm": 0.288229763507843, "tokens_per_second": 1136330.8678333329, "synthetic": false, "world_size": 8} {"step": 40120, "tokens": 10517217280, "loss": 2.3753068923950194, "optimizer_updates": 21060, "effective_batch": 512, "lr": 0.00010314293826767223, "gradient_norm": 0.2430768609046936, "tokens_per_second": 1132850.5507348934, "synthetic": false, "world_size": 8} {"step": 40140, "tokens": 10522460160, "loss": 2.359470176696777, "optimizer_updates": 21070, "effective_batch": 512, "lr": 0.00010306879367475702, "gradient_norm": 0.30346569418907166, "tokens_per_second": 1133697.7945344606, "synthetic": false, "world_size": 8} {"step": 40160, "tokens": 10527703040, "loss": 2.3744277954101562, "optimizer_updates": 21080, "effective_batch": 512, "lr": 0.00010299465381377527, "gradient_norm": 0.24751251935958862, "tokens_per_second": 1136285.445366327, "synthetic": false, "world_size": 8} {"step": 40180, "tokens": 10532945920, "loss": 2.362963104248047, "optimizer_updates": 21090, "effective_batch": 512, "lr": 0.0001029205187353423, "gradient_norm": 0.2612079083919525, "tokens_per_second": 1135199.6354593916, "synthetic": false, "world_size": 8} {"step": 40200, "tokens": 10538188800, "loss": 2.3735118865966798, "optimizer_updates": 21100, "effective_batch": 512, "lr": 0.00010284638849007012, "gradient_norm": 0.24571062624454498, "tokens_per_second": 1126399.400434031, "synthetic": false, "world_size": 8} {"step": 40220, "tokens": 10543431680, "loss": 2.365996170043945, "optimizer_updates": 21110, "effective_batch": 512, "lr": 0.0001027722631285674, "gradient_norm": 0.24230258166790009, "tokens_per_second": 1126484.6982808001, "synthetic": false, "world_size": 8} {"step": 40240, "tokens": 10548674560, "loss": 2.3636241912841798, "optimizer_updates": 21120, "effective_batch": 512, "lr": 0.00010269814270143956, "gradient_norm": 0.24063019454479218, "tokens_per_second": 1142040.320348971, "synthetic": false, "world_size": 8} {"step": 40260, "tokens": 10553917440, "loss": 2.364590644836426, "optimizer_updates": 21130, "effective_batch": 512, "lr": 0.00010262402725928858, "gradient_norm": 0.23199865221977234, "tokens_per_second": 1131447.4654713129, "synthetic": false, "world_size": 8} {"step": 40280, "tokens": 10559160320, "loss": 2.3531192779541015, "optimizer_updates": 21140, "effective_batch": 512, "lr": 0.00010254991685271304, "gradient_norm": 0.23740720748901367, "tokens_per_second": 1134461.9662958393, "synthetic": false, "world_size": 8} {"step": 40300, "tokens": 10564403200, "loss": 2.3644142150878906, "optimizer_updates": 21150, "effective_batch": 512, "lr": 0.00010247581153230817, "gradient_norm": 0.2761424779891968, "tokens_per_second": 1132491.4186731817, "synthetic": false, "world_size": 8} {"step": 40320, "tokens": 10569646080, "loss": 2.363627052307129, "optimizer_updates": 21160, "effective_batch": 512, "lr": 0.0001024017113486656, "gradient_norm": 0.24408960342407227, "tokens_per_second": 1142615.780870991, "synthetic": false, "world_size": 8} {"step": 40340, "tokens": 10574888960, "loss": 2.361054611206055, "optimizer_updates": 21170, "effective_batch": 512, "lr": 0.00010232761635237352, "gradient_norm": 0.24341373145580292, "tokens_per_second": 1136769.6892901044, "synthetic": false, "world_size": 8} {"step": 40360, "tokens": 10580131840, "loss": 2.3563629150390626, "optimizer_updates": 21180, "effective_batch": 512, "lr": 0.00010225352659401659, "gradient_norm": 0.2336956411600113, "tokens_per_second": 1141514.3282396952, "synthetic": false, "world_size": 8} {"step": 40380, "tokens": 10585374720, "loss": 2.3853315353393554, "optimizer_updates": 21190, "effective_batch": 512, "lr": 0.00010217944212417586, "gradient_norm": 0.25745895504951477, "tokens_per_second": 1004035.2892953273, "synthetic": false, "world_size": 8} {"step": 40400, "tokens": 10590617600, "loss": 2.363011360168457, "optimizer_updates": 21200, "effective_batch": 512, "lr": 0.00010210536299342881, "gradient_norm": 0.23801302909851074, "tokens_per_second": 1133047.8741041282, "synthetic": false, "world_size": 8} {"step": 40420, "tokens": 10595860480, "loss": 2.359379768371582, "optimizer_updates": 21210, "effective_batch": 512, "lr": 0.00010203128925234923, "gradient_norm": 0.26516926288604736, "tokens_per_second": 1134378.5209544634, "synthetic": false, "world_size": 8} {"step": 40440, "tokens": 10601103360, "loss": 2.3665187835693358, "optimizer_updates": 21220, "effective_batch": 512, "lr": 0.00010195722095150727, "gradient_norm": 0.23775890469551086, "tokens_per_second": 1141578.6338799368, "synthetic": false, "world_size": 8} {"step": 40460, "tokens": 10606346240, "loss": 2.3687042236328124, "optimizer_updates": 21230, "effective_batch": 512, "lr": 0.00010188315814146935, "gradient_norm": 0.3000979423522949, "tokens_per_second": 1137060.957561944, "synthetic": false, "world_size": 8} {"step": 40480, "tokens": 10611589120, "loss": 2.3759498596191406, "optimizer_updates": 21240, "effective_batch": 512, "lr": 0.00010180910087279811, "gradient_norm": 0.30015942454338074, "tokens_per_second": 1135026.3136606421, "synthetic": false, "world_size": 8} {"step": 40500, "tokens": 10616832000, "loss": 2.3632158279418944, "optimizer_updates": 21250, "effective_batch": 512, "lr": 0.00010173504919605245, "gradient_norm": 0.2662416398525238, "tokens_per_second": 1135566.0858785189, "synthetic": false, "world_size": 8} {"step": 40520, "tokens": 10622074880, "loss": 2.3702999114990235, "optimizer_updates": 21260, "effective_batch": 512, "lr": 0.00010166100316178744, "gradient_norm": 0.30736687779426575, "tokens_per_second": 1132224.6896519861, "synthetic": false, "world_size": 8} {"step": 40540, "tokens": 10627317760, "loss": 2.3730117797851564, "optimizer_updates": 21270, "effective_batch": 512, "lr": 0.0001015869628205543, "gradient_norm": 0.24213817715644836, "tokens_per_second": 1135858.6095605842, "synthetic": false, "world_size": 8} {"step": 40560, "tokens": 10632560640, "loss": 2.361074447631836, "optimizer_updates": 21280, "effective_batch": 512, "lr": 0.00010151292822290037, "gradient_norm": 0.28976309299468994, "tokens_per_second": 1144141.8323407623, "synthetic": false, "world_size": 8} {"step": 40580, "tokens": 10637803520, "loss": 2.3791482925415037, "optimizer_updates": 21290, "effective_batch": 512, "lr": 0.00010143889941936903, "gradient_norm": 0.25553327798843384, "tokens_per_second": 1135880.4233773656, "synthetic": false, "world_size": 8} {"step": 40600, "tokens": 10643046400, "loss": 2.3599348068237305, "optimizer_updates": 21300, "effective_batch": 512, "lr": 0.00010136487646049974, "gradient_norm": 0.43193531036376953, "tokens_per_second": 1127017.3116827782, "synthetic": false, "world_size": 8} {"step": 40620, "tokens": 10648289280, "loss": 2.364999771118164, "optimizer_updates": 21310, "effective_batch": 512, "lr": 0.00010129085939682801, "gradient_norm": 0.30043843388557434, "tokens_per_second": 1133551.9509595656, "synthetic": false, "world_size": 8} {"step": 40640, "tokens": 10653532160, "loss": 2.363890838623047, "optimizer_updates": 21320, "effective_batch": 512, "lr": 0.0001012168482788852, "gradient_norm": 0.2915406823158264, "tokens_per_second": 1133855.401383477, "synthetic": false, "world_size": 8} {"step": 40660, "tokens": 10658775040, "loss": 2.3683948516845703, "optimizer_updates": 21330, "effective_batch": 512, "lr": 0.00010114284315719872, "gradient_norm": 0.30438628792762756, "tokens_per_second": 769298.7409591222, "synthetic": false, "world_size": 8} {"step": 40680, "tokens": 10664017920, "loss": 2.356920051574707, "optimizer_updates": 21340, "effective_batch": 512, "lr": 0.0001010688440822919, "gradient_norm": 0.2785084545612335, "tokens_per_second": 1146489.32037461, "synthetic": false, "world_size": 8} {"step": 40700, "tokens": 10669260800, "loss": 2.362807273864746, "optimizer_updates": 21350, "effective_batch": 512, "lr": 0.00010099485110468383, "gradient_norm": 0.24390073120594025, "tokens_per_second": 1139482.2330118725, "synthetic": false, "world_size": 8} {"step": 40720, "tokens": 10674503680, "loss": 2.3679271697998048, "optimizer_updates": 21360, "effective_batch": 512, "lr": 0.00010092086427488956, "gradient_norm": 0.2508898675441742, "tokens_per_second": 1001625.2384497052, "synthetic": false, "world_size": 8} {"step": 40740, "tokens": 10679746560, "loss": 2.373820495605469, "optimizer_updates": 21370, "effective_batch": 512, "lr": 0.00010084688364341985, "gradient_norm": 0.330128937959671, "tokens_per_second": 1135873.991830005, "synthetic": false, "world_size": 8} {"step": 40760, "tokens": 10684989440, "loss": 2.3538591384887697, "optimizer_updates": 21380, "effective_batch": 512, "lr": 0.0001007729092607813, "gradient_norm": 0.2954186797142029, "tokens_per_second": 1137627.9454079352, "synthetic": false, "world_size": 8} {"step": 40780, "tokens": 10690232320, "loss": 2.35484619140625, "optimizer_updates": 21390, "effective_batch": 512, "lr": 0.00010069894117747616, "gradient_norm": 0.3074558973312378, "tokens_per_second": 1129516.2894817316, "synthetic": false, "world_size": 8} {"step": 40800, "tokens": 10695475200, "loss": 2.3689231872558594, "optimizer_updates": 21400, "effective_batch": 512, "lr": 0.00010062497944400247, "gradient_norm": 0.31714263558387756, "tokens_per_second": 1131226.4997133515, "synthetic": false, "world_size": 8} {"step": 40820, "tokens": 10700718080, "loss": 2.369435119628906, "optimizer_updates": 21410, "effective_batch": 512, "lr": 0.00010055102411085388, "gradient_norm": 0.28985798358917236, "tokens_per_second": 1131220.3008777269, "synthetic": false, "world_size": 8} {"step": 40840, "tokens": 10705960960, "loss": 2.3434541702270506, "optimizer_updates": 21420, "effective_batch": 512, "lr": 0.00010047707522851968, "gradient_norm": 0.2612575590610504, "tokens_per_second": 1130384.1838262018, "synthetic": false, "world_size": 8} {"step": 40860, "tokens": 10711203840, "loss": 2.370890808105469, "optimizer_updates": 21430, "effective_batch": 512, "lr": 0.00010040313284748477, "gradient_norm": 0.2623066306114197, "tokens_per_second": 1136611.0226327528, "synthetic": false, "world_size": 8} {"step": 40880, "tokens": 10716446720, "loss": 2.35721492767334, "optimizer_updates": 21440, "effective_batch": 512, "lr": 0.00010032919701822959, "gradient_norm": 0.2667018175125122, "tokens_per_second": 1140422.6128467873, "synthetic": false, "world_size": 8} {"step": 40900, "tokens": 10721689600, "loss": 2.3714321136474608, "optimizer_updates": 21450, "effective_batch": 512, "lr": 0.00010025526779123014, "gradient_norm": 0.263538122177124, "tokens_per_second": 1132336.8119249053, "synthetic": false, "world_size": 8} {"step": 40920, "tokens": 10726932480, "loss": 2.3627029418945313, "optimizer_updates": 21460, "effective_batch": 512, "lr": 0.00010018134521695788, "gradient_norm": 0.3085053265094757, "tokens_per_second": 1006552.1673799569, "synthetic": false, "world_size": 8} {"step": 40940, "tokens": 10732175360, "loss": 2.3672967910766602, "optimizer_updates": 21470, "effective_batch": 512, "lr": 0.00010010742934587975, "gradient_norm": 0.2735309600830078, "tokens_per_second": 1134022.0179374567, "synthetic": false, "world_size": 8} {"step": 40960, "tokens": 10737418240, "loss": 2.364151382446289, "optimizer_updates": 21480, "effective_batch": 512, "lr": 0.00010003352022845807, "gradient_norm": 0.2495325356721878, "tokens_per_second": 1131764.390843298, "synthetic": false, "world_size": 8} {"step": 40980, "tokens": 10742661120, "loss": 2.3748401641845702, "optimizer_updates": 21490, "effective_batch": 512, "lr": 9.995961791515063e-05, "gradient_norm": 0.2461196482181549, "tokens_per_second": 1136935.2337765798, "synthetic": false, "world_size": 8} {"step": 41000, "tokens": 10747904000, "loss": 2.36865348815918, "optimizer_updates": 21500, "effective_batch": 512, "lr": 9.988572245641049e-05, "gradient_norm": 0.2821120321750641, "tokens_per_second": 1136287.5334604597, "synthetic": false, "world_size": 8} {"step": 41020, "tokens": 10753146880, "loss": 2.3691741943359377, "optimizer_updates": 21510, "effective_batch": 512, "lr": 9.981183390268608e-05, "gradient_norm": 0.23001673817634583, "tokens_per_second": 882278.9924469749, "synthetic": false, "world_size": 8} {"step": 41040, "tokens": 10758389760, "loss": 2.3714088439941405, "optimizer_updates": 21520, "effective_batch": 512, "lr": 9.973795230442111e-05, "gradient_norm": 0.298705130815506, "tokens_per_second": 1132454.8338348812, "synthetic": false, "world_size": 8} {"step": 41060, "tokens": 10763632640, "loss": 2.358219528198242, "optimizer_updates": 21530, "effective_batch": 512, "lr": 9.966407771205455e-05, "gradient_norm": 0.2541559040546417, "tokens_per_second": 1129934.8165874546, "synthetic": false, "world_size": 8} {"step": 41080, "tokens": 10768875520, "loss": 2.370986747741699, "optimizer_updates": 21540, "effective_batch": 512, "lr": 9.959021017602054e-05, "gradient_norm": 0.2631390392780304, "tokens_per_second": 1139032.9075156713, "synthetic": false, "world_size": 8} {"step": 41100, "tokens": 10774118400, "loss": 2.3770044326782225, "optimizer_updates": 21550, "effective_batch": 512, "lr": 9.951634974674846e-05, "gradient_norm": 0.30880963802337646, "tokens_per_second": 1137538.3363340427, "synthetic": false, "world_size": 8} {"step": 41120, "tokens": 10779361280, "loss": 2.3723304748535154, "optimizer_updates": 21560, "effective_batch": 512, "lr": 9.94424964746628e-05, "gradient_norm": 0.25769108533859253, "tokens_per_second": 1132930.957511118, "synthetic": false, "world_size": 8} {"step": 41140, "tokens": 10784604160, "loss": 2.370192527770996, "optimizer_updates": 21570, "effective_batch": 512, "lr": 9.936865041018319e-05, "gradient_norm": 0.2505442500114441, "tokens_per_second": 1130654.026083044, "synthetic": false, "world_size": 8} {"step": 41160, "tokens": 10789847040, "loss": 2.369597816467285, "optimizer_updates": 21580, "effective_batch": 512, "lr": 9.929481160372432e-05, "gradient_norm": 0.25063130259513855, "tokens_per_second": 1139867.8035640244, "synthetic": false, "world_size": 8} {"step": 41180, "tokens": 10795089920, "loss": 2.3610069274902346, "optimizer_updates": 21590, "effective_batch": 512, "lr": 9.922098010569593e-05, "gradient_norm": 0.23087286949157715, "tokens_per_second": 1132479.3698289287, "synthetic": false, "world_size": 8} {"step": 41200, "tokens": 10800332800, "loss": 2.3597841262817383, "optimizer_updates": 21600, "effective_batch": 512, "lr": 9.914715596650278e-05, "gradient_norm": 0.2609215974807739, "tokens_per_second": 1128035.7052531783, "synthetic": false, "world_size": 8} {"step": 41220, "tokens": 10805575680, "loss": 2.3604156494140627, "optimizer_updates": 21610, "effective_batch": 512, "lr": 9.907333923654458e-05, "gradient_norm": 0.31455326080322266, "tokens_per_second": 1133621.574448058, "synthetic": false, "world_size": 8} {"step": 41240, "tokens": 10810818560, "loss": 2.3675403594970703, "optimizer_updates": 21620, "effective_batch": 512, "lr": 9.899952996621605e-05, "gradient_norm": 0.2599583566188812, "tokens_per_second": 1134721.8604987194, "synthetic": false, "world_size": 8} {"step": 41260, "tokens": 10816061440, "loss": 2.365468215942383, "optimizer_updates": 21630, "effective_batch": 512, "lr": 9.89257282059067e-05, "gradient_norm": 0.37152665853500366, "tokens_per_second": 1132688.6073699663, "synthetic": false, "world_size": 8} {"step": 41280, "tokens": 10821304320, "loss": 2.3754222869873045, "optimizer_updates": 21640, "effective_batch": 512, "lr": 9.885193400600103e-05, "gradient_norm": 0.37527909874916077, "tokens_per_second": 1137608.7878092795, "synthetic": false, "world_size": 8} {"step": 41300, "tokens": 10826547200, "loss": 2.365184020996094, "optimizer_updates": 21650, "effective_batch": 512, "lr": 9.877814741687829e-05, "gradient_norm": 0.24559073150157928, "tokens_per_second": 1141349.3380292964, "synthetic": false, "world_size": 8} {"step": 41320, "tokens": 10831790080, "loss": 2.362296485900879, "optimizer_updates": 21660, "effective_batch": 512, "lr": 9.870436848891261e-05, "gradient_norm": 0.26943883299827576, "tokens_per_second": 1134955.8816385528, "synthetic": false, "world_size": 8} {"step": 41340, "tokens": 10837032960, "loss": 2.3685699462890626, "optimizer_updates": 21670, "effective_batch": 512, "lr": 9.863059727247282e-05, "gradient_norm": 0.26566025614738464, "tokens_per_second": 1137089.563936867, "synthetic": false, "world_size": 8} {"step": 41360, "tokens": 10842275840, "loss": 2.356675720214844, "optimizer_updates": 21680, "effective_batch": 512, "lr": 9.855683381792255e-05, "gradient_norm": 0.23581048846244812, "tokens_per_second": 1132055.3407316315, "synthetic": false, "world_size": 8} {"step": 41380, "tokens": 10847518720, "loss": 2.351593589782715, "optimizer_updates": 21690, "effective_batch": 512, "lr": 9.848307817562007e-05, "gradient_norm": 0.2574104070663452, "tokens_per_second": 1135543.2536477041, "synthetic": false, "world_size": 8} {"step": 41400, "tokens": 10852761600, "loss": 2.3657899856567384, "optimizer_updates": 21700, "effective_batch": 512, "lr": 9.840933039591837e-05, "gradient_norm": 0.2816481590270996, "tokens_per_second": 1136915.4200339701, "synthetic": false, "world_size": 8} {"step": 41420, "tokens": 10858004480, "loss": 2.367003631591797, "optimizer_updates": 21710, "effective_batch": 512, "lr": 9.833559052916506e-05, "gradient_norm": 0.27758046984672546, "tokens_per_second": 1134594.2442179217, "synthetic": false, "world_size": 8} {"step": 41440, "tokens": 10863247360, "loss": 2.3742547988891602, "optimizer_updates": 21720, "effective_batch": 512, "lr": 9.826185862570229e-05, "gradient_norm": 0.2394382804632187, "tokens_per_second": 1142176.7075156476, "synthetic": false, "world_size": 8} {"step": 41460, "tokens": 10868490240, "loss": 2.3697273254394533, "optimizer_updates": 21730, "effective_batch": 512, "lr": 9.818813473586685e-05, "gradient_norm": 0.2628057599067688, "tokens_per_second": 1135554.588862297, "synthetic": false, "world_size": 8} {"step": 41480, "tokens": 10873733120, "loss": 2.3713375091552735, "optimizer_updates": 21740, "effective_batch": 512, "lr": 9.811441890999e-05, "gradient_norm": 0.23147152364253998, "tokens_per_second": 1139299.5664994633, "synthetic": false, "world_size": 8} {"step": 41500, "tokens": 10878976000, "loss": 2.3715490341186523, "optimizer_updates": 21750, "effective_batch": 512, "lr": 9.804071119839757e-05, "gradient_norm": 0.27883052825927734, "tokens_per_second": 1127902.2984962312, "synthetic": false, "world_size": 8} {"step": 41520, "tokens": 10884218880, "loss": 2.380851173400879, "optimizer_updates": 21760, "effective_batch": 512, "lr": 9.796701165140974e-05, "gradient_norm": 0.2497311383485794, "tokens_per_second": 1145174.349808682, "synthetic": false, "world_size": 8} {"step": 41540, "tokens": 10889461760, "loss": 2.372113037109375, "optimizer_updates": 21770, "effective_batch": 512, "lr": 9.789332031934125e-05, "gradient_norm": 0.2270675152540207, "tokens_per_second": 1135346.3647947342, "synthetic": false, "world_size": 8} {"step": 41560, "tokens": 10894704640, "loss": 2.3754886627197265, "optimizer_updates": 21780, "effective_batch": 512, "lr": 9.781963725250114e-05, "gradient_norm": 0.30386990308761597, "tokens_per_second": 1125463.0292183405, "synthetic": false, "world_size": 8} {"step": 41580, "tokens": 10899947520, "loss": 2.3588893890380858, "optimizer_updates": 21790, "effective_batch": 512, "lr": 9.77459625011928e-05, "gradient_norm": 0.2674768567085266, "tokens_per_second": 1143067.8718231097, "synthetic": false, "world_size": 8} {"step": 41600, "tokens": 10905190400, "loss": 2.3725509643554688, "optimizer_updates": 21800, "effective_batch": 512, "lr": 9.767229611571399e-05, "gradient_norm": 0.25647833943367004, "tokens_per_second": 1130147.3344557926, "synthetic": false, "world_size": 8} {"step": 41620, "tokens": 10910433280, "loss": 2.371426010131836, "optimizer_updates": 21810, "effective_batch": 512, "lr": 9.759863814635673e-05, "gradient_norm": 0.26362690329551697, "tokens_per_second": 768872.0552840594, "synthetic": false, "world_size": 8} {"step": 41640, "tokens": 10915676160, "loss": 2.3502628326416017, "optimizer_updates": 21820, "effective_batch": 512, "lr": 9.75249886434073e-05, "gradient_norm": 0.2801476716995239, "tokens_per_second": 1146768.8627703234, "synthetic": false, "world_size": 8} {"step": 41660, "tokens": 10920919040, "loss": 2.379526138305664, "optimizer_updates": 21830, "effective_batch": 512, "lr": 9.745134765714625e-05, "gradient_norm": 0.28537148237228394, "tokens_per_second": 1139400.7109009018, "synthetic": false, "world_size": 8} {"step": 41680, "tokens": 10926161920, "loss": 2.3663938522338865, "optimizer_updates": 21840, "effective_batch": 512, "lr": 9.737771523784822e-05, "gradient_norm": 0.26013848185539246, "tokens_per_second": 1136860.9325094144, "synthetic": false, "world_size": 8} {"step": 41700, "tokens": 10931404800, "loss": 2.343521499633789, "optimizer_updates": 21850, "effective_batch": 512, "lr": 9.730409143578207e-05, "gradient_norm": 0.24725815653800964, "tokens_per_second": 1130277.237662208, "synthetic": false, "world_size": 8} {"step": 41720, "tokens": 10936647680, "loss": 2.3738948822021486, "optimizer_updates": 21860, "effective_batch": 512, "lr": 9.723047630121078e-05, "gradient_norm": 0.2809727191925049, "tokens_per_second": 1125853.5191444647, "synthetic": false, "world_size": 8} {"step": 41740, "tokens": 10941890560, "loss": 2.363016891479492, "optimizer_updates": 21870, "effective_batch": 512, "lr": 9.715686988439134e-05, "gradient_norm": 0.24969825148582458, "tokens_per_second": 1138861.5805590106, "synthetic": false, "world_size": 8} {"step": 41760, "tokens": 10947133440, "loss": 2.369407081604004, "optimizer_updates": 21880, "effective_batch": 512, "lr": 9.708327223557488e-05, "gradient_norm": 0.28250548243522644, "tokens_per_second": 1129526.6361753594, "synthetic": false, "world_size": 8} {"step": 41780, "tokens": 10952376320, "loss": 2.358174705505371, "optimizer_updates": 21890, "effective_batch": 512, "lr": 9.700968340500649e-05, "gradient_norm": 0.36063095927238464, "tokens_per_second": 1135916.0441832033, "synthetic": false, "world_size": 8} {"step": 41800, "tokens": 10957619200, "loss": 2.360254669189453, "optimizer_updates": 21900, "effective_batch": 512, "lr": 9.693610344292524e-05, "gradient_norm": 0.25967589020729065, "tokens_per_second": 1128160.4763348314, "synthetic": false, "world_size": 8} {"step": 41820, "tokens": 10962862080, "loss": 2.361567497253418, "optimizer_updates": 21910, "effective_batch": 512, "lr": 9.68625323995642e-05, "gradient_norm": 0.2491142898797989, "tokens_per_second": 1127731.802389321, "synthetic": false, "world_size": 8} {"step": 41840, "tokens": 10968104960, "loss": 2.368213081359863, "optimizer_updates": 21920, "effective_batch": 512, "lr": 9.678897032515026e-05, "gradient_norm": 0.34552130103111267, "tokens_per_second": 1136846.5226000098, "synthetic": false, "world_size": 8} {"step": 41860, "tokens": 10973347840, "loss": 2.372092628479004, "optimizer_updates": 21930, "effective_batch": 512, "lr": 9.671541726990426e-05, "gradient_norm": 0.2990032136440277, "tokens_per_second": 1130619.4620932043, "synthetic": false, "world_size": 8} {"step": 41880, "tokens": 10978590720, "loss": 2.3702472686767577, "optimizer_updates": 21940, "effective_batch": 512, "lr": 9.664187328404089e-05, "gradient_norm": 0.259211927652359, "tokens_per_second": 1133965.863436268, "synthetic": false, "world_size": 8} {"step": 41900, "tokens": 10983833600, "loss": 2.374367904663086, "optimizer_updates": 21950, "effective_batch": 512, "lr": 9.656833841776857e-05, "gradient_norm": 0.2411753237247467, "tokens_per_second": 1136219.2104872877, "synthetic": false, "world_size": 8} {"step": 41920, "tokens": 10989076480, "loss": 2.3621734619140624, "optimizer_updates": 21960, "effective_batch": 512, "lr": 9.649481272128956e-05, "gradient_norm": 0.33045703172683716, "tokens_per_second": 1130805.7185798576, "synthetic": false, "world_size": 8} {"step": 41940, "tokens": 10994319360, "loss": 2.358828544616699, "optimizer_updates": 21970, "effective_batch": 512, "lr": 9.642129624479984e-05, "gradient_norm": 0.3365897536277771, "tokens_per_second": 1135837.7779268115, "synthetic": false, "world_size": 8} {"step": 41960, "tokens": 10999562240, "loss": 2.3478626251220702, "optimizer_updates": 21980, "effective_batch": 512, "lr": 9.634778903848908e-05, "gradient_norm": 0.2441474199295044, "tokens_per_second": 1137756.9337213614, "synthetic": false, "world_size": 8} {"step": 41980, "tokens": 11004805120, "loss": 2.351754379272461, "optimizer_updates": 21990, "effective_batch": 512, "lr": 9.627429115254068e-05, "gradient_norm": 0.28250008821487427, "tokens_per_second": 1132002.3988209863, "synthetic": false, "world_size": 8} {"step": 42000, "tokens": 11010048000, "loss": 2.379974365234375, "optimizer_updates": 22000, "effective_batch": 512, "lr": 9.62008026371316e-05, "gradient_norm": 0.2751513421535492, "tokens_per_second": 1133777.2729688643, "synthetic": false, "world_size": 8} {"step": 42020, "tokens": 11015290880, "loss": 2.370012092590332, "optimizer_updates": 22010, "effective_batch": 512, "lr": 9.612732354243247e-05, "gradient_norm": 0.22722822427749634, "tokens_per_second": 835670.218192414, "synthetic": false, "world_size": 8} {"step": 42040, "tokens": 11020533760, "loss": 2.3629899978637696, "optimizer_updates": 22020, "effective_batch": 512, "lr": 9.605385391860744e-05, "gradient_norm": 0.2564615309238434, "tokens_per_second": 1134326.0396509848, "synthetic": false, "world_size": 8} {"step": 42060, "tokens": 11025776640, "loss": 2.362200164794922, "optimizer_updates": 22030, "effective_batch": 512, "lr": 9.598039381581421e-05, "gradient_norm": 0.25424981117248535, "tokens_per_second": 1038853.3000603649, "synthetic": false, "world_size": 8} {"step": 42080, "tokens": 11031019520, "loss": 2.3674516677856445, "optimizer_updates": 22040, "effective_batch": 512, "lr": 9.590694328420395e-05, "gradient_norm": 0.2673355042934418, "tokens_per_second": 1133588.582723344, "synthetic": false, "world_size": 8} {"step": 42100, "tokens": 11036262400, "loss": 2.360236930847168, "optimizer_updates": 22050, "effective_batch": 512, "lr": 9.58335023739214e-05, "gradient_norm": 0.27266034483909607, "tokens_per_second": 1134709.045574172, "synthetic": false, "world_size": 8} {"step": 42120, "tokens": 11041505280, "loss": 2.3649133682250976, "optimizer_updates": 22060, "effective_batch": 512, "lr": 9.576007113510457e-05, "gradient_norm": 0.2469606250524521, "tokens_per_second": 1135082.2294246044, "synthetic": false, "world_size": 8} {"step": 42140, "tokens": 11046748160, "loss": 2.376865196228027, "optimizer_updates": 22070, "effective_batch": 512, "lr": 9.568664961788503e-05, "gradient_norm": 0.2580563426017761, "tokens_per_second": 1128948.9175509128, "synthetic": false, "world_size": 8} {"step": 42160, "tokens": 11051991040, "loss": 2.3674448013305662, "optimizer_updates": 22080, "effective_batch": 512, "lr": 9.561323787238758e-05, "gradient_norm": 0.2762199938297272, "tokens_per_second": 1127522.7464980814, "synthetic": false, "world_size": 8} {"step": 42180, "tokens": 11057233920, "loss": 2.366458511352539, "optimizer_updates": 22090, "effective_batch": 512, "lr": 9.553983594873045e-05, "gradient_norm": 0.28928980231285095, "tokens_per_second": 1022715.8595736881, "synthetic": false, "world_size": 8} {"step": 42200, "tokens": 11062476800, "loss": 2.3557538986206055, "optimizer_updates": 22100, "effective_batch": 512, "lr": 9.546644389702515e-05, "gradient_norm": 0.26536667346954346, "tokens_per_second": 1139814.02114726, "synthetic": false, "world_size": 8} {"step": 42220, "tokens": 11067719680, "loss": 2.3836175918579103, "optimizer_updates": 22110, "effective_batch": 512, "lr": 9.539306176737632e-05, "gradient_norm": 0.27147766947746277, "tokens_per_second": 1132217.6226413115, "synthetic": false, "world_size": 8} {"step": 42240, "tokens": 11072962560, "loss": 2.3742509841918946, "optimizer_updates": 22120, "effective_batch": 512, "lr": 9.531968960988203e-05, "gradient_norm": 0.2765145003795624, "tokens_per_second": 1143109.587200191, "synthetic": false, "world_size": 8} {"step": 42260, "tokens": 11078205440, "loss": 2.3667892456054687, "optimizer_updates": 22130, "effective_batch": 512, "lr": 9.524632747463336e-05, "gradient_norm": 0.24536074697971344, "tokens_per_second": 1125495.0321489233, "synthetic": false, "world_size": 8} {"step": 42280, "tokens": 11083448320, "loss": 2.34600830078125, "optimizer_updates": 22140, "effective_batch": 512, "lr": 9.517297541171473e-05, "gradient_norm": 0.2811885476112366, "tokens_per_second": 1142340.262449907, "synthetic": false, "world_size": 8} {"step": 42300, "tokens": 11088691200, "loss": 2.3661418914794923, "optimizer_updates": 22150, "effective_batch": 512, "lr": 9.509963347120346e-05, "gradient_norm": 0.2897537052631378, "tokens_per_second": 1026518.916832388, "synthetic": false, "world_size": 8} {"step": 42320, "tokens": 11093934080, "loss": 2.3631982803344727, "optimizer_updates": 22160, "effective_batch": 512, "lr": 9.502630170317019e-05, "gradient_norm": 0.25237080454826355, "tokens_per_second": 1140626.9631972203, "synthetic": false, "world_size": 8} {"step": 42340, "tokens": 11099176960, "loss": 2.3677032470703123, "optimizer_updates": 22170, "effective_batch": 512, "lr": 9.495298015767842e-05, "gradient_norm": 0.2555953562259674, "tokens_per_second": 1132888.5031442533, "synthetic": false, "world_size": 8} {"step": 42360, "tokens": 11104419840, "loss": 2.369325065612793, "optimizer_updates": 22180, "effective_batch": 512, "lr": 9.487966888478484e-05, "gradient_norm": 0.2377338707447052, "tokens_per_second": 1144292.7939011722, "synthetic": false, "world_size": 8} {"step": 42380, "tokens": 11109662720, "loss": 2.3599384307861326, "optimizer_updates": 22190, "effective_batch": 512, "lr": 9.480636793453896e-05, "gradient_norm": 0.2334301471710205, "tokens_per_second": 1131498.089847771, "synthetic": false, "world_size": 8} {"step": 42400, "tokens": 11114905600, "loss": 2.37277889251709, "optimizer_updates": 22200, "effective_batch": 512, "lr": 9.473307735698341e-05, "gradient_norm": 0.25185176730155945, "tokens_per_second": 1125606.4665552836, "synthetic": false, "world_size": 8} {"step": 42420, "tokens": 11120148480, "loss": 2.373662567138672, "optimizer_updates": 22210, "effective_batch": 512, "lr": 9.465979720215358e-05, "gradient_norm": 0.23947973549365997, "tokens_per_second": 1129799.0654512576, "synthetic": false, "world_size": 8} {"step": 42440, "tokens": 11125391360, "loss": 2.3699363708496093, "optimizer_updates": 22220, "effective_batch": 512, "lr": 9.458652752007788e-05, "gradient_norm": 0.2430805265903473, "tokens_per_second": 1125798.9447147974, "synthetic": false, "world_size": 8} {"step": 42460, "tokens": 11130634240, "loss": 2.377597427368164, "optimizer_updates": 22230, "effective_batch": 512, "lr": 9.451326836077747e-05, "gradient_norm": 0.2405758947134018, "tokens_per_second": 1138225.4135861052, "synthetic": false, "world_size": 8} {"step": 42480, "tokens": 11135877120, "loss": 2.3483449935913088, "optimizer_updates": 22240, "effective_batch": 512, "lr": 9.44400197742664e-05, "gradient_norm": 0.24710047245025635, "tokens_per_second": 1115715.2458219777, "synthetic": false, "world_size": 8} {"step": 42500, "tokens": 11141120000, "loss": 2.3590778350830077, "optimizer_updates": 22250, "effective_batch": 512, "lr": 9.436678181055144e-05, "gradient_norm": 0.2605990767478943, "tokens_per_second": 1128374.632585544, "synthetic": false, "world_size": 8} {"step": 42520, "tokens": 11146362880, "loss": 2.368594169616699, "optimizer_updates": 22260, "effective_batch": 512, "lr": 9.429355451963216e-05, "gradient_norm": 0.2822231352329254, "tokens_per_second": 1127205.3477316478, "synthetic": false, "world_size": 8} {"step": 42540, "tokens": 11151605760, "loss": 2.3709121704101563, "optimizer_updates": 22270, "effective_batch": 512, "lr": 9.42203379515008e-05, "gradient_norm": 0.25695377588272095, "tokens_per_second": 1127405.714927154, "synthetic": false, "world_size": 8} {"step": 42560, "tokens": 11156848640, "loss": 2.3747489929199217, "optimizer_updates": 22280, "effective_batch": 512, "lr": 9.414713215614233e-05, "gradient_norm": 0.2556585371494293, "tokens_per_second": 1136174.1059965345, "synthetic": false, "world_size": 8} {"step": 42580, "tokens": 11162091520, "loss": 2.3623882293701173, "optimizer_updates": 22290, "effective_batch": 512, "lr": 9.407393718353427e-05, "gradient_norm": 0.2560883164405823, "tokens_per_second": 1123282.3957036512, "synthetic": false, "world_size": 8} {"step": 42600, "tokens": 11167334400, "loss": 2.3673379898071287, "optimizer_updates": 22300, "effective_batch": 512, "lr": 9.400075308364692e-05, "gradient_norm": 0.31895914673805237, "tokens_per_second": 1133279.0455895998, "synthetic": false, "world_size": 8} {"step": 42620, "tokens": 11172577280, "loss": 2.3625205993652343, "optimizer_updates": 22310, "effective_batch": 512, "lr": 9.392757990644294e-05, "gradient_norm": 0.2683849632740021, "tokens_per_second": 1123171.3030356595, "synthetic": false, "world_size": 8} {"step": 42640, "tokens": 11177820160, "loss": 2.3642398834228517, "optimizer_updates": 22320, "effective_batch": 512, "lr": 9.385441770187771e-05, "gradient_norm": 0.24037013947963715, "tokens_per_second": 1133027.7725211345, "synthetic": false, "world_size": 8} {"step": 42660, "tokens": 11183063040, "loss": 2.3706825256347654, "optimizer_updates": 22330, "effective_batch": 512, "lr": 9.378126651989909e-05, "gradient_norm": 0.26267769932746887, "tokens_per_second": 1125911.5731161279, "synthetic": false, "world_size": 8} {"step": 42680, "tokens": 11188305920, "loss": 2.3707290649414063, "optimizer_updates": 22340, "effective_batch": 512, "lr": 9.370812641044731e-05, "gradient_norm": 0.24474947154521942, "tokens_per_second": 1140243.46865664, "synthetic": false, "world_size": 8} {"step": 42700, "tokens": 11193548800, "loss": 2.3663618087768556, "optimizer_updates": 22350, "effective_batch": 512, "lr": 9.363499742345517e-05, "gradient_norm": 0.23148001730442047, "tokens_per_second": 1132115.7744356242, "synthetic": false, "world_size": 8} {"step": 42720, "tokens": 11198791680, "loss": 2.36385555267334, "optimizer_updates": 22360, "effective_batch": 512, "lr": 9.356187960884774e-05, "gradient_norm": 0.2748793065547943, "tokens_per_second": 1129429.0565736953, "synthetic": false, "world_size": 8} {"step": 42740, "tokens": 11204034560, "loss": 2.3582019805908203, "optimizer_updates": 22370, "effective_batch": 512, "lr": 9.348877301654265e-05, "gradient_norm": 0.2429964691400528, "tokens_per_second": 1127890.13211439, "synthetic": false, "world_size": 8} {"step": 42760, "tokens": 11209277440, "loss": 2.3808734893798826, "optimizer_updates": 22380, "effective_batch": 512, "lr": 9.341567769644962e-05, "gradient_norm": 0.24465641379356384, "tokens_per_second": 1132921.1770287978, "synthetic": false, "world_size": 8} {"step": 42780, "tokens": 11214520320, "loss": 2.358878517150879, "optimizer_updates": 22390, "effective_batch": 512, "lr": 9.334259369847096e-05, "gradient_norm": 0.2432689070701599, "tokens_per_second": 1133131.1705440637, "synthetic": false, "world_size": 8} {"step": 42800, "tokens": 11219763200, "loss": 2.3633455276489257, "optimizer_updates": 22400, "effective_batch": 512, "lr": 9.326952107250099e-05, "gradient_norm": 0.24758099019527435, "tokens_per_second": 1136750.4341378128, "synthetic": false, "world_size": 8} {"step": 42820, "tokens": 11225006080, "loss": 2.3728546142578124, "optimizer_updates": 22410, "effective_batch": 512, "lr": 9.319645986842648e-05, "gradient_norm": 0.2729879915714264, "tokens_per_second": 1018307.9572475273, "synthetic": false, "world_size": 8} {"step": 42840, "tokens": 11230248960, "loss": 2.3729860305786135, "optimizer_updates": 22420, "effective_batch": 512, "lr": 9.312341013612622e-05, "gradient_norm": 0.22535203397274017, "tokens_per_second": 1133559.0005702586, "synthetic": false, "world_size": 8} {"step": 42860, "tokens": 11235491840, "loss": 2.364151382446289, "optimizer_updates": 22430, "effective_batch": 512, "lr": 9.30503719254713e-05, "gradient_norm": 0.27196449041366577, "tokens_per_second": 1127966.680021232, "synthetic": false, "world_size": 8} {"step": 42880, "tokens": 11240734720, "loss": 2.3684001922607423, "optimizer_updates": 22440, "effective_batch": 512, "lr": 9.297734528632483e-05, "gradient_norm": 0.28873082995414734, "tokens_per_second": 1134667.841111091, "synthetic": false, "world_size": 8} {"step": 42900, "tokens": 11245977600, "loss": 2.375041198730469, "optimizer_updates": 22450, "effective_batch": 512, "lr": 9.290433026854219e-05, "gradient_norm": 0.23867566883563995, "tokens_per_second": 789493.0439366682, "synthetic": false, "world_size": 8} {"step": 42920, "tokens": 11251220480, "loss": 2.374407958984375, "optimizer_updates": 22460, "effective_batch": 512, "lr": 9.283132692197061e-05, "gradient_norm": 0.26262980699539185, "tokens_per_second": 1137103.465573926, "synthetic": false, "world_size": 8} {"step": 42940, "tokens": 11256463360, "loss": 2.3718204498291016, "optimizer_updates": 22470, "effective_batch": 512, "lr": 9.275833529644958e-05, "gradient_norm": 0.25893571972846985, "tokens_per_second": 1132177.4849466046, "synthetic": false, "world_size": 8} {"step": 42960, "tokens": 11261706240, "loss": 2.3598583221435545, "optimizer_updates": 22480, "effective_batch": 512, "lr": 9.268535544181034e-05, "gradient_norm": 0.2733788788318634, "tokens_per_second": 1134888.6998709394, "synthetic": false, "world_size": 8} {"step": 42980, "tokens": 11266949120, "loss": 2.36458683013916, "optimizer_updates": 22490, "effective_batch": 512, "lr": 9.261238740787635e-05, "gradient_norm": 0.2641775906085968, "tokens_per_second": 797263.2794423271, "synthetic": false, "world_size": 8} {"step": 43000, "tokens": 11272192000, "loss": 2.3734622955322267, "optimizer_updates": 22500, "effective_batch": 512, "lr": 9.25394312444628e-05, "gradient_norm": 0.22923129796981812, "tokens_per_second": 1129152.2956328425, "synthetic": false, "world_size": 8} {"step": 43020, "tokens": 11277434880, "loss": 2.3705255508422853, "optimizer_updates": 22510, "effective_batch": 512, "lr": 9.24664870013769e-05, "gradient_norm": 0.2535112798213959, "tokens_per_second": 826479.3522226777, "synthetic": false, "world_size": 8} {"step": 43040, "tokens": 11282677760, "loss": 2.3613813400268553, "optimizer_updates": 22520, "effective_batch": 512, "lr": 9.239355472841757e-05, "gradient_norm": 0.3211466372013092, "tokens_per_second": 1134470.467199102, "synthetic": false, "world_size": 8} {"step": 43060, "tokens": 11287920640, "loss": 2.3738662719726564, "optimizer_updates": 22530, "effective_batch": 512, "lr": 9.232063447537576e-05, "gradient_norm": 0.2620813250541687, "tokens_per_second": 1130692.9616832344, "synthetic": false, "world_size": 8} {"step": 43080, "tokens": 11293163520, "loss": 2.373431587219238, "optimizer_updates": 22540, "effective_batch": 512, "lr": 9.224772629203414e-05, "gradient_norm": 0.2816982567310333, "tokens_per_second": 1136116.101726159, "synthetic": false, "world_size": 8} {"step": 43100, "tokens": 11298406400, "loss": 2.3796878814697267, "optimizer_updates": 22550, "effective_batch": 512, "lr": 9.217483022816702e-05, "gradient_norm": 0.24304254353046417, "tokens_per_second": 1126040.8117356698, "synthetic": false, "world_size": 8} {"step": 43120, "tokens": 11303649280, "loss": 2.3502050399780274, "optimizer_updates": 22560, "effective_batch": 512, "lr": 9.210194633354063e-05, "gradient_norm": 0.2500331997871399, "tokens_per_second": 767384.5113413092, "synthetic": false, "world_size": 8} {"step": 43140, "tokens": 11308892160, "loss": 2.36706657409668, "optimizer_updates": 22570, "effective_batch": 512, "lr": 9.202907465791271e-05, "gradient_norm": 0.35552647709846497, "tokens_per_second": 1133618.3718420458, "synthetic": false, "world_size": 8} {"step": 43160, "tokens": 11314135040, "loss": 2.3733362197875976, "optimizer_updates": 22580, "effective_batch": 512, "lr": 9.195621525103279e-05, "gradient_norm": 0.25652679800987244, "tokens_per_second": 1128976.345312112, "synthetic": false, "world_size": 8} {"step": 43180, "tokens": 11319377920, "loss": 2.370103454589844, "optimizer_updates": 22590, "effective_batch": 512, "lr": 9.188336816264195e-05, "gradient_norm": 0.26756301522254944, "tokens_per_second": 1130238.6126054965, "synthetic": false, "world_size": 8} {"step": 43200, "tokens": 11324620800, "loss": 2.3591384887695312, "optimizer_updates": 22600, "effective_batch": 512, "lr": 9.181053344247291e-05, "gradient_norm": 0.26658010482788086, "tokens_per_second": 1133318.2050599896, "synthetic": false, "world_size": 8} {"step": 43220, "tokens": 11329863680, "loss": 2.3786590576171873, "optimizer_updates": 22610, "effective_batch": 512, "lr": 9.173771114024988e-05, "gradient_norm": 0.2615806460380554, "tokens_per_second": 1134891.8382186065, "synthetic": false, "world_size": 8} {"step": 43240, "tokens": 11335106560, "loss": 2.3702564239501953, "optimizer_updates": 22620, "effective_batch": 512, "lr": 9.16649013056887e-05, "gradient_norm": 0.25115901231765747, "tokens_per_second": 1133336.7098421538, "synthetic": false, "world_size": 8} {"step": 43260, "tokens": 11340349440, "loss": 2.362112808227539, "optimizer_updates": 22630, "effective_batch": 512, "lr": 9.159210398849657e-05, "gradient_norm": 0.2836846113204956, "tokens_per_second": 1133687.8973279768, "synthetic": false, "world_size": 8} {"step": 43280, "tokens": 11345592320, "loss": 2.372026062011719, "optimizer_updates": 22640, "effective_batch": 512, "lr": 9.151931923837227e-05, "gradient_norm": 0.28743112087249756, "tokens_per_second": 1139215.8568072533, "synthetic": false, "world_size": 8} {"step": 43300, "tokens": 11350835200, "loss": 2.3776472091674803, "optimizer_updates": 22650, "effective_batch": 512, "lr": 9.144654710500588e-05, "gradient_norm": 0.25077202916145325, "tokens_per_second": 1135731.139256269, "synthetic": false, "world_size": 8} {"step": 43320, "tokens": 11356078080, "loss": 2.3760444641113283, "optimizer_updates": 22660, "effective_batch": 512, "lr": 9.137378763807897e-05, "gradient_norm": 0.2390594780445099, "tokens_per_second": 1125035.1467769977, "synthetic": false, "world_size": 8} {"step": 43340, "tokens": 11361320960, "loss": 2.364240837097168, "optimizer_updates": 22670, "effective_batch": 512, "lr": 9.130104088726434e-05, "gradient_norm": 0.3146301805973053, "tokens_per_second": 1140105.8434694752, "synthetic": false, "world_size": 8} {"step": 43360, "tokens": 11366563840, "loss": 2.357331657409668, "optimizer_updates": 22680, "effective_batch": 512, "lr": 9.122830690222629e-05, "gradient_norm": 0.23638415336608887, "tokens_per_second": 1130851.9566965157, "synthetic": false, "world_size": 8} {"step": 43380, "tokens": 11371806720, "loss": 2.3673728942871093, "optimizer_updates": 22690, "effective_batch": 512, "lr": 9.11555857326202e-05, "gradient_norm": 0.25737690925598145, "tokens_per_second": 1135650.2779737136, "synthetic": false, "world_size": 8} {"step": 43400, "tokens": 11377049600, "loss": 2.36531925201416, "optimizer_updates": 22700, "effective_batch": 512, "lr": 9.108287742809292e-05, "gradient_norm": 0.2438691109418869, "tokens_per_second": 1132783.8536921148, "synthetic": false, "world_size": 8} {"step": 43420, "tokens": 11382292480, "loss": 2.3674062728881835, "optimizer_updates": 22710, "effective_batch": 512, "lr": 9.101018203828226e-05, "gradient_norm": 0.24928489327430725, "tokens_per_second": 1132578.3815301629, "synthetic": false, "world_size": 8} {"step": 43440, "tokens": 11387535360, "loss": 2.366679382324219, "optimizer_updates": 22720, "effective_batch": 512, "lr": 9.093749961281748e-05, "gradient_norm": 0.23277226090431213, "tokens_per_second": 1130970.823220926, "synthetic": false, "world_size": 8} {"step": 43460, "tokens": 11392778240, "loss": 2.365022659301758, "optimizer_updates": 22730, "effective_batch": 512, "lr": 9.086483020131877e-05, "gradient_norm": 0.2739863097667694, "tokens_per_second": 1138850.4233541298, "synthetic": false, "world_size": 8} {"step": 43480, "tokens": 11398021120, "loss": 2.3671590805053713, "optimizer_updates": 22740, "effective_batch": 512, "lr": 9.079217385339753e-05, "gradient_norm": 0.27086809277534485, "tokens_per_second": 1127566.5141399226, "synthetic": false, "world_size": 8} {"step": 43500, "tokens": 11403264000, "loss": 2.3688846588134767, "optimizer_updates": 22750, "effective_batch": 512, "lr": 9.071953061865632e-05, "gradient_norm": 0.23278486728668213, "tokens_per_second": 1130419.9316060077, "synthetic": false, "world_size": 8} {"step": 43520, "tokens": 11408506880, "loss": 2.3729631423950197, "optimizer_updates": 22760, "effective_batch": 512, "lr": 9.064690054668857e-05, "gradient_norm": 0.27569442987442017, "tokens_per_second": 1118204.317132905, "synthetic": false, "world_size": 8} {"step": 43540, "tokens": 11413749760, "loss": 2.369975471496582, "optimizer_updates": 22770, "effective_batch": 512, "lr": 9.05742836870789e-05, "gradient_norm": 0.2944658696651459, "tokens_per_second": 1126664.8527333925, "synthetic": false, "world_size": 8} {"step": 43560, "tokens": 11418992640, "loss": 2.3771968841552735, "optimizer_updates": 22780, "effective_batch": 512, "lr": 9.050168008940276e-05, "gradient_norm": 0.25626885890960693, "tokens_per_second": 1133934.1394444276, "synthetic": false, "world_size": 8} {"step": 43580, "tokens": 11424235520, "loss": 2.3653047561645506, "optimizer_updates": 22790, "effective_batch": 512, "lr": 9.042908980322666e-05, "gradient_norm": 0.29641908407211304, "tokens_per_second": 1129213.8996867079, "synthetic": false, "world_size": 8} {"step": 43600, "tokens": 11429478400, "loss": 2.3515029907226563, "optimizer_updates": 22800, "effective_batch": 512, "lr": 9.035651287810796e-05, "gradient_norm": 0.2819603979587555, "tokens_per_second": 1132532.0160557579, "synthetic": false, "world_size": 8} {"step": 43620, "tokens": 11434721280, "loss": 2.3658199310302734, "optimizer_updates": 22810, "effective_batch": 512, "lr": 9.028394936359492e-05, "gradient_norm": 0.2760525345802307, "tokens_per_second": 1126087.4652400722, "synthetic": false, "world_size": 8} {"step": 43640, "tokens": 11439964160, "loss": 2.3561126708984377, "optimizer_updates": 22820, "effective_batch": 512, "lr": 9.02113993092266e-05, "gradient_norm": 0.26450666785240173, "tokens_per_second": 1140056.7247057925, "synthetic": false, "world_size": 8} {"step": 43660, "tokens": 11445207040, "loss": 2.3754201889038087, "optimizer_updates": 22830, "effective_batch": 512, "lr": 9.013886276453299e-05, "gradient_norm": 0.27804338932037354, "tokens_per_second": 1140112.9383804789, "synthetic": false, "world_size": 8} {"step": 43680, "tokens": 11450449920, "loss": 2.3718441009521483, "optimizer_updates": 22840, "effective_batch": 512, "lr": 9.006633977903472e-05, "gradient_norm": 0.2932252287864685, "tokens_per_second": 1130552.1374237915, "synthetic": false, "world_size": 8} {"step": 43700, "tokens": 11455692800, "loss": 2.354884719848633, "optimizer_updates": 22850, "effective_batch": 512, "lr": 8.999383040224326e-05, "gradient_norm": 0.25361722707748413, "tokens_per_second": 1127894.5797220743, "synthetic": false, "world_size": 8} {"step": 43720, "tokens": 11460935680, "loss": 2.365980529785156, "optimizer_updates": 22860, "effective_batch": 512, "lr": 8.992133468366068e-05, "gradient_norm": 0.3062272071838379, "tokens_per_second": 1125958.4446339896, "synthetic": false, "world_size": 8} {"step": 43740, "tokens": 11466178560, "loss": 2.3658557891845704, "optimizer_updates": 22870, "effective_batch": 512, "lr": 8.984885267277989e-05, "gradient_norm": 0.26444005966186523, "tokens_per_second": 1134150.5138826207, "synthetic": false, "world_size": 8} {"step": 43760, "tokens": 11471421440, "loss": 2.3655534744262696, "optimizer_updates": 22880, "effective_batch": 512, "lr": 8.977638441908425e-05, "gradient_norm": 0.2544848322868347, "tokens_per_second": 1142367.5844080904, "synthetic": false, "world_size": 8} {"step": 43780, "tokens": 11476664320, "loss": 2.3548210144042967, "optimizer_updates": 22890, "effective_batch": 512, "lr": 8.970392997204794e-05, "gradient_norm": 0.2542354464530945, "tokens_per_second": 1130581.1339633006, "synthetic": false, "world_size": 8} {"step": 43800, "tokens": 11481907200, "loss": 2.3638206481933595, "optimizer_updates": 22900, "effective_batch": 512, "lr": 8.96314893811355e-05, "gradient_norm": 0.28154557943344116, "tokens_per_second": 1127247.0001206489, "synthetic": false, "world_size": 8} {"step": 43820, "tokens": 11487150080, "loss": 2.3892974853515625, "optimizer_updates": 22910, "effective_batch": 512, "lr": 8.955906269580218e-05, "gradient_norm": 0.2802900969982147, "tokens_per_second": 1137519.8029277544, "synthetic": false, "world_size": 8} {"step": 43840, "tokens": 11492392960, "loss": 2.368757438659668, "optimizer_updates": 22920, "effective_batch": 512, "lr": 8.94866499654936e-05, "gradient_norm": 0.2853970229625702, "tokens_per_second": 1124032.9617454247, "synthetic": false, "world_size": 8} {"step": 43860, "tokens": 11497635840, "loss": 2.3657045364379883, "optimizer_updates": 22930, "effective_batch": 512, "lr": 8.941425123964598e-05, "gradient_norm": 0.2527911067008972, "tokens_per_second": 1130777.707443768, "synthetic": false, "world_size": 8} {"step": 43880, "tokens": 11502878720, "loss": 2.3646053314208983, "optimizer_updates": 22940, "effective_batch": 512, "lr": 8.934186656768585e-05, "gradient_norm": 0.31273186206817627, "tokens_per_second": 1119518.1892913019, "synthetic": false, "world_size": 8} {"step": 43900, "tokens": 11508121600, "loss": 2.3751142501831053, "optimizer_updates": 22950, "effective_batch": 512, "lr": 8.926949599903032e-05, "gradient_norm": 0.26653966307640076, "tokens_per_second": 1131617.3206054666, "synthetic": false, "world_size": 8} {"step": 43920, "tokens": 11513364480, "loss": 2.3677209854125976, "optimizer_updates": 22960, "effective_batch": 512, "lr": 8.919713958308663e-05, "gradient_norm": 0.2452988177537918, "tokens_per_second": 1124182.4603593869, "synthetic": false, "world_size": 8} {"step": 43940, "tokens": 11518607360, "loss": 2.3551376342773436, "optimizer_updates": 22970, "effective_batch": 512, "lr": 8.912479736925261e-05, "gradient_norm": 0.2519378960132599, "tokens_per_second": 1128891.2995656673, "synthetic": false, "world_size": 8} {"step": 43960, "tokens": 11523850240, "loss": 2.3617568969726563, "optimizer_updates": 22980, "effective_batch": 512, "lr": 8.905246940691625e-05, "gradient_norm": 0.28380948305130005, "tokens_per_second": 1133608.4468602329, "synthetic": false, "world_size": 8} {"step": 43980, "tokens": 11529093120, "loss": 2.3697343826293946, "optimizer_updates": 22990, "effective_batch": 512, "lr": 8.89801557454558e-05, "gradient_norm": 0.27108681201934814, "tokens_per_second": 1125304.384790475, "synthetic": false, "world_size": 8} {"step": 44000, "tokens": 11534336000, "loss": 2.3616910934448243, "optimizer_updates": 23000, "effective_batch": 512, "lr": 8.890785643423985e-05, "gradient_norm": 0.3110846281051636, "tokens_per_second": 823950.2877625572, "synthetic": false, "world_size": 8} {"step": 44020, "tokens": 11539578880, "loss": 2.364908218383789, "optimizer_updates": 23010, "effective_batch": 512, "lr": 8.883557152262703e-05, "gradient_norm": 0.2951182425022125, "tokens_per_second": 838225.8965869157, "synthetic": false, "world_size": 8} {"step": 44040, "tokens": 11544821760, "loss": 2.370149612426758, "optimizer_updates": 23020, "effective_batch": 512, "lr": 8.876330105996635e-05, "gradient_norm": 0.24241533875465393, "tokens_per_second": 1131877.9675274314, "synthetic": false, "world_size": 8} {"step": 44060, "tokens": 11550064640, "loss": 2.358746337890625, "optimizer_updates": 23030, "effective_batch": 512, "lr": 8.869104509559675e-05, "gradient_norm": 0.2745438814163208, "tokens_per_second": 1131081.4698925803, "synthetic": false, "world_size": 8} {"step": 44080, "tokens": 11555307520, "loss": 2.3596521377563477, "optimizer_updates": 23040, "effective_batch": 512, "lr": 8.861880367884745e-05, "gradient_norm": 0.30487295985221863, "tokens_per_second": 1134571.6403255772, "synthetic": false, "world_size": 8} {"step": 44100, "tokens": 11560550400, "loss": 2.3630279541015624, "optimizer_updates": 23050, "effective_batch": 512, "lr": 8.85465768590376e-05, "gradient_norm": 0.25618043541908264, "tokens_per_second": 1124078.303723256, "synthetic": false, "world_size": 8} {"step": 44120, "tokens": 11565793280, "loss": 2.3702791213989256, "optimizer_updates": 23060, "effective_batch": 512, "lr": 8.847436468547646e-05, "gradient_norm": 0.23589062690734863, "tokens_per_second": 1123271.8978884348, "synthetic": false, "world_size": 8} {"step": 44140, "tokens": 11571036160, "loss": 2.3816431045532225, "optimizer_updates": 23070, "effective_batch": 512, "lr": 8.840216720746322e-05, "gradient_norm": 0.31470322608947754, "tokens_per_second": 1130589.5007684445, "synthetic": false, "world_size": 8} {"step": 44160, "tokens": 11576279040, "loss": 2.357013702392578, "optimizer_updates": 23080, "effective_batch": 512, "lr": 8.832998447428717e-05, "gradient_norm": 0.24572229385375977, "tokens_per_second": 1130290.6910276408, "synthetic": false, "world_size": 8} {"step": 44180, "tokens": 11581521920, "loss": 2.3591228485107423, "optimizer_updates": 23090, "effective_batch": 512, "lr": 8.825781653522736e-05, "gradient_norm": 0.2885569930076599, "tokens_per_second": 1121810.2721658836, "synthetic": false, "world_size": 8} {"step": 44200, "tokens": 11586764800, "loss": 2.3645883560180665, "optimizer_updates": 23100, "effective_batch": 512, "lr": 8.818566343955294e-05, "gradient_norm": 0.24603766202926636, "tokens_per_second": 1129176.5357596846, "synthetic": false, "world_size": 8} {"step": 44220, "tokens": 11592007680, "loss": 2.3622703552246094, "optimizer_updates": 23110, "effective_batch": 512, "lr": 8.811352523652269e-05, "gradient_norm": 0.2596435844898224, "tokens_per_second": 1129214.4719582708, "synthetic": false, "world_size": 8} {"step": 44240, "tokens": 11597250560, "loss": 2.362818145751953, "optimizer_updates": 23120, "effective_batch": 512, "lr": 8.804140197538549e-05, "gradient_norm": 0.25785139203071594, "tokens_per_second": 1140959.3394272726, "synthetic": false, "world_size": 8} {"step": 44260, "tokens": 11602493440, "loss": 2.358473205566406, "optimizer_updates": 23130, "effective_batch": 512, "lr": 8.796929370537977e-05, "gradient_norm": 0.27695968747138977, "tokens_per_second": 1135750.6125452314, "synthetic": false, "world_size": 8} {"step": 44280, "tokens": 11607736320, "loss": 2.36292724609375, "optimizer_updates": 23140, "effective_batch": 512, "lr": 8.789720047573388e-05, "gradient_norm": 0.254135400056839, "tokens_per_second": 1130569.7508341135, "synthetic": false, "world_size": 8} {"step": 44300, "tokens": 11612979200, "loss": 2.3615304946899416, "optimizer_updates": 23150, "effective_batch": 512, "lr": 8.782512233566582e-05, "gradient_norm": 0.26322752237319946, "tokens_per_second": 1123052.1390047325, "synthetic": false, "world_size": 8} {"step": 44320, "tokens": 11618222080, "loss": 2.3583986282348635, "optimizer_updates": 23160, "effective_batch": 512, "lr": 8.775305933438339e-05, "gradient_norm": 0.4750412404537201, "tokens_per_second": 1127496.1812090974, "synthetic": false, "world_size": 8} {"step": 44340, "tokens": 11623464960, "loss": 2.364948844909668, "optimizer_updates": 23170, "effective_batch": 512, "lr": 8.768101152108392e-05, "gradient_norm": 0.33518823981285095, "tokens_per_second": 1126998.9834119228, "synthetic": false, "world_size": 8} {"step": 44360, "tokens": 11628707840, "loss": 2.368826484680176, "optimizer_updates": 23180, "effective_batch": 512, "lr": 8.760897894495447e-05, "gradient_norm": 0.25402164459228516, "tokens_per_second": 1008870.6506046439, "synthetic": false, "world_size": 8} {"step": 44380, "tokens": 11633950720, "loss": 2.369259071350098, "optimizer_updates": 23190, "effective_batch": 512, "lr": 8.753696165517171e-05, "gradient_norm": 0.2827438414096832, "tokens_per_second": 1121624.076494348, "synthetic": false, "world_size": 8} {"step": 44400, "tokens": 11639193600, "loss": 2.365402603149414, "optimizer_updates": 23200, "effective_batch": 512, "lr": 8.74649597009018e-05, "gradient_norm": 0.2599535286426544, "tokens_per_second": 1137876.968166238, "synthetic": false, "world_size": 8} {"step": 44420, "tokens": 11644436480, "loss": 2.3828731536865235, "optimizer_updates": 23210, "effective_batch": 512, "lr": 8.739297313130044e-05, "gradient_norm": 0.2501068711280823, "tokens_per_second": 1123799.1308583256, "synthetic": false, "world_size": 8} {"step": 44440, "tokens": 11649679360, "loss": 2.3796884536743166, "optimizer_updates": 23220, "effective_batch": 512, "lr": 8.732100199551286e-05, "gradient_norm": 0.26286065578460693, "tokens_per_second": 1126721.8465424865, "synthetic": false, "world_size": 8} {"step": 44460, "tokens": 11654922240, "loss": 2.375178909301758, "optimizer_updates": 23230, "effective_batch": 512, "lr": 8.724904634267378e-05, "gradient_norm": 0.2645404636859894, "tokens_per_second": 1032587.0829101682, "synthetic": false, "world_size": 8} {"step": 44480, "tokens": 11660165120, "loss": 2.3619035720825194, "optimizer_updates": 23240, "effective_batch": 512, "lr": 8.717710622190726e-05, "gradient_norm": 0.2545628249645233, "tokens_per_second": 1125262.460231052, "synthetic": false, "world_size": 8} {"step": 44500, "tokens": 11665408000, "loss": 2.3738849639892576, "optimizer_updates": 23250, "effective_batch": 512, "lr": 8.710518168232686e-05, "gradient_norm": 0.2726808488368988, "tokens_per_second": 1125771.343333051, "synthetic": false, "world_size": 8} {"step": 44520, "tokens": 11670650880, "loss": 2.3772003173828127, "optimizer_updates": 23260, "effective_batch": 512, "lr": 8.703327277303538e-05, "gradient_norm": 0.24382853507995605, "tokens_per_second": 1130447.9449672224, "synthetic": false, "world_size": 8} {"step": 44540, "tokens": 11675893760, "loss": 2.3663799285888674, "optimizer_updates": 23270, "effective_batch": 512, "lr": 8.696137954312511e-05, "gradient_norm": 0.2358003407716751, "tokens_per_second": 772178.5638699635, "synthetic": false, "world_size": 8} {"step": 44560, "tokens": 11681136640, "loss": 2.3731056213378907, "optimizer_updates": 23280, "effective_batch": 512, "lr": 8.68895020416775e-05, "gradient_norm": 0.23750871419906616, "tokens_per_second": 1129257.826698183, "synthetic": false, "world_size": 8} {"step": 44580, "tokens": 11686379520, "loss": 2.3583723068237306, "optimizer_updates": 23290, "effective_batch": 512, "lr": 8.681764031776334e-05, "gradient_norm": 0.24666033685207367, "tokens_per_second": 1128549.7370546018, "synthetic": false, "world_size": 8} {"step": 44600, "tokens": 11691622400, "loss": 2.3681686401367186, "optimizer_updates": 23300, "effective_batch": 512, "lr": 8.674579442044254e-05, "gradient_norm": 0.2949880063533783, "tokens_per_second": 1114875.2587407778, "synthetic": false, "world_size": 8} {"step": 44620, "tokens": 11696865280, "loss": 2.359701919555664, "optimizer_updates": 23310, "effective_batch": 512, "lr": 8.667396439876438e-05, "gradient_norm": 0.2676076292991638, "tokens_per_second": 1123603.100138554, "synthetic": false, "world_size": 8} {"step": 44640, "tokens": 11702108160, "loss": 2.3672863006591798, "optimizer_updates": 23320, "effective_batch": 512, "lr": 8.660215030176712e-05, "gradient_norm": 0.24034923315048218, "tokens_per_second": 1121246.0337902526, "synthetic": false, "world_size": 8} {"step": 44660, "tokens": 11707351040, "loss": 2.3638628005981444, "optimizer_updates": 23330, "effective_batch": 512, "lr": 8.653035217847833e-05, "gradient_norm": 0.27474403381347656, "tokens_per_second": 1118746.744370379, "synthetic": false, "world_size": 8} {"step": 44680, "tokens": 11712593920, "loss": 2.3709184646606447, "optimizer_updates": 23340, "effective_batch": 512, "lr": 8.645857007791447e-05, "gradient_norm": 0.33038216829299927, "tokens_per_second": 1123075.7609269512, "synthetic": false, "world_size": 8} {"step": 44700, "tokens": 11717836800, "loss": 2.3622371673583986, "optimizer_updates": 23350, "effective_batch": 512, "lr": 8.638680404908126e-05, "gradient_norm": 0.28264153003692627, "tokens_per_second": 1116153.852892838, "synthetic": false, "world_size": 8} {"step": 44720, "tokens": 11723079680, "loss": 2.3695470809936525, "optimizer_updates": 23360, "effective_batch": 512, "lr": 8.63150541409733e-05, "gradient_norm": 0.2538452744483948, "tokens_per_second": 1124033.659622829, "synthetic": false, "world_size": 8} {"step": 44740, "tokens": 11728322560, "loss": 2.368827247619629, "optimizer_updates": 23370, "effective_batch": 512, "lr": 8.624332040257427e-05, "gradient_norm": 0.253091961145401, "tokens_per_second": 1125909.0894475325, "synthetic": false, "world_size": 8} {"step": 44760, "tokens": 11733565440, "loss": 2.361261558532715, "optimizer_updates": 23380, "effective_batch": 512, "lr": 8.617160288285674e-05, "gradient_norm": 0.24220828711986542, "tokens_per_second": 1118533.9705299984, "synthetic": false, "world_size": 8} {"step": 44780, "tokens": 11738808320, "loss": 2.3670778274536133, "optimizer_updates": 23390, "effective_batch": 512, "lr": 8.609990163078233e-05, "gradient_norm": 0.24768948554992676, "tokens_per_second": 1132030.169983306, "synthetic": false, "world_size": 8} {"step": 44800, "tokens": 11744051200, "loss": 2.359340286254883, "optimizer_updates": 23400, "effective_batch": 512, "lr": 8.602821669530138e-05, "gradient_norm": 0.2451583445072174, "tokens_per_second": 1125182.1452758776, "synthetic": false, "world_size": 8} {"step": 44820, "tokens": 11749294080, "loss": 2.3636045455932617, "optimizer_updates": 23410, "effective_batch": 512, "lr": 8.595654812535321e-05, "gradient_norm": 0.3389957845211029, "tokens_per_second": 1131477.09454839, "synthetic": false, "world_size": 8} {"step": 44840, "tokens": 11754536960, "loss": 2.3636093139648438, "optimizer_updates": 23420, "effective_batch": 512, "lr": 8.588489596986603e-05, "gradient_norm": 0.24601203203201294, "tokens_per_second": 1124643.2153592142, "synthetic": false, "world_size": 8} {"step": 44860, "tokens": 11759779840, "loss": 2.37689323425293, "optimizer_updates": 23430, "effective_batch": 512, "lr": 8.581326027775665e-05, "gradient_norm": 0.2505325376987457, "tokens_per_second": 1130203.2013048218, "synthetic": false, "world_size": 8} {"step": 44880, "tokens": 11765022720, "loss": 2.3613607406616213, "optimizer_updates": 23440, "effective_batch": 512, "lr": 8.574164109793078e-05, "gradient_norm": 0.2511580288410187, "tokens_per_second": 1130769.6854215937, "synthetic": false, "world_size": 8} {"step": 44900, "tokens": 11770265600, "loss": 2.3729555130004885, "optimizer_updates": 23450, "effective_batch": 512, "lr": 8.567003847928284e-05, "gradient_norm": 0.25634998083114624, "tokens_per_second": 1127697.9897681505, "synthetic": false, "world_size": 8} {"step": 44920, "tokens": 11775508480, "loss": 2.3620248794555665, "optimizer_updates": 23460, "effective_batch": 512, "lr": 8.559845247069592e-05, "gradient_norm": 0.24083878099918365, "tokens_per_second": 847016.0458485488, "synthetic": false, "world_size": 8} {"step": 44940, "tokens": 11780751360, "loss": 2.3703180313110352, "optimizer_updates": 23470, "effective_batch": 512, "lr": 8.552688312104173e-05, "gradient_norm": 0.28652530908584595, "tokens_per_second": 973826.6747612688, "synthetic": false, "world_size": 8} {"step": 44960, "tokens": 11785994240, "loss": 2.3616058349609377, "optimizer_updates": 23480, "effective_batch": 512, "lr": 8.545533047918075e-05, "gradient_norm": 0.2759125828742981, "tokens_per_second": 1139782.212932745, "synthetic": false, "world_size": 8} {"step": 44980, "tokens": 11791237120, "loss": 2.3662273406982424, "optimizer_updates": 23490, "effective_batch": 512, "lr": 8.538379459396186e-05, "gradient_norm": 0.27112212777137756, "tokens_per_second": 1133191.3118581227, "synthetic": false, "world_size": 8} {"step": 45000, "tokens": 11796480000, "loss": 2.3563413619995117, "optimizer_updates": 23500, "effective_batch": 512, "lr": 8.531227551422267e-05, "gradient_norm": 0.23664133250713348, "tokens_per_second": 1129007.207558868, "synthetic": false, "world_size": 8} {"step": 45020, "tokens": 11801722880, "loss": 2.3586393356323243, "optimizer_updates": 23510, "effective_batch": 512, "lr": 8.524077328878918e-05, "gradient_norm": 0.27053824067115784, "tokens_per_second": 830969.4831438614, "synthetic": false, "world_size": 8} {"step": 45040, "tokens": 11806965760, "loss": 2.366909980773926, "optimizer_updates": 23520, "effective_batch": 512, "lr": 8.516928796647602e-05, "gradient_norm": 0.22550885379314423, "tokens_per_second": 1137564.1457932643, "synthetic": false, "world_size": 8} {"step": 45060, "tokens": 11812208640, "loss": 2.3526338577270507, "optimizer_updates": 23530, "effective_batch": 512, "lr": 8.509781959608615e-05, "gradient_norm": 0.28479334712028503, "tokens_per_second": 1132828.7667667377, "synthetic": false, "world_size": 8} {"step": 45080, "tokens": 11817451520, "loss": 2.3599945068359376, "optimizer_updates": 23540, "effective_batch": 512, "lr": 8.502636822641107e-05, "gradient_norm": 0.25805434584617615, "tokens_per_second": 1131803.2908036844, "synthetic": false, "world_size": 8} {"step": 45100, "tokens": 11822694400, "loss": 2.3831676483154296, "optimizer_updates": 23550, "effective_batch": 512, "lr": 8.495493390623053e-05, "gradient_norm": 0.23786486685276031, "tokens_per_second": 1126412.0264377652, "synthetic": false, "world_size": 8} {"step": 45120, "tokens": 11827937280, "loss": 2.365494155883789, "optimizer_updates": 23560, "effective_batch": 512, "lr": 8.488351668431283e-05, "gradient_norm": 0.25539761781692505, "tokens_per_second": 1139712.7746298066, "synthetic": false, "world_size": 8} {"step": 45140, "tokens": 11833180160, "loss": 2.359904479980469, "optimizer_updates": 23570, "effective_batch": 512, "lr": 8.481211660941441e-05, "gradient_norm": 0.3285747766494751, "tokens_per_second": 1128947.5846435037, "synthetic": false, "world_size": 8} {"step": 45160, "tokens": 11838423040, "loss": 2.359392547607422, "optimizer_updates": 23580, "effective_batch": 512, "lr": 8.474073373028018e-05, "gradient_norm": 0.278143972158432, "tokens_per_second": 1128862.6591296294, "synthetic": false, "world_size": 8} {"step": 45180, "tokens": 11843665920, "loss": 2.362655448913574, "optimizer_updates": 23590, "effective_batch": 512, "lr": 8.466936809564313e-05, "gradient_norm": 0.2927844226360321, "tokens_per_second": 1113691.6712253715, "synthetic": false, "world_size": 8} {"step": 45200, "tokens": 11848908800, "loss": 2.37365779876709, "optimizer_updates": 23600, "effective_batch": 512, "lr": 8.459801975422466e-05, "gradient_norm": 0.29636090993881226, "tokens_per_second": 1013057.7111989794, "synthetic": false, "world_size": 8} {"step": 45220, "tokens": 11854151680, "loss": 2.356362724304199, "optimizer_updates": 23610, "effective_batch": 512, "lr": 8.452668875473419e-05, "gradient_norm": 0.2521151006221771, "tokens_per_second": 1127373.21173413, "synthetic": false, "world_size": 8} {"step": 45240, "tokens": 11859394560, "loss": 2.3661951065063476, "optimizer_updates": 23620, "effective_batch": 512, "lr": 8.44553751458694e-05, "gradient_norm": 0.2943180501461029, "tokens_per_second": 1134527.2783388318, "synthetic": false, "world_size": 8} {"step": 45260, "tokens": 11864637440, "loss": 2.3781625747680666, "optimizer_updates": 23630, "effective_batch": 512, "lr": 8.438407897631614e-05, "gradient_norm": 0.3095163404941559, "tokens_per_second": 1130856.7735838227, "synthetic": false, "world_size": 8} {"step": 45280, "tokens": 11869880320, "loss": 2.3644256591796875, "optimizer_updates": 23640, "effective_batch": 512, "lr": 8.43128002947482e-05, "gradient_norm": 0.2822679579257965, "tokens_per_second": 1125012.0833068648, "synthetic": false, "world_size": 8} {"step": 45300, "tokens": 11875123200, "loss": 2.363834762573242, "optimizer_updates": 23650, "effective_batch": 512, "lr": 8.424153914982762e-05, "gradient_norm": 0.2733913064002991, "tokens_per_second": 1131996.0920068475, "synthetic": false, "world_size": 8} {"step": 45320, "tokens": 11880366080, "loss": 2.359024429321289, "optimizer_updates": 23660, "effective_batch": 512, "lr": 8.417029559020428e-05, "gradient_norm": 0.2602766454219818, "tokens_per_second": 1014374.1590305171, "synthetic": false, "world_size": 8} {"step": 45340, "tokens": 11885608960, "loss": 2.3748119354248045, "optimizer_updates": 23670, "effective_batch": 512, "lr": 8.409906966451624e-05, "gradient_norm": 0.2537078857421875, "tokens_per_second": 1125521.2325679525, "synthetic": false, "world_size": 8} {"step": 45360, "tokens": 11890851840, "loss": 2.3612316131591795, "optimizer_updates": 23680, "effective_batch": 512, "lr": 8.402786142138937e-05, "gradient_norm": 0.2934134006500244, "tokens_per_second": 1133622.778451117, "synthetic": false, "world_size": 8} {"step": 45380, "tokens": 11896094720, "loss": 2.3734481811523436, "optimizer_updates": 23690, "effective_batch": 512, "lr": 8.395667090943755e-05, "gradient_norm": 0.3092231750488281, "tokens_per_second": 1128043.1152696274, "synthetic": false, "world_size": 8} {"step": 45400, "tokens": 11901337600, "loss": 2.3675676345825196, "optimizer_updates": 23700, "effective_batch": 512, "lr": 8.388549817726248e-05, "gradient_norm": 0.24732622504234314, "tokens_per_second": 1015618.0191978266, "synthetic": false, "world_size": 8} {"step": 45420, "tokens": 11906580480, "loss": 2.360695648193359, "optimizer_updates": 23710, "effective_batch": 512, "lr": 8.381434327345386e-05, "gradient_norm": 0.28710129857063293, "tokens_per_second": 1139092.133631781, "synthetic": false, "world_size": 8} {"step": 45440, "tokens": 11911823360, "loss": 2.3672147750854493, "optimizer_updates": 23720, "effective_batch": 512, "lr": 8.374320624658905e-05, "gradient_norm": 0.2568678557872772, "tokens_per_second": 1132068.031246379, "synthetic": false, "world_size": 8} {"step": 45460, "tokens": 11917066240, "loss": 2.3612592697143553, "optimizer_updates": 23730, "effective_batch": 512, "lr": 8.367208714523335e-05, "gradient_norm": 0.2858611047267914, "tokens_per_second": 1128088.149814883, "synthetic": false, "world_size": 8} {"step": 45480, "tokens": 11922309120, "loss": 2.370224380493164, "optimizer_updates": 23740, "effective_batch": 512, "lr": 8.360098601793971e-05, "gradient_norm": 0.28309401869773865, "tokens_per_second": 1132674.6270211288, "synthetic": false, "world_size": 8} {"step": 45500, "tokens": 11927552000, "loss": 2.3768098831176756, "optimizer_updates": 23750, "effective_batch": 512, "lr": 8.352990291324892e-05, "gradient_norm": 0.34520918130874634, "tokens_per_second": 1140594.1755901172, "synthetic": false, "world_size": 8} {"step": 45520, "tokens": 11932794880, "loss": 2.3637208938598633, "optimizer_updates": 23760, "effective_batch": 512, "lr": 8.345883787968934e-05, "gradient_norm": 0.2772405445575714, "tokens_per_second": 1136213.577106825, "synthetic": false, "world_size": 8} {"step": 45540, "tokens": 11938037760, "loss": 2.364389991760254, "optimizer_updates": 23770, "effective_batch": 512, "lr": 8.338779096577711e-05, "gradient_norm": 0.2647174894809723, "tokens_per_second": 1131887.2119738539, "synthetic": false, "world_size": 8} {"step": 45560, "tokens": 11943280640, "loss": 2.3635814666748045, "optimizer_updates": 23780, "effective_batch": 512, "lr": 8.331676222001588e-05, "gradient_norm": 0.26192277669906616, "tokens_per_second": 1136958.2610856711, "synthetic": false, "world_size": 8} {"step": 45580, "tokens": 11948523520, "loss": 2.3796695709228515, "optimizer_updates": 23790, "effective_batch": 512, "lr": 8.324575169089703e-05, "gradient_norm": 0.24937765300273895, "tokens_per_second": 1132616.9919802742, "synthetic": false, "world_size": 8} {"step": 45600, "tokens": 11953766400, "loss": 2.359441947937012, "optimizer_updates": 23800, "effective_batch": 512, "lr": 8.317475942689939e-05, "gradient_norm": 0.28355154395103455, "tokens_per_second": 1133628.9749669046, "synthetic": false, "world_size": 8} {"step": 45620, "tokens": 11959009280, "loss": 2.368202018737793, "optimizer_updates": 23810, "effective_batch": 512, "lr": 8.310378547648943e-05, "gradient_norm": 0.2392825186252594, "tokens_per_second": 1135740.7284414482, "synthetic": false, "world_size": 8} {"step": 45640, "tokens": 11964252160, "loss": 2.3623985290527343, "optimizer_updates": 23820, "effective_batch": 512, "lr": 8.303282988812097e-05, "gradient_norm": 0.24241866171360016, "tokens_per_second": 1133428.4713254166, "synthetic": false, "world_size": 8} {"step": 45660, "tokens": 11969495040, "loss": 2.3666610717773438, "optimizer_updates": 23830, "effective_batch": 512, "lr": 8.296189271023545e-05, "gradient_norm": 0.26416343450546265, "tokens_per_second": 1133431.453327517, "synthetic": false, "world_size": 8} {"step": 45680, "tokens": 11974737920, "loss": 2.3657163619995116, "optimizer_updates": 23840, "effective_batch": 512, "lr": 8.289097399126167e-05, "gradient_norm": 0.2542298436164856, "tokens_per_second": 1122876.2294094898, "synthetic": false, "world_size": 8} {"step": 45700, "tokens": 11979980800, "loss": 2.3610567092895507, "optimizer_updates": 23850, "effective_batch": 512, "lr": 8.282007377961577e-05, "gradient_norm": 0.24162207543849945, "tokens_per_second": 1133575.9612689465, "synthetic": false, "world_size": 8} {"step": 45720, "tokens": 11985223680, "loss": 2.372066307067871, "optimizer_updates": 23860, "effective_batch": 512, "lr": 8.274919212370136e-05, "gradient_norm": 0.2649887204170227, "tokens_per_second": 1123029.4793181273, "synthetic": false, "world_size": 8} {"step": 45740, "tokens": 11990466560, "loss": 2.357997512817383, "optimizer_updates": 23870, "effective_batch": 512, "lr": 8.267832907190931e-05, "gradient_norm": 0.27029868960380554, "tokens_per_second": 1135241.629252225, "synthetic": false, "world_size": 8} {"step": 45760, "tokens": 11995709440, "loss": 2.3742502212524412, "optimizer_updates": 23880, "effective_batch": 512, "lr": 8.260748467261787e-05, "gradient_norm": 0.25374510884284973, "tokens_per_second": 1137608.1869976034, "synthetic": false, "world_size": 8} {"step": 45780, "tokens": 12000952320, "loss": 2.368844413757324, "optimizer_updates": 23890, "effective_batch": 512, "lr": 8.25366589741924e-05, "gradient_norm": 0.2524067163467407, "tokens_per_second": 1138098.2336883433, "synthetic": false, "world_size": 8} {"step": 45800, "tokens": 12006195200, "loss": 2.3591705322265626, "optimizer_updates": 23900, "effective_batch": 512, "lr": 8.246585202498571e-05, "gradient_norm": 0.23152916133403778, "tokens_per_second": 1131842.503294014, "synthetic": false, "world_size": 8} {"step": 45820, "tokens": 12011438080, "loss": 2.36590576171875, "optimizer_updates": 23910, "effective_batch": 512, "lr": 8.239506387333761e-05, "gradient_norm": 0.2246657907962799, "tokens_per_second": 1124868.0120401923, "synthetic": false, "world_size": 8} {"step": 45840, "tokens": 12016680960, "loss": 2.361402702331543, "optimizer_updates": 23920, "effective_batch": 512, "lr": 8.23242945675752e-05, "gradient_norm": 0.2659708559513092, "tokens_per_second": 1130870.909829185, "synthetic": false, "world_size": 8} {"step": 45860, "tokens": 12021923840, "loss": 2.359944152832031, "optimizer_updates": 23930, "effective_batch": 512, "lr": 8.225354415601264e-05, "gradient_norm": 0.25056007504463196, "tokens_per_second": 1127869.5808050751, "synthetic": false, "world_size": 8} {"step": 45880, "tokens": 12027166720, "loss": 2.3724954605102537, "optimizer_updates": 23940, "effective_batch": 512, "lr": 8.218281268695124e-05, "gradient_norm": 0.28130078315734863, "tokens_per_second": 1133876.9134546134, "synthetic": false, "world_size": 8} {"step": 45900, "tokens": 12032409600, "loss": 2.355990409851074, "optimizer_updates": 23950, "effective_batch": 512, "lr": 8.211210020867937e-05, "gradient_norm": 0.24869850277900696, "tokens_per_second": 1130221.15348686, "synthetic": false, "world_size": 8} {"step": 45920, "tokens": 12037652480, "loss": 2.365509796142578, "optimizer_updates": 23960, "effective_batch": 512, "lr": 8.204140676947246e-05, "gradient_norm": 0.24057362973690033, "tokens_per_second": 1131464.680706554, "synthetic": false, "world_size": 8} {"step": 45940, "tokens": 12042895360, "loss": 2.359401321411133, "optimizer_updates": 23970, "effective_batch": 512, "lr": 8.197073241759285e-05, "gradient_norm": 0.2863679528236389, "tokens_per_second": 1124286.0138042774, "synthetic": false, "world_size": 8} {"step": 45960, "tokens": 12048138240, "loss": 2.3517129898071287, "optimizer_updates": 23980, "effective_batch": 512, "lr": 8.190007720128994e-05, "gradient_norm": 0.298797070980072, "tokens_per_second": 1130197.400802413, "synthetic": false, "world_size": 8} {"step": 45980, "tokens": 12053381120, "loss": 2.354159355163574, "optimizer_updates": 23990, "effective_batch": 512, "lr": 8.182944116880004e-05, "gradient_norm": 0.2517656981945038, "tokens_per_second": 1130749.0519819905, "synthetic": false, "world_size": 8} {"step": 46000, "tokens": 12058624000, "loss": 2.3689205169677736, "optimizer_updates": 24000, "effective_batch": 512, "lr": 8.175882436834634e-05, "gradient_norm": 0.28984808921813965, "tokens_per_second": 1129998.73041724, "synthetic": false, "world_size": 8} {"step": 46020, "tokens": 12063866880, "loss": 2.3586442947387694, "optimizer_updates": 24010, "effective_batch": 512, "lr": 8.168822684813893e-05, "gradient_norm": 0.2661297023296356, "tokens_per_second": 833687.6771192978, "synthetic": false, "world_size": 8} {"step": 46040, "tokens": 12069109760, "loss": 2.362736129760742, "optimizer_updates": 24020, "effective_batch": 512, "lr": 8.161764865637475e-05, "gradient_norm": 0.23499524593353271, "tokens_per_second": 1132756.4750746689, "synthetic": false, "world_size": 8} {"step": 46060, "tokens": 12074352640, "loss": 2.3646411895751953, "optimizer_updates": 24030, "effective_batch": 512, "lr": 8.154708984123745e-05, "gradient_norm": 0.26556506752967834, "tokens_per_second": 1138529.0149502477, "synthetic": false, "world_size": 8} {"step": 46080, "tokens": 12079595520, "loss": 2.367252731323242, "optimizer_updates": 24040, "effective_batch": 512, "lr": 8.147655045089761e-05, "gradient_norm": 0.2597053349018097, "tokens_per_second": 1123736.9939791823, "synthetic": false, "world_size": 8} {"step": 46100, "tokens": 12084838400, "loss": 2.3601089477539063, "optimizer_updates": 24050, "effective_batch": 512, "lr": 8.140603053351238e-05, "gradient_norm": 0.29178446531295776, "tokens_per_second": 1135635.3718287335, "synthetic": false, "world_size": 8} {"step": 46120, "tokens": 12090081280, "loss": 2.3559730529785154, "optimizer_updates": 24060, "effective_batch": 512, "lr": 8.133553013722572e-05, "gradient_norm": 0.2716141939163208, "tokens_per_second": 1138712.281749956, "synthetic": false, "world_size": 8} {"step": 46140, "tokens": 12095324160, "loss": 2.380122947692871, "optimizer_updates": 24070, "effective_batch": 512, "lr": 8.126504931016832e-05, "gradient_norm": 0.25712430477142334, "tokens_per_second": 1141025.6458605633, "synthetic": false, "world_size": 8} {"step": 46160, "tokens": 12100567040, "loss": 2.359926223754883, "optimizer_updates": 24080, "effective_batch": 512, "lr": 8.119458810045734e-05, "gradient_norm": 0.34020838141441345, "tokens_per_second": 1134089.1844633769, "synthetic": false, "world_size": 8} {"step": 46180, "tokens": 12105809920, "loss": 2.3675018310546876, "optimizer_updates": 24090, "effective_batch": 512, "lr": 8.112414655619668e-05, "gradient_norm": 0.23390081524848938, "tokens_per_second": 1136593.3338174857, "synthetic": false, "world_size": 8} {"step": 46200, "tokens": 12111052800, "loss": 2.3575206756591798, "optimizer_updates": 24100, "effective_batch": 512, "lr": 8.105372472547672e-05, "gradient_norm": 0.3222416937351227, "tokens_per_second": 1133582.5324809575, "synthetic": false, "world_size": 8} {"step": 46220, "tokens": 12116295680, "loss": 2.3684467315673827, "optimizer_updates": 24110, "effective_batch": 512, "lr": 8.09833226563745e-05, "gradient_norm": 0.2749267518520355, "tokens_per_second": 1127671.7919311358, "synthetic": false, "world_size": 8} {"step": 46240, "tokens": 12121538560, "loss": 2.3663152694702148, "optimizer_updates": 24120, "effective_batch": 512, "lr": 8.091294039695344e-05, "gradient_norm": 0.23156091570854187, "tokens_per_second": 1134509.2718116217, "synthetic": false, "world_size": 8} {"step": 46260, "tokens": 12126781440, "loss": 2.367785835266113, "optimizer_updates": 24130, "effective_batch": 512, "lr": 8.084257799526356e-05, "gradient_norm": 0.2759549915790558, "tokens_per_second": 1135354.5746172974, "synthetic": false, "world_size": 8} {"step": 46280, "tokens": 12132024320, "loss": 2.364771842956543, "optimizer_updates": 24140, "effective_batch": 512, "lr": 8.077223549934118e-05, "gradient_norm": 0.27119216322898865, "tokens_per_second": 1133817.9292267964, "synthetic": false, "world_size": 8} {"step": 46300, "tokens": 12137267200, "loss": 2.3612028121948243, "optimizer_updates": 24150, "effective_batch": 512, "lr": 8.07019129572092e-05, "gradient_norm": 0.3272080719470978, "tokens_per_second": 1129264.831267442, "synthetic": false, "world_size": 8} {"step": 46320, "tokens": 12142510080, "loss": 2.3642742156982424, "optimizer_updates": 24160, "effective_batch": 512, "lr": 8.063161041687675e-05, "gradient_norm": 0.25379419326782227, "tokens_per_second": 1128649.7812798205, "synthetic": false, "world_size": 8} {"step": 46340, "tokens": 12147752960, "loss": 2.3461223602294923, "optimizer_updates": 24170, "effective_batch": 512, "lr": 8.05613279263394e-05, "gradient_norm": 0.2558634579181671, "tokens_per_second": 1130434.1500292206, "synthetic": false, "world_size": 8} {"step": 46360, "tokens": 12152995840, "loss": 2.354487991333008, "optimizer_updates": 24180, "effective_batch": 512, "lr": 8.049106553357896e-05, "gradient_norm": 0.23018494248390198, "tokens_per_second": 1143417.8074730176, "synthetic": false, "world_size": 8} {"step": 46380, "tokens": 12158238720, "loss": 2.372224044799805, "optimizer_updates": 24190, "effective_batch": 512, "lr": 8.042082328656359e-05, "gradient_norm": 0.2270369678735733, "tokens_per_second": 1034962.7775031744, "synthetic": false, "world_size": 8} {"step": 46400, "tokens": 12163481600, "loss": 2.367813301086426, "optimizer_updates": 24200, "effective_batch": 512, "lr": 8.035060123324761e-05, "gradient_norm": 0.24793203175067902, "tokens_per_second": 1128682.5471655643, "synthetic": false, "world_size": 8} {"step": 46420, "tokens": 12168724480, "loss": 2.3645561218261717, "optimizer_updates": 24210, "effective_batch": 512, "lr": 8.028039942157167e-05, "gradient_norm": 0.2730920612812042, "tokens_per_second": 1135287.0582527153, "synthetic": false, "world_size": 8} {"step": 46440, "tokens": 12173967360, "loss": 2.3552679061889648, "optimizer_updates": 24220, "effective_batch": 512, "lr": 8.021021789946248e-05, "gradient_norm": 0.2387417107820511, "tokens_per_second": 1132881.3916240018, "synthetic": false, "world_size": 8} {"step": 46460, "tokens": 12179210240, "loss": 2.363251495361328, "optimizer_updates": 24230, "effective_batch": 512, "lr": 8.014005671483301e-05, "gradient_norm": 0.24043825268745422, "tokens_per_second": 1136666.2572899796, "synthetic": false, "world_size": 8} {"step": 46480, "tokens": 12184453120, "loss": 2.3589006423950196, "optimizer_updates": 24240, "effective_batch": 512, "lr": 8.006991591558224e-05, "gradient_norm": 0.24266088008880615, "tokens_per_second": 1135008.0276393008, "synthetic": false, "world_size": 8} {"step": 46500, "tokens": 12189696000, "loss": 2.367447280883789, "optimizer_updates": 24250, "effective_batch": 512, "lr": 7.999979554959532e-05, "gradient_norm": 0.2821412682533264, "tokens_per_second": 1126671.5636895928, "synthetic": false, "world_size": 8} {"step": 46520, "tokens": 12194938880, "loss": 2.3661365509033203, "optimizer_updates": 24260, "effective_batch": 512, "lr": 7.992969566474335e-05, "gradient_norm": 0.26829105615615845, "tokens_per_second": 1141963.6236455399, "synthetic": false, "world_size": 8} {"step": 46540, "tokens": 12200181760, "loss": 2.3663421630859376, "optimizer_updates": 24270, "effective_batch": 512, "lr": 7.985961630888356e-05, "gradient_norm": 0.3181515336036682, "tokens_per_second": 1015127.972841128, "synthetic": false, "world_size": 8} {"step": 46560, "tokens": 12205424640, "loss": 2.3614261627197264, "optimizer_updates": 24280, "effective_batch": 512, "lr": 7.978955752985914e-05, "gradient_norm": 0.2931423783302307, "tokens_per_second": 1122086.2742141555, "synthetic": false, "world_size": 8} {"step": 46580, "tokens": 12210667520, "loss": 2.3476877212524414, "optimizer_updates": 24290, "effective_batch": 512, "lr": 7.971951937549917e-05, "gradient_norm": 0.25445127487182617, "tokens_per_second": 1126943.4931993373, "synthetic": false, "world_size": 8} {"step": 46600, "tokens": 12215910400, "loss": 2.3625696182250975, "optimizer_updates": 24300, "effective_batch": 512, "lr": 7.964950189361872e-05, "gradient_norm": 0.24071025848388672, "tokens_per_second": 1127437.1529695024, "synthetic": false, "world_size": 8} {"step": 46620, "tokens": 12221153280, "loss": 2.3550222396850584, "optimizer_updates": 24310, "effective_batch": 512, "lr": 7.957950513201867e-05, "gradient_norm": 0.2521885931491852, "tokens_per_second": 1126881.6751752398, "synthetic": false, "world_size": 8} {"step": 46640, "tokens": 12226396160, "loss": 2.3671016693115234, "optimizer_updates": 24320, "effective_batch": 512, "lr": 7.950952913848582e-05, "gradient_norm": 0.2518784701824188, "tokens_per_second": 1132058.430419193, "synthetic": false, "world_size": 8} {"step": 46660, "tokens": 12231639040, "loss": 2.370993804931641, "optimizer_updates": 24330, "effective_batch": 512, "lr": 7.943957396079275e-05, "gradient_norm": 0.2870524525642395, "tokens_per_second": 1120855.0141377463, "synthetic": false, "world_size": 8} {"step": 46680, "tokens": 12236881920, "loss": 2.3615480422973634, "optimizer_updates": 24340, "effective_batch": 512, "lr": 7.93696396466979e-05, "gradient_norm": 0.24649286270141602, "tokens_per_second": 1123124.1467046216, "synthetic": false, "world_size": 8} {"step": 46700, "tokens": 12242124800, "loss": 2.365171432495117, "optimizer_updates": 24350, "effective_batch": 512, "lr": 7.929972624394535e-05, "gradient_norm": 0.2662247121334076, "tokens_per_second": 1130914.9500083493, "synthetic": false, "world_size": 8} {"step": 46720, "tokens": 12247367680, "loss": 2.3764621734619142, "optimizer_updates": 24360, "effective_batch": 512, "lr": 7.922983380026503e-05, "gradient_norm": 0.2802385091781616, "tokens_per_second": 1123734.6234725018, "synthetic": false, "world_size": 8} {"step": 46740, "tokens": 12252610560, "loss": 2.375910186767578, "optimizer_updates": 24370, "effective_batch": 512, "lr": 7.915996236337246e-05, "gradient_norm": 0.2708762586116791, "tokens_per_second": 1126564.377438022, "synthetic": false, "world_size": 8} {"step": 46760, "tokens": 12257853440, "loss": 2.3733049392700196, "optimizer_updates": 24380, "effective_batch": 512, "lr": 7.909011198096888e-05, "gradient_norm": 0.2550564110279083, "tokens_per_second": 1122257.731236934, "synthetic": false, "world_size": 8} {"step": 46780, "tokens": 12263096320, "loss": 2.3535011291503904, "optimizer_updates": 24390, "effective_batch": 512, "lr": 7.902028270074113e-05, "gradient_norm": 0.25209280848503113, "tokens_per_second": 1127096.2039075335, "synthetic": false, "world_size": 8} {"step": 46800, "tokens": 12268339200, "loss": 2.381208038330078, "optimizer_updates": 24400, "effective_batch": 512, "lr": 7.895047457036165e-05, "gradient_norm": 0.27593234181404114, "tokens_per_second": 1009165.6712584579, "synthetic": false, "world_size": 8} {"step": 46820, "tokens": 12273582080, "loss": 2.357779693603516, "optimizer_updates": 24410, "effective_batch": 512, "lr": 7.888068763748842e-05, "gradient_norm": 0.24285481870174408, "tokens_per_second": 1117115.8183845284, "synthetic": false, "world_size": 8} {"step": 46840, "tokens": 12278824960, "loss": 2.366365432739258, "optimizer_updates": 24420, "effective_batch": 512, "lr": 7.881092194976501e-05, "gradient_norm": 0.2858079969882965, "tokens_per_second": 1134617.9689164404, "synthetic": false, "world_size": 8} {"step": 46860, "tokens": 12284067840, "loss": 2.3499637603759767, "optimizer_updates": 24430, "effective_batch": 512, "lr": 7.874117755482039e-05, "gradient_norm": 0.3704998791217804, "tokens_per_second": 1134535.1706468198, "synthetic": false, "world_size": 8} {"step": 46880, "tokens": 12289310720, "loss": 2.3517969131469725, "optimizer_updates": 24440, "effective_batch": 512, "lr": 7.86714545002691e-05, "gradient_norm": 0.3009995222091675, "tokens_per_second": 1020936.4536452545, "synthetic": false, "world_size": 8} {"step": 46900, "tokens": 12294553600, "loss": 2.3647367477416994, "optimizer_updates": 24450, "effective_batch": 512, "lr": 7.860175283371101e-05, "gradient_norm": 0.2804369032382965, "tokens_per_second": 1130724.5077265655, "synthetic": false, "world_size": 8} {"step": 46920, "tokens": 12299796480, "loss": 2.363326835632324, "optimizer_updates": 24460, "effective_batch": 512, "lr": 7.85320726027315e-05, "gradient_norm": 0.23296940326690674, "tokens_per_second": 1132740.6668586559, "synthetic": false, "world_size": 8} {"step": 46940, "tokens": 12305039360, "loss": 2.371566963195801, "optimizer_updates": 24470, "effective_batch": 512, "lr": 7.846241385490119e-05, "gradient_norm": 0.2927357256412506, "tokens_per_second": 1132033.2116152542, "synthetic": false, "world_size": 8} {"step": 46960, "tokens": 12310282240, "loss": 2.3570138931274416, "optimizer_updates": 24480, "effective_batch": 512, "lr": 7.839277663777616e-05, "gradient_norm": 0.23686760663986206, "tokens_per_second": 1135022.449219761, "synthetic": false, "world_size": 8} {"step": 46980, "tokens": 12315525120, "loss": 2.3662811279296876, "optimizer_updates": 24490, "effective_batch": 512, "lr": 7.832316099889765e-05, "gradient_norm": 0.3987095057964325, "tokens_per_second": 1129416.2662602551, "synthetic": false, "world_size": 8} {"step": 47000, "tokens": 12320768000, "loss": 2.3670602798461915, "optimizer_updates": 24500, "effective_batch": 512, "lr": 7.825356698579227e-05, "gradient_norm": 0.2634486258029938, "tokens_per_second": 1129390.2590623258, "synthetic": false, "world_size": 8} {"step": 47020, "tokens": 12326010880, "loss": 2.351834297180176, "optimizer_updates": 24510, "effective_batch": 512, "lr": 7.81839946459719e-05, "gradient_norm": 0.2508361041545868, "tokens_per_second": 834114.7994304637, "synthetic": false, "world_size": 8} {"step": 47040, "tokens": 12331253760, "loss": 2.3517311096191404, "optimizer_updates": 24520, "effective_batch": 512, "lr": 7.81144440269335e-05, "gradient_norm": 0.30294620990753174, "tokens_per_second": 1146331.0906202293, "synthetic": false, "world_size": 8} {"step": 47060, "tokens": 12336496640, "loss": 2.369287872314453, "optimizer_updates": 24530, "effective_batch": 512, "lr": 7.804491517615933e-05, "gradient_norm": 0.2823390066623688, "tokens_per_second": 1009193.0764141958, "synthetic": false, "world_size": 8} {"step": 47080, "tokens": 12341739520, "loss": 2.368599700927734, "optimizer_updates": 24540, "effective_batch": 512, "lr": 7.797540814111665e-05, "gradient_norm": 0.28776395320892334, "tokens_per_second": 1139706.6742111805, "synthetic": false, "world_size": 8} {"step": 47100, "tokens": 12346982400, "loss": 2.3648183822631834, "optimizer_updates": 24550, "effective_batch": 512, "lr": 7.790592296925795e-05, "gradient_norm": 0.25037822127342224, "tokens_per_second": 1130761.060855461, "synthetic": false, "world_size": 8} {"step": 47120, "tokens": 12352225280, "loss": 2.371915817260742, "optimizer_updates": 24560, "effective_batch": 512, "lr": 7.783645970802073e-05, "gradient_norm": 0.2635928988456726, "tokens_per_second": 1128323.240007139, "synthetic": false, "world_size": 8} {"step": 47140, "tokens": 12357468160, "loss": 2.3625038146972654, "optimizer_updates": 24570, "effective_batch": 512, "lr": 7.776701840482758e-05, "gradient_norm": 0.28193116188049316, "tokens_per_second": 1137252.1717964734, "synthetic": false, "world_size": 8} {"step": 47160, "tokens": 12362711040, "loss": 2.371349334716797, "optimizer_updates": 24580, "effective_batch": 512, "lr": 7.769759910708599e-05, "gradient_norm": 0.27474915981292725, "tokens_per_second": 1133649.7783649773, "synthetic": false, "world_size": 8} {"step": 47180, "tokens": 12367953920, "loss": 2.367475128173828, "optimizer_updates": 24590, "effective_batch": 512, "lr": 7.762820186218861e-05, "gradient_norm": 0.2892536222934723, "tokens_per_second": 1144218.1776505387, "synthetic": false, "world_size": 8} {"step": 47200, "tokens": 12373196800, "loss": 2.3643680572509767, "optimizer_updates": 24600, "effective_batch": 512, "lr": 7.755882671751283e-05, "gradient_norm": 0.25167596340179443, "tokens_per_second": 1129343.0768134613, "synthetic": false, "world_size": 8} {"step": 47220, "tokens": 12378439680, "loss": 2.366183280944824, "optimizer_updates": 24610, "effective_batch": 512, "lr": 7.748947372042112e-05, "gradient_norm": 0.32040709257125854, "tokens_per_second": 1124579.097352043, "synthetic": false, "world_size": 8} {"step": 47240, "tokens": 12383682560, "loss": 2.362452507019043, "optimizer_updates": 24620, "effective_batch": 512, "lr": 7.74201429182607e-05, "gradient_norm": 0.22553367912769318, "tokens_per_second": 1124532.9976253554, "synthetic": false, "world_size": 8} {"step": 47260, "tokens": 12388925440, "loss": 2.353206253051758, "optimizer_updates": 24630, "effective_batch": 512, "lr": 7.735083435836378e-05, "gradient_norm": 0.2433146834373474, "tokens_per_second": 1125697.3278430544, "synthetic": false, "world_size": 8} {"step": 47280, "tokens": 12394168320, "loss": 2.3621665954589846, "optimizer_updates": 24640, "effective_batch": 512, "lr": 7.728154808804723e-05, "gradient_norm": 0.41698482632637024, "tokens_per_second": 1128733.575128706, "synthetic": false, "world_size": 8} {"step": 47300, "tokens": 12399411200, "loss": 2.366842269897461, "optimizer_updates": 24650, "effective_batch": 512, "lr": 7.721228415461282e-05, "gradient_norm": 0.2559376358985901, "tokens_per_second": 1135209.1235029213, "synthetic": false, "world_size": 8} {"step": 47320, "tokens": 12404654080, "loss": 2.351252555847168, "optimizer_updates": 24660, "effective_batch": 512, "lr": 7.714304260534697e-05, "gradient_norm": 0.25454917550086975, "tokens_per_second": 1130160.316716868, "synthetic": false, "world_size": 8} {"step": 47340, "tokens": 12409896960, "loss": 2.3672481536865235, "optimizer_updates": 24670, "effective_batch": 512, "lr": 7.707382348752096e-05, "gradient_norm": 0.27387693524360657, "tokens_per_second": 1125321.6162737606, "synthetic": false, "world_size": 8} {"step": 47360, "tokens": 12415139840, "loss": 2.3507545471191404, "optimizer_updates": 24680, "effective_batch": 512, "lr": 7.700462684839059e-05, "gradient_norm": 0.25647518038749695, "tokens_per_second": 1135397.1318661994, "synthetic": false, "world_size": 8} {"step": 47380, "tokens": 12420382720, "loss": 2.366864013671875, "optimizer_updates": 24690, "effective_batch": 512, "lr": 7.693545273519645e-05, "gradient_norm": 0.24984389543533325, "tokens_per_second": 1135456.3424423297, "synthetic": false, "world_size": 8} {"step": 47400, "tokens": 12425625600, "loss": 2.3624969482421876, "optimizer_updates": 24700, "effective_batch": 512, "lr": 7.686630119516364e-05, "gradient_norm": 0.30274486541748047, "tokens_per_second": 1128196.8410654268, "synthetic": false, "world_size": 8} {"step": 47420, "tokens": 12430868480, "loss": 2.353196144104004, "optimizer_updates": 24710, "effective_batch": 512, "lr": 7.679717227550196e-05, "gradient_norm": 0.28727030754089355, "tokens_per_second": 1132166.8639585818, "synthetic": false, "world_size": 8} {"step": 47440, "tokens": 12436111360, "loss": 2.3606882095336914, "optimizer_updates": 24720, "effective_batch": 512, "lr": 7.672806602340572e-05, "gradient_norm": 0.28299689292907715, "tokens_per_second": 1130938.248331056, "synthetic": false, "world_size": 8} {"step": 47460, "tokens": 12441354240, "loss": 2.359688377380371, "optimizer_updates": 24730, "effective_batch": 512, "lr": 7.665898248605369e-05, "gradient_norm": 0.24211695790290833, "tokens_per_second": 1019128.0812986158, "synthetic": false, "world_size": 8} {"step": 47480, "tokens": 12446597120, "loss": 2.3687177658081056, "optimizer_updates": 24740, "effective_batch": 512, "lr": 7.658992171060927e-05, "gradient_norm": 0.2659052014350891, "tokens_per_second": 1135407.3286710226, "synthetic": false, "world_size": 8} {"step": 47500, "tokens": 12451840000, "loss": 2.370528221130371, "optimizer_updates": 24750, "effective_batch": 512, "lr": 7.652088374422013e-05, "gradient_norm": 0.26992401480674744, "tokens_per_second": 1138448.239271719, "synthetic": false, "world_size": 8} {"step": 47520, "tokens": 12457082880, "loss": 2.3473173141479493, "optimizer_updates": 24760, "effective_batch": 512, "lr": 7.64518686340186e-05, "gradient_norm": 0.23548129200935364, "tokens_per_second": 1131834.5409104046, "synthetic": false, "world_size": 8} {"step": 47540, "tokens": 12462325760, "loss": 2.3572820663452148, "optimizer_updates": 24770, "effective_batch": 512, "lr": 7.638287642712117e-05, "gradient_norm": 0.3221743702888489, "tokens_per_second": 1126361.5844061277, "synthetic": false, "world_size": 8} {"step": 47560, "tokens": 12467568640, "loss": 2.3647907257080076, "optimizer_updates": 24780, "effective_batch": 512, "lr": 7.631390717062893e-05, "gradient_norm": 0.2795184552669525, "tokens_per_second": 738210.7189710658, "synthetic": false, "world_size": 8} {"step": 47580, "tokens": 12472811520, "loss": 2.3674991607666014, "optimizer_updates": 24790, "effective_batch": 512, "lr": 7.624496091162708e-05, "gradient_norm": 0.24438533186912537, "tokens_per_second": 1138322.3108486636, "synthetic": false, "world_size": 8} {"step": 47600, "tokens": 12478054400, "loss": 2.366789627075195, "optimizer_updates": 24800, "effective_batch": 512, "lr": 7.61760376971853e-05, "gradient_norm": 0.25523456931114197, "tokens_per_second": 1138066.4836042444, "synthetic": false, "world_size": 8} {"step": 47620, "tokens": 12483297280, "loss": 2.3648870468139647, "optimizer_updates": 24810, "effective_batch": 512, "lr": 7.610713757435735e-05, "gradient_norm": 0.239048570394516, "tokens_per_second": 1131736.679133798, "synthetic": false, "world_size": 8} {"step": 47640, "tokens": 12488540160, "loss": 2.3755760192871094, "optimizer_updates": 24820, "effective_batch": 512, "lr": 7.603826059018145e-05, "gradient_norm": 0.27199786901474, "tokens_per_second": 1130293.5111011034, "synthetic": false, "world_size": 8} {"step": 47660, "tokens": 12493783040, "loss": 2.3549102783203124, "optimizer_updates": 24830, "effective_batch": 512, "lr": 7.596940679167983e-05, "gradient_norm": 0.23876351118087769, "tokens_per_second": 1136345.8173014503, "synthetic": false, "world_size": 8} {"step": 47680, "tokens": 12499025920, "loss": 2.357763481140137, "optimizer_updates": 24840, "effective_batch": 512, "lr": 7.590057622585902e-05, "gradient_norm": 0.24207504093647003, "tokens_per_second": 1134855.8240076883, "synthetic": false, "world_size": 8} {"step": 47700, "tokens": 12504268800, "loss": 2.357246971130371, "optimizer_updates": 24850, "effective_batch": 512, "lr": 7.583176893970957e-05, "gradient_norm": 0.24553652107715607, "tokens_per_second": 1137832.9145429444, "synthetic": false, "world_size": 8} {"step": 47720, "tokens": 12509511680, "loss": 2.3665498733520507, "optimizer_updates": 24860, "effective_batch": 512, "lr": 7.576298498020628e-05, "gradient_norm": 0.25302255153656006, "tokens_per_second": 1139825.2556581062, "synthetic": false, "world_size": 8} {"step": 47740, "tokens": 12514754560, "loss": 2.359263229370117, "optimizer_updates": 24870, "effective_batch": 512, "lr": 7.569422439430791e-05, "gradient_norm": 0.23845680058002472, "tokens_per_second": 1129214.5454317299, "synthetic": false, "world_size": 8} {"step": 47760, "tokens": 12519997440, "loss": 2.3676336288452147, "optimizer_updates": 24880, "effective_batch": 512, "lr": 7.56254872289573e-05, "gradient_norm": 0.2914976179599762, "tokens_per_second": 1133845.3089381375, "synthetic": false, "world_size": 8} {"step": 47780, "tokens": 12525240320, "loss": 2.36412353515625, "optimizer_updates": 24890, "effective_batch": 512, "lr": 7.55567735310813e-05, "gradient_norm": 0.25575321912765503, "tokens_per_second": 1135237.1362758118, "synthetic": false, "world_size": 8} {"step": 47800, "tokens": 12530483200, "loss": 2.3494846343994142, "optimizer_updates": 24900, "effective_batch": 512, "lr": 7.548808334759077e-05, "gradient_norm": 0.2509680390357971, "tokens_per_second": 1123947.742520686, "synthetic": false, "world_size": 8} {"step": 47820, "tokens": 12535726080, "loss": 2.3699005126953123, "optimizer_updates": 24910, "effective_batch": 512, "lr": 7.541941672538043e-05, "gradient_norm": 0.3177032470703125, "tokens_per_second": 1124630.501391579, "synthetic": false, "world_size": 8} {"step": 47840, "tokens": 12540968960, "loss": 2.3518402099609377, "optimizer_updates": 24920, "effective_batch": 512, "lr": 7.535077371132902e-05, "gradient_norm": 0.2435309886932373, "tokens_per_second": 1128252.2971995783, "synthetic": false, "world_size": 8} {"step": 47860, "tokens": 12546211840, "loss": 2.3503482818603514, "optimizer_updates": 24930, "effective_batch": 512, "lr": 7.528215435229912e-05, "gradient_norm": 0.26656749844551086, "tokens_per_second": 1133973.6591079792, "synthetic": false, "world_size": 8} {"step": 47880, "tokens": 12551454720, "loss": 2.369028663635254, "optimizer_updates": 24940, "effective_batch": 512, "lr": 7.521355869513712e-05, "gradient_norm": 0.23670996725559235, "tokens_per_second": 1127153.673434586, "synthetic": false, "world_size": 8} {"step": 47900, "tokens": 12556697600, "loss": 2.366306686401367, "optimizer_updates": 24950, "effective_batch": 512, "lr": 7.514498678667331e-05, "gradient_norm": 0.2956858277320862, "tokens_per_second": 1124410.450579888, "synthetic": false, "world_size": 8} {"step": 47920, "tokens": 12561940480, "loss": 2.3600770950317385, "optimizer_updates": 24960, "effective_batch": 512, "lr": 7.507643867372167e-05, "gradient_norm": 0.26430851221084595, "tokens_per_second": 1125911.7825097411, "synthetic": false, "world_size": 8} {"step": 47940, "tokens": 12567183360, "loss": 2.3648475646972655, "optimizer_updates": 24970, "effective_batch": 512, "lr": 7.500791440308004e-05, "gradient_norm": 0.2645009160041809, "tokens_per_second": 800608.6916551543, "synthetic": false, "world_size": 8} {"step": 47960, "tokens": 12572426240, "loss": 2.3616472244262696, "optimizer_updates": 24980, "effective_batch": 512, "lr": 7.493941402152986e-05, "gradient_norm": 0.2615923583507538, "tokens_per_second": 1130877.6158672008, "synthetic": false, "world_size": 8} {"step": 47980, "tokens": 12577669120, "loss": 2.3785181045532227, "optimizer_updates": 24990, "effective_batch": 512, "lr": 7.487093757583642e-05, "gradient_norm": 0.26137575507164, "tokens_per_second": 1136512.6872053756, "synthetic": false, "world_size": 8} {"step": 48000, "tokens": 12582912000, "loss": 2.3625417709350587, "optimizer_updates": 25000, "effective_batch": 512, "lr": 7.480248511274848e-05, "gradient_norm": 0.31030890345573425, "tokens_per_second": 1130349.551533057, "synthetic": false, "world_size": 8} {"step": 48020, "tokens": 12588154880, "loss": 2.372874641418457, "optimizer_updates": 25010, "effective_batch": 512, "lr": 7.473405667899862e-05, "gradient_norm": 0.24432651698589325, "tokens_per_second": 833680.8771235796, "synthetic": false, "world_size": 8} {"step": 48040, "tokens": 12593397760, "loss": 2.3679824829101563, "optimizer_updates": 25020, "effective_batch": 512, "lr": 7.466565232130284e-05, "gradient_norm": 0.2428373098373413, "tokens_per_second": 1134137.7113741653, "synthetic": false, "world_size": 8} {"step": 48060, "tokens": 12598640640, "loss": 2.3569644927978515, "optimizer_updates": 25030, "effective_batch": 512, "lr": 7.459727208636087e-05, "gradient_norm": 0.24808058142662048, "tokens_per_second": 1131619.1746820505, "synthetic": false, "world_size": 8} {"step": 48080, "tokens": 12603883520, "loss": 2.365447425842285, "optimizer_updates": 25040, "effective_batch": 512, "lr": 7.452891602085578e-05, "gradient_norm": 0.26423755288124084, "tokens_per_second": 1135831.8963551929, "synthetic": false, "world_size": 8} {"step": 48100, "tokens": 12609126400, "loss": 2.3614595413208006, "optimizer_updates": 25050, "effective_batch": 512, "lr": 7.446058417145436e-05, "gradient_norm": 0.31651291251182556, "tokens_per_second": 1130788.538012959, "synthetic": false, "world_size": 8} {"step": 48120, "tokens": 12614369280, "loss": 2.3569614410400392, "optimizer_updates": 25060, "effective_batch": 512, "lr": 7.439227658480664e-05, "gradient_norm": 0.25305330753326416, "tokens_per_second": 1127805.7974761787, "synthetic": false, "world_size": 8} {"step": 48140, "tokens": 12619612160, "loss": 2.3710683822631835, "optimizer_updates": 25070, "effective_batch": 512, "lr": 7.432399330754631e-05, "gradient_norm": 0.2712412178516388, "tokens_per_second": 1136834.83718862, "synthetic": false, "world_size": 8} {"step": 48160, "tokens": 12624855040, "loss": 2.3494754791259767, "optimizer_updates": 25080, "effective_batch": 512, "lr": 7.425573438629025e-05, "gradient_norm": 0.27949926257133484, "tokens_per_second": 1132089.436902844, "synthetic": false, "world_size": 8} {"step": 48180, "tokens": 12630097920, "loss": 2.360089111328125, "optimizer_updates": 25090, "effective_batch": 512, "lr": 7.41874998676389e-05, "gradient_norm": 0.3175927996635437, "tokens_per_second": 1141654.6367392642, "synthetic": false, "world_size": 8} {"step": 48200, "tokens": 12635340800, "loss": 2.364768409729004, "optimizer_updates": 25100, "effective_batch": 512, "lr": 7.41192897981759e-05, "gradient_norm": 0.24699562788009644, "tokens_per_second": 1134194.977202923, "synthetic": false, "world_size": 8} {"step": 48220, "tokens": 12640583680, "loss": 2.354925346374512, "optimizer_updates": 25110, "effective_batch": 512, "lr": 7.405110422446829e-05, "gradient_norm": 0.23610617220401764, "tokens_per_second": 1139420.9647331496, "synthetic": false, "world_size": 8} {"step": 48240, "tokens": 12645826560, "loss": 2.3670671463012694, "optimizer_updates": 25120, "effective_batch": 512, "lr": 7.39829431930663e-05, "gradient_norm": 0.26882416009902954, "tokens_per_second": 1120729.983575093, "synthetic": false, "world_size": 8} {"step": 48260, "tokens": 12651069440, "loss": 2.3681821823120117, "optimizer_updates": 25130, "effective_batch": 512, "lr": 7.391480675050353e-05, "gradient_norm": 0.24695150554180145, "tokens_per_second": 1129093.578231906, "synthetic": false, "world_size": 8} {"step": 48280, "tokens": 12656312320, "loss": 2.3676387786865236, "optimizer_updates": 25140, "effective_batch": 512, "lr": 7.384669494329665e-05, "gradient_norm": 0.2744264304637909, "tokens_per_second": 1135141.8906085207, "synthetic": false, "world_size": 8} {"step": 48300, "tokens": 12661555200, "loss": 2.363247871398926, "optimizer_updates": 25150, "effective_batch": 512, "lr": 7.377860781794559e-05, "gradient_norm": 0.24997776746749878, "tokens_per_second": 1138139.726476993, "synthetic": false, "world_size": 8} {"step": 48320, "tokens": 12666798080, "loss": 2.3436872482299806, "optimizer_updates": 25160, "effective_batch": 512, "lr": 7.371054542093349e-05, "gradient_norm": 0.23295405507087708, "tokens_per_second": 1133288.8800482962, "synthetic": false, "world_size": 8} {"step": 48340, "tokens": 12672040960, "loss": 2.3598915100097657, "optimizer_updates": 25170, "effective_batch": 512, "lr": 7.364250779872646e-05, "gradient_norm": 0.25733670592308044, "tokens_per_second": 1129268.2428454952, "synthetic": false, "world_size": 8} {"step": 48360, "tokens": 12677283840, "loss": 2.355473518371582, "optimizer_updates": 25180, "effective_batch": 512, "lr": 7.35744949977738e-05, "gradient_norm": 0.29086220264434814, "tokens_per_second": 1136441.409736974, "synthetic": false, "world_size": 8} {"step": 48380, "tokens": 12682526720, "loss": 2.341567039489746, "optimizer_updates": 25190, "effective_batch": 512, "lr": 7.350650706450784e-05, "gradient_norm": 0.24648821353912354, "tokens_per_second": 1122295.9768428658, "synthetic": false, "world_size": 8} {"step": 48400, "tokens": 12687769600, "loss": 2.3646190643310545, "optimizer_updates": 25200, "effective_batch": 512, "lr": 7.343854404534396e-05, "gradient_norm": 0.24658289551734924, "tokens_per_second": 1139769.1077600005, "synthetic": false, "world_size": 8} {"step": 48420, "tokens": 12693012480, "loss": 2.3701091766357423, "optimizer_updates": 25210, "effective_batch": 512, "lr": 7.337060598668042e-05, "gradient_norm": 0.2332696169614792, "tokens_per_second": 1119471.2117871088, "synthetic": false, "world_size": 8} {"step": 48440, "tokens": 12698255360, "loss": 2.3644855499267576, "optimizer_updates": 25220, "effective_batch": 512, "lr": 7.330269293489863e-05, "gradient_norm": 0.251086950302124, "tokens_per_second": 1134640.7146130223, "synthetic": false, "world_size": 8} {"step": 48460, "tokens": 12703498240, "loss": 2.378139877319336, "optimizer_updates": 25230, "effective_batch": 512, "lr": 7.323480493636272e-05, "gradient_norm": 0.26736146211624146, "tokens_per_second": 1131427.7016675347, "synthetic": false, "world_size": 8} {"step": 48480, "tokens": 12708741120, "loss": 2.3612308502197266, "optimizer_updates": 25240, "effective_batch": 512, "lr": 7.316694203741991e-05, "gradient_norm": 0.30605024099349976, "tokens_per_second": 1128901.436727782, "synthetic": false, "world_size": 8} {"step": 48500, "tokens": 12713984000, "loss": 2.361754035949707, "optimizer_updates": 25250, "effective_batch": 512, "lr": 7.30991042844001e-05, "gradient_norm": 0.27226874232292175, "tokens_per_second": 1131725.0650301105, "synthetic": false, "world_size": 8} {"step": 48520, "tokens": 12719226880, "loss": 2.350804901123047, "optimizer_updates": 25260, "effective_batch": 512, "lr": 7.30312917236162e-05, "gradient_norm": 0.27121901512145996, "tokens_per_second": 1122877.9243771688, "synthetic": false, "world_size": 8} {"step": 48540, "tokens": 12724469760, "loss": 2.359014129638672, "optimizer_updates": 25270, "effective_batch": 512, "lr": 7.296350440136376e-05, "gradient_norm": 0.285313218832016, "tokens_per_second": 1126986.1422083923, "synthetic": false, "world_size": 8} {"step": 48560, "tokens": 12729712640, "loss": 2.358262062072754, "optimizer_updates": 25280, "effective_batch": 512, "lr": 7.289574236392123e-05, "gradient_norm": 0.24962474405765533, "tokens_per_second": 1137649.0111345868, "synthetic": false, "world_size": 8} {"step": 48580, "tokens": 12734955520, "loss": 2.355648994445801, "optimizer_updates": 25290, "effective_batch": 512, "lr": 7.282800565754969e-05, "gradient_norm": 0.25727880001068115, "tokens_per_second": 1131028.3957696161, "synthetic": false, "world_size": 8} {"step": 48600, "tokens": 12740198400, "loss": 2.362352752685547, "optimizer_updates": 25300, "effective_batch": 512, "lr": 7.276029432849304e-05, "gradient_norm": 0.2310812920331955, "tokens_per_second": 1131983.0834127865, "synthetic": false, "world_size": 8} {"step": 48620, "tokens": 12745441280, "loss": 2.345845413208008, "optimizer_updates": 25310, "effective_batch": 512, "lr": 7.269260842297773e-05, "gradient_norm": 0.26687091588974, "tokens_per_second": 1128002.5058541414, "synthetic": false, "world_size": 8} {"step": 48640, "tokens": 12750684160, "loss": 2.3646514892578123, "optimizer_updates": 25320, "effective_batch": 512, "lr": 7.262494798721298e-05, "gradient_norm": 0.3249519169330597, "tokens_per_second": 1125415.2248867005, "synthetic": false, "world_size": 8} {"step": 48660, "tokens": 12755927040, "loss": 2.3697441101074217, "optimizer_updates": 25330, "effective_batch": 512, "lr": 7.255731306739051e-05, "gradient_norm": 0.26905128359794617, "tokens_per_second": 1130127.2589178625, "synthetic": false, "world_size": 8} {"step": 48680, "tokens": 12761169920, "loss": 2.3695533752441404, "optimizer_updates": 25340, "effective_batch": 512, "lr": 7.248970370968471e-05, "gradient_norm": 0.3023113012313843, "tokens_per_second": 1129256.5677294217, "synthetic": false, "world_size": 8} {"step": 48700, "tokens": 12766412800, "loss": 2.3613372802734376, "optimizer_updates": 25350, "effective_batch": 512, "lr": 7.242211996025242e-05, "gradient_norm": 0.23519127070903778, "tokens_per_second": 1127030.2897657442, "synthetic": false, "world_size": 8} {"step": 48720, "tokens": 12771655680, "loss": 2.3607421875, "optimizer_updates": 25360, "effective_batch": 512, "lr": 7.23545618652331e-05, "gradient_norm": 0.2922477722167969, "tokens_per_second": 1131293.5644508498, "synthetic": false, "world_size": 8} {"step": 48740, "tokens": 12776898560, "loss": 2.3639625549316405, "optimizer_updates": 25370, "effective_batch": 512, "lr": 7.228702947074866e-05, "gradient_norm": 0.3030715584754944, "tokens_per_second": 1021626.564751068, "synthetic": false, "world_size": 8} {"step": 48760, "tokens": 12782141440, "loss": 2.3680322647094725, "optimizer_updates": 25380, "effective_batch": 512, "lr": 7.221952282290345e-05, "gradient_norm": 0.2725348472595215, "tokens_per_second": 1131561.9007491225, "synthetic": false, "world_size": 8} {"step": 48780, "tokens": 12787384320, "loss": 2.369880485534668, "optimizer_updates": 25390, "effective_batch": 512, "lr": 7.215204196778424e-05, "gradient_norm": 0.25406700372695923, "tokens_per_second": 1031792.2835355415, "synthetic": false, "world_size": 8} {"step": 48800, "tokens": 12792627200, "loss": 2.3549850463867186, "optimizer_updates": 25400, "effective_batch": 512, "lr": 7.208458695146017e-05, "gradient_norm": 0.2545204758644104, "tokens_per_second": 1137107.250716508, "synthetic": false, "world_size": 8} {"step": 48820, "tokens": 12797870080, "loss": 2.3654245376586913, "optimizer_updates": 25410, "effective_batch": 512, "lr": 7.201715781998282e-05, "gradient_norm": 0.3038981556892395, "tokens_per_second": 1128428.1309148713, "synthetic": false, "world_size": 8} {"step": 48840, "tokens": 12803112960, "loss": 2.3584692001342775, "optimizer_updates": 25420, "effective_batch": 512, "lr": 7.194975461938598e-05, "gradient_norm": 0.3192479908466339, "tokens_per_second": 1136034.728719761, "synthetic": false, "world_size": 8} {"step": 48860, "tokens": 12808355840, "loss": 2.352924346923828, "optimizer_updates": 25430, "effective_batch": 512, "lr": 7.18823773956859e-05, "gradient_norm": 0.24972744286060333, "tokens_per_second": 1129959.4420159713, "synthetic": false, "world_size": 8} {"step": 48880, "tokens": 12813598720, "loss": 2.3723398208618165, "optimizer_updates": 25440, "effective_batch": 512, "lr": 7.18150261948809e-05, "gradient_norm": 0.3477856516838074, "tokens_per_second": 1129676.0493007333, "synthetic": false, "world_size": 8} {"step": 48900, "tokens": 12818841600, "loss": 2.3521217346191405, "optimizer_updates": 25450, "effective_batch": 512, "lr": 7.174770106295173e-05, "gradient_norm": 0.34514227509498596, "tokens_per_second": 1123334.2004078839, "synthetic": false, "world_size": 8} {"step": 48920, "tokens": 12824084480, "loss": 2.3677833557128904, "optimizer_updates": 25460, "effective_batch": 512, "lr": 7.168040204586114e-05, "gradient_norm": 0.29841336607933044, "tokens_per_second": 1137509.806094588, "synthetic": false, "world_size": 8} {"step": 48940, "tokens": 12829327360, "loss": 2.3715885162353514, "optimizer_updates": 25470, "effective_batch": 512, "lr": 7.161312918955427e-05, "gradient_norm": 0.2728264033794403, "tokens_per_second": 1129367.3115098244, "synthetic": false, "world_size": 8} {"step": 48960, "tokens": 12834570240, "loss": 2.3581188201904295, "optimizer_updates": 25480, "effective_batch": 512, "lr": 7.154588253995822e-05, "gradient_norm": 0.2394498735666275, "tokens_per_second": 1136518.2383412165, "synthetic": false, "world_size": 8} {"step": 48980, "tokens": 12839813120, "loss": 2.358824920654297, "optimizer_updates": 25490, "effective_batch": 512, "lr": 7.14786621429823e-05, "gradient_norm": 0.27690619230270386, "tokens_per_second": 1133842.812466924, "synthetic": false, "world_size": 8} {"step": 49000, "tokens": 12845056000, "loss": 2.351984214782715, "optimizer_updates": 25500, "effective_batch": 512, "lr": 7.141146804451783e-05, "gradient_norm": 0.2295226901769638, "tokens_per_second": 1134221.8001969398, "synthetic": false, "world_size": 8} {"step": 49020, "tokens": 12850298880, "loss": 2.3572929382324217, "optimizer_updates": 25510, "effective_batch": 512, "lr": 7.134430029043825e-05, "gradient_norm": 0.25818848609924316, "tokens_per_second": 830918.1478162004, "synthetic": false, "world_size": 8} {"step": 49040, "tokens": 12855541760, "loss": 2.360772132873535, "optimizer_updates": 25520, "effective_batch": 512, "lr": 7.127715892659892e-05, "gradient_norm": 0.23959609866142273, "tokens_per_second": 1139860.3944994414, "synthetic": false, "world_size": 8} {"step": 49060, "tokens": 12860784640, "loss": 2.3529531478881838, "optimizer_updates": 25530, "effective_batch": 512, "lr": 7.121004399883732e-05, "gradient_norm": 0.23485669493675232, "tokens_per_second": 786855.597295216, "synthetic": false, "world_size": 8} {"step": 49080, "tokens": 12866027520, "loss": 2.3625680923461916, "optimizer_updates": 25540, "effective_batch": 512, "lr": 7.114295555297276e-05, "gradient_norm": 0.2642146050930023, "tokens_per_second": 1145692.6139520272, "synthetic": false, "world_size": 8} {"step": 49100, "tokens": 12871270400, "loss": 2.374308776855469, "optimizer_updates": 25550, "effective_batch": 512, "lr": 7.107589363480649e-05, "gradient_norm": 0.2853204011917114, "tokens_per_second": 1134292.3366884044, "synthetic": false, "world_size": 8} {"step": 49120, "tokens": 12876513280, "loss": 2.361857032775879, "optimizer_updates": 25560, "effective_batch": 512, "lr": 7.100885829012165e-05, "gradient_norm": 0.27769461274147034, "tokens_per_second": 1135225.8320075087, "synthetic": false, "world_size": 8} {"step": 49140, "tokens": 12881756160, "loss": 2.3545276641845705, "optimizer_updates": 25570, "effective_batch": 512, "lr": 7.094184956468336e-05, "gradient_norm": 0.30175888538360596, "tokens_per_second": 1131892.6327012193, "synthetic": false, "world_size": 8} {"step": 49160, "tokens": 12886999040, "loss": 2.3614032745361326, "optimizer_updates": 25580, "effective_batch": 512, "lr": 7.087486750423835e-05, "gradient_norm": 0.2798858880996704, "tokens_per_second": 1130210.0521631422, "synthetic": false, "world_size": 8} {"step": 49180, "tokens": 12892241920, "loss": 2.360358238220215, "optimizer_updates": 25590, "effective_batch": 512, "lr": 7.080791215451532e-05, "gradient_norm": 0.2780510485172272, "tokens_per_second": 1135253.7912896997, "synthetic": false, "world_size": 8} {"step": 49200, "tokens": 12897484800, "loss": 2.3485336303710938, "optimizer_updates": 25600, "effective_batch": 512, "lr": 7.074098356122472e-05, "gradient_norm": 0.23771901428699493, "tokens_per_second": 1037491.1020725059, "synthetic": false, "world_size": 8} {"step": 49220, "tokens": 12902727680, "loss": 2.361039924621582, "optimizer_updates": 25610, "effective_batch": 512, "lr": 7.06740817700586e-05, "gradient_norm": 0.2900056540966034, "tokens_per_second": 1143827.4406539623, "synthetic": false, "world_size": 8} {"step": 49240, "tokens": 12907970560, "loss": 2.350366401672363, "optimizer_updates": 25620, "effective_batch": 512, "lr": 7.060720682669088e-05, "gradient_norm": 0.2791386842727661, "tokens_per_second": 1132644.7228327575, "synthetic": false, "world_size": 8} {"step": 49260, "tokens": 12913213440, "loss": 2.3701759338378907, "optimizer_updates": 25630, "effective_batch": 512, "lr": 7.054035877677702e-05, "gradient_norm": 0.24527062475681305, "tokens_per_second": 1140005.2250366563, "synthetic": false, "world_size": 8} {"step": 49280, "tokens": 12918456320, "loss": 2.3562055587768556, "optimizer_updates": 25640, "effective_batch": 512, "lr": 7.047353766595421e-05, "gradient_norm": 0.24032679200172424, "tokens_per_second": 1046678.195118897, "synthetic": false, "world_size": 8} {"step": 49300, "tokens": 12923699200, "loss": 2.3508255004882814, "optimizer_updates": 25650, "effective_batch": 512, "lr": 7.040674353984118e-05, "gradient_norm": 0.30578839778900146, "tokens_per_second": 1134676.0828334973, "synthetic": false, "world_size": 8} {"step": 49320, "tokens": 12928942080, "loss": 2.367104339599609, "optimizer_updates": 25660, "effective_batch": 512, "lr": 7.033997644403832e-05, "gradient_norm": 0.2601855993270874, "tokens_per_second": 1133171.8740543004, "synthetic": false, "world_size": 8} {"step": 49340, "tokens": 12934184960, "loss": 2.3710561752319337, "optimizer_updates": 25670, "effective_batch": 512, "lr": 7.027323642412744e-05, "gradient_norm": 0.28445950150489807, "tokens_per_second": 1134660.2740520556, "synthetic": false, "world_size": 8} {"step": 49360, "tokens": 12939427840, "loss": 2.3648601531982423, "optimizer_updates": 25680, "effective_batch": 512, "lr": 7.020652352567202e-05, "gradient_norm": 0.24613694846630096, "tokens_per_second": 1133699.7395101588, "synthetic": false, "world_size": 8} {"step": 49380, "tokens": 12944670720, "loss": 2.3636146545410157, "optimizer_updates": 25690, "effective_batch": 512, "lr": 7.01398377942169e-05, "gradient_norm": 0.299934059381485, "tokens_per_second": 1136135.4926895022, "synthetic": false, "world_size": 8} {"step": 49400, "tokens": 12949913600, "loss": 2.3689716339111326, "optimizer_updates": 25700, "effective_batch": 512, "lr": 7.007317927528844e-05, "gradient_norm": 0.34968867897987366, "tokens_per_second": 1132149.7229209822, "synthetic": false, "world_size": 8} {"step": 49420, "tokens": 12955156480, "loss": 2.3614856719970705, "optimizer_updates": 25710, "effective_batch": 512, "lr": 7.000654801439436e-05, "gradient_norm": 0.23564977943897247, "tokens_per_second": 1137499.0362142317, "synthetic": false, "world_size": 8} {"step": 49440, "tokens": 12960399360, "loss": 2.350590133666992, "optimizer_updates": 25720, "effective_batch": 512, "lr": 6.993994405702386e-05, "gradient_norm": 0.24594175815582275, "tokens_per_second": 1140258.2321461628, "synthetic": false, "world_size": 8} {"step": 49460, "tokens": 12965642240, "loss": 2.362466239929199, "optimizer_updates": 25730, "effective_batch": 512, "lr": 6.987336744864741e-05, "gradient_norm": 0.25928574800491333, "tokens_per_second": 1139827.628157243, "synthetic": false, "world_size": 8} {"step": 49480, "tokens": 12970885120, "loss": 2.356709098815918, "optimizer_updates": 25740, "effective_batch": 512, "lr": 6.98068182347169e-05, "gradient_norm": 0.24130746722221375, "tokens_per_second": 1134528.3317891583, "synthetic": false, "world_size": 8} {"step": 49500, "tokens": 12976128000, "loss": 2.356422233581543, "optimizer_updates": 25750, "effective_batch": 512, "lr": 6.97402964606654e-05, "gradient_norm": 0.23945000767707825, "tokens_per_second": 1141764.3956044307, "synthetic": false, "world_size": 8} {"step": 49520, "tokens": 12981370880, "loss": 2.359494209289551, "optimizer_updates": 25760, "effective_batch": 512, "lr": 6.967380217190739e-05, "gradient_norm": 0.23215268552303314, "tokens_per_second": 1135930.01773534, "synthetic": false, "world_size": 8} {"step": 49540, "tokens": 12986613760, "loss": 2.37399959564209, "optimizer_updates": 25770, "effective_batch": 512, "lr": 6.960733541383845e-05, "gradient_norm": 0.23701195418834686, "tokens_per_second": 1134258.9400241328, "synthetic": false, "world_size": 8} {"step": 49560, "tokens": 12991856640, "loss": 2.360451507568359, "optimizer_updates": 25780, "effective_batch": 512, "lr": 6.954089623183549e-05, "gradient_norm": 0.2708669900894165, "tokens_per_second": 1128775.5429635812, "synthetic": false, "world_size": 8} {"step": 49580, "tokens": 12997099520, "loss": 2.3575973510742188, "optimizer_updates": 25790, "effective_batch": 512, "lr": 6.947448467125645e-05, "gradient_norm": 0.2631627321243286, "tokens_per_second": 1131319.4165110383, "synthetic": false, "world_size": 8} {"step": 49600, "tokens": 13002342400, "loss": 2.368790626525879, "optimizer_updates": 25800, "effective_batch": 512, "lr": 6.940810077744053e-05, "gradient_norm": 0.3177776634693146, "tokens_per_second": 1128558.5715300043, "synthetic": false, "world_size": 8} {"step": 49620, "tokens": 13007585280, "loss": 2.3612482070922853, "optimizer_updates": 25810, "effective_batch": 512, "lr": 6.934174459570805e-05, "gradient_norm": 0.2695893943309784, "tokens_per_second": 1130135.3064546091, "synthetic": false, "world_size": 8} {"step": 49640, "tokens": 13012828160, "loss": 2.3598793029785154, "optimizer_updates": 25820, "effective_batch": 512, "lr": 6.927541617136029e-05, "gradient_norm": 0.2827436923980713, "tokens_per_second": 1134687.6868281397, "synthetic": false, "world_size": 8} {"step": 49660, "tokens": 13018071040, "loss": 2.362514686584473, "optimizer_updates": 25830, "effective_batch": 512, "lr": 6.920911554967971e-05, "gradient_norm": 0.28144168853759766, "tokens_per_second": 1130308.7442004797, "synthetic": false, "world_size": 8} {"step": 49680, "tokens": 13023313920, "loss": 2.3742799758911133, "optimizer_updates": 25840, "effective_batch": 512, "lr": 6.914284277592969e-05, "gradient_norm": 0.35727381706237793, "tokens_per_second": 1140692.3119775467, "synthetic": false, "world_size": 8} {"step": 49700, "tokens": 13028556800, "loss": 2.3592771530151366, "optimizer_updates": 25850, "effective_batch": 512, "lr": 6.90765978953547e-05, "gradient_norm": 0.24081633985042572, "tokens_per_second": 806043.0471339219, "synthetic": false, "world_size": 8} {"step": 49720, "tokens": 13033799680, "loss": 2.3603351593017576, "optimizer_updates": 25860, "effective_batch": 512, "lr": 6.901038095318006e-05, "gradient_norm": 0.25238296389579773, "tokens_per_second": 1135107.8828332215, "synthetic": false, "world_size": 8} {"step": 49740, "tokens": 13039042560, "loss": 2.3650718688964845, "optimizer_updates": 25870, "effective_batch": 512, "lr": 6.894419199461209e-05, "gradient_norm": 0.23596079647541046, "tokens_per_second": 1130831.525377069, "synthetic": false, "world_size": 8} {"step": 49760, "tokens": 13044285440, "loss": 2.3641387939453127, "optimizer_updates": 25880, "effective_batch": 512, "lr": 6.887803106483794e-05, "gradient_norm": 0.2743501365184784, "tokens_per_second": 793520.2356290558, "synthetic": false, "world_size": 8} {"step": 49780, "tokens": 13049528320, "loss": 2.3528635025024416, "optimizer_updates": 25890, "effective_batch": 512, "lr": 6.881189820902573e-05, "gradient_norm": 0.2915447950363159, "tokens_per_second": 1138270.1453221706, "synthetic": false, "world_size": 8} {"step": 49800, "tokens": 13054771200, "loss": 2.365863800048828, "optimizer_updates": 25900, "effective_batch": 512, "lr": 6.87457934723243e-05, "gradient_norm": 0.2694926857948303, "tokens_per_second": 1128806.161635918, "synthetic": false, "world_size": 8} {"step": 49820, "tokens": 13060014080, "loss": 2.36456413269043, "optimizer_updates": 25910, "effective_batch": 512, "lr": 6.867971689986338e-05, "gradient_norm": 0.24782603979110718, "tokens_per_second": 1130665.7232720319, "synthetic": false, "world_size": 8} {"step": 49840, "tokens": 13065256960, "loss": 2.358384704589844, "optimizer_updates": 25920, "effective_batch": 512, "lr": 6.861366853675338e-05, "gradient_norm": 0.23254314064979553, "tokens_per_second": 1129743.8972827797, "synthetic": false, "world_size": 8} {"step": 49860, "tokens": 13070499840, "loss": 2.359500503540039, "optimizer_updates": 25930, "effective_batch": 512, "lr": 6.85476484280856e-05, "gradient_norm": 0.2454671710729599, "tokens_per_second": 1131797.1049580113, "synthetic": false, "world_size": 8} {"step": 49880, "tokens": 13075742720, "loss": 2.3665271759033204, "optimizer_updates": 25940, "effective_batch": 512, "lr": 6.848165661893187e-05, "gradient_norm": 0.25827857851982117, "tokens_per_second": 1126208.472760346, "synthetic": false, "world_size": 8} {"step": 49900, "tokens": 13080985600, "loss": 2.3660240173339844, "optimizer_updates": 25950, "effective_batch": 512, "lr": 6.841569315434486e-05, "gradient_norm": 0.2765481770038605, "tokens_per_second": 1130790.8805661076, "synthetic": false, "world_size": 8} {"step": 49920, "tokens": 13086228480, "loss": 2.3733451843261717, "optimizer_updates": 25960, "effective_batch": 512, "lr": 6.834975807935773e-05, "gradient_norm": 0.2793847620487213, "tokens_per_second": 1129660.3900207295, "synthetic": false, "world_size": 8} {"step": 49940, "tokens": 13091471360, "loss": 2.362007904052734, "optimizer_updates": 25970, "effective_batch": 512, "lr": 6.828385143898443e-05, "gradient_norm": 0.2340160459280014, "tokens_per_second": 1131677.7761979126, "synthetic": false, "world_size": 8} {"step": 49960, "tokens": 13096714240, "loss": 2.3640506744384764, "optimizer_updates": 25980, "effective_batch": 512, "lr": 6.821797327821936e-05, "gradient_norm": 0.2672339379787445, "tokens_per_second": 1126587.5549879896, "synthetic": false, "world_size": 8} {"step": 49980, "tokens": 13101957120, "loss": 2.352008056640625, "optimizer_updates": 25990, "effective_batch": 512, "lr": 6.815212364203757e-05, "gradient_norm": 0.29484686255455017, "tokens_per_second": 1131513.976917032, "synthetic": false, "world_size": 8} {"step": 50000, "tokens": 13107200000, "loss": 2.3607019424438476, "optimizer_updates": 26000, "effective_batch": 512, "lr": 6.808630257539456e-05, "gradient_norm": 0.29154178500175476, "tokens_per_second": 1135492.3232627283, "synthetic": false, "world_size": 8} {"step": 50020, "tokens": 13112442880, "loss": 2.3509662628173826, "optimizer_updates": 26010, "effective_batch": 512, "lr": 6.802051012322639e-05, "gradient_norm": 0.30918973684310913, "tokens_per_second": 835936.3339660779, "synthetic": false, "world_size": 8} {"step": 50040, "tokens": 13117685760, "loss": 2.3612621307373045, "optimizer_updates": 26020, "effective_batch": 512, "lr": 6.795474633044956e-05, "gradient_norm": 0.2547447979450226, "tokens_per_second": 1130586.5919705492, "synthetic": false, "world_size": 8} {"step": 50060, "tokens": 13122928640, "loss": 2.3710958480834963, "optimizer_updates": 26030, "effective_batch": 512, "lr": 6.788901124196095e-05, "gradient_norm": 0.28115734457969666, "tokens_per_second": 1136170.0764027636, "synthetic": false, "world_size": 8} {"step": 50080, "tokens": 13128171520, "loss": 2.3610483169555665, "optimizer_updates": 26040, "effective_batch": 512, "lr": 6.782330490263796e-05, "gradient_norm": 0.28299063444137573, "tokens_per_second": 1139881.6143338927, "synthetic": false, "world_size": 8} {"step": 50100, "tokens": 13133414400, "loss": 2.3550704956054687, "optimizer_updates": 26050, "effective_batch": 512, "lr": 6.775762735733823e-05, "gradient_norm": 0.29216843843460083, "tokens_per_second": 1134288.5366377544, "synthetic": false, "world_size": 8} {"step": 50120, "tokens": 13138657280, "loss": 2.3506149291992187, "optimizer_updates": 26060, "effective_batch": 512, "lr": 6.76919786508999e-05, "gradient_norm": 0.27462080121040344, "tokens_per_second": 1125801.9689387183, "synthetic": false, "world_size": 8} {"step": 50140, "tokens": 13143900160, "loss": 2.368005561828613, "optimizer_updates": 26070, "effective_batch": 512, "lr": 6.762635882814124e-05, "gradient_norm": 0.2699052691459656, "tokens_per_second": 1138105.671258628, "synthetic": false, "world_size": 8} {"step": 50160, "tokens": 13149143040, "loss": 2.358047103881836, "optimizer_updates": 26080, "effective_batch": 512, "lr": 6.756076793386098e-05, "gradient_norm": 0.2943572402000427, "tokens_per_second": 1132099.0492977859, "synthetic": false, "world_size": 8} {"step": 50180, "tokens": 13154385920, "loss": 2.361538124084473, "optimizer_updates": 26090, "effective_batch": 512, "lr": 6.749520601283791e-05, "gradient_norm": 0.2628541886806488, "tokens_per_second": 1129916.6141665282, "synthetic": false, "world_size": 8} {"step": 50200, "tokens": 13159628800, "loss": 2.3686346054077148, "optimizer_updates": 26100, "effective_batch": 512, "lr": 6.742967310983124e-05, "gradient_norm": 0.25882822275161743, "tokens_per_second": 1135906.942984827, "synthetic": false, "world_size": 8} {"step": 50220, "tokens": 13164871680, "loss": 2.3598922729492187, "optimizer_updates": 26110, "effective_batch": 512, "lr": 6.736416926958022e-05, "gradient_norm": 0.2347107231616974, "tokens_per_second": 1124170.572486514, "synthetic": false, "world_size": 8} {"step": 50240, "tokens": 13170114560, "loss": 2.336227226257324, "optimizer_updates": 26120, "effective_batch": 512, "lr": 6.729869453680434e-05, "gradient_norm": 0.24753664433956146, "tokens_per_second": 1119760.0567236915, "synthetic": false, "world_size": 8} {"step": 50260, "tokens": 13175357440, "loss": 2.3631690979003905, "optimizer_updates": 26130, "effective_batch": 512, "lr": 6.723324895620316e-05, "gradient_norm": 0.23684222996234894, "tokens_per_second": 1134625.5994998445, "synthetic": false, "world_size": 8} {"step": 50280, "tokens": 13180600320, "loss": 2.366687202453613, "optimizer_updates": 26140, "effective_batch": 512, "lr": 6.71678325724564e-05, "gradient_norm": 0.24327850341796875, "tokens_per_second": 1133523.888426018, "synthetic": false, "world_size": 8} {"step": 50300, "tokens": 13185843200, "loss": 2.3672868728637697, "optimizer_updates": 26150, "effective_batch": 512, "lr": 6.710244543022377e-05, "gradient_norm": 0.2440660148859024, "tokens_per_second": 1124206.0708113958, "synthetic": false, "world_size": 8} {"step": 50320, "tokens": 13191086080, "loss": 2.3555503845214845, "optimizer_updates": 26160, "effective_batch": 512, "lr": 6.703708757414512e-05, "gradient_norm": 0.27025550603866577, "tokens_per_second": 1128166.9135517923, "synthetic": false, "world_size": 8} {"step": 50340, "tokens": 13196328960, "loss": 2.359638786315918, "optimizer_updates": 26170, "effective_batch": 512, "lr": 6.697175904884023e-05, "gradient_norm": 0.3249117434024811, "tokens_per_second": 1134061.3300914874, "synthetic": false, "world_size": 8} {"step": 50360, "tokens": 13201571840, "loss": 2.3744298934936525, "optimizer_updates": 26180, "effective_batch": 512, "lr": 6.690645989890887e-05, "gradient_norm": 0.27097246050834656, "tokens_per_second": 1120593.3857781726, "synthetic": false, "world_size": 8} {"step": 50380, "tokens": 13206814720, "loss": 2.358013916015625, "optimizer_updates": 26190, "effective_batch": 512, "lr": 6.68411901689307e-05, "gradient_norm": 0.25289973616600037, "tokens_per_second": 1122217.7299618972, "synthetic": false, "world_size": 8} {"step": 50400, "tokens": 13212057600, "loss": 2.3649776458740233, "optimizer_updates": 26200, "effective_batch": 512, "lr": 6.677594990346545e-05, "gradient_norm": 0.2825722098350525, "tokens_per_second": 1124112.1698262193, "synthetic": false, "world_size": 8} {"step": 50420, "tokens": 13217300480, "loss": 2.343882751464844, "optimizer_updates": 26210, "effective_batch": 512, "lr": 6.671073914705255e-05, "gradient_norm": 0.24985815584659576, "tokens_per_second": 1125966.442817602, "synthetic": false, "world_size": 8} {"step": 50440, "tokens": 13222543360, "loss": 2.3599613189697264, "optimizer_updates": 26220, "effective_batch": 512, "lr": 6.664555794421149e-05, "gradient_norm": 0.281576931476593, "tokens_per_second": 1132644.190149509, "synthetic": false, "world_size": 8} {"step": 50460, "tokens": 13227786240, "loss": 2.365780830383301, "optimizer_updates": 26230, "effective_batch": 512, "lr": 6.658040633944133e-05, "gradient_norm": 0.26356571912765503, "tokens_per_second": 749475.6745431356, "synthetic": false, "world_size": 8} {"step": 50480, "tokens": 13233029120, "loss": 2.3594017028808594, "optimizer_updates": 26240, "effective_batch": 512, "lr": 6.651528437722115e-05, "gradient_norm": 0.24352820217609406, "tokens_per_second": 1131620.2318092561, "synthetic": false, "world_size": 8} {"step": 50500, "tokens": 13238272000, "loss": 2.3609651565551757, "optimizer_updates": 26250, "effective_batch": 512, "lr": 6.645019210200972e-05, "gradient_norm": 0.29928478598594666, "tokens_per_second": 1119830.0675989094, "synthetic": false, "world_size": 8} {"step": 50520, "tokens": 13243514880, "loss": 2.3773326873779297, "optimizer_updates": 26260, "effective_batch": 512, "lr": 6.638512955824542e-05, "gradient_norm": 0.26099222898483276, "tokens_per_second": 1121221.2510364088, "synthetic": false, "world_size": 8} {"step": 50540, "tokens": 13248757760, "loss": 2.3576608657836915, "optimizer_updates": 26270, "effective_batch": 512, "lr": 6.632009679034657e-05, "gradient_norm": 0.2554599940776825, "tokens_per_second": 1120552.3582745078, "synthetic": false, "world_size": 8} {"step": 50560, "tokens": 13254000640, "loss": 2.368663787841797, "optimizer_updates": 26280, "effective_batch": 512, "lr": 6.625509384271093e-05, "gradient_norm": 0.25320303440093994, "tokens_per_second": 1116316.984686363, "synthetic": false, "world_size": 8} {"step": 50580, "tokens": 13259243520, "loss": 2.3587051391601563, "optimizer_updates": 26290, "effective_batch": 512, "lr": 6.619012075971607e-05, "gradient_norm": 0.23503270745277405, "tokens_per_second": 1119039.5594282588, "synthetic": false, "world_size": 8} {"step": 50600, "tokens": 13264486400, "loss": 2.3680530548095704, "optimizer_updates": 26300, "effective_batch": 512, "lr": 6.612517758571905e-05, "gradient_norm": 0.2823430895805359, "tokens_per_second": 1137424.20126821, "synthetic": false, "world_size": 8} {"step": 50620, "tokens": 13269729280, "loss": 2.3642333984375, "optimizer_updates": 26310, "effective_batch": 512, "lr": 6.60602643650566e-05, "gradient_norm": 0.25619983673095703, "tokens_per_second": 1133715.075377299, "synthetic": false, "world_size": 8} {"step": 50640, "tokens": 13274972160, "loss": 2.365348243713379, "optimizer_updates": 26320, "effective_batch": 512, "lr": 6.599538114204498e-05, "gradient_norm": 0.25922101736068726, "tokens_per_second": 1135731.398545161, "synthetic": false, "world_size": 8} {"step": 50660, "tokens": 13280215040, "loss": 2.3742061614990235, "optimizer_updates": 26330, "effective_batch": 512, "lr": 6.593052796097988e-05, "gradient_norm": 0.2926296293735504, "tokens_per_second": 1129143.694022571, "synthetic": false, "world_size": 8} {"step": 50680, "tokens": 13285457920, "loss": 2.370737838745117, "optimizer_updates": 26340, "effective_batch": 512, "lr": 6.586570486613666e-05, "gradient_norm": 0.2599969804286957, "tokens_per_second": 1118687.286014573, "synthetic": false, "world_size": 8} {"step": 50700, "tokens": 13290700800, "loss": 2.3713920593261717, "optimizer_updates": 26350, "effective_batch": 512, "lr": 6.580091190176997e-05, "gradient_norm": 0.26189669966697693, "tokens_per_second": 1132378.7798151602, "synthetic": false, "world_size": 8} {"step": 50720, "tokens": 13295943680, "loss": 2.3635854721069336, "optimizer_updates": 26360, "effective_batch": 512, "lr": 6.573614911211393e-05, "gradient_norm": 0.30829161405563354, "tokens_per_second": 1138748.8112310434, "synthetic": false, "world_size": 8} {"step": 50740, "tokens": 13301186560, "loss": 2.372119140625, "optimizer_updates": 26370, "effective_batch": 512, "lr": 6.567141654138217e-05, "gradient_norm": 0.24948391318321228, "tokens_per_second": 1134002.025516155, "synthetic": false, "world_size": 8} {"step": 50760, "tokens": 13306429440, "loss": 2.3620704650878905, "optimizer_updates": 26380, "effective_batch": 512, "lr": 6.560671423376754e-05, "gradient_norm": 0.24975359439849854, "tokens_per_second": 1130413.392838089, "synthetic": false, "world_size": 8} {"step": 50780, "tokens": 13311672320, "loss": 2.36181640625, "optimizer_updates": 26390, "effective_batch": 512, "lr": 6.554204223344235e-05, "gradient_norm": 0.298015296459198, "tokens_per_second": 1141780.3696467802, "synthetic": false, "world_size": 8} {"step": 50800, "tokens": 13316915200, "loss": 2.3643436431884766, "optimizer_updates": 26400, "effective_batch": 512, "lr": 6.54774005845581e-05, "gradient_norm": 0.2881510853767395, "tokens_per_second": 1134758.423497077, "synthetic": false, "world_size": 8} {"step": 50820, "tokens": 13322158080, "loss": 2.353386116027832, "optimizer_updates": 26410, "effective_batch": 512, "lr": 6.541278933124571e-05, "gradient_norm": 0.2413756102323532, "tokens_per_second": 1135444.3853546968, "synthetic": false, "world_size": 8} {"step": 50840, "tokens": 13327400960, "loss": 2.3679996490478517, "optimizer_updates": 26420, "effective_batch": 512, "lr": 6.534820851761519e-05, "gradient_norm": 0.2513577342033386, "tokens_per_second": 1136646.49262461, "synthetic": false, "world_size": 8} {"step": 50860, "tokens": 13332643840, "loss": 2.3635227203369142, "optimizer_updates": 26430, "effective_batch": 512, "lr": 6.528365818775592e-05, "gradient_norm": 0.2559683918952942, "tokens_per_second": 1136100.3928542286, "synthetic": false, "world_size": 8} {"step": 50880, "tokens": 13337886720, "loss": 2.357028579711914, "optimizer_updates": 26440, "effective_batch": 512, "lr": 6.521913838573636e-05, "gradient_norm": 0.2798340320587158, "tokens_per_second": 1128395.3572091053, "synthetic": false, "world_size": 8} {"step": 50900, "tokens": 13343129600, "loss": 2.3696489334106445, "optimizer_updates": 26450, "effective_batch": 512, "lr": 6.515464915560417e-05, "gradient_norm": 0.25551125407218933, "tokens_per_second": 1130776.3180586733, "synthetic": false, "world_size": 8} {"step": 50920, "tokens": 13348372480, "loss": 2.3655391693115235, "optimizer_updates": 26460, "effective_batch": 512, "lr": 6.509019054138618e-05, "gradient_norm": 0.2409300059080124, "tokens_per_second": 992084.1772888796, "synthetic": false, "world_size": 8} {"step": 50940, "tokens": 13353615360, "loss": 2.365863800048828, "optimizer_updates": 26470, "effective_batch": 512, "lr": 6.502576258708821e-05, "gradient_norm": 0.24784591794013977, "tokens_per_second": 1130768.288220174, "synthetic": false, "world_size": 8} {"step": 50960, "tokens": 13358858240, "loss": 2.3737897872924805, "optimizer_updates": 26480, "effective_batch": 512, "lr": 6.49613653366953e-05, "gradient_norm": 0.24351119995117188, "tokens_per_second": 1130789.522806288, "synthetic": false, "world_size": 8} {"step": 50980, "tokens": 13364101120, "loss": 2.3616708755493163, "optimizer_updates": 26490, "effective_batch": 512, "lr": 6.489699883417138e-05, "gradient_norm": 0.24173109233379364, "tokens_per_second": 1129027.1754781846, "synthetic": false, "world_size": 8} {"step": 51000, "tokens": 13369344000, "loss": 2.359923553466797, "optimizer_updates": 26500, "effective_batch": 512, "lr": 6.483266312345947e-05, "gradient_norm": 0.23512330651283264, "tokens_per_second": 1133821.7383992155, "synthetic": false, "world_size": 8} {"step": 51020, "tokens": 13374586880, "loss": 2.3744281768798827, "optimizer_updates": 26510, "effective_batch": 512, "lr": 6.47683582484815e-05, "gradient_norm": 0.27302494645118713, "tokens_per_second": 831796.273075983, "synthetic": false, "world_size": 8} {"step": 51040, "tokens": 13379829760, "loss": 2.372088623046875, "optimizer_updates": 26520, "effective_batch": 512, "lr": 6.470408425313849e-05, "gradient_norm": 0.24851958453655243, "tokens_per_second": 1139046.171439097, "synthetic": false, "world_size": 8} {"step": 51060, "tokens": 13385072640, "loss": 2.3544326782226563, "optimizer_updates": 26530, "effective_batch": 512, "lr": 6.463984118131021e-05, "gradient_norm": 0.2367948293685913, "tokens_per_second": 1132751.144193487, "synthetic": false, "world_size": 8} {"step": 51080, "tokens": 13390315520, "loss": 2.355225944519043, "optimizer_updates": 26540, "effective_batch": 512, "lr": 6.457562907685545e-05, "gradient_norm": 0.2652880549430847, "tokens_per_second": 1125626.8073791803, "synthetic": false, "world_size": 8} {"step": 51100, "tokens": 13395558400, "loss": 2.3610158920288087, "optimizer_updates": 26550, "effective_batch": 512, "lr": 6.451144798361176e-05, "gradient_norm": 0.24295923113822937, "tokens_per_second": 1137688.257901817, "synthetic": false, "world_size": 8} {"step": 51120, "tokens": 13400801280, "loss": 2.356552314758301, "optimizer_updates": 26560, "effective_batch": 512, "lr": 6.44472979453956e-05, "gradient_norm": 0.25845587253570557, "tokens_per_second": 1123152.3722711743, "synthetic": false, "world_size": 8} {"step": 51140, "tokens": 13406044160, "loss": 2.359811782836914, "optimizer_updates": 26570, "effective_batch": 512, "lr": 6.438317900600214e-05, "gradient_norm": 0.27891460061073303, "tokens_per_second": 821847.2390399212, "synthetic": false, "world_size": 8} {"step": 51160, "tokens": 13411287040, "loss": 2.365273666381836, "optimizer_updates": 26580, "effective_batch": 512, "lr": 6.431909120920544e-05, "gradient_norm": 0.24650439620018005, "tokens_per_second": 1148131.8070903583, "synthetic": false, "world_size": 8} {"step": 51180, "tokens": 13416529920, "loss": 2.3502803802490235, "optimizer_updates": 26590, "effective_batch": 512, "lr": 6.425503459875816e-05, "gradient_norm": 0.23840944468975067, "tokens_per_second": 1138723.5979459917, "synthetic": false, "world_size": 8} {"step": 51200, "tokens": 13421772800, "loss": 2.359401321411133, "optimizer_updates": 26600, "effective_batch": 512, "lr": 6.41910092183918e-05, "gradient_norm": 0.2740306258201599, "tokens_per_second": 1124923.4628994083, "synthetic": false, "world_size": 8} {"step": 51220, "tokens": 13427015680, "loss": 2.3678590774536135, "optimizer_updates": 26610, "effective_batch": 512, "lr": 6.412701511181643e-05, "gradient_norm": 0.2776131331920624, "tokens_per_second": 1118213.300424593, "synthetic": false, "world_size": 8} {"step": 51240, "tokens": 13432258560, "loss": 2.3581157684326173, "optimizer_updates": 26620, "effective_batch": 512, "lr": 6.406305232272085e-05, "gradient_norm": 0.25307580828666687, "tokens_per_second": 1134052.1190334049, "synthetic": false, "world_size": 8} {"step": 51260, "tokens": 13437501440, "loss": 2.3717437744140626, "optimizer_updates": 26630, "effective_batch": 512, "lr": 6.39991208947724e-05, "gradient_norm": 0.2398664355278015, "tokens_per_second": 1142466.2893397806, "synthetic": false, "world_size": 8} {"step": 51280, "tokens": 13442744320, "loss": 2.3484621047973633, "optimizer_updates": 26640, "effective_batch": 512, "lr": 6.393522087161713e-05, "gradient_norm": 0.34158676862716675, "tokens_per_second": 1130734.8239327637, "synthetic": false, "world_size": 8} {"step": 51300, "tokens": 13447987200, "loss": 2.3572982788085937, "optimizer_updates": 26650, "effective_batch": 512, "lr": 6.387135229687953e-05, "gradient_norm": 0.24556484818458557, "tokens_per_second": 766709.1345347591, "synthetic": false, "world_size": 8} {"step": 51320, "tokens": 13453230080, "loss": 2.3567602157592775, "optimizer_updates": 26660, "effective_batch": 512, "lr": 6.380751521416267e-05, "gradient_norm": 0.2700859606266022, "tokens_per_second": 761590.007163948, "synthetic": false, "world_size": 8} {"step": 51340, "tokens": 13458472960, "loss": 2.3540359497070313, "optimizer_updates": 26670, "effective_batch": 512, "lr": 6.374370966704808e-05, "gradient_norm": 0.2478054016828537, "tokens_per_second": 1137880.397421223, "synthetic": false, "world_size": 8} {"step": 51360, "tokens": 13463715840, "loss": 2.3746814727783203, "optimizer_updates": 26680, "effective_batch": 512, "lr": 6.367993569909583e-05, "gradient_norm": 0.2591184973716736, "tokens_per_second": 1143242.336964135, "synthetic": false, "world_size": 8} {"step": 51380, "tokens": 13468958720, "loss": 2.3612226486206054, "optimizer_updates": 26690, "effective_batch": 512, "lr": 6.361619335384445e-05, "gradient_norm": 0.25397902727127075, "tokens_per_second": 1134295.4464266528, "synthetic": false, "world_size": 8} {"step": 51400, "tokens": 13474201600, "loss": 2.368119812011719, "optimizer_updates": 26700, "effective_batch": 512, "lr": 6.355248267481073e-05, "gradient_norm": 0.265774130821228, "tokens_per_second": 1138610.645021294, "synthetic": false, "world_size": 8} {"step": 51420, "tokens": 13479444480, "loss": 2.3529619216918944, "optimizer_updates": 26710, "effective_batch": 512, "lr": 6.348880370549003e-05, "gradient_norm": 0.2620662748813629, "tokens_per_second": 1140442.043952841, "synthetic": false, "world_size": 8} {"step": 51440, "tokens": 13484687360, "loss": 2.3593984603881837, "optimizer_updates": 26720, "effective_batch": 512, "lr": 6.342515648935591e-05, "gradient_norm": 0.2696801722049713, "tokens_per_second": 1129680.0826081424, "synthetic": false, "world_size": 8} {"step": 51460, "tokens": 13489930240, "loss": 2.358050537109375, "optimizer_updates": 26730, "effective_batch": 512, "lr": 6.336154106986035e-05, "gradient_norm": 0.24664562940597534, "tokens_per_second": 1134195.9490863376, "synthetic": false, "world_size": 8} {"step": 51480, "tokens": 13495173120, "loss": 2.362417793273926, "optimizer_updates": 26740, "effective_batch": 512, "lr": 6.329795749043357e-05, "gradient_norm": 0.3345867991447449, "tokens_per_second": 1126675.3535481323, "synthetic": false, "world_size": 8} {"step": 51500, "tokens": 13500416000, "loss": 2.372317314147949, "optimizer_updates": 26750, "effective_batch": 512, "lr": 6.323440579448409e-05, "gradient_norm": 0.233228862285614, "tokens_per_second": 1129039.4485712755, "synthetic": false, "world_size": 8} {"step": 51520, "tokens": 13505658880, "loss": 2.361729621887207, "optimizer_updates": 26760, "effective_batch": 512, "lr": 6.31708860253986e-05, "gradient_norm": 0.2677639424800873, "tokens_per_second": 1135108.507299214, "synthetic": false, "world_size": 8} {"step": 51540, "tokens": 13510901760, "loss": 2.3496431350708007, "optimizer_updates": 26770, "effective_batch": 512, "lr": 6.31073982265421e-05, "gradient_norm": 0.30315080285072327, "tokens_per_second": 1134688.3629203774, "synthetic": false, "world_size": 8} {"step": 51560, "tokens": 13516144640, "loss": 2.3432889938354493, "optimizer_updates": 26780, "effective_batch": 512, "lr": 6.304394244125764e-05, "gradient_norm": 0.2722929120063782, "tokens_per_second": 1140587.752831701, "synthetic": false, "world_size": 8} {"step": 51580, "tokens": 13521387520, "loss": 2.373235511779785, "optimizer_updates": 26790, "effective_batch": 512, "lr": 6.298051871286653e-05, "gradient_norm": 0.300515741109848, "tokens_per_second": 1130469.1273141473, "synthetic": false, "world_size": 8} {"step": 51600, "tokens": 13526630400, "loss": 2.3555431365966797, "optimizer_updates": 26800, "effective_batch": 512, "lr": 6.291712708466811e-05, "gradient_norm": 0.24690696597099304, "tokens_per_second": 1134092.4790329349, "synthetic": false, "world_size": 8} {"step": 51620, "tokens": 13531873280, "loss": 2.3623115539550783, "optimizer_updates": 26810, "effective_batch": 512, "lr": 6.285376759993984e-05, "gradient_norm": 0.2574634850025177, "tokens_per_second": 1131799.8577761364, "synthetic": false, "world_size": 8} {"step": 51640, "tokens": 13537116160, "loss": 2.354829788208008, "optimizer_updates": 26820, "effective_batch": 512, "lr": 6.279044030193719e-05, "gradient_norm": 0.27503690123558044, "tokens_per_second": 1131292.7296209764, "synthetic": false, "world_size": 8} {"step": 51660, "tokens": 13542359040, "loss": 2.3695085525512694, "optimizer_updates": 26830, "effective_batch": 512, "lr": 6.272714523389377e-05, "gradient_norm": 0.280787855386734, "tokens_per_second": 1128758.7389899942, "synthetic": false, "world_size": 8} {"step": 51680, "tokens": 13547601920, "loss": 2.360519599914551, "optimizer_updates": 26840, "effective_batch": 512, "lr": 6.266388243902104e-05, "gradient_norm": 0.2996174097061157, "tokens_per_second": 763929.7905333986, "synthetic": false, "world_size": 8} {"step": 51700, "tokens": 13552844800, "loss": 2.3718791961669923, "optimizer_updates": 26850, "effective_batch": 512, "lr": 6.260065196050857e-05, "gradient_norm": 0.24247866868972778, "tokens_per_second": 1129900.243261297, "synthetic": false, "world_size": 8} {"step": 51720, "tokens": 13558087680, "loss": 2.363113021850586, "optimizer_updates": 26860, "effective_batch": 512, "lr": 6.253745384152374e-05, "gradient_norm": 0.2512066066265106, "tokens_per_second": 1137983.5710245052, "synthetic": false, "world_size": 8} {"step": 51740, "tokens": 13563330560, "loss": 2.3596721649169923, "optimizer_updates": 26870, "effective_batch": 512, "lr": 6.247428812521195e-05, "gradient_norm": 0.2467600554227829, "tokens_per_second": 1135840.6616711747, "synthetic": false, "world_size": 8} {"step": 51760, "tokens": 13568573440, "loss": 2.361783981323242, "optimizer_updates": 26880, "effective_batch": 512, "lr": 6.241115485469635e-05, "gradient_norm": 0.25461331009864807, "tokens_per_second": 1126416.6008677813, "synthetic": false, "world_size": 8} {"step": 51780, "tokens": 13573816320, "loss": 2.358489227294922, "optimizer_updates": 26890, "effective_batch": 512, "lr": 6.234805407307807e-05, "gradient_norm": 0.25248855352401733, "tokens_per_second": 1134884.7157670548, "synthetic": false, "world_size": 8} {"step": 51800, "tokens": 13579059200, "loss": 2.3666996002197265, "optimizer_updates": 26900, "effective_batch": 512, "lr": 6.228498582343603e-05, "gradient_norm": 0.24505499005317688, "tokens_per_second": 1138428.2561243805, "synthetic": false, "world_size": 8} {"step": 51820, "tokens": 13584302080, "loss": 2.365606689453125, "optimizer_updates": 26910, "effective_batch": 512, "lr": 6.222195014882684e-05, "gradient_norm": 0.23798316717147827, "tokens_per_second": 1136126.7796862538, "synthetic": false, "world_size": 8} {"step": 51840, "tokens": 13589544960, "loss": 2.372265625, "optimizer_updates": 26920, "effective_batch": 512, "lr": 6.215894709228503e-05, "gradient_norm": 0.24768172204494476, "tokens_per_second": 1119020.9683233574, "synthetic": false, "world_size": 8} {"step": 51860, "tokens": 13594787840, "loss": 2.359475517272949, "optimizer_updates": 26930, "effective_batch": 512, "lr": 6.209597669682268e-05, "gradient_norm": 0.22510142624378204, "tokens_per_second": 1128238.4528570194, "synthetic": false, "world_size": 8} {"step": 51880, "tokens": 13600030720, "loss": 2.358781433105469, "optimizer_updates": 26940, "effective_batch": 512, "lr": 6.203303900542977e-05, "gradient_norm": 0.24382835626602173, "tokens_per_second": 1134332.1014896485, "synthetic": false, "world_size": 8} {"step": 51900, "tokens": 13605273600, "loss": 2.3517438888549806, "optimizer_updates": 26950, "effective_batch": 512, "lr": 6.197013406107376e-05, "gradient_norm": 0.25937581062316895, "tokens_per_second": 1123798.7394124107, "synthetic": false, "world_size": 8} {"step": 51920, "tokens": 13610516480, "loss": 2.3561010360717773, "optimizer_updates": 26960, "effective_batch": 512, "lr": 6.190726190669992e-05, "gradient_norm": 0.25546181201934814, "tokens_per_second": 1006852.0620239974, "synthetic": false, "world_size": 8} {"step": 51940, "tokens": 13615759360, "loss": 2.3719108581542967, "optimizer_updates": 26970, "effective_batch": 512, "lr": 6.184442258523104e-05, "gradient_norm": 0.2527228593826294, "tokens_per_second": 1133378.1663147465, "synthetic": false, "world_size": 8} {"step": 51960, "tokens": 13621002240, "loss": 2.3649755477905274, "optimizer_updates": 26980, "effective_batch": 512, "lr": 6.178161613956749e-05, "gradient_norm": 0.25778356194496155, "tokens_per_second": 795352.7100337725, "synthetic": false, "world_size": 8} {"step": 51980, "tokens": 13626245120, "loss": 2.3559125900268554, "optimizer_updates": 26990, "effective_batch": 512, "lr": 6.17188426125872e-05, "gradient_norm": 0.2857401967048645, "tokens_per_second": 1133995.0346398945, "synthetic": false, "world_size": 8} {"step": 52000, "tokens": 13631488000, "loss": 2.359356498718262, "optimizer_updates": 27000, "effective_batch": 512, "lr": 6.165610204714572e-05, "gradient_norm": 0.26196447014808655, "tokens_per_second": 1123845.1829703858, "synthetic": false, "world_size": 8} {"step": 52020, "tokens": 13636730880, "loss": 2.358627510070801, "optimizer_updates": 27010, "effective_batch": 512, "lr": 6.159339448607596e-05, "gradient_norm": 0.24398836493492126, "tokens_per_second": 829868.6291466967, "synthetic": false, "world_size": 8} {"step": 52040, "tokens": 13641973760, "loss": 2.3518205642700196, "optimizer_updates": 27020, "effective_batch": 512, "lr": 6.153071997218841e-05, "gradient_norm": 0.2660520672798157, "tokens_per_second": 1126151.8569405072, "synthetic": false, "world_size": 8} {"step": 52060, "tokens": 13647216640, "loss": 2.3483339309692384, "optimizer_updates": 27030, "effective_batch": 512, "lr": 6.146807854827092e-05, "gradient_norm": 0.24582485854625702, "tokens_per_second": 1125402.031066074, "synthetic": false, "world_size": 8} {"step": 52080, "tokens": 13652459520, "loss": 2.3648860931396483, "optimizer_updates": 27040, "effective_batch": 512, "lr": 6.140547025708879e-05, "gradient_norm": 0.25156542658805847, "tokens_per_second": 1130307.4470865661, "synthetic": false, "world_size": 8} {"step": 52100, "tokens": 13657702400, "loss": 2.356966972351074, "optimizer_updates": 27050, "effective_batch": 512, "lr": 6.134289514138469e-05, "gradient_norm": 0.2658253014087677, "tokens_per_second": 1126546.5676103097, "synthetic": false, "world_size": 8} {"step": 52120, "tokens": 13662945280, "loss": 2.3649673461914062, "optimizer_updates": 27060, "effective_batch": 512, "lr": 6.128035324387866e-05, "gradient_norm": 0.24373336136341095, "tokens_per_second": 1124073.6666216338, "synthetic": false, "world_size": 8} {"step": 52140, "tokens": 13668188160, "loss": 2.346897315979004, "optimizer_updates": 27070, "effective_batch": 512, "lr": 6.1217844607268e-05, "gradient_norm": 0.2516746520996094, "tokens_per_second": 1127575.7484266474, "synthetic": false, "world_size": 8} {"step": 52160, "tokens": 13673431040, "loss": 2.370692825317383, "optimizer_updates": 27080, "effective_batch": 512, "lr": 6.115536927422739e-05, "gradient_norm": 0.24073418974876404, "tokens_per_second": 1140747.2867840382, "synthetic": false, "world_size": 8} {"step": 52180, "tokens": 13678673920, "loss": 2.3566028594970705, "optimizer_updates": 27090, "effective_batch": 512, "lr": 6.10929272874087e-05, "gradient_norm": 0.254281222820282, "tokens_per_second": 1128258.0133928321, "synthetic": false, "world_size": 8} {"step": 52200, "tokens": 13683916800, "loss": 2.3600963592529296, "optimizer_updates": 27100, "effective_batch": 512, "lr": 6.103051868944108e-05, "gradient_norm": 0.268436998128891, "tokens_per_second": 1129916.932919303, "synthetic": false, "world_size": 8} {"step": 52220, "tokens": 13689159680, "loss": 2.367440032958984, "optimizer_updates": 27110, "effective_batch": 512, "lr": 6.096814352293089e-05, "gradient_norm": 0.33199846744537354, "tokens_per_second": 1131414.0241875881, "synthetic": false, "world_size": 8} {"step": 52240, "tokens": 13694402560, "loss": 2.3745946884155273, "optimizer_updates": 27120, "effective_batch": 512, "lr": 6.0905801830461634e-05, "gradient_norm": 0.24236689507961273, "tokens_per_second": 1129301.763215696, "synthetic": false, "world_size": 8} {"step": 52260, "tokens": 13699645440, "loss": 2.3621673583984375, "optimizer_updates": 27130, "effective_batch": 512, "lr": 6.0843493654593955e-05, "gradient_norm": 0.3028976321220398, "tokens_per_second": 1130602.4264046242, "synthetic": false, "world_size": 8} {"step": 52280, "tokens": 13704888320, "loss": 2.365738105773926, "optimizer_updates": 27140, "effective_batch": 512, "lr": 6.078121903786563e-05, "gradient_norm": 0.2780739665031433, "tokens_per_second": 1127074.792542342, "synthetic": false, "world_size": 8} {"step": 52300, "tokens": 13710131200, "loss": 2.3564449310302735, "optimizer_updates": 27150, "effective_batch": 512, "lr": 6.0718978022791575e-05, "gradient_norm": 0.31323304772377014, "tokens_per_second": 1132597.0478433198, "synthetic": false, "world_size": 8} {"step": 52320, "tokens": 13715374080, "loss": 2.3688735961914062, "optimizer_updates": 27160, "effective_batch": 512, "lr": 6.0656770651863664e-05, "gradient_norm": 0.2721400558948517, "tokens_per_second": 1129986.3748505611, "synthetic": false, "world_size": 8} {"step": 52340, "tokens": 13720616960, "loss": 2.3645418167114256, "optimizer_updates": 27170, "effective_batch": 512, "lr": 6.059459696755092e-05, "gradient_norm": 0.234040305018425, "tokens_per_second": 1130468.3609526304, "synthetic": false, "world_size": 8} {"step": 52360, "tokens": 13725859840, "loss": 2.3680238723754883, "optimizer_updates": 27180, "effective_batch": 512, "lr": 6.0532457012299256e-05, "gradient_norm": 0.2454797476530075, "tokens_per_second": 1128562.8315358753, "synthetic": false, "world_size": 8} {"step": 52380, "tokens": 13731102720, "loss": 2.357468605041504, "optimizer_updates": 27190, "effective_batch": 512, "lr": 6.047035082853165e-05, "gradient_norm": 0.23920051753520966, "tokens_per_second": 1139459.5827875917, "synthetic": false, "world_size": 8} {"step": 52400, "tokens": 13736345600, "loss": 2.362212371826172, "optimizer_updates": 27200, "effective_batch": 512, "lr": 6.040827845864794e-05, "gradient_norm": 0.35692623257637024, "tokens_per_second": 1127936.095008184, "synthetic": false, "world_size": 8} {"step": 52420, "tokens": 13741588480, "loss": 2.3551328659057615, "optimizer_updates": 27210, "effective_batch": 512, "lr": 6.0346239945024984e-05, "gradient_norm": 0.2717548906803131, "tokens_per_second": 1133515.9374025455, "synthetic": false, "world_size": 8} {"step": 52440, "tokens": 13746831360, "loss": 2.348940849304199, "optimizer_updates": 27220, "effective_batch": 512, "lr": 6.02842353300164e-05, "gradient_norm": 0.22925521433353424, "tokens_per_second": 1134370.4536469278, "synthetic": false, "world_size": 8} {"step": 52460, "tokens": 13752074240, "loss": 2.3589296340942383, "optimizer_updates": 27230, "effective_batch": 512, "lr": 6.0222264655952786e-05, "gradient_norm": 0.2513091266155243, "tokens_per_second": 1131477.1880733848, "synthetic": false, "world_size": 8} {"step": 52480, "tokens": 13757317120, "loss": 2.3721580505371094, "optimizer_updates": 27240, "effective_batch": 512, "lr": 6.016032796514146e-05, "gradient_norm": 0.2745634913444519, "tokens_per_second": 1133885.0698655127, "synthetic": false, "world_size": 8} {"step": 52500, "tokens": 13762560000, "loss": 2.3661052703857424, "optimizer_updates": 27250, "effective_batch": 512, "lr": 6.009842529986665e-05, "gradient_norm": 0.27073538303375244, "tokens_per_second": 1132086.2673645616, "synthetic": false, "world_size": 8} {"step": 52520, "tokens": 13767802880, "loss": 2.351075553894043, "optimizer_updates": 27260, "effective_batch": 512, "lr": 6.003655670238923e-05, "gradient_norm": 0.2690061032772064, "tokens_per_second": 1129021.7199217663, "synthetic": false, "world_size": 8} {"step": 52540, "tokens": 13773045760, "loss": 2.3563398361206054, "optimizer_updates": 27270, "effective_batch": 512, "lr": 5.997472221494695e-05, "gradient_norm": 0.26333552598953247, "tokens_per_second": 1129167.8793094764, "synthetic": false, "world_size": 8} {"step": 52560, "tokens": 13778288640, "loss": 2.365843963623047, "optimizer_updates": 27280, "effective_batch": 512, "lr": 5.9912921879754166e-05, "gradient_norm": 0.40931111574172974, "tokens_per_second": 1141768.2583289668, "synthetic": false, "world_size": 8} {"step": 52580, "tokens": 13783531520, "loss": 2.353008270263672, "optimizer_updates": 27290, "effective_batch": 512, "lr": 5.985115573900197e-05, "gradient_norm": 0.25423064827919006, "tokens_per_second": 1131942.9154303255, "synthetic": false, "world_size": 8} {"step": 52600, "tokens": 13788774400, "loss": 2.35610294342041, "optimizer_updates": 27300, "effective_batch": 512, "lr": 5.9789423834858045e-05, "gradient_norm": 0.2422502338886261, "tokens_per_second": 1134324.1685798313, "synthetic": false, "world_size": 8} {"step": 52620, "tokens": 13794017280, "loss": 2.350834846496582, "optimizer_updates": 27310, "effective_batch": 512, "lr": 5.972772620946685e-05, "gradient_norm": 0.3154686391353607, "tokens_per_second": 1128939.7263864218, "synthetic": false, "world_size": 8} {"step": 52640, "tokens": 13799260160, "loss": 2.366818428039551, "optimizer_updates": 27320, "effective_batch": 512, "lr": 5.966606290494924e-05, "gradient_norm": 0.24290244281291962, "tokens_per_second": 1128024.1951541915, "synthetic": false, "world_size": 8} {"step": 52660, "tokens": 13804503040, "loss": 2.3564947128295897, "optimizer_updates": 27330, "effective_batch": 512, "lr": 5.9604433963402804e-05, "gradient_norm": 0.25198814272880554, "tokens_per_second": 1135263.3682376947, "synthetic": false, "world_size": 8} {"step": 52680, "tokens": 13809745920, "loss": 2.364420700073242, "optimizer_updates": 27340, "effective_batch": 512, "lr": 5.9542839426901626e-05, "gradient_norm": 0.24920611083507538, "tokens_per_second": 1124755.9178235568, "synthetic": false, "world_size": 8} {"step": 52700, "tokens": 13814988800, "loss": 2.350434684753418, "optimizer_updates": 27350, "effective_batch": 512, "lr": 5.9481279337496244e-05, "gradient_norm": 0.27550584077835083, "tokens_per_second": 1131761.3601835985, "synthetic": false, "world_size": 8} {"step": 52720, "tokens": 13820231680, "loss": 2.3559375762939454, "optimizer_updates": 27360, "effective_batch": 512, "lr": 5.941975373721375e-05, "gradient_norm": 0.2847817838191986, "tokens_per_second": 1121058.4018160414, "synthetic": false, "world_size": 8} {"step": 52740, "tokens": 13825474560, "loss": 2.3642501831054688, "optimizer_updates": 27370, "effective_batch": 512, "lr": 5.935826266805764e-05, "gradient_norm": 0.24340012669563293, "tokens_per_second": 1129122.9934237213, "synthetic": false, "world_size": 8} {"step": 52760, "tokens": 13830717440, "loss": 2.3509801864624023, "optimizer_updates": 27380, "effective_batch": 512, "lr": 5.929680617200789e-05, "gradient_norm": 0.26863303780555725, "tokens_per_second": 1134059.7025134382, "synthetic": false, "world_size": 8} {"step": 52780, "tokens": 13835960320, "loss": 2.3615955352783202, "optimizer_updates": 27390, "effective_batch": 512, "lr": 5.92353842910208e-05, "gradient_norm": 0.2515440285205841, "tokens_per_second": 1122711.2760508438, "synthetic": false, "world_size": 8} {"step": 52800, "tokens": 13841203200, "loss": 2.3729719161987304, "optimizer_updates": 27400, "effective_batch": 512, "lr": 5.917399706702912e-05, "gradient_norm": 0.22989274561405182, "tokens_per_second": 1131584.4684087203, "synthetic": false, "world_size": 8} {"step": 52820, "tokens": 13846446080, "loss": 2.368535614013672, "optimizer_updates": 27410, "effective_batch": 512, "lr": 5.911264454194186e-05, "gradient_norm": 0.2506871819496155, "tokens_per_second": 1132077.846149461, "synthetic": false, "world_size": 8} {"step": 52840, "tokens": 13851688960, "loss": 2.3660604476928713, "optimizer_updates": 27420, "effective_batch": 512, "lr": 5.905132675764441e-05, "gradient_norm": 0.240618035197258, "tokens_per_second": 1137004.2662296828, "synthetic": false, "world_size": 8} {"step": 52860, "tokens": 13856931840, "loss": 2.3508190155029296, "optimizer_updates": 27430, "effective_batch": 512, "lr": 5.899004375599842e-05, "gradient_norm": 0.2422914355993271, "tokens_per_second": 1130199.772588347, "synthetic": false, "world_size": 8} {"step": 52880, "tokens": 13862174720, "loss": 2.3677154541015626, "optimizer_updates": 27440, "effective_batch": 512, "lr": 5.892879557884174e-05, "gradient_norm": 0.24985045194625854, "tokens_per_second": 1118777.671273183, "synthetic": false, "world_size": 8} {"step": 52900, "tokens": 13867417600, "loss": 2.3594877243041994, "optimizer_updates": 27450, "effective_batch": 512, "lr": 5.8867582267988495e-05, "gradient_norm": 0.2530820965766907, "tokens_per_second": 1135284.313286012, "synthetic": false, "world_size": 8} {"step": 52920, "tokens": 13872660480, "loss": 2.363529014587402, "optimizer_updates": 27460, "effective_batch": 512, "lr": 5.880640386522905e-05, "gradient_norm": 0.2507379651069641, "tokens_per_second": 1126375.3096492284, "synthetic": false, "world_size": 8} {"step": 52940, "tokens": 13877903360, "loss": 2.3651891708374024, "optimizer_updates": 27470, "effective_batch": 512, "lr": 5.874526041232984e-05, "gradient_norm": 0.24289236962795258, "tokens_per_second": 1127886.1302493848, "synthetic": false, "world_size": 8} {"step": 52960, "tokens": 13883146240, "loss": 2.372726821899414, "optimizer_updates": 27480, "effective_batch": 512, "lr": 5.868415195103355e-05, "gradient_norm": 0.2627584636211395, "tokens_per_second": 1137677.4468784232, "synthetic": false, "world_size": 8} {"step": 52980, "tokens": 13888389120, "loss": 2.369005584716797, "optimizer_updates": 27490, "effective_batch": 512, "lr": 5.862307852305885e-05, "gradient_norm": 0.3320598602294922, "tokens_per_second": 767230.3325881453, "synthetic": false, "world_size": 8} {"step": 53000, "tokens": 13893632000, "loss": 2.357853317260742, "optimizer_updates": 27500, "effective_batch": 512, "lr": 5.8562040170100617e-05, "gradient_norm": 0.24796847999095917, "tokens_per_second": 1132759.7230146842, "synthetic": false, "world_size": 8} {"step": 53020, "tokens": 13898874880, "loss": 2.3812705993652346, "optimizer_updates": 27510, "effective_batch": 512, "lr": 5.850103693382968e-05, "gradient_norm": 0.25948262214660645, "tokens_per_second": 830310.0560772406, "synthetic": false, "world_size": 8} {"step": 53040, "tokens": 13904117760, "loss": 2.359505271911621, "optimizer_updates": 27520, "effective_batch": 512, "lr": 5.8440068855892995e-05, "gradient_norm": 0.22590816020965576, "tokens_per_second": 1130506.4286142043, "synthetic": false, "world_size": 8} {"step": 53060, "tokens": 13909360640, "loss": 2.35831356048584, "optimizer_updates": 27530, "effective_batch": 512, "lr": 5.837913597791337e-05, "gradient_norm": 0.23296013474464417, "tokens_per_second": 1125838.6476538358, "synthetic": false, "world_size": 8} {"step": 53080, "tokens": 13914603520, "loss": 2.356134796142578, "optimizer_updates": 27540, "effective_batch": 512, "lr": 5.831823834148975e-05, "gradient_norm": 0.2435566931962967, "tokens_per_second": 1025849.9855880676, "synthetic": false, "world_size": 8} {"step": 53100, "tokens": 13919846400, "loss": 2.365409088134766, "optimizer_updates": 27550, "effective_batch": 512, "lr": 5.825737598819694e-05, "gradient_norm": 0.2604493200778961, "tokens_per_second": 1127728.573532215, "synthetic": false, "world_size": 8} {"step": 53120, "tokens": 13925089280, "loss": 2.3575265884399412, "optimizer_updates": 27560, "effective_batch": 512, "lr": 5.81965489595856e-05, "gradient_norm": 0.2550109624862671, "tokens_per_second": 1133769.3206166138, "synthetic": false, "world_size": 8} {"step": 53140, "tokens": 13930332160, "loss": 2.359288215637207, "optimizer_updates": 27570, "effective_batch": 512, "lr": 5.813575729718241e-05, "gradient_norm": 0.24682684242725372, "tokens_per_second": 1136530.9086507475, "synthetic": false, "world_size": 8} {"step": 53160, "tokens": 13935575040, "loss": 2.357896614074707, "optimizer_updates": 27580, "effective_batch": 512, "lr": 5.807500104248976e-05, "gradient_norm": 0.26719599962234497, "tokens_per_second": 1128531.153374356, "synthetic": false, "world_size": 8} {"step": 53180, "tokens": 13940817920, "loss": 2.3480316162109376, "optimizer_updates": 27590, "effective_batch": 512, "lr": 5.801428023698599e-05, "gradient_norm": 0.24707132577896118, "tokens_per_second": 1130520.1943548617, "synthetic": false, "world_size": 8} {"step": 53200, "tokens": 13946060800, "loss": 2.3533071517944335, "optimizer_updates": 27600, "effective_batch": 512, "lr": 5.795359492212517e-05, "gradient_norm": 0.2530803382396698, "tokens_per_second": 1129497.3951267125, "synthetic": false, "world_size": 8} {"step": 53220, "tokens": 13951303680, "loss": 2.3636775970458985, "optimizer_updates": 27610, "effective_batch": 512, "lr": 5.789294513933715e-05, "gradient_norm": 0.22071415185928345, "tokens_per_second": 1134059.0050956465, "synthetic": false, "world_size": 8} {"step": 53240, "tokens": 13956546560, "loss": 2.373287582397461, "optimizer_updates": 27620, "effective_batch": 512, "lr": 5.783233093002748e-05, "gradient_norm": 0.2590833008289337, "tokens_per_second": 1134620.968243356, "synthetic": false, "world_size": 8} {"step": 53260, "tokens": 13961789440, "loss": 2.3614175796508787, "optimizer_updates": 27630, "effective_batch": 512, "lr": 5.7771752335577544e-05, "gradient_norm": 0.25828495621681213, "tokens_per_second": 1136124.0626717594, "synthetic": false, "world_size": 8} {"step": 53280, "tokens": 13967032320, "loss": 2.3685497283935546, "optimizer_updates": 27640, "effective_batch": 512, "lr": 5.7711209397344276e-05, "gradient_norm": 0.2473822981119156, "tokens_per_second": 1129862.8867097327, "synthetic": false, "world_size": 8} {"step": 53300, "tokens": 13972275200, "loss": 2.36389045715332, "optimizer_updates": 27650, "effective_batch": 512, "lr": 5.76507021566604e-05, "gradient_norm": 0.25312912464141846, "tokens_per_second": 1136841.0259382057, "synthetic": false, "world_size": 8} {"step": 53320, "tokens": 13977518080, "loss": 2.3539188385009764, "optimizer_updates": 27660, "effective_batch": 512, "lr": 5.7590230654834136e-05, "gradient_norm": 0.24830302596092224, "tokens_per_second": 1126193.2098993466, "synthetic": false, "world_size": 8} {"step": 53340, "tokens": 13982760960, "loss": 2.369149398803711, "optimizer_updates": 27670, "effective_batch": 512, "lr": 5.752979493314943e-05, "gradient_norm": 0.23998920619487762, "tokens_per_second": 1139005.9824303512, "synthetic": false, "world_size": 8} {"step": 53360, "tokens": 13988003840, "loss": 2.3670095443725585, "optimizer_updates": 27680, "effective_batch": 512, "lr": 5.746939503286566e-05, "gradient_norm": 0.23968766629695892, "tokens_per_second": 1136498.9946603396, "synthetic": false, "world_size": 8} {"step": 53380, "tokens": 13993246720, "loss": 2.3473106384277345, "optimizer_updates": 27690, "effective_batch": 512, "lr": 5.740903099521791e-05, "gradient_norm": 0.24295933544635773, "tokens_per_second": 1134519.3466429214, "synthetic": false, "world_size": 8} {"step": 53400, "tokens": 13998489600, "loss": 2.3548389434814454, "optimizer_updates": 27700, "effective_batch": 512, "lr": 5.734870286141666e-05, "gradient_norm": 0.2633160948753357, "tokens_per_second": 1129871.0699744103, "synthetic": false, "world_size": 8} {"step": 53420, "tokens": 14003732480, "loss": 2.362005615234375, "optimizer_updates": 27710, "effective_batch": 512, "lr": 5.728841067264792e-05, "gradient_norm": 0.23704516887664795, "tokens_per_second": 1138626.0062306153, "synthetic": false, "world_size": 8} {"step": 53440, "tokens": 14008975360, "loss": 2.352711868286133, "optimizer_updates": 27720, "effective_batch": 512, "lr": 5.722815447007314e-05, "gradient_norm": 0.2601248025894165, "tokens_per_second": 1025086.4967778712, "synthetic": false, "world_size": 8} {"step": 53460, "tokens": 14014218240, "loss": 2.352107620239258, "optimizer_updates": 27730, "effective_batch": 512, "lr": 5.716793429482928e-05, "gradient_norm": 0.23712991178035736, "tokens_per_second": 1139240.373278274, "synthetic": false, "world_size": 8} {"step": 53480, "tokens": 14019461120, "loss": 2.356119918823242, "optimizer_updates": 27740, "effective_batch": 512, "lr": 5.710775018802857e-05, "gradient_norm": 0.2673652172088623, "tokens_per_second": 1122691.5727510988, "synthetic": false, "world_size": 8} {"step": 53500, "tokens": 14024704000, "loss": 2.3721992492675783, "optimizer_updates": 27750, "effective_batch": 512, "lr": 5.704760219075876e-05, "gradient_norm": 0.25679251551628113, "tokens_per_second": 1139495.8355610077, "synthetic": false, "world_size": 8} {"step": 53520, "tokens": 14029946880, "loss": 2.3701242446899413, "optimizer_updates": 27760, "effective_batch": 512, "lr": 5.698749034408283e-05, "gradient_norm": 0.30594402551651, "tokens_per_second": 755198.7519857013, "synthetic": false, "world_size": 8} {"step": 53540, "tokens": 14035189760, "loss": 2.3604576110839846, "optimizer_updates": 27770, "effective_batch": 512, "lr": 5.6927414689039136e-05, "gradient_norm": 0.24948546290397644, "tokens_per_second": 1132127.228334434, "synthetic": false, "world_size": 8} {"step": 53560, "tokens": 14040432640, "loss": 2.3649934768676757, "optimizer_updates": 27780, "effective_batch": 512, "lr": 5.6867375266641325e-05, "gradient_norm": 0.2823219895362854, "tokens_per_second": 1130171.0755063838, "synthetic": false, "world_size": 8} {"step": 53580, "tokens": 14045675520, "loss": 2.3605892181396486, "optimizer_updates": 27790, "effective_batch": 512, "lr": 5.68073721178783e-05, "gradient_norm": 0.25337424874305725, "tokens_per_second": 1128574.5542760526, "synthetic": false, "world_size": 8} {"step": 53600, "tokens": 14050918400, "loss": 2.3532039642333986, "optimizer_updates": 27800, "effective_batch": 512, "lr": 5.6747405283714226e-05, "gradient_norm": 0.2738742530345917, "tokens_per_second": 1133278.8322489979, "synthetic": false, "world_size": 8} {"step": 53620, "tokens": 14056161280, "loss": 2.370067596435547, "optimizer_updates": 27810, "effective_batch": 512, "lr": 5.668747480508839e-05, "gradient_norm": 0.2569732367992401, "tokens_per_second": 1132345.3455519492, "synthetic": false, "world_size": 8} {"step": 53640, "tokens": 14061404160, "loss": 2.3698734283447265, "optimizer_updates": 27820, "effective_batch": 512, "lr": 5.662758072291539e-05, "gradient_norm": 0.2591703534126282, "tokens_per_second": 1133151.1078079604, "synthetic": false, "world_size": 8} {"step": 53660, "tokens": 14066647040, "loss": 2.3590671539306642, "optimizer_updates": 27830, "effective_batch": 512, "lr": 5.6567723078084864e-05, "gradient_norm": 0.2379581332206726, "tokens_per_second": 1129292.8917568664, "synthetic": false, "world_size": 8} {"step": 53680, "tokens": 14071889920, "loss": 2.3555700302124025, "optimizer_updates": 27840, "effective_batch": 512, "lr": 5.6507901911461645e-05, "gradient_norm": 0.24973084032535553, "tokens_per_second": 1139815.6880737667, "synthetic": false, "world_size": 8} {"step": 53700, "tokens": 14077132800, "loss": 2.365152931213379, "optimizer_updates": 27850, "effective_batch": 512, "lr": 5.6448117263885585e-05, "gradient_norm": 0.2425709366798401, "tokens_per_second": 1136488.815722246, "synthetic": false, "world_size": 8} {"step": 53720, "tokens": 14082375680, "loss": 2.3527339935302733, "optimizer_updates": 27860, "effective_batch": 512, "lr": 5.638836917617172e-05, "gradient_norm": 0.2520129978656769, "tokens_per_second": 1137335.2590756586, "synthetic": false, "world_size": 8} {"step": 53740, "tokens": 14087618560, "loss": 2.37243595123291, "optimizer_updates": 27870, "effective_batch": 512, "lr": 5.6328657689109994e-05, "gradient_norm": 0.2689168453216553, "tokens_per_second": 1136784.8615833728, "synthetic": false, "world_size": 8} {"step": 53760, "tokens": 14092861440, "loss": 2.3694875717163084, "optimizer_updates": 27880, "effective_batch": 512, "lr": 5.6268982843465506e-05, "gradient_norm": 0.2395503669977188, "tokens_per_second": 1132994.1750790016, "synthetic": false, "world_size": 8} {"step": 53780, "tokens": 14098104320, "loss": 2.349812698364258, "optimizer_updates": 27890, "effective_batch": 512, "lr": 5.620934467997818e-05, "gradient_norm": 0.25626280903816223, "tokens_per_second": 1128713.4256283785, "synthetic": false, "world_size": 8} {"step": 53800, "tokens": 14103347200, "loss": 2.360051727294922, "optimizer_updates": 27900, "effective_batch": 512, "lr": 5.6149743239363074e-05, "gradient_norm": 0.23900362849235535, "tokens_per_second": 1138763.4690077882, "synthetic": false, "world_size": 8} {"step": 53820, "tokens": 14108590080, "loss": 2.3648237228393554, "optimizer_updates": 27910, "effective_batch": 512, "lr": 5.609017856231001e-05, "gradient_norm": 0.27306973934173584, "tokens_per_second": 1129973.5811538887, "synthetic": false, "world_size": 8} {"step": 53840, "tokens": 14113832960, "loss": 2.353855514526367, "optimizer_updates": 27920, "effective_batch": 512, "lr": 5.603065068948381e-05, "gradient_norm": 0.2722320556640625, "tokens_per_second": 1134466.4359348612, "synthetic": false, "world_size": 8} {"step": 53860, "tokens": 14119075840, "loss": 2.3653120040893554, "optimizer_updates": 27930, "effective_batch": 512, "lr": 5.5971159661524124e-05, "gradient_norm": 0.26212432980537415, "tokens_per_second": 1138465.5008529106, "synthetic": false, "world_size": 8} {"step": 53880, "tokens": 14124318720, "loss": 2.3740501403808594, "optimizer_updates": 27940, "effective_batch": 512, "lr": 5.591170551904549e-05, "gradient_norm": 0.2765226662158966, "tokens_per_second": 1117306.5661776732, "synthetic": false, "world_size": 8} {"step": 53900, "tokens": 14129561600, "loss": 2.3650348663330076, "optimizer_updates": 27950, "effective_batch": 512, "lr": 5.585228830263721e-05, "gradient_norm": 0.23182569444179535, "tokens_per_second": 1135032.1876360066, "synthetic": false, "world_size": 8} {"step": 53920, "tokens": 14134804480, "loss": 2.35130615234375, "optimizer_updates": 27960, "effective_batch": 512, "lr": 5.5792908052863476e-05, "gradient_norm": 0.26609984040260315, "tokens_per_second": 1135800.852534419, "synthetic": false, "world_size": 8} {"step": 53940, "tokens": 14140047360, "loss": 2.3705459594726563, "optimizer_updates": 27970, "effective_batch": 512, "lr": 5.5733564810263084e-05, "gradient_norm": 0.24820725619792938, "tokens_per_second": 1124272.7432474357, "synthetic": false, "world_size": 8} {"step": 53960, "tokens": 14145290240, "loss": 2.3514270782470703, "optimizer_updates": 27980, "effective_batch": 512, "lr": 5.567425861534971e-05, "gradient_norm": 0.23494866490364075, "tokens_per_second": 1125962.9991659157, "synthetic": false, "world_size": 8} {"step": 53980, "tokens": 14150533120, "loss": 2.362791633605957, "optimizer_updates": 27990, "effective_batch": 512, "lr": 5.5614989508611726e-05, "gradient_norm": 0.23441316187381744, "tokens_per_second": 1123766.6356063506, "synthetic": false, "world_size": 8} {"step": 54000, "tokens": 14155776000, "loss": 2.347687911987305, "optimizer_updates": 28000, "effective_batch": 512, "lr": 5.555575753051205e-05, "gradient_norm": 0.25914743542671204, "tokens_per_second": 1138077.2845081144, "synthetic": false, "world_size": 8} {"step": 54020, "tokens": 14161018880, "loss": 2.3610443115234374, "optimizer_updates": 28010, "effective_batch": 512, "lr": 5.5496562721488423e-05, "gradient_norm": 0.24458491802215576, "tokens_per_second": 837007.8161553015, "synthetic": false, "world_size": 8} {"step": 54040, "tokens": 14166261760, "loss": 2.361011505126953, "optimizer_updates": 28020, "effective_batch": 512, "lr": 5.5437405121953065e-05, "gradient_norm": 0.25634634494781494, "tokens_per_second": 1141667.8186196708, "synthetic": false, "world_size": 8} {"step": 54060, "tokens": 14171504640, "loss": 2.363877296447754, "optimizer_updates": 28030, "effective_batch": 512, "lr": 5.537828477229293e-05, "gradient_norm": 0.26306888461112976, "tokens_per_second": 1135778.464834178, "synthetic": false, "world_size": 8} {"step": 54080, "tokens": 14176747520, "loss": 2.3693559646606444, "optimizer_updates": 28040, "effective_batch": 512, "lr": 5.5319201712869406e-05, "gradient_norm": 0.2654050886631012, "tokens_per_second": 1049387.610425211, "synthetic": false, "world_size": 8} {"step": 54100, "tokens": 14181990400, "loss": 2.376261901855469, "optimizer_updates": 28050, "effective_batch": 512, "lr": 5.526015598401856e-05, "gradient_norm": 0.2633008658885956, "tokens_per_second": 1139846.2868667967, "synthetic": false, "world_size": 8} {"step": 54120, "tokens": 14187233280, "loss": 2.3588281631469727, "optimizer_updates": 28060, "effective_batch": 512, "lr": 5.5201147626050845e-05, "gradient_norm": 0.23706389963626862, "tokens_per_second": 1134528.79459455, "synthetic": false, "world_size": 8} {"step": 54140, "tokens": 14192476160, "loss": 2.3556514739990235, "optimizer_updates": 28070, "effective_batch": 512, "lr": 5.5142176679251234e-05, "gradient_norm": 0.22292807698249817, "tokens_per_second": 1133315.5901292537, "synthetic": false, "world_size": 8} {"step": 54160, "tokens": 14197719040, "loss": 2.362893295288086, "optimizer_updates": 28080, "effective_batch": 512, "lr": 5.508324318387927e-05, "gradient_norm": 0.31855133175849915, "tokens_per_second": 896052.1698837355, "synthetic": false, "world_size": 8} {"step": 54180, "tokens": 14202961920, "loss": 2.369789886474609, "optimizer_updates": 28090, "effective_batch": 512, "lr": 5.50243471801688e-05, "gradient_norm": 0.27736392617225647, "tokens_per_second": 1137673.766285851, "synthetic": false, "world_size": 8} {"step": 54200, "tokens": 14208204800, "loss": 2.358273506164551, "optimizer_updates": 28100, "effective_batch": 512, "lr": 5.4965488708328064e-05, "gradient_norm": 0.27373865246772766, "tokens_per_second": 1133123.8897073844, "synthetic": false, "world_size": 8} {"step": 54220, "tokens": 14213447680, "loss": 2.367650604248047, "optimizer_updates": 28110, "effective_batch": 512, "lr": 5.490666780853982e-05, "gradient_norm": 0.23297744989395142, "tokens_per_second": 1132551.3746386478, "synthetic": false, "world_size": 8} {"step": 54240, "tokens": 14218690560, "loss": 2.3689598083496093, "optimizer_updates": 28120, "effective_batch": 512, "lr": 5.484788452096102e-05, "gradient_norm": 0.3032773435115814, "tokens_per_second": 1130615.1097687637, "synthetic": false, "world_size": 8} {"step": 54260, "tokens": 14223933440, "loss": 2.361067771911621, "optimizer_updates": 28130, "effective_batch": 512, "lr": 5.478913888572305e-05, "gradient_norm": 0.26341935992240906, "tokens_per_second": 1130947.2790851002, "synthetic": false, "world_size": 8} {"step": 54280, "tokens": 14229176320, "loss": 2.3577045440673827, "optimizer_updates": 28140, "effective_batch": 512, "lr": 5.47304309429315e-05, "gradient_norm": 0.28542545437812805, "tokens_per_second": 1132885.367089208, "synthetic": false, "world_size": 8} {"step": 54300, "tokens": 14234419200, "loss": 2.3527366638183596, "optimizer_updates": 28150, "effective_batch": 512, "lr": 5.467176073266633e-05, "gradient_norm": 0.2314508855342865, "tokens_per_second": 1133289.6453050815, "synthetic": false, "world_size": 8} {"step": 54320, "tokens": 14239662080, "loss": 2.381673812866211, "optimizer_updates": 28160, "effective_batch": 512, "lr": 5.461312829498163e-05, "gradient_norm": 0.25111645460128784, "tokens_per_second": 1129035.9102409196, "synthetic": false, "world_size": 8} {"step": 54340, "tokens": 14244904960, "loss": 2.3733793258666993, "optimizer_updates": 28170, "effective_batch": 512, "lr": 5.45545336699058e-05, "gradient_norm": 0.29764461517333984, "tokens_per_second": 1133576.404637327, "synthetic": false, "world_size": 8} {"step": 54360, "tokens": 14250147840, "loss": 2.356654167175293, "optimizer_updates": 28180, "effective_batch": 512, "lr": 5.4495976897441344e-05, "gradient_norm": 0.24182863533496857, "tokens_per_second": 1134853.099027598, "synthetic": false, "world_size": 8} {"step": 54380, "tokens": 14255390720, "loss": 2.363810920715332, "optimizer_updates": 28190, "effective_batch": 512, "lr": 5.443745801756498e-05, "gradient_norm": 0.25757673382759094, "tokens_per_second": 1130884.819590333, "synthetic": false, "world_size": 8} {"step": 54400, "tokens": 14260633600, "loss": 2.3538177490234373, "optimizer_updates": 28200, "effective_batch": 512, "lr": 5.437897707022757e-05, "gradient_norm": 0.24787059426307678, "tokens_per_second": 1141856.0342996048, "synthetic": false, "world_size": 8} {"step": 54420, "tokens": 14265876480, "loss": 2.3701898574829103, "optimizer_updates": 28210, "effective_batch": 512, "lr": 5.432053409535397e-05, "gradient_norm": 0.26411351561546326, "tokens_per_second": 1140019.553759594, "synthetic": false, "world_size": 8} {"step": 54440, "tokens": 14271119360, "loss": 2.3539318084716796, "optimizer_updates": 28220, "effective_batch": 512, "lr": 5.4262129132843283e-05, "gradient_norm": 0.23574216663837433, "tokens_per_second": 1138418.5146836177, "synthetic": false, "world_size": 8} {"step": 54460, "tokens": 14276362240, "loss": 2.3597396850585937, "optimizer_updates": 28230, "effective_batch": 512, "lr": 5.420376222256853e-05, "gradient_norm": 0.264981746673584, "tokens_per_second": 1132349.308942393, "synthetic": false, "world_size": 8} {"step": 54480, "tokens": 14281605120, "loss": 2.357158088684082, "optimizer_updates": 28240, "effective_batch": 512, "lr": 5.414543340437676e-05, "gradient_norm": 0.2380322813987732, "tokens_per_second": 1135706.0074983397, "synthetic": false, "world_size": 8} {"step": 54500, "tokens": 14286848000, "loss": 2.361385536193848, "optimizer_updates": 28250, "effective_batch": 512, "lr": 5.4087142718089055e-05, "gradient_norm": 0.24805110692977905, "tokens_per_second": 1139436.1937846905, "synthetic": false, "world_size": 8} {"step": 54520, "tokens": 14292090880, "loss": 2.3738698959350586, "optimizer_updates": 28260, "effective_batch": 512, "lr": 5.4028890203500505e-05, "gradient_norm": 0.2739349901676178, "tokens_per_second": 1133014.9798980579, "synthetic": false, "world_size": 8} {"step": 54540, "tokens": 14297333760, "loss": 2.359134864807129, "optimizer_updates": 28270, "effective_batch": 512, "lr": 5.397067590038002e-05, "gradient_norm": 0.2460794597864151, "tokens_per_second": 1136224.9818649576, "synthetic": false, "world_size": 8} {"step": 54560, "tokens": 14302576640, "loss": 2.353763198852539, "optimizer_updates": 28280, "effective_batch": 512, "lr": 5.391249984847058e-05, "gradient_norm": 0.24921098351478577, "tokens_per_second": 1134550.5609932384, "synthetic": false, "world_size": 8} {"step": 54580, "tokens": 14307819520, "loss": 2.3629173278808593, "optimizer_updates": 28290, "effective_batch": 512, "lr": 5.385436208748889e-05, "gradient_norm": 0.2553037405014038, "tokens_per_second": 1131533.917413318, "synthetic": false, "world_size": 8} {"step": 54600, "tokens": 14313062400, "loss": 2.348162841796875, "optimizer_updates": 28300, "effective_batch": 512, "lr": 5.379626265712565e-05, "gradient_norm": 0.2625758647918701, "tokens_per_second": 1137139.975975416, "synthetic": false, "world_size": 8} {"step": 54620, "tokens": 14318305280, "loss": 2.3491195678710937, "optimizer_updates": 28310, "effective_batch": 512, "lr": 5.37382015970453e-05, "gradient_norm": 0.2539173662662506, "tokens_per_second": 1134583.4931458712, "synthetic": false, "world_size": 8} {"step": 54640, "tokens": 14323548160, "loss": 2.3607254028320312, "optimizer_updates": 28320, "effective_batch": 512, "lr": 5.368017894688612e-05, "gradient_norm": 0.28640827536582947, "tokens_per_second": 1126277.5897567805, "synthetic": false, "world_size": 8} {"step": 54660, "tokens": 14328791040, "loss": 2.3598348617553713, "optimizer_updates": 28330, "effective_batch": 512, "lr": 5.362219474626016e-05, "gradient_norm": 0.25700363516807556, "tokens_per_second": 1130401.229479964, "synthetic": false, "world_size": 8} {"step": 54680, "tokens": 14334033920, "loss": 2.3490222930908202, "optimizer_updates": 28340, "effective_batch": 512, "lr": 5.356424903475326e-05, "gradient_norm": 0.2803429961204529, "tokens_per_second": 1134890.9501665821, "synthetic": false, "world_size": 8} {"step": 54700, "tokens": 14339276800, "loss": 2.3600561141967775, "optimizer_updates": 28350, "effective_batch": 512, "lr": 5.3506341851924886e-05, "gradient_norm": 0.23141907155513763, "tokens_per_second": 1137304.1424441123, "synthetic": false, "world_size": 8} {"step": 54720, "tokens": 14344519680, "loss": 2.3597536087036133, "optimizer_updates": 28360, "effective_batch": 512, "lr": 5.344847323730833e-05, "gradient_norm": 0.30938446521759033, "tokens_per_second": 1138467.5927653008, "synthetic": false, "world_size": 8} {"step": 54740, "tokens": 14349762560, "loss": 2.3536659240722657, "optimizer_updates": 28370, "effective_batch": 512, "lr": 5.339064323041044e-05, "gradient_norm": 0.26572859287261963, "tokens_per_second": 1125565.9724666767, "synthetic": false, "world_size": 8} {"step": 54760, "tokens": 14355005440, "loss": 2.363373565673828, "optimizer_updates": 28380, "effective_batch": 512, "lr": 5.3332851870711785e-05, "gradient_norm": 0.3058827519416809, "tokens_per_second": 1143052.5099423497, "synthetic": false, "world_size": 8} {"step": 54780, "tokens": 14360248320, "loss": 2.353410339355469, "optimizer_updates": 28390, "effective_batch": 512, "lr": 5.32750991976665e-05, "gradient_norm": 0.2832528054714203, "tokens_per_second": 1132157.8391329492, "synthetic": false, "world_size": 8} {"step": 54800, "tokens": 14365491200, "loss": 2.3638996124267577, "optimizer_updates": 28400, "effective_batch": 512, "lr": 5.321738525070233e-05, "gradient_norm": 0.26091912388801575, "tokens_per_second": 1137035.0545235102, "synthetic": false, "world_size": 8} {"step": 54820, "tokens": 14370734080, "loss": 2.36047248840332, "optimizer_updates": 28410, "effective_batch": 512, "lr": 5.315971006922054e-05, "gradient_norm": 0.2651468515396118, "tokens_per_second": 1134392.362010744, "synthetic": false, "world_size": 8} {"step": 54840, "tokens": 14375976960, "loss": 2.37001895904541, "optimizer_updates": 28420, "effective_batch": 512, "lr": 5.3102073692596005e-05, "gradient_norm": 0.25790587067604065, "tokens_per_second": 1128872.8150188907, "synthetic": false, "world_size": 8} {"step": 54860, "tokens": 14381219840, "loss": 2.359476089477539, "optimizer_updates": 28430, "effective_batch": 512, "lr": 5.3044476160177086e-05, "gradient_norm": 0.25542736053466797, "tokens_per_second": 1134366.1589986656, "synthetic": false, "world_size": 8} {"step": 54880, "tokens": 14386462720, "loss": 2.369068145751953, "optimizer_updates": 28440, "effective_batch": 512, "lr": 5.2986917511285586e-05, "gradient_norm": 0.2674374580383301, "tokens_per_second": 1130630.9786373551, "synthetic": false, "world_size": 8} {"step": 54900, "tokens": 14391705600, "loss": 2.3656763076782226, "optimizer_updates": 28450, "effective_batch": 512, "lr": 5.29293977852168e-05, "gradient_norm": 0.252584308385849, "tokens_per_second": 1143397.6930578898, "synthetic": false, "world_size": 8} {"step": 54920, "tokens": 14396948480, "loss": 2.3542417526245116, "optimizer_updates": 28460, "effective_batch": 512, "lr": 5.287191702123941e-05, "gradient_norm": 0.31098130345344543, "tokens_per_second": 1124628.8124466399, "synthetic": false, "world_size": 8} {"step": 54940, "tokens": 14402191360, "loss": 2.3669979095458986, "optimizer_updates": 28470, "effective_batch": 512, "lr": 5.281447525859555e-05, "gradient_norm": 0.2578321397304535, "tokens_per_second": 1140240.1489053234, "synthetic": false, "world_size": 8} {"step": 54960, "tokens": 14407434240, "loss": 2.3640039443969725, "optimizer_updates": 28480, "effective_batch": 512, "lr": 5.2757072536500674e-05, "gradient_norm": 0.23664553463459015, "tokens_per_second": 1143213.2324781113, "synthetic": false, "world_size": 8} {"step": 54980, "tokens": 14412677120, "loss": 2.3728851318359374, "optimizer_updates": 28490, "effective_batch": 512, "lr": 5.269970889414368e-05, "gradient_norm": 0.23584124445915222, "tokens_per_second": 1133674.6532261383, "synthetic": false, "world_size": 8} {"step": 55000, "tokens": 14417920000, "loss": 2.35318660736084, "optimizer_updates": 28500, "effective_batch": 512, "lr": 5.264238437068662e-05, "gradient_norm": 0.27872347831726074, "tokens_per_second": 1143629.7520492582, "synthetic": false, "world_size": 8} {"step": 55020, "tokens": 14423162880, "loss": 2.3630550384521483, "optimizer_updates": 28510, "effective_batch": 512, "lr": 5.258509900526502e-05, "gradient_norm": 0.28602853417396545, "tokens_per_second": 832362.3171254178, "synthetic": false, "world_size": 8} {"step": 55040, "tokens": 14428405760, "loss": 2.362043571472168, "optimizer_updates": 28520, "effective_batch": 512, "lr": 5.2527852836987534e-05, "gradient_norm": 0.24436599016189575, "tokens_per_second": 1137568.5133083554, "synthetic": false, "world_size": 8} {"step": 55060, "tokens": 14433648640, "loss": 2.350081443786621, "optimizer_updates": 28530, "effective_batch": 512, "lr": 5.247064590493616e-05, "gradient_norm": 0.2871525287628174, "tokens_per_second": 1136950.260833157, "synthetic": false, "world_size": 8} {"step": 55080, "tokens": 14438891520, "loss": 2.365306282043457, "optimizer_updates": 28540, "effective_batch": 512, "lr": 5.2413478248166046e-05, "gradient_norm": 0.2928425967693329, "tokens_per_second": 1141208.5381662173, "synthetic": false, "world_size": 8} {"step": 55100, "tokens": 14444134400, "loss": 2.355788993835449, "optimizer_updates": 28550, "effective_batch": 512, "lr": 5.235634990570552e-05, "gradient_norm": 0.28159382939338684, "tokens_per_second": 1133417.324306425, "synthetic": false, "world_size": 8} {"step": 55120, "tokens": 14449377280, "loss": 2.3636940002441404, "optimizer_updates": 28560, "effective_batch": 512, "lr": 5.22992609165561e-05, "gradient_norm": 0.25739550590515137, "tokens_per_second": 1141308.6675420045, "synthetic": false, "world_size": 8} {"step": 55140, "tokens": 14454620160, "loss": 2.354344940185547, "optimizer_updates": 28570, "effective_batch": 512, "lr": 5.2242211319692436e-05, "gradient_norm": 0.26180461049079895, "tokens_per_second": 1135055.6139149116, "synthetic": false, "world_size": 8} {"step": 55160, "tokens": 14459863040, "loss": 2.3548828125, "optimizer_updates": 28580, "effective_batch": 512, "lr": 5.218520115406227e-05, "gradient_norm": 0.230811208486557, "tokens_per_second": 1133690.4534186365, "synthetic": false, "world_size": 8} {"step": 55180, "tokens": 14465105920, "loss": 2.3573892593383787, "optimizer_updates": 28590, "effective_batch": 512, "lr": 5.212823045858646e-05, "gradient_norm": 0.24282097816467285, "tokens_per_second": 1135108.4883881295, "synthetic": false, "world_size": 8} {"step": 55200, "tokens": 14470348800, "loss": 2.3693212509155273, "optimizer_updates": 28600, "effective_batch": 512, "lr": 5.207129927215886e-05, "gradient_norm": 0.2938959300518036, "tokens_per_second": 1127876.4385965199, "synthetic": false, "world_size": 8} {"step": 55220, "tokens": 14475591680, "loss": 2.3684366226196287, "optimizer_updates": 28610, "effective_batch": 512, "lr": 5.201440763364642e-05, "gradient_norm": 0.25164681673049927, "tokens_per_second": 1129767.9093896826, "synthetic": false, "world_size": 8} {"step": 55240, "tokens": 14480834560, "loss": 2.3540855407714845, "optimizer_updates": 28620, "effective_batch": 512, "lr": 5.1957555581889e-05, "gradient_norm": 0.28406864404678345, "tokens_per_second": 1132159.2864754503, "synthetic": false, "world_size": 8} {"step": 55260, "tokens": 14486077440, "loss": 2.3590145111083984, "optimizer_updates": 28630, "effective_batch": 512, "lr": 5.190074315569951e-05, "gradient_norm": 0.26662972569465637, "tokens_per_second": 1128006.0435302956, "synthetic": false, "world_size": 8} {"step": 55280, "tokens": 14491320320, "loss": 2.347903251647949, "optimizer_updates": 28640, "effective_batch": 512, "lr": 5.184397039386383e-05, "gradient_norm": 0.3154822885990143, "tokens_per_second": 1017026.0146504564, "synthetic": false, "world_size": 8} {"step": 55300, "tokens": 14496563200, "loss": 2.3658103942871094, "optimizer_updates": 28650, "effective_batch": 512, "lr": 5.1787237335140646e-05, "gradient_norm": 0.2758747339248657, "tokens_per_second": 1138247.7345389081, "synthetic": false, "world_size": 8} {"step": 55320, "tokens": 14501806080, "loss": 2.364775276184082, "optimizer_updates": 28660, "effective_batch": 512, "lr": 5.1730544018261653e-05, "gradient_norm": 0.26495447754859924, "tokens_per_second": 1121778.3488441417, "synthetic": false, "world_size": 8} {"step": 55340, "tokens": 14507048960, "loss": 2.3592729568481445, "optimizer_updates": 28670, "effective_batch": 512, "lr": 5.167389048193135e-05, "gradient_norm": 0.2656918466091156, "tokens_per_second": 1136585.7324206803, "synthetic": false, "world_size": 8} {"step": 55360, "tokens": 14512291840, "loss": 2.365152931213379, "optimizer_updates": 28680, "effective_batch": 512, "lr": 5.1617276764827125e-05, "gradient_norm": 0.25832119584083557, "tokens_per_second": 1128242.4703374216, "synthetic": false, "world_size": 8} {"step": 55380, "tokens": 14517534720, "loss": 2.3641380310058593, "optimizer_updates": 28690, "effective_batch": 512, "lr": 5.15607029055991e-05, "gradient_norm": 0.24464131891727448, "tokens_per_second": 1135432.6099800325, "synthetic": false, "world_size": 8} {"step": 55400, "tokens": 14522777600, "loss": 2.364028549194336, "optimizer_updates": 28700, "effective_batch": 512, "lr": 5.1504168942870314e-05, "gradient_norm": 0.26230308413505554, "tokens_per_second": 1131186.4114887787, "synthetic": false, "world_size": 8} {"step": 55420, "tokens": 14528020480, "loss": 2.359822082519531, "optimizer_updates": 28710, "effective_batch": 512, "lr": 5.144767491523645e-05, "gradient_norm": 0.2676548957824707, "tokens_per_second": 1126835.7395860327, "synthetic": false, "world_size": 8} {"step": 55440, "tokens": 14533263360, "loss": 2.359245491027832, "optimizer_updates": 28720, "effective_batch": 512, "lr": 5.139122086126596e-05, "gradient_norm": 0.24347567558288574, "tokens_per_second": 1137594.7267467764, "synthetic": false, "world_size": 8} {"step": 55460, "tokens": 14538506240, "loss": 2.359548568725586, "optimizer_updates": 28730, "effective_batch": 512, "lr": 5.1334806819500024e-05, "gradient_norm": 0.25168541073799133, "tokens_per_second": 1138886.084491101, "synthetic": false, "world_size": 8} {"step": 55480, "tokens": 14543749120, "loss": 2.3553165435791015, "optimizer_updates": 28740, "effective_batch": 512, "lr": 5.127843282845253e-05, "gradient_norm": 0.31473308801651, "tokens_per_second": 1139676.5459192053, "synthetic": false, "world_size": 8} {"step": 55500, "tokens": 14548992000, "loss": 2.356387901306152, "optimizer_updates": 28750, "effective_batch": 512, "lr": 5.122209892660994e-05, "gradient_norm": 0.26012474298477173, "tokens_per_second": 793745.6653079847, "synthetic": false, "world_size": 8} {"step": 55520, "tokens": 14554234880, "loss": 2.362557220458984, "optimizer_updates": 28760, "effective_batch": 512, "lr": 5.1165805152431464e-05, "gradient_norm": 0.2961657643318176, "tokens_per_second": 1136614.6194455791, "synthetic": false, "world_size": 8} {"step": 55540, "tokens": 14559477760, "loss": 2.359246253967285, "optimizer_updates": 28770, "effective_batch": 512, "lr": 5.1109551544348795e-05, "gradient_norm": 0.26175081729888916, "tokens_per_second": 1130580.2243762347, "synthetic": false, "world_size": 8} {"step": 55560, "tokens": 14564720640, "loss": 2.3557754516601563, "optimizer_updates": 28780, "effective_batch": 512, "lr": 5.1053338140766324e-05, "gradient_norm": 0.28466060757637024, "tokens_per_second": 1138094.247754393, "synthetic": false, "world_size": 8} {"step": 55580, "tokens": 14569963520, "loss": 2.3637725830078127, "optimizer_updates": 28790, "effective_batch": 512, "lr": 5.099716498006086e-05, "gradient_norm": 0.30606377124786377, "tokens_per_second": 1131547.8449109218, "synthetic": false, "world_size": 8} {"step": 55600, "tokens": 14575206400, "loss": 2.3678207397460938, "optimizer_updates": 28800, "effective_batch": 512, "lr": 5.0941032100581876e-05, "gradient_norm": 0.23764172196388245, "tokens_per_second": 1011969.1714977892, "synthetic": false, "world_size": 8} {"step": 55620, "tokens": 14580449280, "loss": 2.372633361816406, "optimizer_updates": 28810, "effective_batch": 512, "lr": 5.0884939540651235e-05, "gradient_norm": 0.3178876042366028, "tokens_per_second": 1131780.8112043731, "synthetic": false, "world_size": 8} {"step": 55640, "tokens": 14585692160, "loss": 2.3514490127563477, "optimizer_updates": 28820, "effective_batch": 512, "lr": 5.082888733856337e-05, "gradient_norm": 0.23851177096366882, "tokens_per_second": 1139240.7559877196, "synthetic": false, "world_size": 8} {"step": 55660, "tokens": 14590935040, "loss": 2.360126495361328, "optimizer_updates": 28830, "effective_batch": 512, "lr": 5.077287553258504e-05, "gradient_norm": 0.243158221244812, "tokens_per_second": 1140599.4187501578, "synthetic": false, "world_size": 8} {"step": 55680, "tokens": 14596177920, "loss": 2.368157386779785, "optimizer_updates": 28840, "effective_batch": 512, "lr": 5.071690416095553e-05, "gradient_norm": 0.27441710233688354, "tokens_per_second": 1140145.514113767, "synthetic": false, "world_size": 8} {"step": 55700, "tokens": 14601420800, "loss": 2.346257781982422, "optimizer_updates": 28850, "effective_batch": 512, "lr": 5.0660973261886535e-05, "gradient_norm": 0.2373342365026474, "tokens_per_second": 1131478.9423095097, "synthetic": false, "world_size": 8} {"step": 55720, "tokens": 14606663680, "loss": 2.368015480041504, "optimizer_updates": 28860, "effective_batch": 512, "lr": 5.0605082873562024e-05, "gradient_norm": 0.2561250627040863, "tokens_per_second": 1130166.1292324793, "synthetic": false, "world_size": 8} {"step": 55740, "tokens": 14611906560, "loss": 2.3558591842651366, "optimizer_updates": 28870, "effective_batch": 512, "lr": 5.0549233034138366e-05, "gradient_norm": 0.2827037274837494, "tokens_per_second": 1132386.6968132332, "synthetic": false, "world_size": 8} {"step": 55760, "tokens": 14617149440, "loss": 2.362300682067871, "optimizer_updates": 28880, "effective_batch": 512, "lr": 5.04934237817442e-05, "gradient_norm": 0.26089221239089966, "tokens_per_second": 1137733.3602522854, "synthetic": false, "world_size": 8} {"step": 55780, "tokens": 14622392320, "loss": 2.351649856567383, "optimizer_updates": 28890, "effective_batch": 512, "lr": 5.0437655154480544e-05, "gradient_norm": 0.24862027168273926, "tokens_per_second": 1138409.0629003793, "synthetic": false, "world_size": 8} {"step": 55800, "tokens": 14627635200, "loss": 2.349679183959961, "optimizer_updates": 28900, "effective_batch": 512, "lr": 5.0381927190420596e-05, "gradient_norm": 0.2851294279098511, "tokens_per_second": 1032396.4165420074, "synthetic": false, "world_size": 8} {"step": 55820, "tokens": 14632878080, "loss": 2.348542594909668, "optimizer_updates": 28910, "effective_batch": 512, "lr": 5.0326239927609876e-05, "gradient_norm": 0.24417662620544434, "tokens_per_second": 1133641.8831608193, "synthetic": false, "world_size": 8} {"step": 55840, "tokens": 14638120960, "loss": 2.36461181640625, "optimizer_updates": 28920, "effective_batch": 512, "lr": 5.0270593404066016e-05, "gradient_norm": 0.23767201602458954, "tokens_per_second": 1129745.0441197474, "synthetic": false, "world_size": 8} {"step": 55860, "tokens": 14643363840, "loss": 2.3604913711547852, "optimizer_updates": 28930, "effective_batch": 512, "lr": 5.021498765777893e-05, "gradient_norm": 0.2929522693157196, "tokens_per_second": 1125542.2166733583, "synthetic": false, "world_size": 8} {"step": 55880, "tokens": 14648606720, "loss": 2.3510128021240235, "optimizer_updates": 28940, "effective_batch": 512, "lr": 5.0159422726710616e-05, "gradient_norm": 0.23623734712600708, "tokens_per_second": 1135487.4648289012, "synthetic": false, "world_size": 8} {"step": 55900, "tokens": 14653849600, "loss": 2.36635799407959, "optimizer_updates": 28950, "effective_batch": 512, "lr": 5.010389864879529e-05, "gradient_norm": 0.2927832007408142, "tokens_per_second": 889901.9204336862, "synthetic": false, "world_size": 8} {"step": 55920, "tokens": 14659092480, "loss": 2.3474538803100584, "optimizer_updates": 28960, "effective_batch": 512, "lr": 5.0048415461939184e-05, "gradient_norm": 0.2607998251914978, "tokens_per_second": 1039272.0920317387, "synthetic": false, "world_size": 8} {"step": 55940, "tokens": 14664335360, "loss": 2.360513114929199, "optimizer_updates": 28970, "effective_batch": 512, "lr": 4.9992973204020706e-05, "gradient_norm": 0.23304390907287598, "tokens_per_second": 1128061.9644198008, "synthetic": false, "world_size": 8} {"step": 55960, "tokens": 14669578240, "loss": 2.360030937194824, "optimizer_updates": 28980, "effective_batch": 512, "lr": 4.993757191289022e-05, "gradient_norm": 0.25655925273895264, "tokens_per_second": 1130492.144977215, "synthetic": false, "world_size": 8} {"step": 55980, "tokens": 14674821120, "loss": 2.355941581726074, "optimizer_updates": 28990, "effective_batch": 512, "lr": 4.988221162637025e-05, "gradient_norm": 0.2830171287059784, "tokens_per_second": 1133010.9778408778, "synthetic": false, "world_size": 8} {"step": 56000, "tokens": 14680064000, "loss": 2.350693130493164, "optimizer_updates": 29000, "effective_batch": 512, "lr": 4.9826892382255175e-05, "gradient_norm": 0.23978574573993683, "tokens_per_second": 1135269.082431996, "synthetic": false, "world_size": 8} {"step": 56020, "tokens": 14685306880, "loss": 2.3581605911254884, "optimizer_updates": 29010, "effective_batch": 512, "lr": 4.977161421831153e-05, "gradient_norm": 0.2502344846725464, "tokens_per_second": 829417.6865450995, "synthetic": false, "world_size": 8} {"step": 56040, "tokens": 14690549760, "loss": 2.3660423278808596, "optimizer_updates": 29020, "effective_batch": 512, "lr": 4.971637717227763e-05, "gradient_norm": 0.25030389428138733, "tokens_per_second": 1134031.763980153, "synthetic": false, "world_size": 8} {"step": 56060, "tokens": 14695792640, "loss": 2.3567621231079103, "optimizer_updates": 29030, "effective_batch": 512, "lr": 4.966118128186384e-05, "gradient_norm": 0.29981571435928345, "tokens_per_second": 1131633.4008544793, "synthetic": false, "world_size": 8} {"step": 56080, "tokens": 14701035520, "loss": 2.352456474304199, "optimizer_updates": 29040, "effective_batch": 512, "lr": 4.960602658475234e-05, "gradient_norm": 0.23644086718559265, "tokens_per_second": 1135791.7418959818, "synthetic": false, "world_size": 8} {"step": 56100, "tokens": 14706278400, "loss": 2.351345252990723, "optimizer_updates": 29050, "effective_batch": 512, "lr": 4.95509131185973e-05, "gradient_norm": 0.24044227600097656, "tokens_per_second": 1134065.881960399, "synthetic": false, "world_size": 8} {"step": 56120, "tokens": 14711521280, "loss": 2.3605499267578125, "optimizer_updates": 29060, "effective_batch": 512, "lr": 4.94958409210246e-05, "gradient_norm": 0.2727991044521332, "tokens_per_second": 1131935.2006288506, "synthetic": false, "world_size": 8} {"step": 56140, "tokens": 14716764160, "loss": 2.353200912475586, "optimizer_updates": 29070, "effective_batch": 512, "lr": 4.9440810029632055e-05, "gradient_norm": 0.2659575045108795, "tokens_per_second": 1136230.1125500284, "synthetic": false, "world_size": 8} {"step": 56160, "tokens": 14722007040, "loss": 2.3657941818237305, "optimizer_updates": 29080, "effective_batch": 512, "lr": 4.938582048198929e-05, "gradient_norm": 0.22350917756557465, "tokens_per_second": 1129938.8580648508, "synthetic": false, "world_size": 8} {"step": 56180, "tokens": 14727249920, "loss": 2.362096405029297, "optimizer_updates": 29090, "effective_batch": 512, "lr": 4.933087231563759e-05, "gradient_norm": 0.2579445242881775, "tokens_per_second": 1137106.369300118, "synthetic": false, "world_size": 8} {"step": 56200, "tokens": 14732492800, "loss": 2.3586200714111327, "optimizer_updates": 29100, "effective_batch": 512, "lr": 4.9275965568090115e-05, "gradient_norm": 0.29051902890205383, "tokens_per_second": 1136092.074513436, "synthetic": false, "world_size": 8} {"step": 56220, "tokens": 14737735680, "loss": 2.3601444244384764, "optimizer_updates": 29110, "effective_batch": 512, "lr": 4.922110027683165e-05, "gradient_norm": 0.24529558420181274, "tokens_per_second": 1132335.9924089797, "synthetic": false, "world_size": 8} {"step": 56240, "tokens": 14742978560, "loss": 2.361052894592285, "optimizer_updates": 29120, "effective_batch": 512, "lr": 4.916627647931876e-05, "gradient_norm": 0.24544191360473633, "tokens_per_second": 1129364.7867995796, "synthetic": false, "world_size": 8} {"step": 56260, "tokens": 14748221440, "loss": 2.3624420166015625, "optimizer_updates": 29130, "effective_batch": 512, "lr": 4.91114942129796e-05, "gradient_norm": 0.24891094863414764, "tokens_per_second": 1121530.3714949314, "synthetic": false, "world_size": 8} {"step": 56280, "tokens": 14753464320, "loss": 2.3536703109741213, "optimizer_updates": 29140, "effective_batch": 512, "lr": 4.9056753515214064e-05, "gradient_norm": 0.2490968406200409, "tokens_per_second": 1124421.2214513363, "synthetic": false, "world_size": 8} {"step": 56300, "tokens": 14758707200, "loss": 2.353235626220703, "optimizer_updates": 29150, "effective_batch": 512, "lr": 4.9002054423393556e-05, "gradient_norm": 0.23327988386154175, "tokens_per_second": 1131442.3307869222, "synthetic": false, "world_size": 8} {"step": 56320, "tokens": 14763950080, "loss": 2.359246253967285, "optimizer_updates": 29160, "effective_batch": 512, "lr": 4.894739697486122e-05, "gradient_norm": 0.28718119859695435, "tokens_per_second": 1132286.5438431816, "synthetic": false, "world_size": 8} {"step": 56340, "tokens": 14769192960, "loss": 2.361838722229004, "optimizer_updates": 29170, "effective_batch": 512, "lr": 4.889278120693163e-05, "gradient_norm": 0.2870332896709442, "tokens_per_second": 1131198.000872725, "synthetic": false, "world_size": 8} {"step": 56360, "tokens": 14774435840, "loss": 2.351374626159668, "optimizer_updates": 29180, "effective_batch": 512, "lr": 4.8838207156890975e-05, "gradient_norm": 0.29718953371047974, "tokens_per_second": 1128154.820109214, "synthetic": false, "world_size": 8} {"step": 56380, "tokens": 14779678720, "loss": 2.360847282409668, "optimizer_updates": 29190, "effective_batch": 512, "lr": 4.8783674861996923e-05, "gradient_norm": 0.24231329560279846, "tokens_per_second": 1016869.5313215196, "synthetic": false, "world_size": 8} {"step": 56400, "tokens": 14784921600, "loss": 2.3600910186767576, "optimizer_updates": 29200, "effective_batch": 512, "lr": 4.872918435947872e-05, "gradient_norm": 0.2964850664138794, "tokens_per_second": 746119.8834385723, "synthetic": false, "world_size": 8} {"step": 56420, "tokens": 14790164480, "loss": 2.364929962158203, "optimizer_updates": 29210, "effective_batch": 512, "lr": 4.867473568653696e-05, "gradient_norm": 0.24343450367450714, "tokens_per_second": 1137981.5441510982, "synthetic": false, "world_size": 8} {"step": 56440, "tokens": 14795407360, "loss": 2.363861846923828, "optimizer_updates": 29220, "effective_batch": 512, "lr": 4.862032888034382e-05, "gradient_norm": 0.24135635793209076, "tokens_per_second": 1140763.1983976206, "synthetic": false, "world_size": 8} {"step": 56460, "tokens": 14800650240, "loss": 2.3620584487915037, "optimizer_updates": 29230, "effective_batch": 512, "lr": 4.856596397804273e-05, "gradient_norm": 0.27044710516929626, "tokens_per_second": 1134426.5009493919, "synthetic": false, "world_size": 8} {"step": 56480, "tokens": 14805893120, "loss": 2.368246078491211, "optimizer_updates": 29240, "effective_batch": 512, "lr": 4.8511641016748684e-05, "gradient_norm": 0.2608034908771515, "tokens_per_second": 1137399.5094864846, "synthetic": false, "world_size": 8} {"step": 56500, "tokens": 14811136000, "loss": 2.3493989944458007, "optimizer_updates": 29250, "effective_batch": 512, "lr": 4.84573600335479e-05, "gradient_norm": 0.2931381165981293, "tokens_per_second": 781690.1934969588, "synthetic": false, "world_size": 8} {"step": 56520, "tokens": 14816378880, "loss": 2.367008018493652, "optimizer_updates": 29260, "effective_batch": 512, "lr": 4.840312106549803e-05, "gradient_norm": 0.24209162592887878, "tokens_per_second": 1140945.3386685406, "synthetic": false, "world_size": 8} {"step": 56540, "tokens": 14821621760, "loss": 2.358656311035156, "optimizer_updates": 29270, "effective_batch": 512, "lr": 4.834892414962798e-05, "gradient_norm": 0.2848983407020569, "tokens_per_second": 1132988.3946334524, "synthetic": false, "world_size": 8} {"step": 56560, "tokens": 14826864640, "loss": 2.3538185119628907, "optimizer_updates": 29280, "effective_batch": 512, "lr": 4.8294769322937985e-05, "gradient_norm": 0.2718680799007416, "tokens_per_second": 1131235.812088521, "synthetic": false, "world_size": 8} {"step": 56580, "tokens": 14832107520, "loss": 2.348151969909668, "optimizer_updates": 29290, "effective_batch": 512, "lr": 4.8240656622399586e-05, "gradient_norm": 0.2471236139535904, "tokens_per_second": 1140552.3374460128, "synthetic": false, "world_size": 8} {"step": 56600, "tokens": 14837350400, "loss": 2.364328956604004, "optimizer_updates": 29300, "effective_batch": 512, "lr": 4.8186586084955445e-05, "gradient_norm": 0.2611786127090454, "tokens_per_second": 1138058.5870679724, "synthetic": false, "world_size": 8} {"step": 56620, "tokens": 14842593280, "loss": 2.34790153503418, "optimizer_updates": 29310, "effective_batch": 512, "lr": 4.813255774751957e-05, "gradient_norm": 0.24682924151420593, "tokens_per_second": 1124043.61089454, "synthetic": false, "world_size": 8} {"step": 56640, "tokens": 14847836160, "loss": 2.358944320678711, "optimizer_updates": 29320, "effective_batch": 512, "lr": 4.807857164697703e-05, "gradient_norm": 0.2333131730556488, "tokens_per_second": 1132274.2237677204, "synthetic": false, "world_size": 8} {"step": 56660, "tokens": 14853079040, "loss": 2.357436943054199, "optimizer_updates": 29330, "effective_batch": 512, "lr": 4.80246278201842e-05, "gradient_norm": 0.2834828495979309, "tokens_per_second": 1135934.38849837, "synthetic": false, "world_size": 8} {"step": 56680, "tokens": 14858321920, "loss": 2.364695167541504, "optimizer_updates": 29340, "effective_batch": 512, "lr": 4.7970726303968496e-05, "gradient_norm": 0.2478553205728531, "tokens_per_second": 1129100.3550942955, "synthetic": false, "world_size": 8} {"step": 56700, "tokens": 14863564800, "loss": 2.3615787506103514, "optimizer_updates": 29350, "effective_batch": 512, "lr": 4.791686713512845e-05, "gradient_norm": 0.2709966003894806, "tokens_per_second": 1136072.3024994754, "synthetic": false, "world_size": 8} {"step": 56720, "tokens": 14868807680, "loss": 2.3586992263793944, "optimizer_updates": 29360, "effective_batch": 512, "lr": 4.7863050350433714e-05, "gradient_norm": 0.30244407057762146, "tokens_per_second": 1130977.923441903, "synthetic": false, "world_size": 8} {"step": 56740, "tokens": 14874050560, "loss": 2.3572917938232423, "optimizer_updates": 29370, "effective_batch": 512, "lr": 4.7809275986625036e-05, "gradient_norm": 0.25046542286872864, "tokens_per_second": 1135930.068476683, "synthetic": false, "world_size": 8} {"step": 56760, "tokens": 14879293440, "loss": 2.37799072265625, "optimizer_updates": 29380, "effective_batch": 512, "lr": 4.775554408041411e-05, "gradient_norm": 0.2907642722129822, "tokens_per_second": 1134114.1065715817, "synthetic": false, "world_size": 8} {"step": 56780, "tokens": 14884536320, "loss": 2.3578027725219726, "optimizer_updates": 29390, "effective_batch": 512, "lr": 4.7701854668483754e-05, "gradient_norm": 0.2924920618534088, "tokens_per_second": 1129891.9835744982, "synthetic": false, "world_size": 8} {"step": 56800, "tokens": 14889779200, "loss": 2.3566959381103514, "optimizer_updates": 29400, "effective_batch": 512, "lr": 4.7648207787487684e-05, "gradient_norm": 0.2587924599647522, "tokens_per_second": 1139670.3869389694, "synthetic": false, "world_size": 8} {"step": 56820, "tokens": 14895022080, "loss": 2.3608524322509767, "optimizer_updates": 29410, "effective_batch": 512, "lr": 4.759460347405066e-05, "gradient_norm": 0.26711928844451904, "tokens_per_second": 1135013.3271794752, "synthetic": false, "world_size": 8} {"step": 56840, "tokens": 14900264960, "loss": 2.3649587631225586, "optimizer_updates": 29420, "effective_batch": 512, "lr": 4.754104176476826e-05, "gradient_norm": 0.23114575445652008, "tokens_per_second": 1123292.1226515623, "synthetic": false, "world_size": 8} {"step": 56860, "tokens": 14905507840, "loss": 2.3703639984130858, "optimizer_updates": 29430, "effective_batch": 512, "lr": 4.7487522696207146e-05, "gradient_norm": 0.2537490129470825, "tokens_per_second": 1129065.3917211047, "synthetic": false, "world_size": 8} {"step": 56880, "tokens": 14910750720, "loss": 2.3594482421875, "optimizer_updates": 29440, "effective_batch": 512, "lr": 4.7434046304904715e-05, "gradient_norm": 0.24503718316555023, "tokens_per_second": 1136298.3328775922, "synthetic": false, "world_size": 8} {"step": 56900, "tokens": 14915993600, "loss": 2.3583898544311523, "optimizer_updates": 29450, "effective_batch": 512, "lr": 4.7380612627369336e-05, "gradient_norm": 0.24063877761363983, "tokens_per_second": 1120801.6784767203, "synthetic": false, "world_size": 8} {"step": 56920, "tokens": 14921236480, "loss": 2.363845443725586, "optimizer_updates": 29460, "effective_batch": 512, "lr": 4.732722170008012e-05, "gradient_norm": 0.230668306350708, "tokens_per_second": 1119804.796346375, "synthetic": false, "world_size": 8} {"step": 56940, "tokens": 14926479360, "loss": 2.3687566757202148, "optimizer_updates": 29470, "effective_batch": 512, "lr": 4.7273873559487096e-05, "gradient_norm": 0.3330930471420288, "tokens_per_second": 1141115.47465371, "synthetic": false, "world_size": 8} {"step": 56960, "tokens": 14931722240, "loss": 2.356024742126465, "optimizer_updates": 29480, "effective_batch": 512, "lr": 4.7220568242010986e-05, "gradient_norm": 0.2600935399532318, "tokens_per_second": 1139452.7911881942, "synthetic": false, "world_size": 8} {"step": 56980, "tokens": 14936965120, "loss": 2.3540515899658203, "optimizer_updates": 29490, "effective_batch": 512, "lr": 4.716730578404338e-05, "gradient_norm": 0.2702617347240448, "tokens_per_second": 1130994.753819952, "synthetic": false, "world_size": 8} {"step": 57000, "tokens": 14942208000, "loss": 2.3684520721435547, "optimizer_updates": 29500, "effective_batch": 512, "lr": 4.7114086221946503e-05, "gradient_norm": 0.2730713486671448, "tokens_per_second": 1124795.7436210068, "synthetic": false, "world_size": 8} {"step": 57020, "tokens": 14947450880, "loss": 2.3568485260009764, "optimizer_updates": 29510, "effective_batch": 512, "lr": 4.706090959205334e-05, "gradient_norm": 0.280582070350647, "tokens_per_second": 828509.7537447179, "synthetic": false, "world_size": 8} {"step": 57040, "tokens": 14952693760, "loss": 2.36245059967041, "optimizer_updates": 29520, "effective_batch": 512, "lr": 4.70077759306676e-05, "gradient_norm": 0.24216967821121216, "tokens_per_second": 1138992.3348836554, "synthetic": false, "world_size": 8} {"step": 57060, "tokens": 14957936640, "loss": 2.3444923400878905, "optimizer_updates": 29530, "effective_batch": 512, "lr": 4.6954685274063594e-05, "gradient_norm": 0.28355279564857483, "tokens_per_second": 1131638.8804857298, "synthetic": false, "world_size": 8} {"step": 57080, "tokens": 14963179520, "loss": 2.3588493347167967, "optimizer_updates": 29540, "effective_batch": 512, "lr": 4.690163765848633e-05, "gradient_norm": 0.24237702786922455, "tokens_per_second": 1130754.2823269893, "synthetic": false, "world_size": 8} {"step": 57100, "tokens": 14968422400, "loss": 2.3621728897094725, "optimizer_updates": 29550, "effective_batch": 512, "lr": 4.684863312015139e-05, "gradient_norm": 0.24709177017211914, "tokens_per_second": 1124384.7030512204, "synthetic": false, "world_size": 8} {"step": 57120, "tokens": 14973665280, "loss": 2.361338996887207, "optimizer_updates": 29560, "effective_batch": 512, "lr": 4.679567169524498e-05, "gradient_norm": 0.2540088891983032, "tokens_per_second": 1137385.7751126187, "synthetic": false, "world_size": 8} {"step": 57140, "tokens": 14978908160, "loss": 2.3555120468139648, "optimizer_updates": 29570, "effective_batch": 512, "lr": 4.674275341992383e-05, "gradient_norm": 0.24932195246219635, "tokens_per_second": 1138494.1468031032, "synthetic": false, "world_size": 8} {"step": 57160, "tokens": 14984151040, "loss": 2.364124298095703, "optimizer_updates": 29580, "effective_batch": 512, "lr": 4.668987833031528e-05, "gradient_norm": 0.35211339592933655, "tokens_per_second": 1142202.3997006968, "synthetic": false, "world_size": 8} {"step": 57180, "tokens": 14989393920, "loss": 2.346749114990234, "optimizer_updates": 29590, "effective_batch": 512, "lr": 4.6637046462517096e-05, "gradient_norm": 0.2642241418361664, "tokens_per_second": 1125627.6529706414, "synthetic": false, "world_size": 8} {"step": 57200, "tokens": 14994636800, "loss": 2.358908462524414, "optimizer_updates": 29600, "effective_batch": 512, "lr": 4.6584257852597625e-05, "gradient_norm": 0.26029080152511597, "tokens_per_second": 1131173.6736235048, "synthetic": false, "world_size": 8} {"step": 57220, "tokens": 14999879680, "loss": 2.365721321105957, "optimizer_updates": 29610, "effective_batch": 512, "lr": 4.653151253659562e-05, "gradient_norm": 0.27149826288223267, "tokens_per_second": 1137412.0035415294, "synthetic": false, "world_size": 8} {"step": 57240, "tokens": 15005122560, "loss": 2.363651466369629, "optimizer_updates": 29620, "effective_batch": 512, "lr": 4.647881055052032e-05, "gradient_norm": 0.2548248767852783, "tokens_per_second": 1139066.7574053458, "synthetic": false, "world_size": 8} {"step": 57260, "tokens": 15010365440, "loss": 2.363214874267578, "optimizer_updates": 29630, "effective_batch": 512, "lr": 4.642615193035135e-05, "gradient_norm": 0.36001133918762207, "tokens_per_second": 1137752.3267365291, "synthetic": false, "world_size": 8} {"step": 57280, "tokens": 15015608320, "loss": 2.355790138244629, "optimizer_updates": 29640, "effective_batch": 512, "lr": 4.637353671203875e-05, "gradient_norm": 0.2672344148159027, "tokens_per_second": 1133838.331555041, "synthetic": false, "world_size": 8} {"step": 57300, "tokens": 15020851200, "loss": 2.345328140258789, "optimizer_updates": 29650, "effective_batch": 512, "lr": 4.632096493150292e-05, "gradient_norm": 0.23360319435596466, "tokens_per_second": 1145703.9744103518, "synthetic": false, "world_size": 8} {"step": 57320, "tokens": 15026094080, "loss": 2.353634071350098, "optimizer_updates": 29660, "effective_batch": 512, "lr": 4.6268436624634605e-05, "gradient_norm": 0.2745707929134369, "tokens_per_second": 1125865.1979947812, "synthetic": false, "world_size": 8} {"step": 57340, "tokens": 15031336960, "loss": 2.3606122970581054, "optimizer_updates": 29670, "effective_batch": 512, "lr": 4.6215951827294856e-05, "gradient_norm": 0.3033466339111328, "tokens_per_second": 1144101.6556529375, "synthetic": false, "world_size": 8} {"step": 57360, "tokens": 15036579840, "loss": 2.369151306152344, "optimizer_updates": 29680, "effective_batch": 512, "lr": 4.616351057531506e-05, "gradient_norm": 0.2790364921092987, "tokens_per_second": 1136005.3254846632, "synthetic": false, "world_size": 8} {"step": 57380, "tokens": 15041822720, "loss": 2.3515077590942384, "optimizer_updates": 29690, "effective_batch": 512, "lr": 4.611111290449681e-05, "gradient_norm": 0.24668331444263458, "tokens_per_second": 1132361.7218746226, "synthetic": false, "world_size": 8} {"step": 57400, "tokens": 15047065600, "loss": 2.351387786865234, "optimizer_updates": 29700, "effective_batch": 512, "lr": 4.605875885061206e-05, "gradient_norm": 0.30743902921676636, "tokens_per_second": 1131075.7238326515, "synthetic": false, "world_size": 8} {"step": 57420, "tokens": 15052308480, "loss": 2.36706485748291, "optimizer_updates": 29710, "effective_batch": 512, "lr": 4.600644844940284e-05, "gradient_norm": 0.265872061252594, "tokens_per_second": 1130754.390609281, "synthetic": false, "world_size": 8} {"step": 57440, "tokens": 15057551360, "loss": 2.362073516845703, "optimizer_updates": 29720, "effective_batch": 512, "lr": 4.595418173658149e-05, "gradient_norm": 0.24228034913539886, "tokens_per_second": 1118920.953351399, "synthetic": false, "world_size": 8} {"step": 57460, "tokens": 15062794240, "loss": 2.3502342224121096, "optimizer_updates": 29730, "effective_batch": 512, "lr": 4.590195874783051e-05, "gradient_norm": 0.23364487290382385, "tokens_per_second": 1015874.4248453791, "synthetic": false, "world_size": 8} {"step": 57480, "tokens": 15068037120, "loss": 2.353364181518555, "optimizer_updates": 29740, "effective_batch": 512, "lr": 4.584977951880247e-05, "gradient_norm": 0.2426266223192215, "tokens_per_second": 1133085.2485673323, "synthetic": false, "world_size": 8} {"step": 57500, "tokens": 15073280000, "loss": 2.35675163269043, "optimizer_updates": 29750, "effective_batch": 512, "lr": 4.579764408512018e-05, "gradient_norm": 0.2785261869430542, "tokens_per_second": 1117511.930765839, "synthetic": false, "world_size": 8} {"step": 57520, "tokens": 15078522880, "loss": 2.366472625732422, "optimizer_updates": 29760, "effective_batch": 512, "lr": 4.5745552482376434e-05, "gradient_norm": 0.2480844259262085, "tokens_per_second": 1134449.4957305188, "synthetic": false, "world_size": 8} {"step": 57540, "tokens": 15083765760, "loss": 2.362482261657715, "optimizer_updates": 29770, "effective_batch": 512, "lr": 4.569350474613422e-05, "gradient_norm": 0.23373179137706757, "tokens_per_second": 1125732.1566251738, "synthetic": false, "world_size": 8} {"step": 57560, "tokens": 15089008640, "loss": 2.3786479949951174, "optimizer_updates": 29780, "effective_batch": 512, "lr": 4.564150091192647e-05, "gradient_norm": 0.26503878831863403, "tokens_per_second": 1132751.8245614066, "synthetic": false, "world_size": 8} {"step": 57580, "tokens": 15094251520, "loss": 2.36373291015625, "optimizer_updates": 29790, "effective_batch": 512, "lr": 4.5589541015256236e-05, "gradient_norm": 0.29707029461860657, "tokens_per_second": 1133052.4454921589, "synthetic": false, "world_size": 8} {"step": 57600, "tokens": 15099494400, "loss": 2.354139518737793, "optimizer_updates": 29800, "effective_batch": 512, "lr": 4.553762509159652e-05, "gradient_norm": 0.24310041964054108, "tokens_per_second": 1132673.5080144573, "synthetic": false, "world_size": 8} {"step": 57620, "tokens": 15104737280, "loss": 2.356171417236328, "optimizer_updates": 29810, "effective_batch": 512, "lr": 4.548575317639027e-05, "gradient_norm": 0.31816941499710083, "tokens_per_second": 1139745.9468676145, "synthetic": false, "world_size": 8} {"step": 57640, "tokens": 15109980160, "loss": 2.3691335678100587, "optimizer_updates": 29820, "effective_batch": 512, "lr": 4.5433925305050494e-05, "gradient_norm": 0.27942606806755066, "tokens_per_second": 1125415.6000793544, "synthetic": false, "world_size": 8} {"step": 57660, "tokens": 15115223040, "loss": 2.366304397583008, "optimizer_updates": 29830, "effective_batch": 512, "lr": 4.538214151296006e-05, "gradient_norm": 0.2430938333272934, "tokens_per_second": 1127090.098686589, "synthetic": false, "world_size": 8} {"step": 57680, "tokens": 15120465920, "loss": 2.3569211959838867, "optimizer_updates": 29840, "effective_batch": 512, "lr": 4.5330401835471705e-05, "gradient_norm": 0.2473178654909134, "tokens_per_second": 1138670.5508591912, "synthetic": false, "world_size": 8} {"step": 57700, "tokens": 15125708800, "loss": 2.3491344451904297, "optimizer_updates": 29850, "effective_batch": 512, "lr": 4.5278706307908166e-05, "gradient_norm": 0.2606574296951294, "tokens_per_second": 1132838.9872199837, "synthetic": false, "world_size": 8} {"step": 57720, "tokens": 15130951680, "loss": 2.3505168914794923, "optimizer_updates": 29860, "effective_batch": 512, "lr": 4.5227054965561913e-05, "gradient_norm": 0.24221542477607727, "tokens_per_second": 1131318.7876529826, "synthetic": false, "world_size": 8} {"step": 57740, "tokens": 15136194560, "loss": 2.3615036010742188, "optimizer_updates": 29870, "effective_batch": 512, "lr": 4.517544784369537e-05, "gradient_norm": 0.24049139022827148, "tokens_per_second": 1032570.512929368, "synthetic": false, "world_size": 8} {"step": 57760, "tokens": 15141437440, "loss": 2.3614805221557615, "optimizer_updates": 29880, "effective_batch": 512, "lr": 4.512388497754065e-05, "gradient_norm": 0.2581147849559784, "tokens_per_second": 1127448.6721755257, "synthetic": false, "world_size": 8} {"step": 57780, "tokens": 15146680320, "loss": 2.3743959426879884, "optimizer_updates": 29890, "effective_batch": 512, "lr": 4.507236640229978e-05, "gradient_norm": 0.24389488995075226, "tokens_per_second": 1146564.6521638352, "synthetic": false, "world_size": 8} {"step": 57800, "tokens": 15151923200, "loss": 2.3712945938110352, "optimizer_updates": 29900, "effective_batch": 512, "lr": 4.502089215314442e-05, "gradient_norm": 0.2460719645023346, "tokens_per_second": 1136126.5066600745, "synthetic": false, "world_size": 8} {"step": 57820, "tokens": 15157166080, "loss": 2.359655570983887, "optimizer_updates": 29910, "effective_batch": 512, "lr": 4.496946226521608e-05, "gradient_norm": 0.23569729924201965, "tokens_per_second": 1133065.1324309944, "synthetic": false, "world_size": 8} {"step": 57840, "tokens": 15162408960, "loss": 2.3484014511108398, "optimizer_updates": 29920, "effective_batch": 512, "lr": 4.491807677362589e-05, "gradient_norm": 0.2791458070278168, "tokens_per_second": 1134513.7814064834, "synthetic": false, "world_size": 8} {"step": 57860, "tokens": 15167651840, "loss": 2.36942195892334, "optimizer_updates": 29930, "effective_batch": 512, "lr": 4.4866735713454745e-05, "gradient_norm": 0.2511703670024872, "tokens_per_second": 1133280.4666265626, "synthetic": false, "world_size": 8} {"step": 57880, "tokens": 15172894720, "loss": 2.3601892471313475, "optimizer_updates": 29940, "effective_batch": 512, "lr": 4.48154391197532e-05, "gradient_norm": 0.24997256696224213, "tokens_per_second": 1128807.6949487322, "synthetic": false, "world_size": 8} {"step": 57900, "tokens": 15178137600, "loss": 2.362845230102539, "optimizer_updates": 29950, "effective_batch": 512, "lr": 4.476418702754138e-05, "gradient_norm": 0.2944561839103699, "tokens_per_second": 1126208.3476887962, "synthetic": false, "world_size": 8} {"step": 57920, "tokens": 15183380480, "loss": 2.3721446990966797, "optimizer_updates": 29960, "effective_batch": 512, "lr": 4.471297947180915e-05, "gradient_norm": 0.27240875363349915, "tokens_per_second": 1135347.074844842, "synthetic": false, "world_size": 8} {"step": 57940, "tokens": 15188623360, "loss": 2.3593387603759766, "optimizer_updates": 29970, "effective_batch": 512, "lr": 4.466181648751585e-05, "gradient_norm": 0.31008148193359375, "tokens_per_second": 1127919.3002277364, "synthetic": false, "world_size": 8} {"step": 57960, "tokens": 15193866240, "loss": 2.361521339416504, "optimizer_updates": 29980, "effective_batch": 512, "lr": 4.461069810959045e-05, "gradient_norm": 0.2736259400844574, "tokens_per_second": 1129923.2786713217, "synthetic": false, "world_size": 8} {"step": 57980, "tokens": 15199109120, "loss": 2.3616317749023437, "optimizer_updates": 29990, "effective_batch": 512, "lr": 4.455962437293144e-05, "gradient_norm": 0.24189020693302155, "tokens_per_second": 1122002.8025877164, "synthetic": false, "world_size": 8} {"step": 58000, "tokens": 15204352000, "loss": 2.3607580184936525, "optimizer_updates": 30000, "effective_batch": 512, "lr": 4.45085953124069e-05, "gradient_norm": 0.2436816394329071, "tokens_per_second": 1124131.7579490056, "synthetic": false, "world_size": 8} {"step": 58020, "tokens": 15209594880, "loss": 2.370322036743164, "optimizer_updates": 30010, "effective_batch": 512, "lr": 4.44576109628543e-05, "gradient_norm": 0.27110525965690613, "tokens_per_second": 659246.9979304118, "synthetic": false, "world_size": 8} {"step": 58040, "tokens": 15214837760, "loss": 2.3524457931518556, "optimizer_updates": 30020, "effective_batch": 512, "lr": 4.440667135908072e-05, "gradient_norm": 0.24837714433670044, "tokens_per_second": 769301.8569263975, "synthetic": false, "world_size": 8} {"step": 58060, "tokens": 15220080640, "loss": 2.3590862274169924, "optimizer_updates": 30030, "effective_batch": 512, "lr": 4.435577653586255e-05, "gradient_norm": 0.2371438890695572, "tokens_per_second": 1133846.2897568247, "synthetic": false, "world_size": 8} {"step": 58080, "tokens": 15225323520, "loss": 2.362795829772949, "optimizer_updates": 30040, "effective_batch": 512, "lr": 4.430492652794574e-05, "gradient_norm": 0.29610466957092285, "tokens_per_second": 1139225.9876818266, "synthetic": false, "world_size": 8} {"step": 58100, "tokens": 15230566400, "loss": 2.3576242446899416, "optimizer_updates": 30050, "effective_batch": 512, "lr": 4.425412137004552e-05, "gradient_norm": 0.2645470201969147, "tokens_per_second": 1131375.3248087694, "synthetic": false, "world_size": 8} {"step": 58120, "tokens": 15235809280, "loss": 2.3563264846801757, "optimizer_updates": 30060, "effective_batch": 512, "lr": 4.420336109684662e-05, "gradient_norm": 0.27251890301704407, "tokens_per_second": 1135595.4159835572, "synthetic": false, "world_size": 8} {"step": 58140, "tokens": 15241052160, "loss": 2.3661434173583986, "optimizer_updates": 30070, "effective_batch": 512, "lr": 4.415264574300302e-05, "gradient_norm": 0.30885934829711914, "tokens_per_second": 1131146.2443969948, "synthetic": false, "world_size": 8} {"step": 58160, "tokens": 15246295040, "loss": 2.3622768402099608, "optimizer_updates": 30080, "effective_batch": 512, "lr": 4.410197534313814e-05, "gradient_norm": 0.260905921459198, "tokens_per_second": 1139557.2035280794, "synthetic": false, "world_size": 8} {"step": 58180, "tokens": 15251537920, "loss": 2.356283187866211, "optimizer_updates": 30090, "effective_batch": 512, "lr": 4.405134993184461e-05, "gradient_norm": 0.23292939364910126, "tokens_per_second": 1128830.5429461875, "synthetic": false, "world_size": 8} {"step": 58200, "tokens": 15256780800, "loss": 2.3535974502563475, "optimizer_updates": 30100, "effective_batch": 512, "lr": 4.4000769543684424e-05, "gradient_norm": 0.23985351622104645, "tokens_per_second": 1145528.168301273, "synthetic": false, "world_size": 8} {"step": 58220, "tokens": 15262023680, "loss": 2.34525089263916, "optimizer_updates": 30110, "effective_batch": 512, "lr": 4.3950234213188765e-05, "gradient_norm": 0.24195292592048645, "tokens_per_second": 1133854.8408126438, "synthetic": false, "world_size": 8} {"step": 58240, "tokens": 15267266560, "loss": 2.3599210739135743, "optimizer_updates": 30120, "effective_batch": 512, "lr": 4.3899743974858134e-05, "gradient_norm": 0.23848451673984528, "tokens_per_second": 1132178.8081013039, "synthetic": false, "world_size": 8} {"step": 58260, "tokens": 15272509440, "loss": 2.366777229309082, "optimizer_updates": 30130, "effective_batch": 512, "lr": 4.38492988631622e-05, "gradient_norm": 0.2788669764995575, "tokens_per_second": 1140130.189491957, "synthetic": false, "world_size": 8} {"step": 58280, "tokens": 15277752320, "loss": 2.345474052429199, "optimizer_updates": 30140, "effective_batch": 512, "lr": 4.3798898912539825e-05, "gradient_norm": 0.28635531663894653, "tokens_per_second": 824719.2118174585, "synthetic": false, "world_size": 8} {"step": 58300, "tokens": 15282995200, "loss": 2.3654247283935548, "optimizer_updates": 30150, "effective_batch": 512, "lr": 4.374854415739903e-05, "gradient_norm": 0.24500969052314758, "tokens_per_second": 1136750.1327217277, "synthetic": false, "world_size": 8} {"step": 58320, "tokens": 15288238080, "loss": 2.3547060012817385, "optimizer_updates": 30160, "effective_batch": 512, "lr": 4.3698234632117e-05, "gradient_norm": 0.2402828186750412, "tokens_per_second": 1130061.0837891714, "synthetic": false, "world_size": 8} {"step": 58340, "tokens": 15293480960, "loss": 2.347747802734375, "optimizer_updates": 30170, "effective_batch": 512, "lr": 4.3647970371040097e-05, "gradient_norm": 0.24537710845470428, "tokens_per_second": 1139212.5192916328, "synthetic": false, "world_size": 8} {"step": 58360, "tokens": 15298723840, "loss": 2.3620792388916017, "optimizer_updates": 30180, "effective_batch": 512, "lr": 4.359775140848365e-05, "gradient_norm": 0.2767079174518585, "tokens_per_second": 1141222.1789836558, "synthetic": false, "world_size": 8} {"step": 58380, "tokens": 15303966720, "loss": 2.3585590362548827, "optimizer_updates": 30190, "effective_batch": 512, "lr": 4.3547577778732195e-05, "gradient_norm": 0.2711070477962494, "tokens_per_second": 1132555.8116623827, "synthetic": false, "world_size": 8} {"step": 58400, "tokens": 15309209600, "loss": 2.3600536346435548, "optimizer_updates": 30200, "effective_batch": 512, "lr": 4.3497449516039226e-05, "gradient_norm": 0.2730827033519745, "tokens_per_second": 1129718.6432572564, "synthetic": false, "world_size": 8} {"step": 58420, "tokens": 15314452480, "loss": 2.341268539428711, "optimizer_updates": 30210, "effective_batch": 512, "lr": 4.344736665462732e-05, "gradient_norm": 0.26598623394966125, "tokens_per_second": 1117095.4424522617, "synthetic": false, "world_size": 8} {"step": 58440, "tokens": 15319695360, "loss": 2.377005386352539, "optimizer_updates": 30220, "effective_batch": 512, "lr": 4.339732922868802e-05, "gradient_norm": 0.29002630710601807, "tokens_per_second": 1138080.1168526823, "synthetic": false, "world_size": 8} {"step": 58460, "tokens": 15324938240, "loss": 2.3569793701171875, "optimizer_updates": 30230, "effective_batch": 512, "lr": 4.33473372723819e-05, "gradient_norm": 0.24701538681983948, "tokens_per_second": 1129580.470879833, "synthetic": false, "world_size": 8} {"step": 58480, "tokens": 15330181120, "loss": 2.3698896408081054, "optimizer_updates": 30240, "effective_batch": 512, "lr": 4.329739081983842e-05, "gradient_norm": 0.24651525914669037, "tokens_per_second": 1125592.7107834923, "synthetic": false, "world_size": 8} {"step": 58500, "tokens": 15335424000, "loss": 2.355482482910156, "optimizer_updates": 30250, "effective_batch": 512, "lr": 4.324748990515605e-05, "gradient_norm": 0.2401147037744522, "tokens_per_second": 1135136.4251815248, "synthetic": false, "world_size": 8} {"step": 58520, "tokens": 15340666880, "loss": 2.3630022048950194, "optimizer_updates": 30260, "effective_batch": 512, "lr": 4.319763456240211e-05, "gradient_norm": 0.2934493124485016, "tokens_per_second": 1136639.0238252913, "synthetic": false, "world_size": 8} {"step": 58540, "tokens": 15345909760, "loss": 2.3504755020141603, "optimizer_updates": 30270, "effective_batch": 512, "lr": 4.314782482561288e-05, "gradient_norm": 0.24213862419128418, "tokens_per_second": 1124060.3801196555, "synthetic": false, "world_size": 8} {"step": 58560, "tokens": 15351152640, "loss": 2.359096717834473, "optimizer_updates": 30280, "effective_batch": 512, "lr": 4.3098060728793406e-05, "gradient_norm": 0.24513143301010132, "tokens_per_second": 1135195.9173158552, "synthetic": false, "world_size": 8} {"step": 58580, "tokens": 15356395520, "loss": 2.366549491882324, "optimizer_updates": 30290, "effective_batch": 512, "lr": 4.3048342305917666e-05, "gradient_norm": 0.285503089427948, "tokens_per_second": 1022149.903860592, "synthetic": false, "world_size": 8} {"step": 58600, "tokens": 15361638400, "loss": 2.348729705810547, "optimizer_updates": 30300, "effective_batch": 512, "lr": 4.299866959092838e-05, "gradient_norm": 0.22680580615997314, "tokens_per_second": 1135586.8559205753, "synthetic": false, "world_size": 8} {"step": 58620, "tokens": 15366881280, "loss": 2.356944465637207, "optimizer_updates": 30310, "effective_batch": 512, "lr": 4.294904261773715e-05, "gradient_norm": 0.26502877473831177, "tokens_per_second": 1138058.4371200562, "synthetic": false, "world_size": 8} {"step": 58640, "tokens": 15372124160, "loss": 2.3574909210205077, "optimizer_updates": 30320, "effective_batch": 512, "lr": 4.289946142022426e-05, "gradient_norm": 0.25710761547088623, "tokens_per_second": 799244.5400014764, "synthetic": false, "world_size": 8} {"step": 58660, "tokens": 15377367040, "loss": 2.352718734741211, "optimizer_updates": 30330, "effective_batch": 512, "lr": 4.284992603223882e-05, "gradient_norm": 0.28357675671577454, "tokens_per_second": 1142841.7985735273, "synthetic": false, "world_size": 8} {"step": 58680, "tokens": 15382609920, "loss": 2.3619665145874023, "optimizer_updates": 30340, "effective_batch": 512, "lr": 4.2800436487598605e-05, "gradient_norm": 0.2548375427722931, "tokens_per_second": 1128170.513925074, "synthetic": false, "world_size": 8} {"step": 58700, "tokens": 15387852800, "loss": 2.3669450759887694, "optimizer_updates": 30350, "effective_batch": 512, "lr": 4.275099282009015e-05, "gradient_norm": 0.2362132966518402, "tokens_per_second": 1132932.7302230909, "synthetic": false, "world_size": 8} {"step": 58720, "tokens": 15393095680, "loss": 2.3715183258056642, "optimizer_updates": 30360, "effective_batch": 512, "lr": 4.27015950634686e-05, "gradient_norm": 0.2575255334377289, "tokens_per_second": 1131016.1589567258, "synthetic": false, "world_size": 8} {"step": 58740, "tokens": 15398338560, "loss": 2.3629486083984377, "optimizer_updates": 30370, "effective_batch": 512, "lr": 4.2652243251457826e-05, "gradient_norm": 0.2802591621875763, "tokens_per_second": 1141668.8923181945, "synthetic": false, "world_size": 8} {"step": 58760, "tokens": 15403581440, "loss": 2.3555110931396483, "optimizer_updates": 30380, "effective_batch": 512, "lr": 4.260293741775031e-05, "gradient_norm": 0.3153937757015228, "tokens_per_second": 1123515.0976315567, "synthetic": false, "world_size": 8} {"step": 58780, "tokens": 15408824320, "loss": 2.3687980651855467, "optimizer_updates": 30390, "effective_batch": 512, "lr": 4.2553677596007106e-05, "gradient_norm": 0.2842312455177307, "tokens_per_second": 1125604.2923701701, "synthetic": false, "world_size": 8} {"step": 58800, "tokens": 15414067200, "loss": 2.3564701080322266, "optimizer_updates": 30400, "effective_batch": 512, "lr": 4.250446381985792e-05, "gradient_norm": 0.22875820100307465, "tokens_per_second": 1126723.2841352245, "synthetic": false, "world_size": 8} {"step": 58820, "tokens": 15419310080, "loss": 2.358534812927246, "optimizer_updates": 30410, "effective_batch": 512, "lr": 4.245529612290096e-05, "gradient_norm": 0.2841664254665375, "tokens_per_second": 1138608.446994228, "synthetic": false, "world_size": 8} {"step": 58840, "tokens": 15424552960, "loss": 2.3709796905517577, "optimizer_updates": 30420, "effective_batch": 512, "lr": 4.240617453870303e-05, "gradient_norm": 0.2371940165758133, "tokens_per_second": 1127777.540850943, "synthetic": false, "world_size": 8} {"step": 58860, "tokens": 15429795840, "loss": 2.3419755935668944, "optimizer_updates": 30430, "effective_batch": 512, "lr": 4.235709910079939e-05, "gradient_norm": 0.2576739490032196, "tokens_per_second": 1125695.5486918471, "synthetic": false, "world_size": 8} {"step": 58880, "tokens": 15435038720, "loss": 2.3412288665771483, "optimizer_updates": 30440, "effective_batch": 512, "lr": 4.230806984269389e-05, "gradient_norm": 0.2509595453739166, "tokens_per_second": 1143849.5316725704, "synthetic": false, "world_size": 8} {"step": 58900, "tokens": 15440281600, "loss": 2.359012794494629, "optimizer_updates": 30450, "effective_batch": 512, "lr": 4.2259086797858766e-05, "gradient_norm": 0.2829230725765228, "tokens_per_second": 800322.6533867515, "synthetic": false, "world_size": 8} {"step": 58920, "tokens": 15445524480, "loss": 2.372457504272461, "optimizer_updates": 30460, "effective_batch": 512, "lr": 4.221014999973474e-05, "gradient_norm": 0.2589201331138611, "tokens_per_second": 1139381.6327485635, "synthetic": false, "world_size": 8} {"step": 58940, "tokens": 15450767360, "loss": 2.358001708984375, "optimizer_updates": 30470, "effective_batch": 512, "lr": 4.216125948173092e-05, "gradient_norm": 0.24368812143802643, "tokens_per_second": 1131979.7182059344, "synthetic": false, "world_size": 8} {"step": 58960, "tokens": 15456010240, "loss": 2.3625156402587892, "optimizer_updates": 30480, "effective_batch": 512, "lr": 4.211241527722491e-05, "gradient_norm": 0.3095492720603943, "tokens_per_second": 1136862.4838223327, "synthetic": false, "world_size": 8} {"step": 58980, "tokens": 15461253120, "loss": 2.344392013549805, "optimizer_updates": 30490, "effective_batch": 512, "lr": 4.20636174195626e-05, "gradient_norm": 0.2506271302700043, "tokens_per_second": 1128027.2580170287, "synthetic": false, "world_size": 8} {"step": 59000, "tokens": 15466496000, "loss": 2.3582605361938476, "optimizer_updates": 30500, "effective_batch": 512, "lr": 4.201486594205833e-05, "gradient_norm": 0.24355338513851166, "tokens_per_second": 1133478.2463353407, "synthetic": false, "world_size": 8} {"step": 59020, "tokens": 15471738880, "loss": 2.3548837661743165, "optimizer_updates": 30510, "effective_batch": 512, "lr": 4.196616087799465e-05, "gradient_norm": 0.2614719867706299, "tokens_per_second": 827997.3380722657, "synthetic": false, "world_size": 8} {"step": 59040, "tokens": 15476981760, "loss": 2.3553306579589846, "optimizer_updates": 30520, "effective_batch": 512, "lr": 4.1917502260622584e-05, "gradient_norm": 0.2699733376502991, "tokens_per_second": 1134438.1496763618, "synthetic": false, "world_size": 8} {"step": 59060, "tokens": 15482224640, "loss": 2.367872619628906, "optimizer_updates": 30530, "effective_batch": 512, "lr": 4.1868890123161295e-05, "gradient_norm": 0.27317970991134644, "tokens_per_second": 1128012.2108337048, "synthetic": false, "world_size": 8} {"step": 59080, "tokens": 15487467520, "loss": 2.3426031112670898, "optimizer_updates": 30540, "effective_batch": 512, "lr": 4.182032449879833e-05, "gradient_norm": 0.24945124983787537, "tokens_per_second": 1125571.6709242463, "synthetic": false, "world_size": 8} {"step": 59100, "tokens": 15492710400, "loss": 2.3615461349487306, "optimizer_updates": 30550, "effective_batch": 512, "lr": 4.1771805420689395e-05, "gradient_norm": 0.2746652662754059, "tokens_per_second": 1131146.4720781923, "synthetic": false, "world_size": 8} {"step": 59120, "tokens": 15497953280, "loss": 2.357075309753418, "optimizer_updates": 30560, "effective_batch": 512, "lr": 4.1723332921958495e-05, "gradient_norm": 0.2598373591899872, "tokens_per_second": 1132469.7859726702, "synthetic": false, "world_size": 8} {"step": 59140, "tokens": 15503196160, "loss": 2.3628070831298826, "optimizer_updates": 30570, "effective_batch": 512, "lr": 4.1674907035697765e-05, "gradient_norm": 0.24655723571777344, "tokens_per_second": 1133132.7846810892, "synthetic": false, "world_size": 8} {"step": 59160, "tokens": 15508439040, "loss": 2.3551815032958983, "optimizer_updates": 30580, "effective_batch": 512, "lr": 4.1626527794967586e-05, "gradient_norm": 0.233205184340477, "tokens_per_second": 1126523.0102921105, "synthetic": false, "world_size": 8} {"step": 59180, "tokens": 15513681920, "loss": 2.3541805267333986, "optimizer_updates": 30590, "effective_batch": 512, "lr": 4.15781952327964e-05, "gradient_norm": 0.275093138217926, "tokens_per_second": 1135988.9336937468, "synthetic": false, "world_size": 8} {"step": 59200, "tokens": 15518924800, "loss": 2.3566730499267576, "optimizer_updates": 30600, "effective_batch": 512, "lr": 4.15299093821809e-05, "gradient_norm": 0.24480246007442474, "tokens_per_second": 1131762.0997156277, "synthetic": false, "world_size": 8} {"step": 59220, "tokens": 15524167680, "loss": 2.3451278686523436, "optimizer_updates": 30610, "effective_batch": 512, "lr": 4.1481670276085806e-05, "gradient_norm": 0.24066562950611115, "tokens_per_second": 1119969.3050463884, "synthetic": false, "world_size": 8} {"step": 59240, "tokens": 15529410560, "loss": 2.364768409729004, "optimizer_updates": 30620, "effective_batch": 512, "lr": 4.143347794744393e-05, "gradient_norm": 0.2552727162837982, "tokens_per_second": 1120120.7224396532, "synthetic": false, "world_size": 8} {"step": 59260, "tokens": 15534653440, "loss": 2.374804878234863, "optimizer_updates": 30630, "effective_batch": 512, "lr": 4.138533242915621e-05, "gradient_norm": 0.2592177391052246, "tokens_per_second": 1124786.8328087807, "synthetic": false, "world_size": 8} {"step": 59280, "tokens": 15539896320, "loss": 2.3573617935180664, "optimizer_updates": 30640, "effective_batch": 512, "lr": 4.133723375409151e-05, "gradient_norm": 0.26441842317581177, "tokens_per_second": 1126627.5045444726, "synthetic": false, "world_size": 8} {"step": 59300, "tokens": 15545139200, "loss": 2.3634124755859376, "optimizer_updates": 30650, "effective_batch": 512, "lr": 4.128918195508688e-05, "gradient_norm": 0.2730642259120941, "tokens_per_second": 1124715.2163841513, "synthetic": false, "world_size": 8} {"step": 59320, "tokens": 15550382080, "loss": 2.3624305725097656, "optimizer_updates": 30660, "effective_batch": 512, "lr": 4.12411770649472e-05, "gradient_norm": 0.2251814901828766, "tokens_per_second": 1110896.1544890564, "synthetic": false, "world_size": 8} {"step": 59340, "tokens": 15555624960, "loss": 2.3591808319091796, "optimizer_updates": 30670, "effective_batch": 512, "lr": 4.119321911644546e-05, "gradient_norm": 0.33492937684059143, "tokens_per_second": 1137928.6972866452, "synthetic": false, "world_size": 8} {"step": 59360, "tokens": 15560867840, "loss": 2.3622209548950197, "optimizer_updates": 30680, "effective_batch": 512, "lr": 4.11453081423225e-05, "gradient_norm": 0.25015413761138916, "tokens_per_second": 1119202.4251587363, "synthetic": false, "world_size": 8} {"step": 59380, "tokens": 15566110720, "loss": 2.3390148162841795, "optimizer_updates": 30690, "effective_batch": 512, "lr": 4.1097444175287164e-05, "gradient_norm": 0.24369436502456665, "tokens_per_second": 1132720.3055237185, "synthetic": false, "world_size": 8} {"step": 59400, "tokens": 15571353600, "loss": 2.3638259887695314, "optimizer_updates": 30700, "effective_batch": 512, "lr": 4.104962724801615e-05, "gradient_norm": 0.2511838674545288, "tokens_per_second": 1129550.1805779655, "synthetic": false, "world_size": 8} {"step": 59420, "tokens": 15576596480, "loss": 2.3554462432861327, "optimizer_updates": 30710, "effective_batch": 512, "lr": 4.100185739315409e-05, "gradient_norm": 0.2533032298088074, "tokens_per_second": 1133797.5977933544, "synthetic": false, "world_size": 8} {"step": 59440, "tokens": 15581839360, "loss": 2.3536075592041015, "optimizer_updates": 30720, "effective_batch": 512, "lr": 4.0954134643313434e-05, "gradient_norm": 0.2515518069267273, "tokens_per_second": 1120092.6763131728, "synthetic": false, "world_size": 8} {"step": 59460, "tokens": 15587082240, "loss": 2.3744735717773438, "optimizer_updates": 30730, "effective_batch": 512, "lr": 4.090645903107452e-05, "gradient_norm": 0.28229227662086487, "tokens_per_second": 1129339.43052233, "synthetic": false, "world_size": 8} {"step": 59480, "tokens": 15592325120, "loss": 2.363262748718262, "optimizer_updates": 30740, "effective_batch": 512, "lr": 4.0858830588985456e-05, "gradient_norm": 0.28057771921157837, "tokens_per_second": 1128161.0426783336, "synthetic": false, "world_size": 8} {"step": 59500, "tokens": 15597568000, "loss": 2.3677089691162108, "optimizer_updates": 30750, "effective_batch": 512, "lr": 4.081124934956221e-05, "gradient_norm": 0.22933557629585266, "tokens_per_second": 1123859.7358866108, "synthetic": false, "world_size": 8} {"step": 59520, "tokens": 15602810880, "loss": 2.3527244567871093, "optimizer_updates": 30760, "effective_batch": 512, "lr": 4.076371534528846e-05, "gradient_norm": 0.27100297808647156, "tokens_per_second": 1124582.001884832, "synthetic": false, "world_size": 8} {"step": 59540, "tokens": 15608053760, "loss": 2.358664321899414, "optimizer_updates": 30770, "effective_batch": 512, "lr": 4.071622860861566e-05, "gradient_norm": 0.2553459405899048, "tokens_per_second": 1135690.904571146, "synthetic": false, "world_size": 8} {"step": 59560, "tokens": 15613296640, "loss": 2.359910583496094, "optimizer_updates": 30780, "effective_batch": 512, "lr": 4.066878917196299e-05, "gradient_norm": 0.26536935567855835, "tokens_per_second": 1129024.4908427454, "synthetic": false, "world_size": 8} {"step": 59580, "tokens": 15618539520, "loss": 2.349380302429199, "optimizer_updates": 30790, "effective_batch": 512, "lr": 4.062139706771738e-05, "gradient_norm": 0.22860106825828552, "tokens_per_second": 1125739.7767198153, "synthetic": false, "world_size": 8} {"step": 59600, "tokens": 15623782400, "loss": 2.3604623794555666, "optimizer_updates": 30800, "effective_batch": 512, "lr": 4.0574052328233375e-05, "gradient_norm": 0.29145190119743347, "tokens_per_second": 1126067.1889937897, "synthetic": false, "world_size": 8} {"step": 59620, "tokens": 15629025280, "loss": 2.3526071548461913, "optimizer_updates": 30810, "effective_batch": 512, "lr": 4.052675498583322e-05, "gradient_norm": 0.262616902589798, "tokens_per_second": 1129250.4950893363, "synthetic": false, "world_size": 8} {"step": 59640, "tokens": 15634268160, "loss": 2.354676055908203, "optimizer_updates": 30820, "effective_batch": 512, "lr": 4.0479505072806864e-05, "gradient_norm": 0.2696938216686249, "tokens_per_second": 741690.3820570078, "synthetic": false, "world_size": 8} {"step": 59660, "tokens": 15639511040, "loss": 2.355890083312988, "optimizer_updates": 30830, "effective_batch": 512, "lr": 4.0432302621411744e-05, "gradient_norm": 0.26548343896865845, "tokens_per_second": 1137183.032283348, "synthetic": false, "world_size": 8} {"step": 59680, "tokens": 15644753920, "loss": 2.353266143798828, "optimizer_updates": 30840, "effective_batch": 512, "lr": 4.038514766387302e-05, "gradient_norm": 0.2645588219165802, "tokens_per_second": 1130031.8160269582, "synthetic": false, "world_size": 8} {"step": 59700, "tokens": 15649996800, "loss": 2.3539546966552733, "optimizer_updates": 30850, "effective_batch": 512, "lr": 4.033804023238332e-05, "gradient_norm": 0.26196709275245667, "tokens_per_second": 1134014.0758863438, "synthetic": false, "world_size": 8} {"step": 59720, "tokens": 15655239680, "loss": 2.356785202026367, "optimizer_updates": 30860, "effective_batch": 512, "lr": 4.029098035910294e-05, "gradient_norm": 0.28182414174079895, "tokens_per_second": 1135750.4959142553, "synthetic": false, "world_size": 8} {"step": 59740, "tokens": 15660482560, "loss": 2.3469287872314455, "optimizer_updates": 30870, "effective_batch": 512, "lr": 4.02439680761596e-05, "gradient_norm": 0.2520686089992523, "tokens_per_second": 1128049.0269027865, "synthetic": false, "world_size": 8} {"step": 59760, "tokens": 15665725440, "loss": 2.3522220611572267, "optimizer_updates": 30880, "effective_batch": 512, "lr": 4.0197003415648605e-05, "gradient_norm": 0.3093346357345581, "tokens_per_second": 1125194.8343019173, "synthetic": false, "world_size": 8} {"step": 59780, "tokens": 15670968320, "loss": 2.3400026321411134, "optimizer_updates": 30890, "effective_batch": 512, "lr": 4.0150086409632704e-05, "gradient_norm": 0.25111350417137146, "tokens_per_second": 1131859.1396953065, "synthetic": false, "world_size": 8} {"step": 59800, "tokens": 15676211200, "loss": 2.359764289855957, "optimizer_updates": 30900, "effective_batch": 512, "lr": 4.010321709014216e-05, "gradient_norm": 0.23694205284118652, "tokens_per_second": 1132794.7339800992, "synthetic": false, "world_size": 8} {"step": 59820, "tokens": 15681454080, "loss": 2.363996124267578, "optimizer_updates": 30910, "effective_batch": 512, "lr": 4.005639548917464e-05, "gradient_norm": 0.30137181282043457, "tokens_per_second": 1126898.8471708728, "synthetic": false, "world_size": 8} {"step": 59840, "tokens": 15686696960, "loss": 2.351542282104492, "optimizer_updates": 30920, "effective_batch": 512, "lr": 4.000962163869522e-05, "gradient_norm": 0.2509245276451111, "tokens_per_second": 1010931.8650596056, "synthetic": false, "world_size": 8} {"step": 59860, "tokens": 15691939840, "loss": 2.361286735534668, "optimizer_updates": 30930, "effective_batch": 512, "lr": 3.996289557063639e-05, "gradient_norm": 0.2640652060508728, "tokens_per_second": 1134804.3362530086, "synthetic": false, "world_size": 8} {"step": 59880, "tokens": 15697182720, "loss": 2.3540359497070313, "optimizer_updates": 30940, "effective_batch": 512, "lr": 3.991621731689809e-05, "gradient_norm": 0.2586480379104614, "tokens_per_second": 1134626.8449130948, "synthetic": false, "world_size": 8} {"step": 59900, "tokens": 15702425600, "loss": 2.371141815185547, "optimizer_updates": 30950, "effective_batch": 512, "lr": 3.9869586909347484e-05, "gradient_norm": 0.24673156440258026, "tokens_per_second": 1129623.3927632512, "synthetic": false, "world_size": 8} {"step": 59920, "tokens": 15707668480, "loss": 2.3535253524780275, "optimizer_updates": 30960, "effective_batch": 512, "lr": 3.982300437981921e-05, "gradient_norm": 0.2513088583946228, "tokens_per_second": 1135953.130384949, "synthetic": false, "world_size": 8} {"step": 59940, "tokens": 15712911360, "loss": 2.366988182067871, "optimizer_updates": 30970, "effective_batch": 512, "lr": 3.977646976011509e-05, "gradient_norm": 0.24228736758232117, "tokens_per_second": 1129769.9721248513, "synthetic": false, "world_size": 8} {"step": 59960, "tokens": 15718154240, "loss": 2.3399141311645506, "optimizer_updates": 30980, "effective_batch": 512, "lr": 3.972998308200438e-05, "gradient_norm": 0.2599603831768036, "tokens_per_second": 1133365.9403257652, "synthetic": false, "world_size": 8} {"step": 59980, "tokens": 15723397120, "loss": 2.3639835357666015, "optimizer_updates": 30990, "effective_batch": 512, "lr": 3.968354437722344e-05, "gradient_norm": 0.24643944203853607, "tokens_per_second": 1127705.2250741967, "synthetic": false, "world_size": 8} {"step": 60000, "tokens": 15728640000, "loss": 2.352667236328125, "optimizer_updates": 31000, "effective_batch": 512, "lr": 3.9637153677476045e-05, "gradient_norm": 0.2516225278377533, "tokens_per_second": 1124694.6928105443, "synthetic": false, "world_size": 8} {"step": 60020, "tokens": 15733882880, "loss": 2.3578216552734377, "optimizer_updates": 31010, "effective_batch": 512, "lr": 3.9590811014433066e-05, "gradient_norm": 0.266071617603302, "tokens_per_second": 829991.839198832, "synthetic": false, "world_size": 8} {"step": 60040, "tokens": 15739125760, "loss": 2.3607061386108397, "optimizer_updates": 31020, "effective_batch": 512, "lr": 3.954451641973264e-05, "gradient_norm": 0.30105218291282654, "tokens_per_second": 1129916.1826712629, "synthetic": false, "world_size": 8} {"step": 60060, "tokens": 15744368640, "loss": 2.3630596160888673, "optimizer_updates": 31030, "effective_batch": 512, "lr": 3.949826992498012e-05, "gradient_norm": 0.27724525332450867, "tokens_per_second": 1127716.415246628, "synthetic": false, "world_size": 8} {"step": 60080, "tokens": 15749611520, "loss": 2.3680578231811524, "optimizer_updates": 31040, "effective_batch": 512, "lr": 3.9452071561747916e-05, "gradient_norm": 0.22023208439350128, "tokens_per_second": 1127102.1783111398, "synthetic": false, "world_size": 8} {"step": 60100, "tokens": 15754854400, "loss": 2.362282562255859, "optimizer_updates": 31050, "effective_batch": 512, "lr": 3.940592136157572e-05, "gradient_norm": 0.234132319688797, "tokens_per_second": 1136112.2079356646, "synthetic": false, "world_size": 8} {"step": 60120, "tokens": 15760097280, "loss": 2.379851722717285, "optimizer_updates": 31060, "effective_batch": 512, "lr": 3.935981935597019e-05, "gradient_norm": 0.25702932476997375, "tokens_per_second": 1127055.4964256985, "synthetic": false, "world_size": 8} {"step": 60140, "tokens": 15765340160, "loss": 2.3493871688842773, "optimizer_updates": 31070, "effective_batch": 512, "lr": 3.9313765576405216e-05, "gradient_norm": 0.2573907673358917, "tokens_per_second": 1126939.840560283, "synthetic": false, "world_size": 8} {"step": 60160, "tokens": 15770583040, "loss": 2.350665283203125, "optimizer_updates": 31080, "effective_batch": 512, "lr": 3.9267760054321694e-05, "gradient_norm": 0.2636640667915344, "tokens_per_second": 1123493.6514506273, "synthetic": false, "world_size": 8} {"step": 60180, "tokens": 15775825920, "loss": 2.3508333206176757, "optimizer_updates": 31090, "effective_batch": 512, "lr": 3.922180282112757e-05, "gradient_norm": 0.3183162808418274, "tokens_per_second": 1118794.9896948696, "synthetic": false, "world_size": 8} {"step": 60200, "tokens": 15781068800, "loss": 2.3608192443847655, "optimizer_updates": 31100, "effective_batch": 512, "lr": 3.9175893908197826e-05, "gradient_norm": 0.2591093182563782, "tokens_per_second": 1130033.7903523084, "synthetic": false, "world_size": 8} {"step": 60220, "tokens": 15786311680, "loss": 2.357594299316406, "optimizer_updates": 31110, "effective_batch": 512, "lr": 3.913003334687451e-05, "gradient_norm": 0.27537640929222107, "tokens_per_second": 1128423.407556537, "synthetic": false, "world_size": 8} {"step": 60240, "tokens": 15791554560, "loss": 2.369709777832031, "optimizer_updates": 31120, "effective_batch": 512, "lr": 3.908422116846658e-05, "gradient_norm": 0.2676476836204529, "tokens_per_second": 1125156.9156055092, "synthetic": false, "world_size": 8} {"step": 60260, "tokens": 15796797440, "loss": 2.3581533432006836, "optimizer_updates": 31130, "effective_batch": 512, "lr": 3.903845740425004e-05, "gradient_norm": 0.2300146222114563, "tokens_per_second": 1131744.3403778437, "synthetic": false, "world_size": 8} {"step": 60280, "tokens": 15802040320, "loss": 2.352908897399902, "optimizer_updates": 31140, "effective_batch": 512, "lr": 3.8992742085467764e-05, "gradient_norm": 0.2843446433544159, "tokens_per_second": 1022936.0945189475, "synthetic": false, "world_size": 8} {"step": 60300, "tokens": 15807283200, "loss": 2.3700944900512697, "optimizer_updates": 31150, "effective_batch": 512, "lr": 3.894707524332965e-05, "gradient_norm": 0.3006443679332733, "tokens_per_second": 1140885.579052753, "synthetic": false, "world_size": 8} {"step": 60320, "tokens": 15812526080, "loss": 2.349309730529785, "optimizer_updates": 31160, "effective_batch": 512, "lr": 3.890145690901239e-05, "gradient_norm": 0.27079352736473083, "tokens_per_second": 1126091.2136648735, "synthetic": false, "world_size": 8} {"step": 60340, "tokens": 15817768960, "loss": 2.3563995361328125, "optimizer_updates": 31170, "effective_batch": 512, "lr": 3.8855887113659664e-05, "gradient_norm": 0.2778399586677551, "tokens_per_second": 1132805.3777503045, "synthetic": false, "world_size": 8} {"step": 60360, "tokens": 15823011840, "loss": 2.357833480834961, "optimizer_updates": 31180, "effective_batch": 512, "lr": 3.8810365888381905e-05, "gradient_norm": 0.28023380041122437, "tokens_per_second": 1123282.7206142761, "synthetic": false, "world_size": 8} {"step": 60380, "tokens": 15828254720, "loss": 2.3672296524047853, "optimizer_updates": 31190, "effective_batch": 512, "lr": 3.8764893264256505e-05, "gradient_norm": 0.25790876150131226, "tokens_per_second": 1124675.7034127081, "synthetic": false, "world_size": 8} {"step": 60400, "tokens": 15833497600, "loss": 2.3531621932983398, "optimizer_updates": 31200, "effective_batch": 512, "lr": 3.871946927232756e-05, "gradient_norm": 0.24460680782794952, "tokens_per_second": 1138237.8847409275, "synthetic": false, "world_size": 8} {"step": 60420, "tokens": 15838740480, "loss": 2.3535087585449217, "optimizer_updates": 31210, "effective_batch": 512, "lr": 3.867409394360607e-05, "gradient_norm": 0.2701623737812042, "tokens_per_second": 1125852.6877365108, "synthetic": false, "world_size": 8} {"step": 60440, "tokens": 15843983360, "loss": 2.3514019012451173, "optimizer_updates": 31220, "effective_batch": 512, "lr": 3.862876730906974e-05, "gradient_norm": 0.26655569672584534, "tokens_per_second": 1127094.392209136, "synthetic": false, "world_size": 8} {"step": 60460, "tokens": 15849226240, "loss": 2.3737255096435548, "optimizer_updates": 31230, "effective_batch": 512, "lr": 3.858348939966308e-05, "gradient_norm": 0.27192285656929016, "tokens_per_second": 1117941.1045777933, "synthetic": false, "world_size": 8} {"step": 60480, "tokens": 15854469120, "loss": 2.3560266494750977, "optimizer_updates": 31240, "effective_batch": 512, "lr": 3.85382602462973e-05, "gradient_norm": 0.2253049612045288, "tokens_per_second": 1131535.705998204, "synthetic": false, "world_size": 8} {"step": 60500, "tokens": 15859712000, "loss": 2.352824020385742, "optimizer_updates": 31250, "effective_batch": 512, "lr": 3.8493079879850305e-05, "gradient_norm": 0.2802918255329132, "tokens_per_second": 1129229.479231092, "synthetic": false, "world_size": 8} {"step": 60520, "tokens": 15864954880, "loss": 2.3689361572265626, "optimizer_updates": 31260, "effective_batch": 512, "lr": 3.8447948331166775e-05, "gradient_norm": 0.26532232761383057, "tokens_per_second": 1017159.2749082951, "synthetic": false, "world_size": 8} {"step": 60540, "tokens": 15870197760, "loss": 2.3594638824462892, "optimizer_updates": 31270, "effective_batch": 512, "lr": 3.840286563105796e-05, "gradient_norm": 0.24235285818576813, "tokens_per_second": 1138562.7490909393, "synthetic": false, "world_size": 8} {"step": 60560, "tokens": 15875440640, "loss": 2.361837959289551, "optimizer_updates": 31280, "effective_batch": 512, "lr": 3.835783181030187e-05, "gradient_norm": 0.24088838696479797, "tokens_per_second": 1128041.512661912, "synthetic": false, "world_size": 8} {"step": 60580, "tokens": 15880683520, "loss": 2.351802635192871, "optimizer_updates": 31290, "effective_batch": 512, "lr": 3.8312846899643034e-05, "gradient_norm": 0.2675067186355591, "tokens_per_second": 1128556.5965303269, "synthetic": false, "world_size": 8} {"step": 60600, "tokens": 15885926400, "loss": 2.357222557067871, "optimizer_updates": 31300, "effective_batch": 512, "lr": 3.826791092979269e-05, "gradient_norm": 0.2423357516527176, "tokens_per_second": 1134011.8860045245, "synthetic": false, "world_size": 8} {"step": 60620, "tokens": 15891169280, "loss": 2.3580322265625, "optimizer_updates": 31310, "effective_batch": 512, "lr": 3.8223023931428565e-05, "gradient_norm": 0.26183804869651794, "tokens_per_second": 1123196.0474153245, "synthetic": false, "world_size": 8} {"step": 60640, "tokens": 15896412160, "loss": 2.3629093170166016, "optimizer_updates": 31320, "effective_batch": 512, "lr": 3.817818593519507e-05, "gradient_norm": 0.2839749753475189, "tokens_per_second": 1127939.042360446, "synthetic": false, "world_size": 8} {"step": 60660, "tokens": 15901655040, "loss": 2.344038200378418, "optimizer_updates": 31330, "effective_batch": 512, "lr": 3.8133396971703036e-05, "gradient_norm": 0.2680104672908783, "tokens_per_second": 818583.384160441, "synthetic": false, "world_size": 8} {"step": 60680, "tokens": 15906897920, "loss": 2.362373924255371, "optimizer_updates": 31340, "effective_batch": 512, "lr": 3.8088657071529936e-05, "gradient_norm": 0.2908174693584442, "tokens_per_second": 1136372.4153038396, "synthetic": false, "world_size": 8} {"step": 60700, "tokens": 15912140800, "loss": 2.353363800048828, "optimizer_updates": 31350, "effective_batch": 512, "lr": 3.804396626521964e-05, "gradient_norm": 0.315218985080719, "tokens_per_second": 1129454.5660378956, "synthetic": false, "world_size": 8} {"step": 60720, "tokens": 15917383680, "loss": 2.347841262817383, "optimizer_updates": 31360, "effective_batch": 512, "lr": 3.79993245832826e-05, "gradient_norm": 0.2865108847618103, "tokens_per_second": 1128258.5495053276, "synthetic": false, "world_size": 8} {"step": 60740, "tokens": 15922626560, "loss": 2.3542196273803713, "optimizer_updates": 31370, "effective_batch": 512, "lr": 3.795473205619565e-05, "gradient_norm": 0.25564509630203247, "tokens_per_second": 1127002.650225477, "synthetic": false, "world_size": 8} {"step": 60760, "tokens": 15927869440, "loss": 2.3513444900512694, "optimizer_updates": 31380, "effective_batch": 512, "lr": 3.7910188714402145e-05, "gradient_norm": 0.24006934463977814, "tokens_per_second": 1132172.9557950867, "synthetic": false, "world_size": 8} {"step": 60780, "tokens": 15933112320, "loss": 2.365752410888672, "optimizer_updates": 31390, "effective_batch": 512, "lr": 3.7865694588311784e-05, "gradient_norm": 0.24250099062919617, "tokens_per_second": 790536.2663092369, "synthetic": false, "world_size": 8} {"step": 60800, "tokens": 15938355200, "loss": 2.3499624252319338, "optimizer_updates": 31400, "effective_batch": 512, "lr": 3.782124970830071e-05, "gradient_norm": 0.23736707866191864, "tokens_per_second": 1128335.1240791904, "synthetic": false, "world_size": 8} {"step": 60820, "tokens": 15943598080, "loss": 2.350511932373047, "optimizer_updates": 31410, "effective_batch": 512, "lr": 3.777685410471141e-05, "gradient_norm": 0.2578328251838684, "tokens_per_second": 1133016.295490528, "synthetic": false, "world_size": 8} {"step": 60840, "tokens": 15948840960, "loss": 2.369160461425781, "optimizer_updates": 31420, "effective_batch": 512, "lr": 3.77325078078528e-05, "gradient_norm": 0.2690059542655945, "tokens_per_second": 1122371.6855720854, "synthetic": false, "world_size": 8} {"step": 60860, "tokens": 15954083840, "loss": 2.353557014465332, "optimizer_updates": 31430, "effective_batch": 512, "lr": 3.768821084800004e-05, "gradient_norm": 0.2793603539466858, "tokens_per_second": 1005453.4658482077, "synthetic": false, "world_size": 8} {"step": 60880, "tokens": 15959326720, "loss": 2.3639625549316405, "optimizer_updates": 31440, "effective_batch": 512, "lr": 3.7643963255394724e-05, "gradient_norm": 0.26495394110679626, "tokens_per_second": 1136258.8051651097, "synthetic": false, "world_size": 8} {"step": 60900, "tokens": 15964569600, "loss": 2.3540603637695314, "optimizer_updates": 31450, "effective_batch": 512, "lr": 3.7599765060244605e-05, "gradient_norm": 0.2582190930843353, "tokens_per_second": 1129440.9418013091, "synthetic": false, "world_size": 8} {"step": 60920, "tokens": 15969812480, "loss": 2.360746955871582, "optimizer_updates": 31460, "effective_batch": 512, "lr": 3.7555616292723826e-05, "gradient_norm": 0.24837933480739594, "tokens_per_second": 1131668.8517577166, "synthetic": false, "world_size": 8} {"step": 60940, "tokens": 15975055360, "loss": 2.354581832885742, "optimizer_updates": 31470, "effective_batch": 512, "lr": 3.7511516982972755e-05, "gradient_norm": 0.2443588674068451, "tokens_per_second": 1137083.0250106605, "synthetic": false, "world_size": 8} {"step": 60960, "tokens": 15980298240, "loss": 2.3493511199951174, "optimizer_updates": 31480, "effective_batch": 512, "lr": 3.7467467161097945e-05, "gradient_norm": 0.2736935019493103, "tokens_per_second": 1136006.640351172, "synthetic": false, "world_size": 8} {"step": 60980, "tokens": 15985541120, "loss": 2.363373947143555, "optimizer_updates": 31490, "effective_batch": 512, "lr": 3.7423466857172235e-05, "gradient_norm": 0.2885708808898926, "tokens_per_second": 1144059.9560154595, "synthetic": false, "world_size": 8} {"step": 61000, "tokens": 15990784000, "loss": 2.373623275756836, "optimizer_updates": 31500, "effective_batch": 512, "lr": 3.7379516101234593e-05, "gradient_norm": 0.2507731020450592, "tokens_per_second": 1131517.3239751642, "synthetic": false, "world_size": 8} {"step": 61020, "tokens": 15996026880, "loss": 2.348143196105957, "optimizer_updates": 31510, "effective_batch": 512, "lr": 3.7335614923290246e-05, "gradient_norm": 0.23139895498752594, "tokens_per_second": 829021.774983351, "synthetic": false, "world_size": 8} {"step": 61040, "tokens": 16001269760, "loss": 2.354718017578125, "optimizer_updates": 31520, "effective_batch": 512, "lr": 3.729176335331046e-05, "gradient_norm": 0.2596200704574585, "tokens_per_second": 1131234.8411513623, "synthetic": false, "world_size": 8} {"step": 61060, "tokens": 16006512640, "loss": 2.3501415252685547, "optimizer_updates": 31530, "effective_batch": 512, "lr": 3.724796142123275e-05, "gradient_norm": 0.24085623025894165, "tokens_per_second": 1134923.145085474, "synthetic": false, "world_size": 8} {"step": 61080, "tokens": 16011755520, "loss": 2.3656408309936525, "optimizer_updates": 31540, "effective_batch": 512, "lr": 3.720420915696066e-05, "gradient_norm": 0.2503216862678528, "tokens_per_second": 1125767.32483076, "synthetic": false, "world_size": 8} {"step": 61100, "tokens": 16016998400, "loss": 2.3505575180053713, "optimizer_updates": 31550, "effective_batch": 512, "lr": 3.716050659036383e-05, "gradient_norm": 0.26268383860588074, "tokens_per_second": 1127960.3055171457, "synthetic": false, "world_size": 8} {"step": 61120, "tokens": 16022241280, "loss": 2.3471330642700194, "optimizer_updates": 31560, "effective_batch": 512, "lr": 3.7116853751278056e-05, "gradient_norm": 0.25069183111190796, "tokens_per_second": 1132555.7223735875, "synthetic": false, "world_size": 8} {"step": 61140, "tokens": 16027484160, "loss": 2.362535095214844, "optimizer_updates": 31570, "effective_batch": 512, "lr": 3.707325066950508e-05, "gradient_norm": 0.2548137605190277, "tokens_per_second": 1131257.1118628052, "synthetic": false, "world_size": 8} {"step": 61160, "tokens": 16032727040, "loss": 2.367702102661133, "optimizer_updates": 31580, "effective_batch": 512, "lr": 3.7029697374812724e-05, "gradient_norm": 0.2590909004211426, "tokens_per_second": 1136649.630804387, "synthetic": false, "world_size": 8} {"step": 61180, "tokens": 16037969920, "loss": 2.3493152618408204, "optimizer_updates": 31590, "effective_batch": 512, "lr": 3.698619389693483e-05, "gradient_norm": 0.26916736364364624, "tokens_per_second": 1132643.9775321214, "synthetic": false, "world_size": 8} {"step": 61200, "tokens": 16043212800, "loss": 2.358752632141113, "optimizer_updates": 31600, "effective_batch": 512, "lr": 3.6942740265571186e-05, "gradient_norm": 0.274139940738678, "tokens_per_second": 1138488.8114560775, "synthetic": false, "world_size": 8} {"step": 61220, "tokens": 16048455680, "loss": 2.3538450241088866, "optimizer_updates": 31610, "effective_batch": 512, "lr": 3.689933651038763e-05, "gradient_norm": 0.25111913681030273, "tokens_per_second": 1134426.5390118815, "synthetic": false, "world_size": 8} {"step": 61240, "tokens": 16053698560, "loss": 2.341435432434082, "optimizer_updates": 31620, "effective_batch": 512, "lr": 3.6855982661015843e-05, "gradient_norm": 0.24181129038333893, "tokens_per_second": 1133884.5237392522, "synthetic": false, "world_size": 8} {"step": 61260, "tokens": 16058941440, "loss": 2.3571006774902346, "optimizer_updates": 31630, "effective_batch": 512, "lr": 3.681267874705354e-05, "gradient_norm": 0.23395875096321106, "tokens_per_second": 1131522.6852681523, "synthetic": false, "world_size": 8} {"step": 61280, "tokens": 16064184320, "loss": 2.3568326950073244, "optimizer_updates": 31640, "effective_batch": 512, "lr": 3.676942479806425e-05, "gradient_norm": 0.2454572319984436, "tokens_per_second": 1125132.9008468995, "synthetic": false, "world_size": 8} {"step": 61300, "tokens": 16069427200, "loss": 2.362957572937012, "optimizer_updates": 31650, "effective_batch": 512, "lr": 3.67262208435775e-05, "gradient_norm": 0.23261551558971405, "tokens_per_second": 791736.3389486573, "synthetic": false, "world_size": 8} {"step": 61320, "tokens": 16074670080, "loss": 2.3609479904174804, "optimizer_updates": 31660, "effective_batch": 512, "lr": 3.668306691308854e-05, "gradient_norm": 0.2458794116973877, "tokens_per_second": 1133297.8511335058, "synthetic": false, "world_size": 8} {"step": 61340, "tokens": 16079912960, "loss": 2.361846351623535, "optimizer_updates": 31670, "effective_batch": 512, "lr": 3.663996303605864e-05, "gradient_norm": 0.26432520151138306, "tokens_per_second": 1132894.4296788205, "synthetic": false, "world_size": 8} {"step": 61360, "tokens": 16085155840, "loss": 2.353406524658203, "optimizer_updates": 31680, "effective_batch": 512, "lr": 3.6596909241914744e-05, "gradient_norm": 0.24670812487602234, "tokens_per_second": 1136390.2842295303, "synthetic": false, "world_size": 8} {"step": 61380, "tokens": 16090398720, "loss": 2.364400863647461, "optimizer_updates": 31690, "effective_batch": 512, "lr": 3.6553905560049677e-05, "gradient_norm": 0.3025873899459839, "tokens_per_second": 1134714.2843708994, "synthetic": false, "world_size": 8} {"step": 61400, "tokens": 16095641600, "loss": 2.3550968170166016, "optimizer_updates": 31700, "effective_batch": 512, "lr": 3.6510952019822094e-05, "gradient_norm": 0.26003721356391907, "tokens_per_second": 1139595.0232826076, "synthetic": false, "world_size": 8} {"step": 61420, "tokens": 16100884480, "loss": 2.3626718521118164, "optimizer_updates": 31710, "effective_batch": 512, "lr": 3.646804865055635e-05, "gradient_norm": 0.24254150688648224, "tokens_per_second": 1142939.4216678794, "synthetic": false, "world_size": 8} {"step": 61440, "tokens": 16106127360, "loss": 2.362733268737793, "optimizer_updates": 31720, "effective_batch": 512, "lr": 3.6425195481542545e-05, "gradient_norm": 0.236611008644104, "tokens_per_second": 1136804.9887491087, "synthetic": false, "world_size": 8} {"step": 61460, "tokens": 16111370240, "loss": 2.3726640701293946, "optimizer_updates": 31730, "effective_batch": 512, "lr": 3.6382392542036526e-05, "gradient_norm": 0.2562843859195709, "tokens_per_second": 1129957.8627062659, "synthetic": false, "world_size": 8} {"step": 61480, "tokens": 16116613120, "loss": 2.365184783935547, "optimizer_updates": 31740, "effective_batch": 512, "lr": 3.6339639861259896e-05, "gradient_norm": 0.27474623918533325, "tokens_per_second": 1131148.2413977538, "synthetic": false, "world_size": 8} {"step": 61500, "tokens": 16121856000, "loss": 2.3524465560913086, "optimizer_updates": 31750, "effective_batch": 512, "lr": 3.629693746839986e-05, "gradient_norm": 0.2427286058664322, "tokens_per_second": 1126204.754984483, "synthetic": false, "world_size": 8} {"step": 61520, "tokens": 16127098880, "loss": 2.345114326477051, "optimizer_updates": 31760, "effective_batch": 512, "lr": 3.625428539260936e-05, "gradient_norm": 0.25981399416923523, "tokens_per_second": 1126885.9264219857, "synthetic": false, "world_size": 8} {"step": 61540, "tokens": 16132341760, "loss": 2.359680938720703, "optimizer_updates": 31770, "effective_batch": 512, "lr": 3.621168366300695e-05, "gradient_norm": 0.23668435215950012, "tokens_per_second": 1131640.0045294198, "synthetic": false, "world_size": 8} {"step": 61560, "tokens": 16137584640, "loss": 2.364086723327637, "optimizer_updates": 31780, "effective_batch": 512, "lr": 3.6169132308676844e-05, "gradient_norm": 0.3154888153076172, "tokens_per_second": 1137170.6086395406, "synthetic": false, "world_size": 8} {"step": 61580, "tokens": 16142827520, "loss": 2.355490493774414, "optimizer_updates": 31790, "effective_batch": 512, "lr": 3.6126631358668816e-05, "gradient_norm": 0.28484436869621277, "tokens_per_second": 1137176.2041643928, "synthetic": false, "world_size": 8} {"step": 61600, "tokens": 16148070400, "loss": 2.3542613983154297, "optimizer_updates": 31800, "effective_batch": 512, "lr": 3.608418084199829e-05, "gradient_norm": 0.24258975684642792, "tokens_per_second": 1131515.46926573, "synthetic": false, "world_size": 8} {"step": 61620, "tokens": 16153313280, "loss": 2.3565893173217773, "optimizer_updates": 31810, "effective_batch": 512, "lr": 3.6041780787646196e-05, "gradient_norm": 0.24308285117149353, "tokens_per_second": 1127774.0635192252, "synthetic": false, "world_size": 8} {"step": 61640, "tokens": 16158556160, "loss": 2.370869445800781, "optimizer_updates": 31820, "effective_batch": 512, "lr": 3.599943122455907e-05, "gradient_norm": 0.2842843234539032, "tokens_per_second": 1137534.0166886675, "synthetic": false, "world_size": 8} {"step": 61660, "tokens": 16163799040, "loss": 2.351653480529785, "optimizer_updates": 31830, "effective_batch": 512, "lr": 3.595713218164892e-05, "gradient_norm": 0.22824928164482117, "tokens_per_second": 1125797.0857402037, "synthetic": false, "world_size": 8} {"step": 61680, "tokens": 16169041920, "loss": 2.3681217193603517, "optimizer_updates": 31840, "effective_batch": 512, "lr": 3.5914883687793346e-05, "gradient_norm": 0.24102778732776642, "tokens_per_second": 1124671.3470165394, "synthetic": false, "world_size": 8} {"step": 61700, "tokens": 16174284800, "loss": 2.3653160095214845, "optimizer_updates": 31850, "effective_batch": 512, "lr": 3.587268577183534e-05, "gradient_norm": 0.24469250440597534, "tokens_per_second": 1136092.2409386698, "synthetic": false, "world_size": 8} {"step": 61720, "tokens": 16179527680, "loss": 2.359531593322754, "optimizer_updates": 31860, "effective_batch": 512, "lr": 3.583053846258344e-05, "gradient_norm": 0.25043192505836487, "tokens_per_second": 1131713.033994351, "synthetic": false, "world_size": 8} {"step": 61740, "tokens": 16184770560, "loss": 2.3636245727539062, "optimizer_updates": 31870, "effective_batch": 512, "lr": 3.5788441788811606e-05, "gradient_norm": 0.2937968969345093, "tokens_per_second": 1140327.1533411655, "synthetic": false, "world_size": 8} {"step": 61760, "tokens": 16190013440, "loss": 2.3462263107299806, "optimizer_updates": 31880, "effective_batch": 512, "lr": 3.574639577925924e-05, "gradient_norm": 0.2669491171836853, "tokens_per_second": 1126551.64975466, "synthetic": false, "world_size": 8} {"step": 61780, "tokens": 16195256320, "loss": 2.3551008224487306, "optimizer_updates": 31890, "effective_batch": 512, "lr": 3.570440046263109e-05, "gradient_norm": 0.263631135225296, "tokens_per_second": 1127340.5730140537, "synthetic": false, "world_size": 8} {"step": 61800, "tokens": 16200499200, "loss": 2.369975280761719, "optimizer_updates": 31900, "effective_batch": 512, "lr": 3.56624558675974e-05, "gradient_norm": 0.23621129989624023, "tokens_per_second": 1059106.0316569677, "synthetic": false, "world_size": 8} {"step": 61820, "tokens": 16205742080, "loss": 2.3614852905273436, "optimizer_updates": 31910, "effective_batch": 512, "lr": 3.562056202279376e-05, "gradient_norm": 0.24794256687164307, "tokens_per_second": 787157.6923236098, "synthetic": false, "world_size": 8} {"step": 61840, "tokens": 16210984960, "loss": 2.366878890991211, "optimizer_updates": 31920, "effective_batch": 512, "lr": 3.5578718956821036e-05, "gradient_norm": 0.2384321689605713, "tokens_per_second": 1137476.9600564975, "synthetic": false, "world_size": 8} {"step": 61860, "tokens": 16216227840, "loss": 2.3413232803344726, "optimizer_updates": 31930, "effective_batch": 512, "lr": 3.553692669824553e-05, "gradient_norm": 0.25483545660972595, "tokens_per_second": 1133409.4602934776, "synthetic": false, "world_size": 8} {"step": 61880, "tokens": 16221470720, "loss": 2.3774387359619142, "optimizer_updates": 31940, "effective_batch": 512, "lr": 3.549518527559877e-05, "gradient_norm": 0.25786569714546204, "tokens_per_second": 1134739.7917180515, "synthetic": false, "world_size": 8} {"step": 61900, "tokens": 16226713600, "loss": 2.359735107421875, "optimizer_updates": 31950, "effective_batch": 512, "lr": 3.545349471737766e-05, "gradient_norm": 0.25268930196762085, "tokens_per_second": 1132097.1376710841, "synthetic": false, "world_size": 8} {"step": 61920, "tokens": 16231956480, "loss": 2.3623464584350584, "optimizer_updates": 31960, "effective_batch": 512, "lr": 3.54118550520443e-05, "gradient_norm": 0.2513350546360016, "tokens_per_second": 1127198.3783931006, "synthetic": false, "world_size": 8} {"step": 61940, "tokens": 16237199360, "loss": 2.365595245361328, "optimizer_updates": 31970, "effective_batch": 512, "lr": 3.537026630802612e-05, "gradient_norm": 0.27844950556755066, "tokens_per_second": 1134143.3146209796, "synthetic": false, "world_size": 8} {"step": 61960, "tokens": 16242442240, "loss": 2.346484375, "optimizer_updates": 31980, "effective_batch": 512, "lr": 3.5328728513715714e-05, "gradient_norm": 0.26034680008888245, "tokens_per_second": 1135444.3961756064, "synthetic": false, "world_size": 8} {"step": 61980, "tokens": 16247685120, "loss": 2.365461730957031, "optimizer_updates": 31990, "effective_batch": 512, "lr": 3.528724169747096e-05, "gradient_norm": 0.23479200899600983, "tokens_per_second": 766490.3462527071, "synthetic": false, "world_size": 8} {"step": 62000, "tokens": 16252928000, "loss": 2.352896499633789, "optimizer_updates": 32000, "effective_batch": 512, "lr": 3.524580588761485e-05, "gradient_norm": 0.2446298599243164, "tokens_per_second": 1141554.8162471345, "synthetic": false, "world_size": 8} {"step": 62020, "tokens": 16258170880, "loss": 2.363128089904785, "optimizer_updates": 32010, "effective_batch": 512, "lr": 3.520442111243569e-05, "gradient_norm": 0.2472178041934967, "tokens_per_second": 832726.3551587455, "synthetic": false, "world_size": 8} {"step": 62040, "tokens": 16263413760, "loss": 2.3654375076293945, "optimizer_updates": 32020, "effective_batch": 512, "lr": 3.516308740018679e-05, "gradient_norm": 0.2617385983467102, "tokens_per_second": 1141641.9909022164, "synthetic": false, "world_size": 8} {"step": 62060, "tokens": 16268656640, "loss": 2.352964401245117, "optimizer_updates": 32030, "effective_batch": 512, "lr": 3.512180477908669e-05, "gradient_norm": 0.251015841960907, "tokens_per_second": 1130029.5859521192, "synthetic": false, "world_size": 8} {"step": 62080, "tokens": 16273899520, "loss": 2.34959716796875, "optimizer_updates": 32040, "effective_batch": 512, "lr": 3.508057327731901e-05, "gradient_norm": 0.24988293647766113, "tokens_per_second": 1139130.9390131868, "synthetic": false, "world_size": 8} {"step": 62100, "tokens": 16279142400, "loss": 2.3549163818359373, "optimizer_updates": 32050, "effective_batch": 512, "lr": 3.5039392923032525e-05, "gradient_norm": 0.3237515389919281, "tokens_per_second": 1137750.9384110873, "synthetic": false, "world_size": 8} {"step": 62120, "tokens": 16284385280, "loss": 2.3553417205810545, "optimizer_updates": 32060, "effective_batch": 512, "lr": 3.499826374434102e-05, "gradient_norm": 0.26603564620018005, "tokens_per_second": 1132022.3374429701, "synthetic": false, "world_size": 8} {"step": 62140, "tokens": 16289628160, "loss": 2.3548845291137694, "optimizer_updates": 32070, "effective_batch": 512, "lr": 3.4957185769323424e-05, "gradient_norm": 0.2841232120990753, "tokens_per_second": 1127517.9223188974, "synthetic": false, "world_size": 8} {"step": 62160, "tokens": 16294871040, "loss": 2.351276397705078, "optimizer_updates": 32080, "effective_batch": 512, "lr": 3.491615902602361e-05, "gradient_norm": 0.2311159372329712, "tokens_per_second": 1139289.3596123045, "synthetic": false, "world_size": 8} {"step": 62180, "tokens": 16300113920, "loss": 2.3570804595947266, "optimizer_updates": 32090, "effective_batch": 512, "lr": 3.487518354245058e-05, "gradient_norm": 0.25971558690071106, "tokens_per_second": 1127507.2098625484, "synthetic": false, "world_size": 8} {"step": 62200, "tokens": 16305356800, "loss": 2.358325958251953, "optimizer_updates": 32100, "effective_batch": 512, "lr": 3.483425934657824e-05, "gradient_norm": 0.2440435141324997, "tokens_per_second": 1132851.4481348672, "synthetic": false, "world_size": 8} {"step": 62220, "tokens": 16310599680, "loss": 2.358272361755371, "optimizer_updates": 32110, "effective_batch": 512, "lr": 3.4793386466345576e-05, "gradient_norm": 0.2558380365371704, "tokens_per_second": 1130387.1018250708, "synthetic": false, "world_size": 8} {"step": 62240, "tokens": 16315842560, "loss": 2.3588445663452147, "optimizer_updates": 32120, "effective_batch": 512, "lr": 3.475256492965649e-05, "gradient_norm": 0.23513303697109222, "tokens_per_second": 1128125.6262493457, "synthetic": false, "world_size": 8} {"step": 62260, "tokens": 16321085440, "loss": 2.356209564208984, "optimizer_updates": 32130, "effective_batch": 512, "lr": 3.471179476437981e-05, "gradient_norm": 0.25088173151016235, "tokens_per_second": 1136987.4059583584, "synthetic": false, "world_size": 8} {"step": 62280, "tokens": 16326328320, "loss": 2.358686637878418, "optimizer_updates": 32140, "effective_batch": 512, "lr": 3.467107599834937e-05, "gradient_norm": 0.24276728928089142, "tokens_per_second": 1132450.191891907, "synthetic": false, "world_size": 8} {"step": 62300, "tokens": 16331571200, "loss": 2.3626237869262696, "optimizer_updates": 32150, "effective_batch": 512, "lr": 3.4630408659363814e-05, "gradient_norm": 0.27666741609573364, "tokens_per_second": 1134359.4540099031, "synthetic": false, "world_size": 8} {"step": 62320, "tokens": 16336814080, "loss": 2.353206443786621, "optimizer_updates": 32160, "effective_batch": 512, "lr": 3.458979277518677e-05, "gradient_norm": 0.2784024178981781, "tokens_per_second": 1127563.9111167458, "synthetic": false, "world_size": 8} {"step": 62340, "tokens": 16342056960, "loss": 2.344511032104492, "optimizer_updates": 32170, "effective_batch": 512, "lr": 3.454922837354667e-05, "gradient_norm": 0.233148455619812, "tokens_per_second": 1138534.5815982607, "synthetic": false, "world_size": 8} {"step": 62360, "tokens": 16347299840, "loss": 2.3542770385742187, "optimizer_updates": 32180, "effective_batch": 512, "lr": 3.450871548213683e-05, "gradient_norm": 0.2530067265033722, "tokens_per_second": 1133406.039792532, "synthetic": false, "world_size": 8} {"step": 62380, "tokens": 16352542720, "loss": 2.3701026916503904, "optimizer_updates": 32190, "effective_batch": 512, "lr": 3.446825412861541e-05, "gradient_norm": 0.2547908127307892, "tokens_per_second": 1126618.1962155213, "synthetic": false, "world_size": 8} {"step": 62400, "tokens": 16357785600, "loss": 2.366001319885254, "optimizer_updates": 32200, "effective_batch": 512, "lr": 3.4427844340605355e-05, "gradient_norm": 0.24659909307956696, "tokens_per_second": 1133916.362665521, "synthetic": false, "world_size": 8} {"step": 62420, "tokens": 16363028480, "loss": 2.3715829849243164, "optimizer_updates": 32210, "effective_batch": 512, "lr": 3.43874861456944e-05, "gradient_norm": 0.35452502965927124, "tokens_per_second": 1134020.3928994192, "synthetic": false, "world_size": 8} {"step": 62440, "tokens": 16368271360, "loss": 2.3594039916992187, "optimizer_updates": 32220, "effective_batch": 512, "lr": 3.434717957143513e-05, "gradient_norm": 0.31720516085624695, "tokens_per_second": 1135718.8821269216, "synthetic": false, "world_size": 8} {"step": 62460, "tokens": 16373514240, "loss": 2.3521718978881836, "optimizer_updates": 32230, "effective_batch": 512, "lr": 3.430692464534478e-05, "gradient_norm": 0.31535306572914124, "tokens_per_second": 1137320.2349373554, "synthetic": false, "world_size": 8} {"step": 62480, "tokens": 16378757120, "loss": 2.3700235366821287, "optimizer_updates": 32240, "effective_batch": 512, "lr": 3.426672139490543e-05, "gradient_norm": 0.3000240921974182, "tokens_per_second": 1133972.0975095425, "synthetic": false, "world_size": 8} {"step": 62500, "tokens": 16384000000, "loss": 2.3537960052490234, "optimizer_updates": 32250, "effective_batch": 512, "lr": 3.42265698475638e-05, "gradient_norm": 0.26093578338623047, "tokens_per_second": 1132449.5833323938, "synthetic": false, "world_size": 8} {"step": 62520, "tokens": 16389242880, "loss": 2.3505075454711912, "optimizer_updates": 32260, "effective_batch": 512, "lr": 3.4186470030731365e-05, "gradient_norm": 0.2724444270133972, "tokens_per_second": 1027276.6630403082, "synthetic": false, "world_size": 8} {"step": 62540, "tokens": 16394485760, "loss": 2.355459213256836, "optimizer_updates": 32270, "effective_batch": 512, "lr": 3.414642197178425e-05, "gradient_norm": 0.2342940717935562, "tokens_per_second": 1134168.0563373605, "synthetic": false, "world_size": 8} {"step": 62560, "tokens": 16399728640, "loss": 2.348072814941406, "optimizer_updates": 32280, "effective_batch": 512, "lr": 3.410642569806329e-05, "gradient_norm": 0.25174567103385925, "tokens_per_second": 1127689.7826344143, "synthetic": false, "world_size": 8} {"step": 62580, "tokens": 16404971520, "loss": 2.349118232727051, "optimizer_updates": 32290, "effective_batch": 512, "lr": 3.406648123687387e-05, "gradient_norm": 0.2998533844947815, "tokens_per_second": 1136397.0287319694, "synthetic": false, "world_size": 8} {"step": 62600, "tokens": 16410214400, "loss": 2.3610490798950194, "optimizer_updates": 32300, "effective_batch": 512, "lr": 3.4026588615486155e-05, "gradient_norm": 0.24542348086833954, "tokens_per_second": 1133712.528222626, "synthetic": false, "world_size": 8} {"step": 62620, "tokens": 16415457280, "loss": 2.354821968078613, "optimizer_updates": 32310, "effective_batch": 512, "lr": 3.398674786113475e-05, "gradient_norm": 0.2436331808567047, "tokens_per_second": 1131385.9331678264, "synthetic": false, "world_size": 8} {"step": 62640, "tokens": 16420700160, "loss": 2.354302978515625, "optimizer_updates": 32320, "effective_batch": 512, "lr": 3.3946959001018994e-05, "gradient_norm": 0.2504163384437561, "tokens_per_second": 1140609.1893466741, "synthetic": false, "world_size": 8} {"step": 62660, "tokens": 16425943040, "loss": 2.3533603668212892, "optimizer_updates": 32330, "effective_batch": 512, "lr": 3.390722206230268e-05, "gradient_norm": 0.2423609346151352, "tokens_per_second": 1129919.346873582, "synthetic": false, "world_size": 8} {"step": 62680, "tokens": 16431185920, "loss": 2.3540618896484373, "optimizer_updates": 32340, "effective_batch": 512, "lr": 3.386753707211426e-05, "gradient_norm": 0.2497161477804184, "tokens_per_second": 1138386.376245292, "synthetic": false, "world_size": 8} {"step": 62700, "tokens": 16436428800, "loss": 2.362566375732422, "optimizer_updates": 32350, "effective_batch": 512, "lr": 3.382790405754665e-05, "gradient_norm": 0.23751826584339142, "tokens_per_second": 1136431.4185145753, "synthetic": false, "world_size": 8} {"step": 62720, "tokens": 16441671680, "loss": 2.3632827758789063, "optimizer_updates": 32360, "effective_batch": 512, "lr": 3.378832304565729e-05, "gradient_norm": 0.26092052459716797, "tokens_per_second": 1133796.3201186873, "synthetic": false, "world_size": 8} {"step": 62740, "tokens": 16446914560, "loss": 2.3753292083740236, "optimizer_updates": 32370, "effective_batch": 512, "lr": 3.374879406346816e-05, "gradient_norm": 0.2923281490802765, "tokens_per_second": 1127775.9496729807, "synthetic": false, "world_size": 8} {"step": 62760, "tokens": 16452157440, "loss": 2.3596424102783202, "optimizer_updates": 32380, "effective_batch": 512, "lr": 3.3709317137965654e-05, "gradient_norm": 0.23455175757408142, "tokens_per_second": 1128132.6653010827, "synthetic": false, "world_size": 8} {"step": 62780, "tokens": 16457400320, "loss": 2.348047637939453, "optimizer_updates": 32390, "effective_batch": 512, "lr": 3.36698922961007e-05, "gradient_norm": 0.27647414803504944, "tokens_per_second": 1126731.8079778133, "synthetic": false, "world_size": 8} {"step": 62800, "tokens": 16462643200, "loss": 2.3687774658203127, "optimizer_updates": 32400, "effective_batch": 512, "lr": 3.363051956478859e-05, "gradient_norm": 0.2547793388366699, "tokens_per_second": 1131524.925362322, "synthetic": false, "world_size": 8} {"step": 62820, "tokens": 16467886080, "loss": 2.3649436950683596, "optimizer_updates": 32410, "effective_batch": 512, "lr": 3.359119897090913e-05, "gradient_norm": 0.2512463629245758, "tokens_per_second": 1124854.1922451374, "synthetic": false, "world_size": 8} {"step": 62840, "tokens": 16473128960, "loss": 2.3487079620361326, "optimizer_updates": 32420, "effective_batch": 512, "lr": 3.3551930541306436e-05, "gradient_norm": 0.2532421946525574, "tokens_per_second": 1134796.2385828942, "synthetic": false, "world_size": 8} {"step": 62860, "tokens": 16478371840, "loss": 2.3552267074584963, "optimizer_updates": 32430, "effective_batch": 512, "lr": 3.3512714302789105e-05, "gradient_norm": 0.23639316856861115, "tokens_per_second": 1132761.4653031202, "synthetic": false, "world_size": 8} {"step": 62880, "tokens": 16483614720, "loss": 2.3466554641723634, "optimizer_updates": 32440, "effective_batch": 512, "lr": 3.347355028213001e-05, "gradient_norm": 0.28611502051353455, "tokens_per_second": 1132851.1401770823, "synthetic": false, "world_size": 8} {"step": 62900, "tokens": 16488857600, "loss": 2.3610151290893553, "optimizer_updates": 32450, "effective_batch": 512, "lr": 3.343443850606647e-05, "gradient_norm": 0.23932497203350067, "tokens_per_second": 1131664.6510779273, "synthetic": false, "world_size": 8} {"step": 62920, "tokens": 16494100480, "loss": 2.3528566360473633, "optimizer_updates": 32460, "effective_batch": 512, "lr": 3.339537900130004e-05, "gradient_norm": 0.27711302042007446, "tokens_per_second": 1132095.3304352167, "synthetic": false, "world_size": 8} {"step": 62940, "tokens": 16499343360, "loss": 2.3554182052612305, "optimizer_updates": 32470, "effective_batch": 512, "lr": 3.335637179449669e-05, "gradient_norm": 0.2635331451892853, "tokens_per_second": 1126602.220893855, "synthetic": false, "world_size": 8} {"step": 62960, "tokens": 16504586240, "loss": 2.3690816879272463, "optimizer_updates": 32480, "effective_batch": 512, "lr": 3.331741691228658e-05, "gradient_norm": 0.26821914315223694, "tokens_per_second": 1137925.3176252116, "synthetic": false, "world_size": 8} {"step": 62980, "tokens": 16509829120, "loss": 2.356826591491699, "optimizer_updates": 32490, "effective_batch": 512, "lr": 3.327851438126425e-05, "gradient_norm": 0.2873227596282959, "tokens_per_second": 1125618.0206573682, "synthetic": false, "world_size": 8} {"step": 63000, "tokens": 16515072000, "loss": 2.3552824020385743, "optimizer_updates": 32500, "effective_batch": 512, "lr": 3.323966422798843e-05, "gradient_norm": 0.2541930675506592, "tokens_per_second": 1017486.3826767853, "synthetic": false, "world_size": 8} {"step": 63020, "tokens": 16520314880, "loss": 2.3363554000854494, "optimizer_updates": 32510, "effective_batch": 512, "lr": 3.320086647898211e-05, "gradient_norm": 0.29926374554634094, "tokens_per_second": 773412.3870519224, "synthetic": false, "world_size": 8} {"step": 63040, "tokens": 16525557760, "loss": 2.3524959564208983, "optimizer_updates": 32520, "effective_batch": 512, "lr": 3.316212116073251e-05, "gradient_norm": 0.2592245638370514, "tokens_per_second": 1016047.131381573, "synthetic": false, "world_size": 8} {"step": 63060, "tokens": 16530800640, "loss": 2.368526840209961, "optimizer_updates": 32530, "effective_batch": 512, "lr": 3.312342829969106e-05, "gradient_norm": 0.26144298911094666, "tokens_per_second": 1134218.3824179892, "synthetic": false, "world_size": 8} {"step": 63080, "tokens": 16536043520, "loss": 2.347747802734375, "optimizer_updates": 32540, "effective_batch": 512, "lr": 3.3084787922273335e-05, "gradient_norm": 0.26033249497413635, "tokens_per_second": 1130338.4043093733, "synthetic": false, "world_size": 8} {"step": 63100, "tokens": 16541286400, "loss": 2.359730911254883, "optimizer_updates": 32550, "effective_batch": 512, "lr": 3.3046200054859155e-05, "gradient_norm": 0.24731415510177612, "tokens_per_second": 809933.9175974268, "synthetic": false, "world_size": 8} {"step": 63120, "tokens": 16546529280, "loss": 2.359696960449219, "optimizer_updates": 32560, "effective_batch": 512, "lr": 3.300766472379246e-05, "gradient_norm": 0.24030199646949768, "tokens_per_second": 1138880.5463448525, "synthetic": false, "world_size": 8} {"step": 63140, "tokens": 16551772160, "loss": 2.3471752166748048, "optimizer_updates": 32570, "effective_batch": 512, "lr": 3.296918195538128e-05, "gradient_norm": 0.2932949364185333, "tokens_per_second": 1129412.1090522828, "synthetic": false, "world_size": 8} {"step": 63160, "tokens": 16557015040, "loss": 2.360244369506836, "optimizer_updates": 32580, "effective_batch": 512, "lr": 3.293075177589782e-05, "gradient_norm": 0.25084924697875977, "tokens_per_second": 1118368.4021553863, "synthetic": false, "world_size": 8} {"step": 63180, "tokens": 16562257920, "loss": 2.3449470520019533, "optimizer_updates": 32590, "effective_batch": 512, "lr": 3.2892374211578347e-05, "gradient_norm": 0.2468901425600052, "tokens_per_second": 1137594.963209408, "synthetic": false, "world_size": 8} {"step": 63200, "tokens": 16567500800, "loss": 2.353071403503418, "optimizer_updates": 32600, "effective_batch": 512, "lr": 3.2854049288623226e-05, "gradient_norm": 0.24716341495513916, "tokens_per_second": 1135618.649319449, "synthetic": false, "world_size": 8} {"step": 63220, "tokens": 16572743680, "loss": 2.351640319824219, "optimizer_updates": 32610, "effective_batch": 512, "lr": 3.2815777033196836e-05, "gradient_norm": 0.2586217522621155, "tokens_per_second": 1126724.7069325356, "synthetic": false, "world_size": 8} {"step": 63240, "tokens": 16577986560, "loss": 2.3595027923583984, "optimizer_updates": 32620, "effective_batch": 512, "lr": 3.277755747142772e-05, "gradient_norm": 0.283883273601532, "tokens_per_second": 1133009.937952555, "synthetic": false, "world_size": 8} {"step": 63260, "tokens": 16583229440, "loss": 2.369454002380371, "optimizer_updates": 32630, "effective_batch": 512, "lr": 3.273939062940828e-05, "gradient_norm": 0.27392521500587463, "tokens_per_second": 1139671.8661564, "synthetic": false, "world_size": 8} {"step": 63280, "tokens": 16588472320, "loss": 2.3691032409667967, "optimizer_updates": 32640, "effective_batch": 512, "lr": 3.2701276533195076e-05, "gradient_norm": 0.2759593427181244, "tokens_per_second": 1132433.5258954554, "synthetic": false, "world_size": 8} {"step": 63300, "tokens": 16593715200, "loss": 2.3503849029541017, "optimizer_updates": 32650, "effective_batch": 512, "lr": 3.266321520880859e-05, "gradient_norm": 0.2712594270706177, "tokens_per_second": 1126594.8070242105, "synthetic": false, "world_size": 8} {"step": 63320, "tokens": 16598958080, "loss": 2.3580860137939452, "optimizer_updates": 32660, "effective_batch": 512, "lr": 3.2625206682233245e-05, "gradient_norm": 0.28948894143104553, "tokens_per_second": 1132685.0923659324, "synthetic": false, "world_size": 8} {"step": 63340, "tokens": 16604200960, "loss": 2.3727977752685545, "optimizer_updates": 32670, "effective_batch": 512, "lr": 3.258725097941747e-05, "gradient_norm": 0.2542662024497986, "tokens_per_second": 1133209.2603768818, "synthetic": false, "world_size": 8} {"step": 63360, "tokens": 16609443840, "loss": 2.3470180511474608, "optimizer_updates": 32680, "effective_batch": 512, "lr": 3.2549348126273634e-05, "gradient_norm": 0.2424449473619461, "tokens_per_second": 1136925.5812431676, "synthetic": false, "world_size": 8} {"step": 63380, "tokens": 16614686720, "loss": 2.3563510894775392, "optimizer_updates": 32690, "effective_batch": 512, "lr": 3.2511498148677996e-05, "gradient_norm": 0.2557517886161804, "tokens_per_second": 1134493.1547114456, "synthetic": false, "world_size": 8} {"step": 63400, "tokens": 16619929600, "loss": 2.3573318481445313, "optimizer_updates": 32700, "effective_batch": 512, "lr": 3.247370107247074e-05, "gradient_norm": 0.2710787355899811, "tokens_per_second": 1131588.5673583194, "synthetic": false, "world_size": 8} {"step": 63420, "tokens": 16625172480, "loss": 2.3491973876953125, "optimizer_updates": 32710, "effective_batch": 512, "lr": 3.24359569234559e-05, "gradient_norm": 0.23300719261169434, "tokens_per_second": 1129913.6652299627, "synthetic": false, "world_size": 8} {"step": 63440, "tokens": 16630415360, "loss": 2.354390335083008, "optimizer_updates": 32720, "effective_batch": 512, "lr": 3.239826572740144e-05, "gradient_norm": 0.24582229554653168, "tokens_per_second": 1134903.988329531, "synthetic": false, "world_size": 8} {"step": 63460, "tokens": 16635658240, "loss": 2.3534530639648437, "optimizer_updates": 32730, "effective_batch": 512, "lr": 3.236062751003909e-05, "gradient_norm": 0.24470172822475433, "tokens_per_second": 1126373.0032718445, "synthetic": false, "world_size": 8} {"step": 63480, "tokens": 16640901120, "loss": 2.3752363204956053, "optimizer_updates": 32740, "effective_batch": 512, "lr": 3.23230422970645e-05, "gradient_norm": 0.3119044005870819, "tokens_per_second": 1126255.4360069407, "synthetic": false, "world_size": 8} {"step": 63500, "tokens": 16646144000, "loss": 2.3495594024658204, "optimizer_updates": 32750, "effective_batch": 512, "lr": 3.228551011413704e-05, "gradient_norm": 0.23618999123573303, "tokens_per_second": 1132536.9967594563, "synthetic": false, "world_size": 8} {"step": 63520, "tokens": 16651386880, "loss": 2.352561187744141, "optimizer_updates": 32760, "effective_batch": 512, "lr": 3.224803098687998e-05, "gradient_norm": 0.24031659960746765, "tokens_per_second": 1129206.5593898578, "synthetic": false, "world_size": 8} {"step": 63540, "tokens": 16656629760, "loss": 2.3486942291259765, "optimizer_updates": 32770, "effective_batch": 512, "lr": 3.2210604940880265e-05, "gradient_norm": 0.24842029809951782, "tokens_per_second": 1132716.9694641584, "synthetic": false, "world_size": 8} {"step": 63560, "tokens": 16661872640, "loss": 2.3748662948608397, "optimizer_updates": 32780, "effective_batch": 512, "lr": 3.2173232001688665e-05, "gradient_norm": 0.27894818782806396, "tokens_per_second": 1135731.7092738254, "synthetic": false, "world_size": 8} {"step": 63580, "tokens": 16667115520, "loss": 2.361585998535156, "optimizer_updates": 32790, "effective_batch": 512, "lr": 3.213591219481972e-05, "gradient_norm": 0.27657586336135864, "tokens_per_second": 1131232.9612262666, "synthetic": false, "world_size": 8} {"step": 63600, "tokens": 16672358400, "loss": 2.356458282470703, "optimizer_updates": 32800, "effective_batch": 512, "lr": 3.209864554575158e-05, "gradient_norm": 0.27256548404693604, "tokens_per_second": 1128005.68607468, "synthetic": false, "world_size": 8} {"step": 63620, "tokens": 16677601280, "loss": 2.3501569747924806, "optimizer_updates": 32810, "effective_batch": 512, "lr": 3.206143207992627e-05, "gradient_norm": 0.2833265960216522, "tokens_per_second": 1137990.341929015, "synthetic": false, "world_size": 8} {"step": 63640, "tokens": 16682844160, "loss": 2.3589244842529298, "optimizer_updates": 32820, "effective_batch": 512, "lr": 3.2024271822749365e-05, "gradient_norm": 0.25383085012435913, "tokens_per_second": 1134339.0294948006, "synthetic": false, "world_size": 8} {"step": 63660, "tokens": 16688087040, "loss": 2.3470203399658205, "optimizer_updates": 32830, "effective_batch": 512, "lr": 3.198716479959017e-05, "gradient_norm": 0.25261056423187256, "tokens_per_second": 1125628.3533360509, "synthetic": false, "world_size": 8} {"step": 63680, "tokens": 16693329920, "loss": 2.364025115966797, "optimizer_updates": 32840, "effective_batch": 512, "lr": 3.195011103578162e-05, "gradient_norm": 0.24733148515224457, "tokens_per_second": 1130315.3746085514, "synthetic": false, "world_size": 8} {"step": 63700, "tokens": 16698572800, "loss": 2.366977882385254, "optimizer_updates": 32850, "effective_batch": 512, "lr": 3.191311055662038e-05, "gradient_norm": 0.24466098845005035, "tokens_per_second": 784374.2088141236, "synthetic": false, "world_size": 8} {"step": 63720, "tokens": 16703815680, "loss": 2.3596160888671873, "optimizer_updates": 32860, "effective_batch": 512, "lr": 3.1876163387366595e-05, "gradient_norm": 0.25858861207962036, "tokens_per_second": 1143190.7006572648, "synthetic": false, "world_size": 8} {"step": 63740, "tokens": 16709058560, "loss": 2.370985412597656, "optimizer_updates": 32870, "effective_batch": 512, "lr": 3.183926955324416e-05, "gradient_norm": 0.2456257939338684, "tokens_per_second": 1136911.406619625, "synthetic": false, "world_size": 8} {"step": 63760, "tokens": 16714301440, "loss": 2.354227066040039, "optimizer_updates": 32880, "effective_batch": 512, "lr": 3.180242907944044e-05, "gradient_norm": 0.24014243483543396, "tokens_per_second": 1136232.7928913105, "synthetic": false, "world_size": 8} {"step": 63780, "tokens": 16719544320, "loss": 2.3489667892456056, "optimizer_updates": 32890, "effective_batch": 512, "lr": 3.176564199110645e-05, "gradient_norm": 0.28608059883117676, "tokens_per_second": 1140241.8659250704, "synthetic": false, "world_size": 8} {"step": 63800, "tokens": 16724787200, "loss": 2.3622156143188477, "optimizer_updates": 32900, "effective_batch": 512, "lr": 3.172890831335672e-05, "gradient_norm": 0.3072498142719269, "tokens_per_second": 1133031.04234131, "synthetic": false, "world_size": 8} {"step": 63820, "tokens": 16730030080, "loss": 2.367590141296387, "optimizer_updates": 32910, "effective_batch": 512, "lr": 3.169222807126933e-05, "gradient_norm": 0.24075227975845337, "tokens_per_second": 1131454.1453749763, "synthetic": false, "world_size": 8} {"step": 63840, "tokens": 16735272960, "loss": 2.3549274444580077, "optimizer_updates": 32920, "effective_batch": 512, "lr": 3.165560128988585e-05, "gradient_norm": 0.2454550415277481, "tokens_per_second": 1137744.800225747, "synthetic": false, "world_size": 8} {"step": 63860, "tokens": 16740515840, "loss": 2.3607927322387696, "optimizer_updates": 32930, "effective_batch": 512, "lr": 3.161902799421143e-05, "gradient_norm": 0.23419828712940216, "tokens_per_second": 1134530.721530142, "synthetic": false, "world_size": 8} {"step": 63880, "tokens": 16745758720, "loss": 2.3496028900146486, "optimizer_updates": 32940, "effective_batch": 512, "lr": 3.1582508209214603e-05, "gradient_norm": 0.2402852326631546, "tokens_per_second": 1139694.4968448963, "synthetic": false, "world_size": 8} {"step": 63900, "tokens": 16751001600, "loss": 2.3520990371704102, "optimizer_updates": 32950, "effective_batch": 512, "lr": 3.154604195982746e-05, "gradient_norm": 0.26647472381591797, "tokens_per_second": 1130132.535665318, "synthetic": false, "world_size": 8} {"step": 63920, "tokens": 16756244480, "loss": 2.3655374526977537, "optimizer_updates": 32960, "effective_batch": 512, "lr": 3.150962927094545e-05, "gradient_norm": 0.2447792887687683, "tokens_per_second": 1132583.5392627036, "synthetic": false, "world_size": 8} {"step": 63940, "tokens": 16761487360, "loss": 2.3577959060668947, "optimizer_updates": 32970, "effective_batch": 512, "lr": 3.147327016742758e-05, "gradient_norm": 0.2268735021352768, "tokens_per_second": 1138657.8426731979, "synthetic": false, "world_size": 8} {"step": 63960, "tokens": 16766730240, "loss": 2.347540092468262, "optimizer_updates": 32980, "effective_batch": 512, "lr": 3.1436964674096174e-05, "gradient_norm": 0.22959566116333008, "tokens_per_second": 1134810.100614859, "synthetic": false, "world_size": 8} {"step": 63980, "tokens": 16771973120, "loss": 2.365486907958984, "optimizer_updates": 32990, "effective_batch": 512, "lr": 3.1400712815736955e-05, "gradient_norm": 0.24725009500980377, "tokens_per_second": 1020991.6994127425, "synthetic": false, "world_size": 8} {"step": 64000, "tokens": 16777216000, "loss": 2.349773979187012, "optimizer_updates": 33000, "effective_batch": 512, "lr": 3.1364514617099104e-05, "gradient_norm": 0.23097428679466248, "tokens_per_second": 1133404.091916663, "synthetic": false, "world_size": 8} {"step": 64020, "tokens": 16782458880, "loss": 2.353891372680664, "optimizer_updates": 33010, "effective_batch": 512, "lr": 3.13283701028951e-05, "gradient_norm": 0.2439245581626892, "tokens_per_second": 833983.7287910894, "synthetic": false, "world_size": 8} {"step": 64040, "tokens": 16787701760, "loss": 2.34979133605957, "optimizer_updates": 33020, "effective_batch": 512, "lr": 3.129227929780083e-05, "gradient_norm": 0.23866114020347595, "tokens_per_second": 1135682.1814314823, "synthetic": false, "world_size": 8} {"step": 64060, "tokens": 16792944640, "loss": 2.365696907043457, "optimizer_updates": 33030, "effective_batch": 512, "lr": 3.1256242226455426e-05, "gradient_norm": 0.3320052921772003, "tokens_per_second": 1133965.760905183, "synthetic": false, "world_size": 8} {"step": 64080, "tokens": 16798187520, "loss": 2.3461788177490233, "optimizer_updates": 33040, "effective_batch": 512, "lr": 3.122025891346145e-05, "gradient_norm": 0.2500464618206024, "tokens_per_second": 1127632.7949051268, "synthetic": false, "world_size": 8} {"step": 64100, "tokens": 16803430400, "loss": 2.3588230133056642, "optimizer_updates": 33050, "effective_batch": 512, "lr": 3.118432938338465e-05, "gradient_norm": 0.29211097955703735, "tokens_per_second": 1039471.6091215189, "synthetic": false, "world_size": 8} {"step": 64120, "tokens": 16808673280, "loss": 2.3544490814208983, "optimizer_updates": 33060, "effective_batch": 512, "lr": 3.1148453660754166e-05, "gradient_norm": 0.26170653104782104, "tokens_per_second": 1136708.9073075291, "synthetic": false, "world_size": 8} {"step": 64140, "tokens": 16813916160, "loss": 2.3576932907104493, "optimizer_updates": 33070, "effective_batch": 512, "lr": 3.11126317700623e-05, "gradient_norm": 0.2391243726015091, "tokens_per_second": 1134910.9324168882, "synthetic": false, "world_size": 8} {"step": 64160, "tokens": 16819159040, "loss": 2.353878211975098, "optimizer_updates": 33080, "effective_batch": 512, "lr": 3.107686373576469e-05, "gradient_norm": 0.2545938789844513, "tokens_per_second": 1135846.634173299, "synthetic": false, "world_size": 8} {"step": 64180, "tokens": 16824401920, "loss": 2.368617820739746, "optimizer_updates": 33090, "effective_batch": 512, "lr": 3.104114958228013e-05, "gradient_norm": 0.23859240114688873, "tokens_per_second": 1141890.5058264423, "synthetic": false, "world_size": 8} {"step": 64200, "tokens": 16829644800, "loss": 2.3660867691040037, "optimizer_updates": 33100, "effective_batch": 512, "lr": 3.100548933399071e-05, "gradient_norm": 0.23467426002025604, "tokens_per_second": 1139699.691848679, "synthetic": false, "world_size": 8} {"step": 64220, "tokens": 16834887680, "loss": 2.3527666091918946, "optimizer_updates": 33110, "effective_batch": 512, "lr": 3.0969883015241636e-05, "gradient_norm": 0.25710728764533997, "tokens_per_second": 1135464.643116865, "synthetic": false, "world_size": 8} {"step": 64240, "tokens": 16840130560, "loss": 2.3623769760131834, "optimizer_updates": 33120, "effective_batch": 512, "lr": 3.093433065034137e-05, "gradient_norm": 0.29150888323783875, "tokens_per_second": 1134807.2103200373, "synthetic": false, "world_size": 8} {"step": 64260, "tokens": 16845373440, "loss": 2.3721555709838866, "optimizer_updates": 33130, "effective_batch": 512, "lr": 3.0898832263561495e-05, "gradient_norm": 0.2269013226032257, "tokens_per_second": 1136686.514092127, "synthetic": false, "world_size": 8} {"step": 64280, "tokens": 16850616320, "loss": 2.3614734649658202, "optimizer_updates": 33140, "effective_batch": 512, "lr": 3.0863387879136734e-05, "gradient_norm": 0.2314392328262329, "tokens_per_second": 1129193.7592795542, "synthetic": false, "world_size": 8} {"step": 64300, "tokens": 16855859200, "loss": 2.3461397171020506, "optimizer_updates": 33150, "effective_batch": 512, "lr": 3.0827997521264966e-05, "gradient_norm": 0.2541503310203552, "tokens_per_second": 1131446.7041500797, "synthetic": false, "world_size": 8} {"step": 64320, "tokens": 16861102080, "loss": 2.3433210372924806, "optimizer_updates": 33160, "effective_batch": 512, "lr": 3.0792661214107216e-05, "gradient_norm": 0.24130673706531525, "tokens_per_second": 1131831.9161815082, "synthetic": false, "world_size": 8} {"step": 64340, "tokens": 16866344960, "loss": 2.3727304458618166, "optimizer_updates": 33170, "effective_batch": 512, "lr": 3.075737898178753e-05, "gradient_norm": 0.24999703466892242, "tokens_per_second": 1135068.6578355643, "synthetic": false, "world_size": 8} {"step": 64360, "tokens": 16871587840, "loss": 2.3633317947387695, "optimizer_updates": 33180, "effective_batch": 512, "lr": 3.072215084839314e-05, "gradient_norm": 0.24536404013633728, "tokens_per_second": 1141369.9168491536, "synthetic": false, "world_size": 8} {"step": 64380, "tokens": 16876830720, "loss": 2.3513364791870117, "optimizer_updates": 33190, "effective_batch": 512, "lr": 3.0686976837974215e-05, "gradient_norm": 0.24940891563892365, "tokens_per_second": 1134268.3519862946, "synthetic": false, "world_size": 8} {"step": 64400, "tokens": 16882073600, "loss": 2.3509159088134766, "optimizer_updates": 33200, "effective_batch": 512, "lr": 3.065185697454409e-05, "gradient_norm": 0.23988758027553558, "tokens_per_second": 1138082.2995245496, "synthetic": false, "world_size": 8} {"step": 64420, "tokens": 16887316480, "loss": 2.339894485473633, "optimizer_updates": 33210, "effective_batch": 512, "lr": 3.061679128207912e-05, "gradient_norm": 0.2748103439807892, "tokens_per_second": 1140294.7319127186, "synthetic": false, "world_size": 8} {"step": 64440, "tokens": 16892559360, "loss": 2.359397125244141, "optimizer_updates": 33220, "effective_batch": 512, "lr": 3.0581779784518584e-05, "gradient_norm": 0.2481578141450882, "tokens_per_second": 1135451.875105108, "synthetic": false, "world_size": 8} {"step": 64460, "tokens": 16897802240, "loss": 2.366200637817383, "optimizer_updates": 33230, "effective_batch": 512, "lr": 3.0546822505764874e-05, "gradient_norm": 0.2348499596118927, "tokens_per_second": 1139255.2548708608, "synthetic": false, "world_size": 8} {"step": 64480, "tokens": 16903045120, "loss": 2.349355697631836, "optimizer_updates": 33240, "effective_batch": 512, "lr": 3.051191946968328e-05, "gradient_norm": 0.24870769679546356, "tokens_per_second": 1133555.0747855694, "synthetic": false, "world_size": 8} {"step": 64500, "tokens": 16908288000, "loss": 2.3556840896606444, "optimizer_updates": 33250, "effective_batch": 512, "lr": 3.0477070700102138e-05, "gradient_norm": 0.26070013642311096, "tokens_per_second": 1144117.2737380783, "synthetic": false, "world_size": 8} {"step": 64520, "tokens": 16913530880, "loss": 2.359885406494141, "optimizer_updates": 33260, "effective_batch": 512, "lr": 3.0442276220812666e-05, "gradient_norm": 0.24330131709575653, "tokens_per_second": 1134705.928392997, "synthetic": false, "world_size": 8} {"step": 64540, "tokens": 16918773760, "loss": 2.358871078491211, "optimizer_updates": 33270, "effective_batch": 512, "lr": 3.0407536055569076e-05, "gradient_norm": 0.24994519352912903, "tokens_per_second": 1137208.0432035986, "synthetic": false, "world_size": 8} {"step": 64560, "tokens": 16924016640, "loss": 2.3530157089233397, "optimizer_updates": 33280, "effective_batch": 512, "lr": 3.0372850228088468e-05, "gradient_norm": 0.2727685570716858, "tokens_per_second": 1137614.6130257545, "synthetic": false, "world_size": 8} {"step": 64580, "tokens": 16929259520, "loss": 2.3489227294921875, "optimizer_updates": 33290, "effective_batch": 512, "lr": 3.033821876205082e-05, "gradient_norm": 0.2871018946170807, "tokens_per_second": 1138808.4453991877, "synthetic": false, "world_size": 8} {"step": 64600, "tokens": 16934502400, "loss": 2.355984115600586, "optimizer_updates": 33300, "effective_batch": 512, "lr": 3.030364168109907e-05, "gradient_norm": 0.25062066316604614, "tokens_per_second": 1141151.0870036632, "synthetic": false, "world_size": 8} {"step": 64620, "tokens": 16939745280, "loss": 2.366621398925781, "optimizer_updates": 33310, "effective_batch": 512, "lr": 3.0269119008838975e-05, "gradient_norm": 0.31547391414642334, "tokens_per_second": 1137702.3062451922, "synthetic": false, "world_size": 8} {"step": 64640, "tokens": 16944988160, "loss": 2.3556650161743162, "optimizer_updates": 33320, "effective_batch": 512, "lr": 3.0234650768839128e-05, "gradient_norm": 0.2676416337490082, "tokens_per_second": 1135157.228407377, "synthetic": false, "world_size": 8} {"step": 64660, "tokens": 16950231040, "loss": 2.362099456787109, "optimizer_updates": 33330, "effective_batch": 512, "lr": 3.020023698463104e-05, "gradient_norm": 0.28717026114463806, "tokens_per_second": 1138995.8943277295, "synthetic": false, "world_size": 8} {"step": 64680, "tokens": 16955473920, "loss": 2.353438949584961, "optimizer_updates": 33340, "effective_batch": 512, "lr": 3.016587767970894e-05, "gradient_norm": 0.25108638405799866, "tokens_per_second": 1123805.224286589, "synthetic": false, "world_size": 8} {"step": 64700, "tokens": 16960716800, "loss": 2.3710765838623047, "optimizer_updates": 33350, "effective_batch": 512, "lr": 3.013157287752998e-05, "gradient_norm": 0.28017428517341614, "tokens_per_second": 1138894.6401910959, "synthetic": false, "world_size": 8} {"step": 64720, "tokens": 16965959680, "loss": 2.3589181900024414, "optimizer_updates": 33360, "effective_batch": 512, "lr": 3.0097322601513997e-05, "gradient_norm": 0.2665271759033203, "tokens_per_second": 1141101.0056382322, "synthetic": false, "world_size": 8} {"step": 64740, "tokens": 16971202560, "loss": 2.3623559951782225, "optimizer_updates": 33370, "effective_batch": 512, "lr": 3.006312687504368e-05, "gradient_norm": 0.2732604742050171, "tokens_per_second": 1125225.2662756245, "synthetic": false, "world_size": 8} {"step": 64760, "tokens": 16976445440, "loss": 2.3651145935058593, "optimizer_updates": 33380, "effective_batch": 512, "lr": 3.002898572146441e-05, "gradient_norm": 0.2576557695865631, "tokens_per_second": 1125457.7442913856, "synthetic": false, "world_size": 8} {"step": 64780, "tokens": 16981688320, "loss": 2.359239196777344, "optimizer_updates": 33390, "effective_batch": 512, "lr": 2.9994899164084397e-05, "gradient_norm": 0.24483409523963928, "tokens_per_second": 1125586.4099227153, "synthetic": false, "world_size": 8} {"step": 64800, "tokens": 16986931200, "loss": 2.350599670410156, "optimizer_updates": 33400, "effective_batch": 512, "lr": 2.9960867226174476e-05, "gradient_norm": 0.23214414715766907, "tokens_per_second": 1020377.1269150403, "synthetic": false, "world_size": 8} {"step": 64820, "tokens": 16992174080, "loss": 2.3582698822021486, "optimizer_updates": 33410, "effective_batch": 512, "lr": 2.9926889930968298e-05, "gradient_norm": 0.2325051724910736, "tokens_per_second": 1137603.3563603081, "synthetic": false, "world_size": 8} {"step": 64840, "tokens": 16997416960, "loss": 2.35974063873291, "optimizer_updates": 33420, "effective_batch": 512, "lr": 2.9892967301662107e-05, "gradient_norm": 0.2613571286201477, "tokens_per_second": 1135695.5431056186, "synthetic": false, "world_size": 8} {"step": 64860, "tokens": 17002659840, "loss": 2.3526889801025392, "optimizer_updates": 33430, "effective_batch": 512, "lr": 2.98590993614149e-05, "gradient_norm": 0.24856498837471008, "tokens_per_second": 1140640.807969716, "synthetic": false, "world_size": 8} {"step": 64880, "tokens": 17007902720, "loss": 2.3643281936645506, "optimizer_updates": 33440, "effective_batch": 512, "lr": 2.9825286133348335e-05, "gradient_norm": 0.2343108355998993, "tokens_per_second": 1136759.8423882995, "synthetic": false, "world_size": 8} {"step": 64900, "tokens": 17013145600, "loss": 2.369586944580078, "optimizer_updates": 33450, "effective_batch": 512, "lr": 2.9791527640546672e-05, "gradient_norm": 0.3005247712135315, "tokens_per_second": 1136017.4155169267, "synthetic": false, "world_size": 8} {"step": 64920, "tokens": 17018388480, "loss": 2.3623138427734376, "optimizer_updates": 33460, "effective_batch": 512, "lr": 2.9757823906056844e-05, "gradient_norm": 0.24998217821121216, "tokens_per_second": 1131083.281193581, "synthetic": false, "world_size": 8} {"step": 64940, "tokens": 17023631360, "loss": 2.345417785644531, "optimizer_updates": 33470, "effective_batch": 512, "lr": 2.9724174952888353e-05, "gradient_norm": 0.24304978549480438, "tokens_per_second": 1137058.4745563902, "synthetic": false, "world_size": 8} {"step": 64960, "tokens": 17028874240, "loss": 2.3571378707885744, "optimizer_updates": 33480, "effective_batch": 512, "lr": 2.969058080401338e-05, "gradient_norm": 0.2705554664134979, "tokens_per_second": 1128252.0786527845, "synthetic": false, "world_size": 8} {"step": 64980, "tokens": 17034117120, "loss": 2.353814697265625, "optimizer_updates": 33490, "effective_batch": 512, "lr": 2.9657041482366598e-05, "gradient_norm": 0.2545709013938904, "tokens_per_second": 1140418.1876663137, "synthetic": false, "world_size": 8} {"step": 65000, "tokens": 17039360000, "loss": 2.346798324584961, "optimizer_updates": 33500, "effective_batch": 512, "lr": 2.9623557010845343e-05, "gradient_norm": 0.2487606257200241, "tokens_per_second": 1125164.3750482998, "synthetic": false, "world_size": 8} {"step": 65020, "tokens": 17044602880, "loss": 2.347248840332031, "optimizer_updates": 33510, "effective_batch": 512, "lr": 2.9590127412309422e-05, "gradient_norm": 0.24271224439144135, "tokens_per_second": 831749.5014559537, "synthetic": false, "world_size": 8} {"step": 65040, "tokens": 17049845760, "loss": 2.3554201126098633, "optimizer_updates": 33520, "effective_batch": 512, "lr": 2.955675270958124e-05, "gradient_norm": 0.31862133741378784, "tokens_per_second": 1140663.9327883986, "synthetic": false, "world_size": 8} {"step": 65060, "tokens": 17055088640, "loss": 2.353692054748535, "optimizer_updates": 33530, "effective_batch": 512, "lr": 2.9523432925445684e-05, "gradient_norm": 0.25408145785331726, "tokens_per_second": 1138746.7343518343, "synthetic": false, "world_size": 8} {"step": 65080, "tokens": 17060331520, "loss": 2.3509191513061523, "optimizer_updates": 33540, "effective_batch": 512, "lr": 2.9490168082650192e-05, "gradient_norm": 0.23555348813533783, "tokens_per_second": 1142446.498950156, "synthetic": false, "world_size": 8} {"step": 65100, "tokens": 17065574400, "loss": 2.356960678100586, "optimizer_updates": 33550, "effective_batch": 512, "lr": 2.945695820390462e-05, "gradient_norm": 0.30456939339637756, "tokens_per_second": 1133930.160812142, "synthetic": false, "world_size": 8} {"step": 65120, "tokens": 17070817280, "loss": 2.3477569580078126, "optimizer_updates": 33560, "effective_batch": 512, "lr": 2.942380331188141e-05, "gradient_norm": 0.26361459493637085, "tokens_per_second": 1140997.9391499534, "synthetic": false, "world_size": 8} {"step": 65140, "tokens": 17076060160, "loss": 2.353947067260742, "optimizer_updates": 33570, "effective_batch": 512, "lr": 2.9390703429215343e-05, "gradient_norm": 0.31106388568878174, "tokens_per_second": 1133642.060368956, "synthetic": false, "world_size": 8} {"step": 65160, "tokens": 17081303040, "loss": 2.3647104263305665, "optimizer_updates": 33580, "effective_batch": 512, "lr": 2.9357658578503754e-05, "gradient_norm": 0.2562512159347534, "tokens_per_second": 1135991.9478953157, "synthetic": false, "world_size": 8} {"step": 65180, "tokens": 17086545920, "loss": 2.3605571746826173, "optimizer_updates": 33590, "effective_batch": 512, "lr": 2.9324668782306308e-05, "gradient_norm": 0.2336219996213913, "tokens_per_second": 1142793.1370253987, "synthetic": false, "world_size": 8} {"step": 65200, "tokens": 17091788800, "loss": 2.353169822692871, "optimizer_updates": 33600, "effective_batch": 512, "lr": 2.9291734063145177e-05, "gradient_norm": 0.3410913646221161, "tokens_per_second": 1129090.1448368647, "synthetic": false, "world_size": 8} {"step": 65220, "tokens": 17097031680, "loss": 2.3575132369995115, "optimizer_updates": 33610, "effective_batch": 512, "lr": 2.9258854443504872e-05, "gradient_norm": 0.2486385554075241, "tokens_per_second": 789715.2544304187, "synthetic": false, "world_size": 8} {"step": 65240, "tokens": 17102274560, "loss": 2.3475488662719726, "optimizer_updates": 33620, "effective_batch": 512, "lr": 2.9226029945832307e-05, "gradient_norm": 0.252173513174057, "tokens_per_second": 1138804.6592891745, "synthetic": false, "world_size": 8} {"step": 65260, "tokens": 17107517440, "loss": 2.3630929946899415, "optimizer_updates": 33630, "effective_batch": 512, "lr": 2.9193260592536736e-05, "gradient_norm": 0.2587273418903351, "tokens_per_second": 1135953.4176253616, "synthetic": false, "world_size": 8} {"step": 65280, "tokens": 17112760320, "loss": 2.3523538589477537, "optimizer_updates": 33640, "effective_batch": 512, "lr": 2.9160546405989816e-05, "gradient_norm": 0.2610393464565277, "tokens_per_second": 1131213.1463262807, "synthetic": false, "world_size": 8} {"step": 65300, "tokens": 17118003200, "loss": 2.3494937896728514, "optimizer_updates": 33650, "effective_batch": 512, "lr": 2.9127887408525526e-05, "gradient_norm": 0.24265015125274658, "tokens_per_second": 1133702.4564998706, "synthetic": false, "world_size": 8} {"step": 65320, "tokens": 17123246080, "loss": 2.35971736907959, "optimizer_updates": 33660, "effective_batch": 512, "lr": 2.9095283622440134e-05, "gradient_norm": 0.2881544232368469, "tokens_per_second": 1134946.1246249152, "synthetic": false, "world_size": 8} {"step": 65340, "tokens": 17128488960, "loss": 2.3582342147827147, "optimizer_updates": 33670, "effective_batch": 512, "lr": 2.906273506999227e-05, "gradient_norm": 0.23989415168762207, "tokens_per_second": 755899.147095903, "synthetic": false, "world_size": 8} {"step": 65360, "tokens": 17133731840, "loss": 2.354802703857422, "optimizer_updates": 33680, "effective_batch": 512, "lr": 2.9030241773402783e-05, "gradient_norm": 0.2684237062931061, "tokens_per_second": 1136078.573310559, "synthetic": false, "world_size": 8} {"step": 65380, "tokens": 17138974720, "loss": 2.3532682418823243, "optimizer_updates": 33690, "effective_batch": 512, "lr": 2.8997803754854892e-05, "gradient_norm": 0.2743494212627411, "tokens_per_second": 1143553.7059793978, "synthetic": false, "world_size": 8} {"step": 65400, "tokens": 17144217600, "loss": 2.351506805419922, "optimizer_updates": 33700, "effective_batch": 512, "lr": 2.896542103649399e-05, "gradient_norm": 0.23569577932357788, "tokens_per_second": 1138389.1609513487, "synthetic": false, "world_size": 8} {"step": 65420, "tokens": 17149460480, "loss": 2.35904598236084, "optimizer_updates": 33710, "effective_batch": 512, "lr": 2.893309364042777e-05, "gradient_norm": 0.266384482383728, "tokens_per_second": 777127.4226648826, "synthetic": false, "world_size": 8} {"step": 65440, "tokens": 17154703360, "loss": 2.3595056533813477, "optimizer_updates": 33720, "effective_batch": 512, "lr": 2.8900821588726127e-05, "gradient_norm": 0.27535566687583923, "tokens_per_second": 1139072.5851744327, "synthetic": false, "world_size": 8} {"step": 65460, "tokens": 17159946240, "loss": 2.3562284469604493, "optimizer_updates": 33730, "effective_batch": 512, "lr": 2.886860490342122e-05, "gradient_norm": 0.23976103961467743, "tokens_per_second": 1138573.1385549686, "synthetic": false, "world_size": 8} {"step": 65480, "tokens": 17165189120, "loss": 2.3578418731689452, "optimizer_updates": 33740, "effective_batch": 512, "lr": 2.8836443606507315e-05, "gradient_norm": 0.25666365027427673, "tokens_per_second": 1138114.3012341047, "synthetic": false, "world_size": 8} {"step": 65500, "tokens": 17170432000, "loss": 2.3400949478149413, "optimizer_updates": 33750, "effective_batch": 512, "lr": 2.8804337719940986e-05, "gradient_norm": 0.2690897285938263, "tokens_per_second": 1133004.4289022249, "synthetic": false, "world_size": 8} {"step": 65520, "tokens": 17175674880, "loss": 2.353855514526367, "optimizer_updates": 33760, "effective_batch": 512, "lr": 2.877228726564089e-05, "gradient_norm": 0.2686932682991028, "tokens_per_second": 1134244.6099977156, "synthetic": false, "world_size": 8} {"step": 65540, "tokens": 17180917760, "loss": 2.353413391113281, "optimizer_updates": 33770, "effective_batch": 512, "lr": 2.8740292265487876e-05, "gradient_norm": 0.28213009238243103, "tokens_per_second": 1138898.5763199585, "synthetic": false, "world_size": 8} {"step": 65560, "tokens": 17186160640, "loss": 2.371747589111328, "optimizer_updates": 33780, "effective_batch": 512, "lr": 2.8708352741324885e-05, "gradient_norm": 0.2833051085472107, "tokens_per_second": 1022657.6076906335, "synthetic": false, "world_size": 8} {"step": 65580, "tokens": 17191403520, "loss": 2.354194450378418, "optimizer_updates": 33790, "effective_batch": 512, "lr": 2.8676468714957083e-05, "gradient_norm": 0.29878750443458557, "tokens_per_second": 1136524.652549187, "synthetic": false, "world_size": 8} {"step": 65600, "tokens": 17196646400, "loss": 2.359078788757324, "optimizer_updates": 33800, "effective_batch": 512, "lr": 2.8644640208151648e-05, "gradient_norm": 0.28435787558555603, "tokens_per_second": 1138080.498294069, "synthetic": false, "world_size": 8} {"step": 65620, "tokens": 17201889280, "loss": 2.3634157180786133, "optimizer_updates": 33810, "effective_batch": 512, "lr": 2.861286724263794e-05, "gradient_norm": 0.2403898537158966, "tokens_per_second": 1138172.7850008705, "synthetic": false, "world_size": 8} {"step": 65640, "tokens": 17207132160, "loss": 2.3394603729248047, "optimizer_updates": 33820, "effective_batch": 512, "lr": 2.8581149840107295e-05, "gradient_norm": 0.23300832509994507, "tokens_per_second": 1130320.5980203073, "synthetic": false, "world_size": 8} {"step": 65660, "tokens": 17212375040, "loss": 2.3419729232788087, "optimizer_updates": 33830, "effective_batch": 512, "lr": 2.8549488022213245e-05, "gradient_norm": 0.24935176968574524, "tokens_per_second": 1137806.2631912376, "synthetic": false, "world_size": 8} {"step": 65680, "tokens": 17217617920, "loss": 2.3624359130859376, "optimizer_updates": 33840, "effective_batch": 512, "lr": 2.8517881810571257e-05, "gradient_norm": 0.3419133722782135, "tokens_per_second": 1149081.2274605606, "synthetic": false, "world_size": 8} {"step": 65700, "tokens": 17222860800, "loss": 2.3596641540527346, "optimizer_updates": 33850, "effective_batch": 512, "lr": 2.848633122675893e-05, "gradient_norm": 0.2608618438243866, "tokens_per_second": 1137943.3347057037, "synthetic": false, "world_size": 8} {"step": 65720, "tokens": 17228103680, "loss": 2.362277793884277, "optimizer_updates": 33860, "effective_batch": 512, "lr": 2.8454836292315796e-05, "gradient_norm": 0.24773110449314117, "tokens_per_second": 1135041.7942578045, "synthetic": false, "world_size": 8} {"step": 65740, "tokens": 17233346560, "loss": 2.3599878311157227, "optimizer_updates": 33870, "effective_batch": 512, "lr": 2.842339702874348e-05, "gradient_norm": 0.24392090737819672, "tokens_per_second": 1130046.0790168871, "synthetic": false, "world_size": 8} {"step": 65760, "tokens": 17238589440, "loss": 2.3717369079589843, "optimizer_updates": 33880, "effective_batch": 512, "lr": 2.8392013457505552e-05, "gradient_norm": 0.24443122744560242, "tokens_per_second": 1136604.3568553282, "synthetic": false, "world_size": 8} {"step": 65780, "tokens": 17243832320, "loss": 2.3560924530029297, "optimizer_updates": 33890, "effective_batch": 512, "lr": 2.8360685600027555e-05, "gradient_norm": 0.2321881353855133, "tokens_per_second": 1138592.1419722433, "synthetic": false, "world_size": 8} {"step": 65800, "tokens": 17249075200, "loss": 2.3582862854003905, "optimizer_updates": 33900, "effective_batch": 512, "lr": 2.8329413477697054e-05, "gradient_norm": 0.2509864568710327, "tokens_per_second": 1137321.8509210676, "synthetic": false, "world_size": 8} {"step": 65820, "tokens": 17254318080, "loss": 2.35540885925293, "optimizer_updates": 33910, "effective_batch": 512, "lr": 2.829819711186346e-05, "gradient_norm": 0.24651087820529938, "tokens_per_second": 1135731.4549110816, "synthetic": false, "world_size": 8} {"step": 65840, "tokens": 17259560960, "loss": 2.3541378021240233, "optimizer_updates": 33920, "effective_batch": 512, "lr": 2.8267036523838247e-05, "gradient_norm": 0.23506419360637665, "tokens_per_second": 1137363.5382763443, "synthetic": false, "world_size": 8} {"step": 65860, "tokens": 17264803840, "loss": 2.357447052001953, "optimizer_updates": 33930, "effective_batch": 512, "lr": 2.8235931734894703e-05, "gradient_norm": 0.2360331267118454, "tokens_per_second": 1128442.846477882, "synthetic": false, "world_size": 8} {"step": 65880, "tokens": 17270046720, "loss": 2.346537208557129, "optimizer_updates": 33940, "effective_batch": 512, "lr": 2.8204882766268074e-05, "gradient_norm": 0.23488813638687134, "tokens_per_second": 1136265.138611043, "synthetic": false, "world_size": 8} {"step": 65900, "tokens": 17275289600, "loss": 2.3630977630615235, "optimizer_updates": 33950, "effective_batch": 512, "lr": 2.817388963915547e-05, "gradient_norm": 0.24289828538894653, "tokens_per_second": 1141330.673060864, "synthetic": false, "world_size": 8} {"step": 65920, "tokens": 17280532480, "loss": 2.3483261108398437, "optimizer_updates": 33960, "effective_batch": 512, "lr": 2.8142952374715924e-05, "gradient_norm": 0.2590782344341278, "tokens_per_second": 1134804.6113605644, "synthetic": false, "world_size": 8} {"step": 65940, "tokens": 17285775360, "loss": 2.357529067993164, "optimizer_updates": 33970, "effective_batch": 512, "lr": 2.811207099407027e-05, "gradient_norm": 0.25517886877059937, "tokens_per_second": 1129853.7210781309, "synthetic": false, "world_size": 8} {"step": 65960, "tokens": 17291018240, "loss": 2.353466606140137, "optimizer_updates": 33980, "effective_batch": 512, "lr": 2.8081245518301244e-05, "gradient_norm": 0.25699684023857117, "tokens_per_second": 1136985.4558284336, "synthetic": false, "world_size": 8} {"step": 65980, "tokens": 17296261120, "loss": 2.349139404296875, "optimizer_updates": 33990, "effective_batch": 512, "lr": 2.8050475968453382e-05, "gradient_norm": 0.2480815201997757, "tokens_per_second": 1137525.940208372, "synthetic": false, "world_size": 8} {"step": 66000, "tokens": 17301504000, "loss": 2.366592597961426, "optimizer_updates": 34000, "effective_batch": 512, "lr": 2.8019762365533072e-05, "gradient_norm": 0.2601042091846466, "tokens_per_second": 1134976.670638919, "synthetic": false, "world_size": 8} {"step": 66020, "tokens": 17306746880, "loss": 2.356097412109375, "optimizer_updates": 34010, "effective_batch": 512, "lr": 2.7989104730508448e-05, "gradient_norm": 0.2675993740558624, "tokens_per_second": 835659.2440925173, "synthetic": false, "world_size": 8} {"step": 66040, "tokens": 17311989760, "loss": 2.3534969329833983, "optimizer_updates": 34020, "effective_batch": 512, "lr": 2.795850308430952e-05, "gradient_norm": 0.2455299198627472, "tokens_per_second": 1135370.2645597395, "synthetic": false, "world_size": 8} {"step": 66060, "tokens": 17317232640, "loss": 2.371485137939453, "optimizer_updates": 34030, "effective_batch": 512, "lr": 2.7927957447827976e-05, "gradient_norm": 0.2704758048057556, "tokens_per_second": 1139032.5066239983, "synthetic": false, "world_size": 8} {"step": 66080, "tokens": 17322475520, "loss": 2.3588912963867186, "optimizer_updates": 34040, "effective_batch": 512, "lr": 2.7897467841917364e-05, "gradient_norm": 0.25784674286842346, "tokens_per_second": 1140228.9592458166, "synthetic": false, "world_size": 8} {"step": 66100, "tokens": 17327718400, "loss": 2.359349250793457, "optimizer_updates": 34050, "effective_batch": 512, "lr": 2.7867034287392894e-05, "gradient_norm": 0.24602487683296204, "tokens_per_second": 799545.7555020634, "synthetic": false, "world_size": 8} {"step": 66120, "tokens": 17332961280, "loss": 2.364296531677246, "optimizer_updates": 34060, "effective_batch": 512, "lr": 2.783665680503159e-05, "gradient_norm": 0.25568079948425293, "tokens_per_second": 1124719.4664962008, "synthetic": false, "world_size": 8} {"step": 66140, "tokens": 17338204160, "loss": 2.3625246047973634, "optimizer_updates": 34070, "effective_batch": 512, "lr": 2.780633541557212e-05, "gradient_norm": 0.2753766179084778, "tokens_per_second": 1141542.0749366535, "synthetic": false, "world_size": 8} {"step": 66160, "tokens": 17343447040, "loss": 2.3634735107421876, "optimizer_updates": 34080, "effective_batch": 512, "lr": 2.777607013971491e-05, "gradient_norm": 0.26166918873786926, "tokens_per_second": 800922.4763086927, "synthetic": false, "world_size": 8} {"step": 66180, "tokens": 17348689920, "loss": 2.351387596130371, "optimizer_updates": 34090, "effective_batch": 512, "lr": 2.774586099812206e-05, "gradient_norm": 0.23086665570735931, "tokens_per_second": 1139561.1130100638, "synthetic": false, "world_size": 8} {"step": 66200, "tokens": 17353932800, "loss": 2.34906120300293, "optimizer_updates": 34100, "effective_batch": 512, "lr": 2.7715708011417318e-05, "gradient_norm": 0.24795658886432648, "tokens_per_second": 1141217.1442096445, "synthetic": false, "world_size": 8} {"step": 66220, "tokens": 17359175680, "loss": 2.3534414291381838, "optimizer_updates": 34110, "effective_batch": 512, "lr": 2.7685611200186162e-05, "gradient_norm": 0.25684306025505066, "tokens_per_second": 775418.3890780911, "synthetic": false, "world_size": 8} {"step": 66240, "tokens": 17364418560, "loss": 2.352364158630371, "optimizer_updates": 34120, "effective_batch": 512, "lr": 2.765557058497565e-05, "gradient_norm": 0.24612422287464142, "tokens_per_second": 1146771.0056031172, "synthetic": false, "world_size": 8} {"step": 66260, "tokens": 17369661440, "loss": 2.362991142272949, "optimizer_updates": 34130, "effective_batch": 512, "lr": 2.762558618629454e-05, "gradient_norm": 0.2432245910167694, "tokens_per_second": 1141712.786057746, "synthetic": false, "world_size": 8} {"step": 66280, "tokens": 17374904320, "loss": 2.3590728759765627, "optimizer_updates": 34140, "effective_batch": 512, "lr": 2.7595658024613137e-05, "gradient_norm": 0.2556389570236206, "tokens_per_second": 1135042.0655328135, "synthetic": false, "world_size": 8} {"step": 66300, "tokens": 17380147200, "loss": 2.35904541015625, "optimizer_updates": 34150, "effective_batch": 512, "lr": 2.7565786120363427e-05, "gradient_norm": 0.26991981267929077, "tokens_per_second": 1139999.1864437244, "synthetic": false, "world_size": 8} {"step": 66320, "tokens": 17385390080, "loss": 2.357868194580078, "optimizer_updates": 34160, "effective_batch": 512, "lr": 2.7535970493938918e-05, "gradient_norm": 0.251640260219574, "tokens_per_second": 1133565.365726671, "synthetic": false, "world_size": 8} {"step": 66340, "tokens": 17390632960, "loss": 2.3560459136962892, "optimizer_updates": 34170, "effective_batch": 512, "lr": 2.7506211165694774e-05, "gradient_norm": 0.24791190028190613, "tokens_per_second": 1138383.5584038957, "synthetic": false, "world_size": 8} {"step": 66360, "tokens": 17395875840, "loss": 2.350967216491699, "optimizer_updates": 34180, "effective_batch": 512, "lr": 2.7476508155947638e-05, "gradient_norm": 0.2687581479549408, "tokens_per_second": 1128217.6745018763, "synthetic": false, "world_size": 8} {"step": 66380, "tokens": 17401118720, "loss": 2.3672163009643556, "optimizer_updates": 34190, "effective_batch": 512, "lr": 2.744686148497581e-05, "gradient_norm": 0.3254271447658539, "tokens_per_second": 1135379.3381827255, "synthetic": false, "world_size": 8} {"step": 66400, "tokens": 17406361600, "loss": 2.3701141357421873, "optimizer_updates": 34200, "effective_batch": 512, "lr": 2.7417271173019002e-05, "gradient_norm": 0.2695757746696472, "tokens_per_second": 1136626.4144445919, "synthetic": false, "world_size": 8} {"step": 66420, "tokens": 17411604480, "loss": 2.358622360229492, "optimizer_updates": 34210, "effective_batch": 512, "lr": 2.738773724027857e-05, "gradient_norm": 0.2574211061000824, "tokens_per_second": 1131692.8827446047, "synthetic": false, "world_size": 8} {"step": 66440, "tokens": 17416847360, "loss": 2.364615631103516, "optimizer_updates": 34220, "effective_batch": 512, "lr": 2.7358259706917285e-05, "gradient_norm": 0.25185006856918335, "tokens_per_second": 1130687.6994587057, "synthetic": false, "world_size": 8} {"step": 66460, "tokens": 17422090240, "loss": 2.358747100830078, "optimizer_updates": 34230, "effective_batch": 512, "lr": 2.7328838593059492e-05, "gradient_norm": 0.23583157360553741, "tokens_per_second": 1142744.2763299493, "synthetic": false, "world_size": 8} {"step": 66480, "tokens": 17427333120, "loss": 2.3478288650512695, "optimizer_updates": 34240, "effective_batch": 512, "lr": 2.7299473918790957e-05, "gradient_norm": 0.27055421471595764, "tokens_per_second": 1132716.3366013647, "synthetic": false, "world_size": 8} {"step": 66500, "tokens": 17432576000, "loss": 2.3552520751953123, "optimizer_updates": 34250, "effective_batch": 512, "lr": 2.7270165704158953e-05, "gradient_norm": 0.2506599724292755, "tokens_per_second": 1134628.587089826, "synthetic": false, "world_size": 8} {"step": 66520, "tokens": 17437818880, "loss": 2.351283645629883, "optimizer_updates": 34260, "effective_batch": 512, "lr": 2.7240913969172155e-05, "gradient_norm": 0.23455260694026947, "tokens_per_second": 1142010.4312605404, "synthetic": false, "world_size": 8} {"step": 66540, "tokens": 17443061760, "loss": 2.379791259765625, "optimizer_updates": 34270, "effective_batch": 512, "lr": 2.7211718733800768e-05, "gradient_norm": 0.25521421432495117, "tokens_per_second": 1140980.3193707422, "synthetic": false, "world_size": 8} {"step": 66560, "tokens": 17448304640, "loss": 2.3573532104492188, "optimizer_updates": 34280, "effective_batch": 512, "lr": 2.7182580017976328e-05, "gradient_norm": 0.2412755787372589, "tokens_per_second": 1131438.7531898564, "synthetic": false, "world_size": 8} {"step": 66580, "tokens": 17453547520, "loss": 2.3566009521484377, "optimizer_updates": 34290, "effective_batch": 512, "lr": 2.715349784159187e-05, "gradient_norm": 0.2830544710159302, "tokens_per_second": 1127990.6430831323, "synthetic": false, "world_size": 8} {"step": 66600, "tokens": 17458790400, "loss": 2.347615432739258, "optimizer_updates": 34300, "effective_batch": 512, "lr": 2.712447222450179e-05, "gradient_norm": 0.2678607106208801, "tokens_per_second": 1138217.788387261, "synthetic": false, "world_size": 8} {"step": 66620, "tokens": 17464033280, "loss": 2.352359390258789, "optimizer_updates": 34310, "effective_batch": 512, "lr": 2.709550318652184e-05, "gradient_norm": 0.30980318784713745, "tokens_per_second": 1138105.4200017666, "synthetic": false, "world_size": 8} {"step": 66640, "tokens": 17469276160, "loss": 2.3529558181762695, "optimizer_updates": 34320, "effective_batch": 512, "lr": 2.7066590747429224e-05, "gradient_norm": 0.2720688283443451, "tokens_per_second": 1129445.701185537, "synthetic": false, "world_size": 8} {"step": 66660, "tokens": 17474519040, "loss": 2.3471454620361327, "optimizer_updates": 34330, "effective_batch": 512, "lr": 2.7037734926962405e-05, "gradient_norm": 0.25723788142204285, "tokens_per_second": 1138580.7947389637, "synthetic": false, "world_size": 8} {"step": 66680, "tokens": 17479761920, "loss": 2.3525875091552733, "optimizer_updates": 34340, "effective_batch": 512, "lr": 2.700893574482131e-05, "gradient_norm": 0.25158342719078064, "tokens_per_second": 1135957.535508425, "synthetic": false, "world_size": 8} {"step": 66700, "tokens": 17485004800, "loss": 2.343935012817383, "optimizer_updates": 34350, "effective_batch": 512, "lr": 2.6980193220667072e-05, "gradient_norm": 0.2841935455799103, "tokens_per_second": 1138879.861791622, "synthetic": false, "world_size": 8} {"step": 66720, "tokens": 17490247680, "loss": 2.366277313232422, "optimizer_updates": 34360, "effective_batch": 512, "lr": 2.6951507374122263e-05, "gradient_norm": 0.24294885993003845, "tokens_per_second": 1136621.2185620966, "synthetic": false, "world_size": 8} {"step": 66740, "tokens": 17495490560, "loss": 2.358712005615234, "optimizer_updates": 34370, "effective_batch": 512, "lr": 2.692287822477066e-05, "gradient_norm": 0.322192907333374, "tokens_per_second": 1133191.7431781958, "synthetic": false, "world_size": 8} {"step": 66760, "tokens": 17500733440, "loss": 2.3604507446289062, "optimizer_updates": 34380, "effective_batch": 512, "lr": 2.6894305792157418e-05, "gradient_norm": 0.2780277132987976, "tokens_per_second": 1137477.488906183, "synthetic": false, "world_size": 8} {"step": 66780, "tokens": 17505976320, "loss": 2.35601921081543, "optimizer_updates": 34390, "effective_batch": 512, "lr": 2.6865790095788915e-05, "gradient_norm": 0.28315305709838867, "tokens_per_second": 1140639.3793344975, "synthetic": false, "world_size": 8} {"step": 66800, "tokens": 17511219200, "loss": 2.3503746032714843, "optimizer_updates": 34400, "effective_batch": 512, "lr": 2.6837331155132813e-05, "gradient_norm": 0.23462218046188354, "tokens_per_second": 1129641.0704682271, "synthetic": false, "world_size": 8} {"step": 66820, "tokens": 17516462080, "loss": 2.3547197341918946, "optimizer_updates": 34410, "effective_batch": 512, "lr": 2.680892898961801e-05, "gradient_norm": 0.2461342215538025, "tokens_per_second": 1129081.8627383288, "synthetic": false, "world_size": 8} {"step": 66840, "tokens": 17521704960, "loss": 2.3511024475097657, "optimizer_updates": 34420, "effective_batch": 512, "lr": 2.6780583618634693e-05, "gradient_norm": 0.2498847246170044, "tokens_per_second": 1125669.8541729364, "synthetic": false, "world_size": 8} {"step": 66860, "tokens": 17526947840, "loss": 2.369615936279297, "optimizer_updates": 34430, "effective_batch": 512, "lr": 2.6752295061534207e-05, "gradient_norm": 0.24229806661605835, "tokens_per_second": 1138499.693337601, "synthetic": false, "world_size": 8} {"step": 66880, "tokens": 17532190720, "loss": 2.355280113220215, "optimizer_updates": 34440, "effective_batch": 512, "lr": 2.672406333762918e-05, "gradient_norm": 0.2277732640504837, "tokens_per_second": 1141358.1240895693, "synthetic": false, "world_size": 8} {"step": 66900, "tokens": 17537433600, "loss": 2.3556449890136717, "optimizer_updates": 34450, "effective_batch": 512, "lr": 2.669588846619337e-05, "gradient_norm": 0.25054842233657837, "tokens_per_second": 1127241.632008956, "synthetic": false, "world_size": 8} {"step": 66920, "tokens": 17542676480, "loss": 2.366511917114258, "optimizer_updates": 34460, "effective_batch": 512, "lr": 2.6667770466461803e-05, "gradient_norm": 0.24782821536064148, "tokens_per_second": 1137975.8848567298, "synthetic": false, "world_size": 8} {"step": 66940, "tokens": 17547919360, "loss": 2.3490215301513673, "optimizer_updates": 34470, "effective_batch": 512, "lr": 2.6639709357630585e-05, "gradient_norm": 0.2555323839187622, "tokens_per_second": 1121059.980290018, "synthetic": false, "world_size": 8} {"step": 66960, "tokens": 17553162240, "loss": 2.3611051559448244, "optimizer_updates": 34480, "effective_batch": 512, "lr": 2.6611705158857074e-05, "gradient_norm": 0.24661199748516083, "tokens_per_second": 1127425.2104721419, "synthetic": false, "world_size": 8} {"step": 66980, "tokens": 17558405120, "loss": 2.3565622329711915, "optimizer_updates": 34490, "effective_batch": 512, "lr": 2.6583757889259695e-05, "gradient_norm": 0.2563841640949249, "tokens_per_second": 1136653.5211363223, "synthetic": false, "world_size": 8} {"step": 67000, "tokens": 17563648000, "loss": 2.3516868591308593, "optimizer_updates": 34500, "effective_batch": 512, "lr": 2.6555867567918065e-05, "gradient_norm": 0.2596220374107361, "tokens_per_second": 1111784.008761903, "synthetic": false, "world_size": 8} {"step": 67020, "tokens": 17568890880, "loss": 2.370835876464844, "optimizer_updates": 34510, "effective_batch": 512, "lr": 2.65280342138729e-05, "gradient_norm": 0.2609586715698242, "tokens_per_second": 629163.4729755004, "synthetic": false, "world_size": 8} {"step": 67040, "tokens": 17574133760, "loss": 2.3555912017822265, "optimizer_updates": 34520, "effective_batch": 512, "lr": 2.650025784612601e-05, "gradient_norm": 0.2320816069841385, "tokens_per_second": 1131370.0203343602, "synthetic": false, "world_size": 8} {"step": 67060, "tokens": 17579376640, "loss": 2.3514551162719726, "optimizer_updates": 34530, "effective_batch": 512, "lr": 2.6472538483640355e-05, "gradient_norm": 0.26306039094924927, "tokens_per_second": 1134129.5812310332, "synthetic": false, "world_size": 8} {"step": 67080, "tokens": 17584619520, "loss": 2.363016891479492, "optimizer_updates": 34540, "effective_batch": 512, "lr": 2.6444876145339892e-05, "gradient_norm": 0.24818947911262512, "tokens_per_second": 1132875.4505212102, "synthetic": false, "world_size": 8} {"step": 67100, "tokens": 17589862400, "loss": 2.3553720474243165, "optimizer_updates": 34550, "effective_batch": 512, "lr": 2.6417270850109744e-05, "gradient_norm": 0.3085671365261078, "tokens_per_second": 1137988.9848834006, "synthetic": false, "world_size": 8} {"step": 67120, "tokens": 17595105280, "loss": 2.3431375503540037, "optimizer_updates": 34560, "effective_batch": 512, "lr": 2.6389722616796012e-05, "gradient_norm": 0.24023820459842682, "tokens_per_second": 1127650.3427107004, "synthetic": false, "world_size": 8} {"step": 67140, "tokens": 17600348160, "loss": 2.355897903442383, "optimizer_updates": 34570, "effective_batch": 512, "lr": 2.6362231464205878e-05, "gradient_norm": 0.275624543428421, "tokens_per_second": 1119168.8279823703, "synthetic": false, "world_size": 8} {"step": 67160, "tokens": 17605591040, "loss": 2.362270736694336, "optimizer_updates": 34580, "effective_batch": 512, "lr": 2.6334797411107525e-05, "gradient_norm": 0.231607124209404, "tokens_per_second": 1132815.4599828867, "synthetic": false, "world_size": 8} {"step": 67180, "tokens": 17610833920, "loss": 2.3760862350463867, "optimizer_updates": 34590, "effective_batch": 512, "lr": 2.6307420476230217e-05, "gradient_norm": 0.34128668904304504, "tokens_per_second": 1126606.1330220704, "synthetic": false, "world_size": 8} {"step": 67200, "tokens": 17616076800, "loss": 2.3507802963256834, "optimizer_updates": 34600, "effective_batch": 512, "lr": 2.6280100678264142e-05, "gradient_norm": 0.23918107151985168, "tokens_per_second": 1129774.9955068433, "synthetic": false, "world_size": 8} {"step": 67220, "tokens": 17621319680, "loss": 2.358721923828125, "optimizer_updates": 34610, "effective_batch": 512, "lr": 2.6252838035860567e-05, "gradient_norm": 0.29369044303894043, "tokens_per_second": 1143592.4981708443, "synthetic": false, "world_size": 8} {"step": 67240, "tokens": 17626562560, "loss": 2.3518310546875, "optimizer_updates": 34620, "effective_batch": 512, "lr": 2.622563256763165e-05, "gradient_norm": 0.2347618043422699, "tokens_per_second": 1127090.000582517, "synthetic": false, "world_size": 8} {"step": 67260, "tokens": 17631805440, "loss": 2.365434455871582, "optimizer_updates": 34630, "effective_batch": 512, "lr": 2.61984842921506e-05, "gradient_norm": 0.2785673439502716, "tokens_per_second": 1135721.943355697, "synthetic": false, "world_size": 8} {"step": 67280, "tokens": 17637048320, "loss": 2.3531988143920897, "optimizer_updates": 34640, "effective_batch": 512, "lr": 2.6171393227951503e-05, "gradient_norm": 0.24179470539093018, "tokens_per_second": 1128534.1094365893, "synthetic": false, "world_size": 8} {"step": 67300, "tokens": 17642291200, "loss": 2.359176254272461, "optimizer_updates": 34650, "effective_batch": 512, "lr": 2.6144359393529452e-05, "gradient_norm": 0.2436525523662567, "tokens_per_second": 1129088.83761024, "synthetic": false, "world_size": 8} {"step": 67320, "tokens": 17647534080, "loss": 2.3572790145874025, "optimizer_updates": 34660, "effective_batch": 512, "lr": 2.6117382807340423e-05, "gradient_norm": 0.23023341596126556, "tokens_per_second": 1131684.3261889673, "synthetic": false, "world_size": 8} {"step": 67340, "tokens": 17652776960, "loss": 2.349478530883789, "optimizer_updates": 34670, "effective_batch": 512, "lr": 2.609046348780135e-05, "gradient_norm": 0.29280799627304077, "tokens_per_second": 1131603.9780640842, "synthetic": false, "world_size": 8} {"step": 67360, "tokens": 17658019840, "loss": 2.3474681854248045, "optimizer_updates": 34680, "effective_batch": 512, "lr": 2.6063601453290015e-05, "gradient_norm": 0.24565716087818146, "tokens_per_second": 1127308.7445155573, "synthetic": false, "world_size": 8} {"step": 67380, "tokens": 17663262720, "loss": 2.3645349502563477, "optimizer_updates": 34690, "effective_batch": 512, "lr": 2.6036796722145166e-05, "gradient_norm": 0.24819160997867584, "tokens_per_second": 1128033.216075265, "synthetic": false, "world_size": 8} {"step": 67400, "tokens": 17668505600, "loss": 2.3513425827026366, "optimizer_updates": 34700, "effective_batch": 512, "lr": 2.6010049312666347e-05, "gradient_norm": 0.24190329015254974, "tokens_per_second": 1011974.2889305397, "synthetic": false, "world_size": 8} {"step": 67420, "tokens": 17673748480, "loss": 2.360202980041504, "optimizer_updates": 34710, "effective_batch": 512, "lr": 2.5983359243114045e-05, "gradient_norm": 0.25813162326812744, "tokens_per_second": 1133475.019263722, "synthetic": false, "world_size": 8} {"step": 67440, "tokens": 17678991360, "loss": 2.35849666595459, "optimizer_updates": 34720, "effective_batch": 512, "lr": 2.5956726531709557e-05, "gradient_norm": 0.2860909402370453, "tokens_per_second": 1132146.9615985672, "synthetic": false, "world_size": 8} {"step": 67460, "tokens": 17684234240, "loss": 2.3516746520996095, "optimizer_updates": 34730, "effective_batch": 512, "lr": 2.5930151196635013e-05, "gradient_norm": 0.25100821256637573, "tokens_per_second": 1131537.9043801052, "synthetic": false, "world_size": 8} {"step": 67480, "tokens": 17689477120, "loss": 2.3609031677246093, "optimizer_updates": 34740, "effective_batch": 512, "lr": 2.5903633256033405e-05, "gradient_norm": 0.24227842688560486, "tokens_per_second": 1130042.7920647007, "synthetic": false, "world_size": 8} {"step": 67500, "tokens": 17694720000, "loss": 2.3583133697509764, "optimizer_updates": 34750, "effective_batch": 512, "lr": 2.587717272800852e-05, "gradient_norm": 0.2945789694786072, "tokens_per_second": 1136492.065139951, "synthetic": false, "world_size": 8} {"step": 67520, "tokens": 17699962880, "loss": 2.3597333908081053, "optimizer_updates": 34760, "effective_batch": 512, "lr": 2.5850769630624976e-05, "gradient_norm": 0.24557532370090485, "tokens_per_second": 1129204.9763798479, "synthetic": false, "world_size": 8} {"step": 67540, "tokens": 17705205760, "loss": 2.356262969970703, "optimizer_updates": 34770, "effective_batch": 512, "lr": 2.582442398190813e-05, "gradient_norm": 0.24243579804897308, "tokens_per_second": 1130594.4890087987, "synthetic": false, "world_size": 8} {"step": 67560, "tokens": 17710448640, "loss": 2.3561824798583983, "optimizer_updates": 34780, "effective_batch": 512, "lr": 2.5798135799844195e-05, "gradient_norm": 0.24425345659255981, "tokens_per_second": 1127044.0715025035, "synthetic": false, "world_size": 8} {"step": 67580, "tokens": 17715691520, "loss": 2.3412044525146483, "optimizer_updates": 34790, "effective_batch": 512, "lr": 2.5771905102380063e-05, "gradient_norm": 0.25237810611724854, "tokens_per_second": 1014376.5798542636, "synthetic": false, "world_size": 8} {"step": 67600, "tokens": 17720934400, "loss": 2.3527528762817385, "optimizer_updates": 34800, "effective_batch": 512, "lr": 2.5745731907423467e-05, "gradient_norm": 0.22984132170677185, "tokens_per_second": 1133039.6866041897, "synthetic": false, "world_size": 8} {"step": 67620, "tokens": 17726177280, "loss": 2.3560054779052733, "optimizer_updates": 34810, "effective_batch": 512, "lr": 2.5719616232842802e-05, "gradient_norm": 0.269339919090271, "tokens_per_second": 1139522.8199960818, "synthetic": false, "world_size": 8} {"step": 67640, "tokens": 17731420160, "loss": 2.3685121536254883, "optimizer_updates": 34820, "effective_batch": 512, "lr": 2.5693558096467277e-05, "gradient_norm": 0.240643709897995, "tokens_per_second": 1130590.840479178, "synthetic": false, "world_size": 8} {"step": 67660, "tokens": 17736663040, "loss": 2.36721134185791, "optimizer_updates": 34830, "effective_batch": 512, "lr": 2.5667557516086753e-05, "gradient_norm": 0.3092668354511261, "tokens_per_second": 1139599.792557753, "synthetic": false, "world_size": 8} {"step": 67680, "tokens": 17741905920, "loss": 2.3688446044921876, "optimizer_updates": 34840, "effective_batch": 512, "lr": 2.5641614509451842e-05, "gradient_norm": 0.23854440450668335, "tokens_per_second": 1134831.5853018758, "synthetic": false, "world_size": 8} {"step": 67700, "tokens": 17747148800, "loss": 2.363008499145508, "optimizer_updates": 34850, "effective_batch": 512, "lr": 2.561572909427379e-05, "gradient_norm": 0.2516615390777588, "tokens_per_second": 1135521.5046864457, "synthetic": false, "world_size": 8} {"step": 67720, "tokens": 17752391680, "loss": 2.3725044250488283, "optimizer_updates": 34860, "effective_batch": 512, "lr": 2.5589901288224617e-05, "gradient_norm": 0.22962868213653564, "tokens_per_second": 1143709.3403578491, "synthetic": false, "world_size": 8} {"step": 67740, "tokens": 17757634560, "loss": 2.351059341430664, "optimizer_updates": 34870, "effective_batch": 512, "lr": 2.556413110893694e-05, "gradient_norm": 0.23870635032653809, "tokens_per_second": 1135537.728266091, "synthetic": false, "world_size": 8} {"step": 67760, "tokens": 17762877440, "loss": 2.3647539138793947, "optimizer_updates": 34880, "effective_batch": 512, "lr": 2.553841857400406e-05, "gradient_norm": 0.25581806898117065, "tokens_per_second": 1131312.1427963541, "synthetic": false, "world_size": 8} {"step": 67780, "tokens": 17768120320, "loss": 2.36539249420166, "optimizer_updates": 34890, "effective_batch": 512, "lr": 2.5512763700979886e-05, "gradient_norm": 0.2299165427684784, "tokens_per_second": 1132209.7754950367, "synthetic": false, "world_size": 8} {"step": 67800, "tokens": 17773363200, "loss": 2.357697296142578, "optimizer_updates": 34900, "effective_batch": 512, "lr": 2.5487166507379053e-05, "gradient_norm": 0.25567489862442017, "tokens_per_second": 835902.4549509153, "synthetic": false, "world_size": 8} {"step": 67820, "tokens": 17778606080, "loss": 2.352281951904297, "optimizer_updates": 34910, "effective_batch": 512, "lr": 2.5461627010676716e-05, "gradient_norm": 0.22966012358665466, "tokens_per_second": 1134674.152659658, "synthetic": false, "world_size": 8} {"step": 67840, "tokens": 17783848960, "loss": 2.368825912475586, "optimizer_updates": 34920, "effective_batch": 512, "lr": 2.5436145228308713e-05, "gradient_norm": 0.24335941672325134, "tokens_per_second": 1139837.7788009676, "synthetic": false, "world_size": 8} {"step": 67860, "tokens": 17789091840, "loss": 2.3546541213989256, "optimizer_updates": 34930, "effective_batch": 512, "lr": 2.5410721177671433e-05, "gradient_norm": 0.2636016309261322, "tokens_per_second": 1139614.8255084804, "synthetic": false, "world_size": 8} {"step": 67880, "tokens": 17794334720, "loss": 2.3627250671386717, "optimizer_updates": 34940, "effective_batch": 512, "lr": 2.5385354876121878e-05, "gradient_norm": 0.2490234225988388, "tokens_per_second": 1132174.5650117428, "synthetic": false, "world_size": 8} {"step": 67900, "tokens": 17799577600, "loss": 2.358641242980957, "optimizer_updates": 34950, "effective_batch": 512, "lr": 2.536004634097764e-05, "gradient_norm": 0.26288557052612305, "tokens_per_second": 1141572.1055517916, "synthetic": false, "world_size": 8} {"step": 67920, "tokens": 17804820480, "loss": 2.3518871307373046, "optimizer_updates": 34960, "effective_batch": 512, "lr": 2.533479558951682e-05, "gradient_norm": 0.24084711074829102, "tokens_per_second": 1137353.6877763271, "synthetic": false, "world_size": 8} {"step": 67940, "tokens": 17810063360, "loss": 2.3627309799194336, "optimizer_updates": 34970, "effective_batch": 512, "lr": 2.530960263897812e-05, "gradient_norm": 0.22590026259422302, "tokens_per_second": 1128038.3953599588, "synthetic": false, "world_size": 8} {"step": 67960, "tokens": 17815306240, "loss": 2.354705810546875, "optimizer_updates": 34980, "effective_batch": 512, "lr": 2.528446750656076e-05, "gradient_norm": 0.25021499395370483, "tokens_per_second": 1132494.62499608, "synthetic": false, "world_size": 8} {"step": 67980, "tokens": 17820549120, "loss": 2.3662225723266603, "optimizer_updates": 34990, "effective_batch": 512, "lr": 2.5259390209424495e-05, "gradient_norm": 0.27431732416152954, "tokens_per_second": 1132831.495939568, "synthetic": false, "world_size": 8} {"step": 68000, "tokens": 17825792000, "loss": 2.3652873992919923, "optimizer_updates": 35000, "effective_batch": 512, "lr": 2.523437076468958e-05, "gradient_norm": 0.24786819517612457, "tokens_per_second": 1135294.5073204197, "synthetic": false, "world_size": 8} {"step": 68020, "tokens": 17831034880, "loss": 2.353159713745117, "optimizer_updates": 35010, "effective_batch": 512, "lr": 2.52094091894368e-05, "gradient_norm": 0.23089560866355896, "tokens_per_second": 835013.4055836212, "synthetic": false, "world_size": 8} {"step": 68040, "tokens": 17836277760, "loss": 2.3654449462890623, "optimizer_updates": 35020, "effective_batch": 512, "lr": 2.5184505500707412e-05, "gradient_norm": 0.24391575157642365, "tokens_per_second": 1137858.7628138664, "synthetic": false, "world_size": 8} {"step": 68060, "tokens": 17841520640, "loss": 2.3645071029663085, "optimizer_updates": 35030, "effective_batch": 512, "lr": 2.5159659715503154e-05, "gradient_norm": 0.24768774211406708, "tokens_per_second": 1123051.840944517, "synthetic": false, "world_size": 8} {"step": 68080, "tokens": 17846763520, "loss": 2.3425086975097655, "optimizer_updates": 35040, "effective_batch": 512, "lr": 2.5134871850786258e-05, "gradient_norm": 0.23749318718910217, "tokens_per_second": 1014910.0630823225, "synthetic": false, "world_size": 8} {"step": 68100, "tokens": 17852006400, "loss": 2.3615385055541993, "optimizer_updates": 35050, "effective_batch": 512, "lr": 2.5110141923479386e-05, "gradient_norm": 0.29955682158470154, "tokens_per_second": 1139059.282751594, "synthetic": false, "world_size": 8} {"step": 68120, "tokens": 17857249280, "loss": 2.3607112884521486, "optimizer_updates": 35060, "effective_batch": 512, "lr": 2.5085469950465635e-05, "gradient_norm": 0.25567689538002014, "tokens_per_second": 1133052.599026899, "synthetic": false, "world_size": 8} {"step": 68140, "tokens": 17862492160, "loss": 2.358933448791504, "optimizer_updates": 35070, "effective_batch": 512, "lr": 2.5060855948588595e-05, "gradient_norm": 0.24540701508522034, "tokens_per_second": 1139087.8603178107, "synthetic": false, "world_size": 8} {"step": 68160, "tokens": 17867735040, "loss": 2.3681594848632814, "optimizer_updates": 35080, "effective_batch": 512, "lr": 2.5036299934652204e-05, "gradient_norm": 0.2551150321960449, "tokens_per_second": 1131346.7054407564, "synthetic": false, "world_size": 8} {"step": 68180, "tokens": 17872977920, "loss": 2.360224151611328, "optimizer_updates": 35090, "effective_batch": 512, "lr": 2.5011801925420875e-05, "gradient_norm": 0.2630916237831116, "tokens_per_second": 1123343.5912584541, "synthetic": false, "world_size": 8} {"step": 68200, "tokens": 17878220800, "loss": 2.3572341918945314, "optimizer_updates": 35100, "effective_batch": 512, "lr": 2.4987361937619385e-05, "gradient_norm": 0.2699906527996063, "tokens_per_second": 1134809.242171912, "synthetic": false, "world_size": 8} {"step": 68220, "tokens": 17883463680, "loss": 2.3602434158325196, "optimizer_updates": 35110, "effective_batch": 512, "lr": 2.4962979987932918e-05, "gradient_norm": 0.23600444197654724, "tokens_per_second": 1137423.223356045, "synthetic": false, "world_size": 8} {"step": 68240, "tokens": 17888706560, "loss": 2.345738410949707, "optimizer_updates": 35120, "effective_batch": 512, "lr": 2.493865609300701e-05, "gradient_norm": 0.28179141879081726, "tokens_per_second": 1136587.9349794828, "synthetic": false, "world_size": 8} {"step": 68260, "tokens": 17893949440, "loss": 2.355602264404297, "optimizer_updates": 35130, "effective_batch": 512, "lr": 2.491439026944761e-05, "gradient_norm": 0.24479055404663086, "tokens_per_second": 1132464.1280296412, "synthetic": false, "world_size": 8} {"step": 68280, "tokens": 17899192320, "loss": 2.3652576446533202, "optimizer_updates": 35140, "effective_batch": 512, "lr": 2.489018253382095e-05, "gradient_norm": 0.24410761892795563, "tokens_per_second": 1130791.652958314, "synthetic": false, "world_size": 8} {"step": 68300, "tokens": 17904435200, "loss": 2.3734367370605467, "optimizer_updates": 35150, "effective_batch": 512, "lr": 2.4866032902653697e-05, "gradient_norm": 0.25439098477363586, "tokens_per_second": 1136526.0460290143, "synthetic": false, "world_size": 8} {"step": 68320, "tokens": 17909678080, "loss": 2.366931343078613, "optimizer_updates": 35160, "effective_batch": 512, "lr": 2.484194139243275e-05, "gradient_norm": 0.24218499660491943, "tokens_per_second": 1129300.7705061082, "synthetic": false, "world_size": 8} {"step": 68340, "tokens": 17914920960, "loss": 2.3555227279663087, "optimizer_updates": 35170, "effective_batch": 512, "lr": 2.481790801960541e-05, "gradient_norm": 0.31877076625823975, "tokens_per_second": 1138267.4197725803, "synthetic": false, "world_size": 8} {"step": 68360, "tokens": 17920163840, "loss": 2.36196231842041, "optimizer_updates": 35180, "effective_batch": 512, "lr": 2.4793932800579266e-05, "gradient_norm": 0.24001283943653107, "tokens_per_second": 940242.9062666937, "synthetic": false, "world_size": 8} {"step": 68380, "tokens": 17925406720, "loss": 2.363273811340332, "optimizer_updates": 35190, "effective_batch": 512, "lr": 2.4770015751722174e-05, "gradient_norm": 0.2349221408367157, "tokens_per_second": 1140637.6050434103, "synthetic": false, "world_size": 8} {"step": 68400, "tokens": 17930649600, "loss": 2.372662353515625, "optimizer_updates": 35200, "effective_batch": 512, "lr": 2.474615688936231e-05, "gradient_norm": 0.30815228819847107, "tokens_per_second": 1138740.889617312, "synthetic": false, "world_size": 8} {"step": 68420, "tokens": 17935892480, "loss": 2.365109443664551, "optimizer_updates": 35210, "effective_batch": 512, "lr": 2.472235622978811e-05, "gradient_norm": 0.3005974590778351, "tokens_per_second": 1132270.588585647, "synthetic": false, "world_size": 8} {"step": 68440, "tokens": 17941135360, "loss": 2.357580375671387, "optimizer_updates": 35220, "effective_batch": 512, "lr": 2.469861378924828e-05, "gradient_norm": 0.27762141823768616, "tokens_per_second": 1142128.5394927585, "synthetic": false, "world_size": 8} {"step": 68460, "tokens": 17946378240, "loss": 2.355151557922363, "optimizer_updates": 35230, "effective_batch": 512, "lr": 2.467492958395178e-05, "gradient_norm": 0.2615744471549988, "tokens_per_second": 1134484.076528304, "synthetic": false, "world_size": 8} {"step": 68480, "tokens": 17951621120, "loss": 2.354497528076172, "optimizer_updates": 35240, "effective_batch": 512, "lr": 2.4651303630067833e-05, "gradient_norm": 0.24489592015743256, "tokens_per_second": 1135852.891922496, "synthetic": false, "world_size": 8} {"step": 68500, "tokens": 17956864000, "loss": 2.368480682373047, "optimizer_updates": 35250, "effective_batch": 512, "lr": 2.4627735943725838e-05, "gradient_norm": 0.2484259307384491, "tokens_per_second": 1136139.527942296, "synthetic": false, "world_size": 8} {"step": 68520, "tokens": 17962106880, "loss": 2.3560279846191405, "optimizer_updates": 35260, "effective_batch": 512, "lr": 2.4604226541015483e-05, "gradient_norm": 0.26157549023628235, "tokens_per_second": 1030075.2328395919, "synthetic": false, "world_size": 8} {"step": 68540, "tokens": 17967349760, "loss": 2.3455503463745115, "optimizer_updates": 35270, "effective_batch": 512, "lr": 2.4580775437986614e-05, "gradient_norm": 0.2684626579284668, "tokens_per_second": 1130780.4367652417, "synthetic": false, "world_size": 8} {"step": 68560, "tokens": 17972592640, "loss": 2.3563982009887696, "optimizer_updates": 35280, "effective_batch": 512, "lr": 2.4557382650649314e-05, "gradient_norm": 0.29514551162719727, "tokens_per_second": 1135964.6916039584, "synthetic": false, "world_size": 8} {"step": 68580, "tokens": 17977835520, "loss": 2.3611082077026366, "optimizer_updates": 35290, "effective_batch": 512, "lr": 2.4534048194973822e-05, "gradient_norm": 0.30021658539772034, "tokens_per_second": 1137098.089249389, "synthetic": false, "world_size": 8} {"step": 68600, "tokens": 17983078400, "loss": 2.368247222900391, "optimizer_updates": 35300, "effective_batch": 512, "lr": 2.4510772086890574e-05, "gradient_norm": 0.2381514459848404, "tokens_per_second": 1134215.3459425252, "synthetic": false, "world_size": 8} {"step": 68620, "tokens": 17988321280, "loss": 2.3639097213745117, "optimizer_updates": 35310, "effective_batch": 512, "lr": 2.448755434229014e-05, "gradient_norm": 0.23860521614551544, "tokens_per_second": 1141975.8139623303, "synthetic": false, "world_size": 8} {"step": 68640, "tokens": 17993564160, "loss": 2.3546846389770506, "optimizer_updates": 35320, "effective_batch": 512, "lr": 2.446439497702332e-05, "gradient_norm": 0.2588314414024353, "tokens_per_second": 1127054.9309377861, "synthetic": false, "world_size": 8} {"step": 68660, "tokens": 17998807040, "loss": 2.367718505859375, "optimizer_updates": 35330, "effective_batch": 512, "lr": 2.4441294006900953e-05, "gradient_norm": 0.2581563889980316, "tokens_per_second": 1137890.858386603, "synthetic": false, "world_size": 8} {"step": 68680, "tokens": 18004049920, "loss": 2.3508859634399415, "optimizer_updates": 35340, "effective_batch": 512, "lr": 2.4418251447694123e-05, "gradient_norm": 0.2658465504646301, "tokens_per_second": 1135373.5764230506, "synthetic": false, "world_size": 8} {"step": 68700, "tokens": 18009292800, "loss": 2.352248954772949, "optimizer_updates": 35350, "effective_batch": 512, "lr": 2.4395267315133946e-05, "gradient_norm": 0.24575524032115936, "tokens_per_second": 1136456.3843391025, "synthetic": false, "world_size": 8} {"step": 68720, "tokens": 18014535680, "loss": 2.3574758529663087, "optimizer_updates": 35360, "effective_batch": 512, "lr": 2.4372341624911695e-05, "gradient_norm": 0.2400921881198883, "tokens_per_second": 1124930.077343392, "synthetic": false, "world_size": 8} {"step": 68740, "tokens": 18019778560, "loss": 2.369695281982422, "optimizer_updates": 35370, "effective_batch": 512, "lr": 2.4349474392678725e-05, "gradient_norm": 0.25844085216522217, "tokens_per_second": 1145678.0138251784, "synthetic": false, "world_size": 8} {"step": 68760, "tokens": 18025021440, "loss": 2.3586402893066407, "optimizer_updates": 35380, "effective_batch": 512, "lr": 2.4326665634046506e-05, "gradient_norm": 0.27236831188201904, "tokens_per_second": 1135641.97114844, "synthetic": false, "world_size": 8} {"step": 68780, "tokens": 18030264320, "loss": 2.3609975814819335, "optimizer_updates": 35390, "effective_batch": 512, "lr": 2.4303915364586573e-05, "gradient_norm": 0.24155737459659576, "tokens_per_second": 1133402.605877483, "synthetic": false, "world_size": 8} {"step": 68800, "tokens": 18035507200, "loss": 2.341776657104492, "optimizer_updates": 35400, "effective_batch": 512, "lr": 2.4281223599830522e-05, "gradient_norm": 0.23851856589317322, "tokens_per_second": 1132857.6496429679, "synthetic": false, "world_size": 8} {"step": 68820, "tokens": 18040750080, "loss": 2.350300598144531, "optimizer_updates": 35410, "effective_batch": 512, "lr": 2.4258590355270027e-05, "gradient_norm": 0.24494558572769165, "tokens_per_second": 1131825.9416221143, "synthetic": false, "world_size": 8} {"step": 68840, "tokens": 18045992960, "loss": 2.352988052368164, "optimizer_updates": 35420, "effective_batch": 512, "lr": 2.4236015646356796e-05, "gradient_norm": 0.2337639033794403, "tokens_per_second": 1133979.7878494998, "synthetic": false, "world_size": 8} {"step": 68860, "tokens": 18051235840, "loss": 2.362914276123047, "optimizer_updates": 35430, "effective_batch": 512, "lr": 2.421349948850258e-05, "gradient_norm": 0.26565414667129517, "tokens_per_second": 1141044.2643694275, "synthetic": false, "world_size": 8} {"step": 68880, "tokens": 18056478720, "loss": 2.3405017852783203, "optimizer_updates": 35440, "effective_batch": 512, "lr": 2.4191041897079155e-05, "gradient_norm": 0.2926247715950012, "tokens_per_second": 1134799.6642487983, "synthetic": false, "world_size": 8} {"step": 68900, "tokens": 18061721600, "loss": 2.35983829498291, "optimizer_updates": 35450, "effective_batch": 512, "lr": 2.416864288741833e-05, "gradient_norm": 0.2502669095993042, "tokens_per_second": 1137867.366563485, "synthetic": false, "world_size": 8} {"step": 68920, "tokens": 18066964480, "loss": 2.3605846405029296, "optimizer_updates": 35460, "effective_batch": 512, "lr": 2.4146302474811883e-05, "gradient_norm": 0.25270143151283264, "tokens_per_second": 1139296.2165901472, "synthetic": false, "world_size": 8} {"step": 68940, "tokens": 18072207360, "loss": 2.363245391845703, "optimizer_updates": 35470, "effective_batch": 512, "lr": 2.4124020674511624e-05, "gradient_norm": 0.2434242218732834, "tokens_per_second": 1135485.9836565736, "synthetic": false, "world_size": 8} {"step": 68960, "tokens": 18077450240, "loss": 2.3588062286376954, "optimizer_updates": 35480, "effective_batch": 512, "lr": 2.4101797501729316e-05, "gradient_norm": 0.2571701407432556, "tokens_per_second": 1124850.3200044397, "synthetic": false, "world_size": 8} {"step": 68980, "tokens": 18082693120, "loss": 2.361817741394043, "optimizer_updates": 35490, "effective_batch": 512, "lr": 2.4079632971636752e-05, "gradient_norm": 0.27429214119911194, "tokens_per_second": 1129446.1975542216, "synthetic": false, "world_size": 8} {"step": 69000, "tokens": 18087936000, "loss": 2.3645465850830076, "optimizer_updates": 35500, "effective_batch": 512, "lr": 2.4057527099365627e-05, "gradient_norm": 0.23510177433490753, "tokens_per_second": 1136936.6920967447, "synthetic": false, "world_size": 8} {"step": 69020, "tokens": 18093178880, "loss": 2.3327352523803713, "optimizer_updates": 35510, "effective_batch": 512, "lr": 2.403547990000762e-05, "gradient_norm": 0.23412469029426575, "tokens_per_second": 836000.2080555308, "synthetic": false, "world_size": 8} {"step": 69040, "tokens": 18098421760, "loss": 2.341281509399414, "optimizer_updates": 35520, "effective_batch": 512, "lr": 2.401349138861433e-05, "gradient_norm": 0.2525729238986969, "tokens_per_second": 1131263.701172645, "synthetic": false, "world_size": 8} {"step": 69060, "tokens": 18103664640, "loss": 2.3667617797851563, "optimizer_updates": 35530, "effective_batch": 512, "lr": 2.3991561580197365e-05, "gradient_norm": 0.2484794706106186, "tokens_per_second": 1135515.4000956654, "synthetic": false, "world_size": 8} {"step": 69080, "tokens": 18108907520, "loss": 2.363779830932617, "optimizer_updates": 35540, "effective_batch": 512, "lr": 2.396969048972814e-05, "gradient_norm": 0.25281473994255066, "tokens_per_second": 1134263.774952499, "synthetic": false, "world_size": 8} {"step": 69100, "tokens": 18114150400, "loss": 2.3571140289306642, "optimizer_updates": 35550, "effective_batch": 512, "lr": 2.3947878132138097e-05, "gradient_norm": 0.24927937984466553, "tokens_per_second": 1142888.556133134, "synthetic": false, "world_size": 8} {"step": 69120, "tokens": 18119393280, "loss": 2.349356460571289, "optimizer_updates": 35560, "effective_batch": 512, "lr": 2.392612452231849e-05, "gradient_norm": 0.2436809092760086, "tokens_per_second": 1140785.3484360855, "synthetic": false, "world_size": 8} {"step": 69140, "tokens": 18124636160, "loss": 2.3522003173828123, "optimizer_updates": 35570, "effective_batch": 512, "lr": 2.390442967512053e-05, "gradient_norm": 0.2540622353553772, "tokens_per_second": 1132147.160083642, "synthetic": false, "world_size": 8} {"step": 69160, "tokens": 18129879040, "loss": 2.3652881622314452, "optimizer_updates": 35580, "effective_batch": 512, "lr": 2.3882793605355266e-05, "gradient_norm": 0.24494080245494843, "tokens_per_second": 1129275.807503389, "synthetic": false, "world_size": 8} {"step": 69180, "tokens": 18135121920, "loss": 2.346654510498047, "optimizer_updates": 35590, "effective_batch": 512, "lr": 2.3861216327793665e-05, "gradient_norm": 0.26905572414398193, "tokens_per_second": 1139841.2463681365, "synthetic": false, "world_size": 8} {"step": 69200, "tokens": 18140364800, "loss": 2.3561931610107423, "optimizer_updates": 35600, "effective_batch": 512, "lr": 2.3839697857166507e-05, "gradient_norm": 0.23566047847270966, "tokens_per_second": 1134596.3779237957, "synthetic": false, "world_size": 8} {"step": 69220, "tokens": 18145607680, "loss": 2.3405363082885744, "optimizer_updates": 35610, "effective_batch": 512, "lr": 2.3818238208164448e-05, "gradient_norm": 0.24145947396755219, "tokens_per_second": 1134590.1754868461, "synthetic": false, "world_size": 8} {"step": 69240, "tokens": 18150850560, "loss": 2.3519786834716796, "optimizer_updates": 35620, "effective_batch": 512, "lr": 2.3796837395438023e-05, "gradient_norm": 0.28110554814338684, "tokens_per_second": 1128230.0363314427, "synthetic": false, "world_size": 8} {"step": 69260, "tokens": 18156093440, "loss": 2.3633527755737305, "optimizer_updates": 35630, "effective_batch": 512, "lr": 2.377549543359752e-05, "gradient_norm": 0.2571565806865692, "tokens_per_second": 1125169.3993020607, "synthetic": false, "world_size": 8} {"step": 69280, "tokens": 18161336320, "loss": 2.358469581604004, "optimizer_updates": 35640, "effective_batch": 512, "lr": 2.3754212337213127e-05, "gradient_norm": 0.25409364700317383, "tokens_per_second": 869281.9659421977, "synthetic": false, "world_size": 8} {"step": 69300, "tokens": 18166579200, "loss": 2.3704973220825196, "optimizer_updates": 35650, "effective_batch": 512, "lr": 2.373298812081477e-05, "gradient_norm": 0.23171785473823547, "tokens_per_second": 1027002.7679530449, "synthetic": false, "world_size": 8} {"step": 69320, "tokens": 18171822080, "loss": 2.369275665283203, "optimizer_updates": 35660, "effective_batch": 512, "lr": 2.3711822798892273e-05, "gradient_norm": 0.2556541860103607, "tokens_per_second": 1135928.6449416268, "synthetic": false, "world_size": 8} {"step": 69340, "tokens": 18177064960, "loss": 2.3538331985473633, "optimizer_updates": 35670, "effective_batch": 512, "lr": 2.369071638589516e-05, "gradient_norm": 0.2905175983905792, "tokens_per_second": 1129431.667479086, "synthetic": false, "world_size": 8} {"step": 69360, "tokens": 18182307840, "loss": 2.3557964324951173, "optimizer_updates": 35680, "effective_batch": 512, "lr": 2.3669668896232782e-05, "gradient_norm": 0.27234891057014465, "tokens_per_second": 1134571.0461475963, "synthetic": false, "world_size": 8} {"step": 69380, "tokens": 18187550720, "loss": 2.3472162246704102, "optimizer_updates": 35690, "effective_batch": 512, "lr": 2.3648680344274246e-05, "gradient_norm": 0.24225352704524994, "tokens_per_second": 1127413.2202200934, "synthetic": false, "world_size": 8} {"step": 69400, "tokens": 18192793600, "loss": 2.3466615676879883, "optimizer_updates": 35700, "effective_batch": 512, "lr": 2.362775074434847e-05, "gradient_norm": 0.2359500378370285, "tokens_per_second": 1134678.669911966, "synthetic": false, "world_size": 8} {"step": 69420, "tokens": 18198036480, "loss": 2.349553871154785, "optimizer_updates": 35710, "effective_batch": 512, "lr": 2.360688011074404e-05, "gradient_norm": 0.24682925641536713, "tokens_per_second": 1127171.3492770426, "synthetic": false, "world_size": 8} {"step": 69440, "tokens": 18203279360, "loss": 2.352733612060547, "optimizer_updates": 35720, "effective_batch": 512, "lr": 2.3586068457709374e-05, "gradient_norm": 0.3024657964706421, "tokens_per_second": 1129379.3258595394, "synthetic": false, "world_size": 8} {"step": 69460, "tokens": 18208522240, "loss": 2.3593191146850585, "optimizer_updates": 35730, "effective_batch": 512, "lr": 2.3565315799452563e-05, "gradient_norm": 0.25335925817489624, "tokens_per_second": 1133021.4014001442, "synthetic": false, "world_size": 8} {"step": 69480, "tokens": 18213765120, "loss": 2.3588140487670897, "optimizer_updates": 35740, "effective_batch": 512, "lr": 2.3544622150141464e-05, "gradient_norm": 0.271989643573761, "tokens_per_second": 1127605.028091592, "synthetic": false, "world_size": 8} {"step": 69500, "tokens": 18219008000, "loss": 2.3539318084716796, "optimizer_updates": 35750, "effective_batch": 512, "lr": 2.352398752390359e-05, "gradient_norm": 0.23561310768127441, "tokens_per_second": 1132801.184528315, "synthetic": false, "world_size": 8} {"step": 69520, "tokens": 18224250880, "loss": 2.353221130371094, "optimizer_updates": 35760, "effective_batch": 512, "lr": 2.3503411934826248e-05, "gradient_norm": 0.27253037691116333, "tokens_per_second": 1128024.0730694816, "synthetic": false, "world_size": 8} {"step": 69540, "tokens": 18229493760, "loss": 2.34307804107666, "optimizer_updates": 35770, "effective_batch": 512, "lr": 2.348289539695634e-05, "gradient_norm": 0.26133349537849426, "tokens_per_second": 1136848.245456384, "synthetic": false, "world_size": 8} {"step": 69560, "tokens": 18234736640, "loss": 2.371261978149414, "optimizer_updates": 35780, "effective_batch": 512, "lr": 2.346243792430054e-05, "gradient_norm": 0.26530924439430237, "tokens_per_second": 1128322.8337564364, "synthetic": false, "world_size": 8} {"step": 69580, "tokens": 18239979520, "loss": 2.3562080383300783, "optimizer_updates": 35790, "effective_batch": 512, "lr": 2.3442039530825143e-05, "gradient_norm": 0.28503167629241943, "tokens_per_second": 1123467.475026216, "synthetic": false, "world_size": 8} {"step": 69600, "tokens": 18245222400, "loss": 2.3454874038696287, "optimizer_updates": 35800, "effective_batch": 512, "lr": 2.342170023045614e-05, "gradient_norm": 0.24776506423950195, "tokens_per_second": 1118905.9790579046, "synthetic": false, "world_size": 8} {"step": 69620, "tokens": 18250465280, "loss": 2.3558586120605467, "optimizer_updates": 35810, "effective_batch": 512, "lr": 2.340142003707916e-05, "gradient_norm": 0.24839402735233307, "tokens_per_second": 999424.8308891112, "synthetic": false, "world_size": 8} {"step": 69640, "tokens": 18255708160, "loss": 2.3616003036499023, "optimizer_updates": 35820, "effective_batch": 512, "lr": 2.3381198964539494e-05, "gradient_norm": 0.25254660844802856, "tokens_per_second": 1128641.1742280538, "synthetic": false, "world_size": 8} {"step": 69660, "tokens": 18260951040, "loss": 2.3522520065307617, "optimizer_updates": 35830, "effective_batch": 512, "lr": 2.336103702664206e-05, "gradient_norm": 0.24242334067821503, "tokens_per_second": 1128597.9217200938, "synthetic": false, "world_size": 8} {"step": 69680, "tokens": 18266193920, "loss": 2.3624704360961912, "optimizer_updates": 35840, "effective_batch": 512, "lr": 2.3340934237151402e-05, "gradient_norm": 0.26475846767425537, "tokens_per_second": 1122722.1519306274, "synthetic": false, "world_size": 8} {"step": 69700, "tokens": 18271436800, "loss": 2.3649690628051756, "optimizer_updates": 35850, "effective_batch": 512, "lr": 2.3320890609791716e-05, "gradient_norm": 0.2590908110141754, "tokens_per_second": 1134310.7400184316, "synthetic": false, "world_size": 8} {"step": 69720, "tokens": 18276679680, "loss": 2.358343505859375, "optimizer_updates": 35860, "effective_batch": 512, "lr": 2.3300906158246746e-05, "gradient_norm": 0.251311719417572, "tokens_per_second": 1134154.2065304054, "synthetic": false, "world_size": 8} {"step": 69740, "tokens": 18281922560, "loss": 2.351165008544922, "optimizer_updates": 35870, "effective_batch": 512, "lr": 2.3280980896159914e-05, "gradient_norm": 0.23590180277824402, "tokens_per_second": 1124631.543283204, "synthetic": false, "world_size": 8} {"step": 69760, "tokens": 18287165440, "loss": 2.374347686767578, "optimizer_updates": 35880, "effective_batch": 512, "lr": 2.3261114837134166e-05, "gradient_norm": 0.2591729164123535, "tokens_per_second": 1122694.581003111, "synthetic": false, "world_size": 8} {"step": 69780, "tokens": 18292408320, "loss": 2.35404109954834, "optimizer_updates": 35890, "effective_batch": 512, "lr": 2.324130799473208e-05, "gradient_norm": 0.2672053575515747, "tokens_per_second": 1125136.2295716354, "synthetic": false, "world_size": 8} {"step": 69800, "tokens": 18297651200, "loss": 2.352017402648926, "optimizer_updates": 35900, "effective_batch": 512, "lr": 2.3221560382475754e-05, "gradient_norm": 0.2588184177875519, "tokens_per_second": 1126544.7047287077, "synthetic": false, "world_size": 8} {"step": 69820, "tokens": 18302894080, "loss": 2.3621870040893556, "optimizer_updates": 35910, "effective_batch": 512, "lr": 2.320187201384691e-05, "gradient_norm": 0.25941896438598633, "tokens_per_second": 801521.2625392776, "synthetic": false, "world_size": 8} {"step": 69840, "tokens": 18308136960, "loss": 2.3684114456176757, "optimizer_updates": 35920, "effective_batch": 512, "lr": 2.3182242902286768e-05, "gradient_norm": 0.2597428560256958, "tokens_per_second": 1134501.8799718437, "synthetic": false, "world_size": 8} {"step": 69860, "tokens": 18313379840, "loss": 2.3359420776367186, "optimizer_updates": 35930, "effective_batch": 512, "lr": 2.316267306119615e-05, "gradient_norm": 0.24786534905433655, "tokens_per_second": 1137397.8585244287, "synthetic": false, "world_size": 8} {"step": 69880, "tokens": 18318622720, "loss": 2.3602405548095704, "optimizer_updates": 35940, "effective_batch": 512, "lr": 2.3143162503935355e-05, "gradient_norm": 0.29907453060150146, "tokens_per_second": 1131128.6110309097, "synthetic": false, "world_size": 8} {"step": 69900, "tokens": 18323865600, "loss": 2.3589994430541994, "optimizer_updates": 35950, "effective_batch": 512, "lr": 2.3123711243824255e-05, "gradient_norm": 0.2535563111305237, "tokens_per_second": 1135390.0397096495, "synthetic": false, "world_size": 8} {"step": 69920, "tokens": 18329108480, "loss": 2.3695125579833984, "optimizer_updates": 35960, "effective_batch": 512, "lr": 2.310431929414221e-05, "gradient_norm": 0.24834871292114258, "tokens_per_second": 1134164.9882558587, "synthetic": false, "world_size": 8} {"step": 69940, "tokens": 18334351360, "loss": 2.35654354095459, "optimizer_updates": 35970, "effective_batch": 512, "lr": 2.308498666812811e-05, "gradient_norm": 0.23454229533672333, "tokens_per_second": 1137204.411046906, "synthetic": false, "world_size": 8} {"step": 69960, "tokens": 18339594240, "loss": 2.3623979568481444, "optimizer_updates": 35980, "effective_batch": 512, "lr": 2.3065713378980336e-05, "gradient_norm": 0.2501741349697113, "tokens_per_second": 1126453.8670879144, "synthetic": false, "world_size": 8} {"step": 69980, "tokens": 18344837120, "loss": 2.3493160247802733, "optimizer_updates": 35990, "effective_batch": 512, "lr": 2.3046499439856753e-05, "gradient_norm": 0.2355612963438034, "tokens_per_second": 1135270.3135183938, "synthetic": false, "world_size": 8} {"step": 70000, "tokens": 18350080000, "loss": 2.349593925476074, "optimizer_updates": 36000, "effective_batch": 512, "lr": 2.3027344863874716e-05, "gradient_norm": 0.26042962074279785, "tokens_per_second": 1140142.413347611, "synthetic": false, "world_size": 8} {"step": 70020, "tokens": 18355322880, "loss": 2.3705238342285155, "optimizer_updates": 36010, "effective_batch": 512, "lr": 2.3008249664111058e-05, "gradient_norm": 0.23723278939723969, "tokens_per_second": 830448.2343534726, "synthetic": false, "world_size": 8} {"step": 70040, "tokens": 18360565760, "loss": 2.366667938232422, "optimizer_updates": 36020, "effective_batch": 512, "lr": 2.2989213853602056e-05, "gradient_norm": 0.24185995757579803, "tokens_per_second": 1133869.395679999, "synthetic": false, "world_size": 8} {"step": 70060, "tokens": 18365808640, "loss": 2.3560508728027343, "optimizer_updates": 36030, "effective_batch": 512, "lr": 2.2970237445343463e-05, "gradient_norm": 0.27315932512283325, "tokens_per_second": 1138399.876732308, "synthetic": false, "world_size": 8} {"step": 70080, "tokens": 18371051520, "loss": 2.3497735977172853, "optimizer_updates": 36040, "effective_batch": 512, "lr": 2.2951320452290484e-05, "gradient_norm": 0.25718608498573303, "tokens_per_second": 1140419.6512387716, "synthetic": false, "world_size": 8} {"step": 70100, "tokens": 18376294400, "loss": 2.3523269653320313, "optimizer_updates": 36050, "effective_batch": 512, "lr": 2.293246288735771e-05, "gradient_norm": 0.2271750420331955, "tokens_per_second": 1139531.8578130056, "synthetic": false, "world_size": 8} {"step": 70120, "tokens": 18381537280, "loss": 2.3541400909423826, "optimizer_updates": 36060, "effective_batch": 512, "lr": 2.291366476341924e-05, "gradient_norm": 0.22968412935733795, "tokens_per_second": 1135401.9834013707, "synthetic": false, "world_size": 8} {"step": 70140, "tokens": 18386780160, "loss": 2.3619543075561524, "optimizer_updates": 36070, "effective_batch": 512, "lr": 2.2894926093308527e-05, "gradient_norm": 0.2653288245201111, "tokens_per_second": 1131017.583811334, "synthetic": false, "world_size": 8} {"step": 70160, "tokens": 18392023040, "loss": 2.350945472717285, "optimizer_updates": 36080, "effective_batch": 512, "lr": 2.2876246889818457e-05, "gradient_norm": 0.25044479966163635, "tokens_per_second": 1137991.7263816998, "synthetic": false, "world_size": 8} {"step": 70180, "tokens": 18397265920, "loss": 2.3433744430541994, "optimizer_updates": 36090, "effective_batch": 512, "lr": 2.2857627165701325e-05, "gradient_norm": 0.24815919995307922, "tokens_per_second": 815298.8183448756, "synthetic": false, "world_size": 8} {"step": 70200, "tokens": 18402508800, "loss": 2.355726432800293, "optimizer_updates": 36100, "effective_batch": 512, "lr": 2.2839066933668822e-05, "gradient_norm": 0.24167050421237946, "tokens_per_second": 1142921.3148349132, "synthetic": false, "world_size": 8} {"step": 70220, "tokens": 18407751680, "loss": 2.3547946929931642, "optimizer_updates": 36110, "effective_batch": 512, "lr": 2.2820566206391992e-05, "gradient_norm": 0.26208552718162537, "tokens_per_second": 1136096.510749904, "synthetic": false, "world_size": 8} {"step": 70240, "tokens": 18412994560, "loss": 2.3755435943603516, "optimizer_updates": 36120, "effective_batch": 512, "lr": 2.280212499650131e-05, "gradient_norm": 0.24450257420539856, "tokens_per_second": 1137806.0794758163, "synthetic": false, "world_size": 8} {"step": 70260, "tokens": 18418237440, "loss": 2.366719055175781, "optimizer_updates": 36130, "effective_batch": 512, "lr": 2.278374331658657e-05, "gradient_norm": 0.24518123269081116, "tokens_per_second": 1123842.5749451267, "synthetic": false, "world_size": 8} {"step": 70280, "tokens": 18423480320, "loss": 2.361324691772461, "optimizer_updates": 36140, "effective_batch": 512, "lr": 2.276542117919694e-05, "gradient_norm": 0.25361472368240356, "tokens_per_second": 1135712.1340436998, "synthetic": false, "world_size": 8} {"step": 70300, "tokens": 18428723200, "loss": 2.3619220733642576, "optimizer_updates": 36150, "effective_batch": 512, "lr": 2.2747158596840932e-05, "gradient_norm": 0.2532080411911011, "tokens_per_second": 1127249.3898142609, "synthetic": false, "world_size": 8} {"step": 70320, "tokens": 18433966080, "loss": 2.352798080444336, "optimizer_updates": 36160, "effective_batch": 512, "lr": 2.2728955581986437e-05, "gradient_norm": 0.291265606880188, "tokens_per_second": 1127201.7123256293, "synthetic": false, "world_size": 8} {"step": 70340, "tokens": 18439208960, "loss": 2.355693244934082, "optimizer_updates": 36170, "effective_batch": 512, "lr": 2.2710812147060623e-05, "gradient_norm": 0.23959876596927643, "tokens_per_second": 1135180.0753329177, "synthetic": false, "world_size": 8} {"step": 70360, "tokens": 18444451840, "loss": 2.354203796386719, "optimizer_updates": 36180, "effective_batch": 512, "lr": 2.269272830445002e-05, "gradient_norm": 0.27586743235588074, "tokens_per_second": 1121841.8507031584, "synthetic": false, "world_size": 8} {"step": 70380, "tokens": 18449694720, "loss": 2.3428802490234375, "optimizer_updates": 36190, "effective_batch": 512, "lr": 2.2674704066500464e-05, "gradient_norm": 0.2290896326303482, "tokens_per_second": 1131035.062176069, "synthetic": false, "world_size": 8} {"step": 70400, "tokens": 18454937600, "loss": 2.371745300292969, "optimizer_updates": 36200, "effective_batch": 512, "lr": 2.2656739445517104e-05, "gradient_norm": 0.2955072522163391, "tokens_per_second": 1134294.8152556277, "synthetic": false, "world_size": 8} {"step": 70420, "tokens": 18460180480, "loss": 2.346142387390137, "optimizer_updates": 36210, "effective_batch": 512, "lr": 2.2638834453764373e-05, "gradient_norm": 0.2759518027305603, "tokens_per_second": 1140526.2577051595, "synthetic": false, "world_size": 8} {"step": 70440, "tokens": 18465423360, "loss": 2.348697280883789, "optimizer_updates": 36220, "effective_batch": 512, "lr": 2.2620989103466022e-05, "gradient_norm": 0.25037482380867004, "tokens_per_second": 1141817.2844978103, "synthetic": false, "world_size": 8} {"step": 70460, "tokens": 18470666240, "loss": 2.361715888977051, "optimizer_updates": 36230, "effective_batch": 512, "lr": 2.2603203406805058e-05, "gradient_norm": 0.3195112347602844, "tokens_per_second": 1135501.4099164212, "synthetic": false, "world_size": 8} {"step": 70480, "tokens": 18475909120, "loss": 2.3543117523193358, "optimizer_updates": 36240, "effective_batch": 512, "lr": 2.2585477375923782e-05, "gradient_norm": 0.22945870459079742, "tokens_per_second": 1141640.8284662252, "synthetic": false, "world_size": 8} {"step": 70500, "tokens": 18481152000, "loss": 2.361123466491699, "optimizer_updates": 36250, "effective_batch": 512, "lr": 2.256781102292373e-05, "gradient_norm": 0.2817709445953369, "tokens_per_second": 928026.2301485096, "synthetic": false, "world_size": 8} {"step": 70520, "tokens": 18486394880, "loss": 2.3666187286376954, "optimizer_updates": 36260, "effective_batch": 512, "lr": 2.255020435986574e-05, "gradient_norm": 0.2410997450351715, "tokens_per_second": 894777.3428185967, "synthetic": false, "world_size": 8} {"step": 70540, "tokens": 18491637760, "loss": 2.377140235900879, "optimizer_updates": 36270, "effective_batch": 512, "lr": 2.2532657398769882e-05, "gradient_norm": 0.25149795413017273, "tokens_per_second": 1025597.9392908618, "synthetic": false, "world_size": 8} {"step": 70560, "tokens": 18496880640, "loss": 2.3517974853515624, "optimizer_updates": 36280, "effective_batch": 512, "lr": 2.2515170151615447e-05, "gradient_norm": 0.2364831119775772, "tokens_per_second": 1132893.2788897282, "synthetic": false, "world_size": 8} {"step": 70580, "tokens": 18502123520, "loss": 2.3585222244262694, "optimizer_updates": 36290, "effective_batch": 512, "lr": 2.2497742630340996e-05, "gradient_norm": 0.24219347536563873, "tokens_per_second": 1137184.424420509, "synthetic": false, "world_size": 8} {"step": 70600, "tokens": 18507366400, "loss": 2.352451515197754, "optimizer_updates": 36300, "effective_batch": 512, "lr": 2.2480374846844277e-05, "gradient_norm": 0.2786250412464142, "tokens_per_second": 1020026.9192547248, "synthetic": false, "world_size": 8} {"step": 70620, "tokens": 18512609280, "loss": 2.3461320877075194, "optimizer_updates": 36310, "effective_batch": 512, "lr": 2.2463066812982276e-05, "gradient_norm": 0.24914592504501343, "tokens_per_second": 1135362.5341965053, "synthetic": false, "world_size": 8} {"step": 70640, "tokens": 18517852160, "loss": 2.3547271728515624, "optimizer_updates": 36320, "effective_batch": 512, "lr": 2.2445818540571186e-05, "gradient_norm": 0.2820621132850647, "tokens_per_second": 1130728.8246115749, "synthetic": false, "world_size": 8} {"step": 70660, "tokens": 18523095040, "loss": 2.3583372116088865, "optimizer_updates": 36330, "effective_batch": 512, "lr": 2.2428630041386412e-05, "gradient_norm": 0.2335314005613327, "tokens_per_second": 1136109.4631617232, "synthetic": false, "world_size": 8} {"step": 70680, "tokens": 18528337920, "loss": 2.3642892837524414, "optimizer_updates": 36340, "effective_batch": 512, "lr": 2.241150132716251e-05, "gradient_norm": 0.24503618478775024, "tokens_per_second": 1134173.403248171, "synthetic": false, "world_size": 8} {"step": 70700, "tokens": 18533580800, "loss": 2.3592159271240236, "optimizer_updates": 36350, "effective_batch": 512, "lr": 2.239443240959329e-05, "gradient_norm": 0.2703658640384674, "tokens_per_second": 1134323.2053048674, "synthetic": false, "world_size": 8} {"step": 70720, "tokens": 18538823680, "loss": 2.3791236877441406, "optimizer_updates": 36360, "effective_batch": 512, "lr": 2.2377423300331662e-05, "gradient_norm": 0.32320693135261536, "tokens_per_second": 1132246.2041937062, "synthetic": false, "world_size": 8} {"step": 70740, "tokens": 18544066560, "loss": 2.3585079193115233, "optimizer_updates": 36370, "effective_batch": 512, "lr": 2.2360474010989784e-05, "gradient_norm": 0.2366076111793518, "tokens_per_second": 1133478.5087901484, "synthetic": false, "world_size": 8} {"step": 70760, "tokens": 18549309440, "loss": 2.3683984756469725, "optimizer_updates": 36380, "effective_batch": 512, "lr": 2.2343584553138888e-05, "gradient_norm": 0.24068184196949005, "tokens_per_second": 1130637.4014158838, "synthetic": false, "world_size": 8} {"step": 70780, "tokens": 18554552320, "loss": 2.372236442565918, "optimizer_updates": 36390, "effective_batch": 512, "lr": 2.232675493830944e-05, "gradient_norm": 0.26980355381965637, "tokens_per_second": 1134439.53510107, "synthetic": false, "world_size": 8} {"step": 70800, "tokens": 18559795200, "loss": 2.358184242248535, "optimizer_updates": 36400, "effective_batch": 512, "lr": 2.2309985177990988e-05, "gradient_norm": 0.2354453057050705, "tokens_per_second": 1142288.2668316464, "synthetic": false, "world_size": 8} {"step": 70820, "tokens": 18565038080, "loss": 2.367085838317871, "optimizer_updates": 36410, "effective_batch": 512, "lr": 2.2293275283632266e-05, "gradient_norm": 0.25133565068244934, "tokens_per_second": 1135339.56068901, "synthetic": false, "world_size": 8} {"step": 70840, "tokens": 18570280960, "loss": 2.363129425048828, "optimizer_updates": 36420, "effective_batch": 512, "lr": 2.2276625266641097e-05, "gradient_norm": 0.246175155043602, "tokens_per_second": 1136776.7355949685, "synthetic": false, "world_size": 8} {"step": 70860, "tokens": 18575523840, "loss": 2.355207824707031, "optimizer_updates": 36430, "effective_batch": 512, "lr": 2.226003513838447e-05, "gradient_norm": 0.2371678501367569, "tokens_per_second": 1145624.4705332916, "synthetic": false, "world_size": 8} {"step": 70880, "tokens": 18580766720, "loss": 2.3598453521728517, "optimizer_updates": 36440, "effective_batch": 512, "lr": 2.2243504910188438e-05, "gradient_norm": 0.25701504945755005, "tokens_per_second": 1131867.3697666842, "synthetic": false, "world_size": 8} {"step": 70900, "tokens": 18586009600, "loss": 2.358178901672363, "optimizer_updates": 36450, "effective_batch": 512, "lr": 2.2227034593338206e-05, "gradient_norm": 0.262297123670578, "tokens_per_second": 1132208.2221950362, "synthetic": false, "world_size": 8} {"step": 70920, "tokens": 18591252480, "loss": 2.3533668518066406, "optimizer_updates": 36460, "effective_batch": 512, "lr": 2.2210624199078058e-05, "gradient_norm": 0.2365645468235016, "tokens_per_second": 787415.8958407358, "synthetic": false, "world_size": 8} {"step": 70940, "tokens": 18596495360, "loss": 2.3485336303710938, "optimizer_updates": 36470, "effective_batch": 512, "lr": 2.2194273738611336e-05, "gradient_norm": 0.22913770377635956, "tokens_per_second": 1144190.8218384061, "synthetic": false, "world_size": 8} {"step": 70960, "tokens": 18601738240, "loss": 2.370202827453613, "optimizer_updates": 36480, "effective_batch": 512, "lr": 2.2177983223100523e-05, "gradient_norm": 0.23940624296665192, "tokens_per_second": 1136856.8970379047, "synthetic": false, "world_size": 8} {"step": 70980, "tokens": 18606981120, "loss": 2.359819221496582, "optimizer_updates": 36490, "effective_batch": 512, "lr": 2.2161752663667144e-05, "gradient_norm": 0.26819947361946106, "tokens_per_second": 1139779.2804091987, "synthetic": false, "world_size": 8} {"step": 71000, "tokens": 18612224000, "loss": 2.3570384979248047, "optimizer_updates": 36500, "effective_batch": 512, "lr": 2.214558207139181e-05, "gradient_norm": 0.22865000367164612, "tokens_per_second": 1125475.8540739021, "synthetic": false, "world_size": 8} {"step": 71020, "tokens": 18617466880, "loss": 2.3503467559814455, "optimizer_updates": 36510, "effective_batch": 512, "lr": 2.212947145731417e-05, "gradient_norm": 0.24128329753875732, "tokens_per_second": 832443.3153482853, "synthetic": false, "world_size": 8} {"step": 71040, "tokens": 18622709760, "loss": 2.3527393341064453, "optimizer_updates": 36520, "effective_batch": 512, "lr": 2.2113420832432937e-05, "gradient_norm": 0.23880821466445923, "tokens_per_second": 1130017.67370207, "synthetic": false, "world_size": 8} {"step": 71060, "tokens": 18627952640, "loss": 2.356924819946289, "optimizer_updates": 36530, "effective_batch": 512, "lr": 2.209743020770588e-05, "gradient_norm": 0.25298747420310974, "tokens_per_second": 1132515.9134482369, "synthetic": false, "world_size": 8} {"step": 71080, "tokens": 18633195520, "loss": 2.3526525497436523, "optimizer_updates": 36540, "effective_batch": 512, "lr": 2.2081499594049796e-05, "gradient_norm": 0.23644082248210907, "tokens_per_second": 1144114.3955399697, "synthetic": false, "world_size": 8} {"step": 71100, "tokens": 18638438400, "loss": 2.3696548461914064, "optimizer_updates": 36550, "effective_batch": 512, "lr": 2.2065629002340495e-05, "gradient_norm": 0.2721329927444458, "tokens_per_second": 1136116.7984377171, "synthetic": false, "world_size": 8} {"step": 71120, "tokens": 18643681280, "loss": 2.355233001708984, "optimizer_updates": 36560, "effective_batch": 512, "lr": 2.2049818443412847e-05, "gradient_norm": 0.2775478661060333, "tokens_per_second": 1134101.855618256, "synthetic": false, "world_size": 8} {"step": 71140, "tokens": 18648924160, "loss": 2.3569812774658203, "optimizer_updates": 36570, "effective_batch": 512, "lr": 2.2034067928060705e-05, "gradient_norm": 0.2378252148628235, "tokens_per_second": 1129145.5336891431, "synthetic": false, "world_size": 8} {"step": 71160, "tokens": 18654167040, "loss": 2.367890739440918, "optimizer_updates": 36580, "effective_batch": 512, "lr": 2.2018377467036948e-05, "gradient_norm": 0.3149775266647339, "tokens_per_second": 1125814.9170762124, "synthetic": false, "world_size": 8} {"step": 71180, "tokens": 18659409920, "loss": 2.35219669342041, "optimizer_updates": 36590, "effective_batch": 512, "lr": 2.2002747071053458e-05, "gradient_norm": 0.2529691457748413, "tokens_per_second": 1123024.698328394, "synthetic": false, "world_size": 8} {"step": 71200, "tokens": 18664652800, "loss": 2.3573122024536133, "optimizer_updates": 36600, "effective_batch": 512, "lr": 2.19871767507811e-05, "gradient_norm": 0.3043891191482544, "tokens_per_second": 1118930.2700862708, "synthetic": false, "world_size": 8} {"step": 71220, "tokens": 18669895680, "loss": 2.3522579193115236, "optimizer_updates": 36610, "effective_batch": 512, "lr": 2.1971666516849725e-05, "gradient_norm": 0.2827240228652954, "tokens_per_second": 1125580.7730083773, "synthetic": false, "world_size": 8} {"step": 71240, "tokens": 18675138560, "loss": 2.3510578155517576, "optimizer_updates": 36620, "effective_batch": 512, "lr": 2.1956216379848177e-05, "gradient_norm": 0.2543657720088959, "tokens_per_second": 1117971.984316935, "synthetic": false, "world_size": 8} {"step": 71260, "tokens": 18680381440, "loss": 2.364601898193359, "optimizer_updates": 36630, "effective_batch": 512, "lr": 2.1940826350324248e-05, "gradient_norm": 0.23858878016471863, "tokens_per_second": 1121226.1629259852, "synthetic": false, "world_size": 8} {"step": 71280, "tokens": 18685624320, "loss": 2.3615095138549806, "optimizer_updates": 36640, "effective_batch": 512, "lr": 2.1925496438784725e-05, "gradient_norm": 0.25671622157096863, "tokens_per_second": 1131320.7335116772, "synthetic": false, "world_size": 8} {"step": 71300, "tokens": 18690867200, "loss": 2.360220718383789, "optimizer_updates": 36650, "effective_batch": 512, "lr": 2.1910226655695306e-05, "gradient_norm": 0.268581360578537, "tokens_per_second": 1141945.2770989693, "synthetic": false, "world_size": 8} {"step": 71320, "tokens": 18696110080, "loss": 2.3627382278442384, "optimizer_updates": 36660, "effective_batch": 512, "lr": 2.189501701148071e-05, "gradient_norm": 0.2585044503211975, "tokens_per_second": 1124441.6706702474, "synthetic": false, "world_size": 8} {"step": 71340, "tokens": 18701352960, "loss": 2.3723621368408203, "optimizer_updates": 36670, "effective_batch": 512, "lr": 2.1879867516524527e-05, "gradient_norm": 0.2568870484828949, "tokens_per_second": 1122470.2610885967, "synthetic": false, "world_size": 8} {"step": 71360, "tokens": 18706595840, "loss": 2.3608203887939454, "optimizer_updates": 36680, "effective_batch": 512, "lr": 2.1864778181169347e-05, "gradient_norm": 0.258213073015213, "tokens_per_second": 1129085.1893090357, "synthetic": false, "world_size": 8} {"step": 71380, "tokens": 18711838720, "loss": 2.3528202056884764, "optimizer_updates": 36690, "effective_batch": 512, "lr": 2.1849749015716614e-05, "gradient_norm": 0.24821171164512634, "tokens_per_second": 1128000.7293820472, "synthetic": false, "world_size": 8} {"step": 71400, "tokens": 18717081600, "loss": 2.36267147064209, "optimizer_updates": 36700, "effective_batch": 512, "lr": 2.1834780030426767e-05, "gradient_norm": 0.2452027052640915, "tokens_per_second": 1124205.9278310935, "synthetic": false, "world_size": 8} {"step": 71420, "tokens": 18722324480, "loss": 2.3738380432128907, "optimizer_updates": 36710, "effective_batch": 512, "lr": 2.1819871235519136e-05, "gradient_norm": 0.24156740307807922, "tokens_per_second": 1127340.7737117216, "synthetic": false, "world_size": 8} {"step": 71440, "tokens": 18727567360, "loss": 2.356214904785156, "optimizer_updates": 36720, "effective_batch": 512, "lr": 2.1805022641171922e-05, "gradient_norm": 0.26576536893844604, "tokens_per_second": 1132535.082172489, "synthetic": false, "world_size": 8} {"step": 71460, "tokens": 18732810240, "loss": 2.3490482330322267, "optimizer_updates": 36730, "effective_batch": 512, "lr": 2.17902342575223e-05, "gradient_norm": 0.26775050163269043, "tokens_per_second": 1125834.2297548093, "synthetic": false, "world_size": 8} {"step": 71480, "tokens": 18738053120, "loss": 2.337047576904297, "optimizer_updates": 36740, "effective_batch": 512, "lr": 2.1775506094666254e-05, "gradient_norm": 0.2655329406261444, "tokens_per_second": 1126836.6221249765, "synthetic": false, "world_size": 8} {"step": 71500, "tokens": 18743296000, "loss": 2.3546701431274415, "optimizer_updates": 36750, "effective_batch": 512, "lr": 2.176083816265873e-05, "gradient_norm": 0.276486337184906, "tokens_per_second": 1126990.317928658, "synthetic": false, "world_size": 8} {"step": 71520, "tokens": 18748538880, "loss": 2.352945327758789, "optimizer_updates": 36760, "effective_batch": 512, "lr": 2.174623047151351e-05, "gradient_norm": 0.25438711047172546, "tokens_per_second": 1032965.6204548819, "synthetic": false, "world_size": 8} {"step": 71540, "tokens": 18753781760, "loss": 2.3584268569946287, "optimizer_updates": 36770, "effective_batch": 512, "lr": 2.1731683031203258e-05, "gradient_norm": 0.23211053013801575, "tokens_per_second": 1140281.5546974041, "synthetic": false, "world_size": 8} {"step": 71560, "tokens": 18759024640, "loss": 2.338827133178711, "optimizer_updates": 36780, "effective_batch": 512, "lr": 2.1717195851659518e-05, "gradient_norm": 0.2628936469554901, "tokens_per_second": 1139779.7893637288, "synthetic": false, "world_size": 8} {"step": 71580, "tokens": 18764267520, "loss": 2.3576591491699217, "optimizer_updates": 36790, "effective_batch": 512, "lr": 2.1702768942772686e-05, "gradient_norm": 0.28103014826774597, "tokens_per_second": 1124336.4636963059, "synthetic": false, "world_size": 8} {"step": 71600, "tokens": 18769510400, "loss": 2.3562788009643554, "optimizer_updates": 36800, "effective_batch": 512, "lr": 2.1688402314392e-05, "gradient_norm": 0.25691673159599304, "tokens_per_second": 1122342.5453990542, "synthetic": false, "world_size": 8} {"step": 71620, "tokens": 18774753280, "loss": 2.3547014236450194, "optimizer_updates": 36810, "effective_batch": 512, "lr": 2.1674095976325563e-05, "gradient_norm": 0.29111719131469727, "tokens_per_second": 1124443.2276073298, "synthetic": false, "world_size": 8} {"step": 71640, "tokens": 18779996160, "loss": 2.373801040649414, "optimizer_updates": 36820, "effective_batch": 512, "lr": 2.1659849938340307e-05, "gradient_norm": 0.26227447390556335, "tokens_per_second": 1122845.6138973928, "synthetic": false, "world_size": 8} {"step": 71660, "tokens": 18785239040, "loss": 2.3619962692260743, "optimizer_updates": 36830, "effective_batch": 512, "lr": 2.164566421016201e-05, "gradient_norm": 0.24943159520626068, "tokens_per_second": 1092548.3119735045, "synthetic": false, "world_size": 8} {"step": 71680, "tokens": 18790481920, "loss": 2.339933395385742, "optimizer_updates": 36840, "effective_batch": 512, "lr": 2.163153880147525e-05, "gradient_norm": 0.2495213896036148, "tokens_per_second": 1135489.107816175, "synthetic": false, "world_size": 8} {"step": 71700, "tokens": 18795724800, "loss": 2.3404144287109374, "optimizer_updates": 36850, "effective_batch": 512, "lr": 2.161747372192345e-05, "gradient_norm": 0.25402411818504333, "tokens_per_second": 1132461.242126284, "synthetic": false, "world_size": 8} {"step": 71720, "tokens": 18800967680, "loss": 2.332059860229492, "optimizer_updates": 36860, "effective_batch": 512, "lr": 2.160346898110884e-05, "gradient_norm": 0.2603985071182251, "tokens_per_second": 1131537.4970337308, "synthetic": false, "world_size": 8} {"step": 71740, "tokens": 18806210560, "loss": 2.3554624557495116, "optimizer_updates": 36870, "effective_batch": 512, "lr": 2.1589524588592454e-05, "gradient_norm": 0.23304051160812378, "tokens_per_second": 1132591.8527888276, "synthetic": false, "world_size": 8} {"step": 71760, "tokens": 18811453440, "loss": 2.349534034729004, "optimizer_updates": 36880, "effective_batch": 512, "lr": 2.1575640553894116e-05, "gradient_norm": 0.24301856756210327, "tokens_per_second": 1134300.9516116504, "synthetic": false, "world_size": 8} {"step": 71780, "tokens": 18816696320, "loss": 2.3490991592407227, "optimizer_updates": 36890, "effective_batch": 512, "lr": 2.1561816886492476e-05, "gradient_norm": 0.2440936267375946, "tokens_per_second": 1134445.7967588783, "synthetic": false, "world_size": 8} {"step": 71800, "tokens": 18821939200, "loss": 2.354788970947266, "optimizer_updates": 36900, "effective_batch": 512, "lr": 2.154805359582492e-05, "gradient_norm": 0.24624812602996826, "tokens_per_second": 1130722.0912960109, "synthetic": false, "world_size": 8} {"step": 71820, "tokens": 18827182080, "loss": 2.3600950241088867, "optimizer_updates": 36910, "effective_batch": 512, "lr": 2.153435069128767e-05, "gradient_norm": 0.23195910453796387, "tokens_per_second": 779390.3493009702, "synthetic": false, "world_size": 8} {"step": 71840, "tokens": 18832424960, "loss": 2.36269474029541, "optimizer_updates": 36920, "effective_batch": 512, "lr": 2.152070818223568e-05, "gradient_norm": 0.2534870207309723, "tokens_per_second": 1139610.6993788194, "synthetic": false, "world_size": 8} {"step": 71860, "tokens": 18837667840, "loss": 2.3611112594604493, "optimizer_updates": 36930, "effective_batch": 512, "lr": 2.1507126077982706e-05, "gradient_norm": 0.25356292724609375, "tokens_per_second": 1137127.4129584013, "synthetic": false, "world_size": 8} {"step": 71880, "tokens": 18842910720, "loss": 2.3698747634887694, "optimizer_updates": 36940, "effective_batch": 512, "lr": 2.1493604387801246e-05, "gradient_norm": 0.22414378821849823, "tokens_per_second": 1139519.3330299254, "synthetic": false, "world_size": 8} {"step": 71900, "tokens": 18848153600, "loss": 2.3437246322631835, "optimizer_updates": 36950, "effective_batch": 512, "lr": 2.1480143120922527e-05, "gradient_norm": 0.25724461674690247, "tokens_per_second": 1137797.5366448904, "synthetic": false, "world_size": 8} {"step": 71920, "tokens": 18853396480, "loss": 2.346647262573242, "optimizer_updates": 36960, "effective_batch": 512, "lr": 2.146674228653659e-05, "gradient_norm": 0.24298420548439026, "tokens_per_second": 1132596.457212869, "synthetic": false, "world_size": 8} {"step": 71940, "tokens": 18858639360, "loss": 2.354015922546387, "optimizer_updates": 36970, "effective_batch": 512, "lr": 2.1453401893792164e-05, "gradient_norm": 0.2868417203426361, "tokens_per_second": 1145298.0470642513, "synthetic": false, "world_size": 8} {"step": 71960, "tokens": 18863882240, "loss": 2.3418113708496096, "optimizer_updates": 36980, "effective_batch": 512, "lr": 2.1440121951796743e-05, "gradient_norm": 0.2571355998516083, "tokens_per_second": 1140552.2292432387, "synthetic": false, "world_size": 8} {"step": 71980, "tokens": 18869125120, "loss": 2.3615839004516603, "optimizer_updates": 36990, "effective_batch": 512, "lr": 2.1426902469616518e-05, "gradient_norm": 0.30845504999160767, "tokens_per_second": 1132420.805145767, "synthetic": false, "world_size": 8} {"step": 72000, "tokens": 18874368000, "loss": 2.342035484313965, "optimizer_updates": 37000, "effective_batch": 512, "lr": 2.1413743456276468e-05, "gradient_norm": 0.22949166595935822, "tokens_per_second": 1135886.0857135293, "synthetic": false, "world_size": 8} {"step": 72020, "tokens": 18879610880, "loss": 2.352756118774414, "optimizer_updates": 37010, "effective_batch": 512, "lr": 2.1400644920760206e-05, "gradient_norm": 0.28636807203292847, "tokens_per_second": 832365.6815717043, "synthetic": false, "world_size": 8} {"step": 72040, "tokens": 18884853760, "loss": 2.340286445617676, "optimizer_updates": 37020, "effective_batch": 512, "lr": 2.138760687201013e-05, "gradient_norm": 0.23012474179267883, "tokens_per_second": 813283.1932147059, "synthetic": false, "world_size": 8} {"step": 72060, "tokens": 18890096640, "loss": 2.349403190612793, "optimizer_updates": 37030, "effective_batch": 512, "lr": 2.13746293189273e-05, "gradient_norm": 0.24464242160320282, "tokens_per_second": 1137020.8086482203, "synthetic": false, "world_size": 8} {"step": 72080, "tokens": 18895339520, "loss": 2.346810531616211, "optimizer_updates": 37040, "effective_batch": 512, "lr": 2.13617122703715e-05, "gradient_norm": 0.28017616271972656, "tokens_per_second": 1136392.3542139009, "synthetic": false, "world_size": 8} {"step": 72100, "tokens": 18900582400, "loss": 2.349704551696777, "optimizer_updates": 37050, "effective_batch": 512, "lr": 2.134885573516119e-05, "gradient_norm": 0.25112634897232056, "tokens_per_second": 1135866.9867351316, "synthetic": false, "world_size": 8} {"step": 72120, "tokens": 18905825280, "loss": 2.3608013153076173, "optimizer_updates": 37060, "effective_batch": 512, "lr": 2.133605972207353e-05, "gradient_norm": 0.2611854374408722, "tokens_per_second": 1129094.2160547771, "synthetic": false, "world_size": 8} {"step": 72140, "tokens": 18911068160, "loss": 2.3509559631347656, "optimizer_updates": 37070, "effective_batch": 512, "lr": 2.132332423984434e-05, "gradient_norm": 0.2571161091327667, "tokens_per_second": 1135295.3908240423, "synthetic": false, "world_size": 8} {"step": 72160, "tokens": 18916311040, "loss": 2.3545150756835938, "optimizer_updates": 37080, "effective_batch": 512, "lr": 2.1310649297168153e-05, "gradient_norm": 0.30223438143730164, "tokens_per_second": 1133883.851088279, "synthetic": false, "world_size": 8} {"step": 72180, "tokens": 18921553920, "loss": 2.364065170288086, "optimizer_updates": 37090, "effective_batch": 512, "lr": 2.1298034902698135e-05, "gradient_norm": 0.26572278141975403, "tokens_per_second": 1135620.1515128142, "synthetic": false, "world_size": 8} {"step": 72200, "tokens": 18926796800, "loss": 2.3470941543579102, "optimizer_updates": 37100, "effective_batch": 512, "lr": 2.1285481065046146e-05, "gradient_norm": 0.2550433874130249, "tokens_per_second": 1131089.7908689827, "synthetic": false, "world_size": 8} {"step": 72220, "tokens": 18932039680, "loss": 2.346780014038086, "optimizer_updates": 37110, "effective_batch": 512, "lr": 2.127298779278267e-05, "gradient_norm": 0.24555812776088715, "tokens_per_second": 1137241.9709482454, "synthetic": false, "world_size": 8} {"step": 72240, "tokens": 18937282560, "loss": 2.3445444107055664, "optimizer_updates": 37120, "effective_batch": 512, "lr": 2.126055509443687e-05, "gradient_norm": 0.23136352002620697, "tokens_per_second": 1129936.6853964846, "synthetic": false, "world_size": 8} {"step": 72260, "tokens": 18942525440, "loss": 2.3514034271240236, "optimizer_updates": 37130, "effective_batch": 512, "lr": 2.124818297849656e-05, "gradient_norm": 0.23981888592243195, "tokens_per_second": 1131857.6181075545, "synthetic": false, "world_size": 8} {"step": 72280, "tokens": 18947768320, "loss": 2.3457321166992187, "optimizer_updates": 37140, "effective_batch": 512, "lr": 2.1235871453408163e-05, "gradient_norm": 0.24167726933956146, "tokens_per_second": 1137156.0295971176, "synthetic": false, "world_size": 8} {"step": 72300, "tokens": 18953011200, "loss": 2.3431022644042967, "optimizer_updates": 37150, "effective_batch": 512, "lr": 2.1223620527576774e-05, "gradient_norm": 0.250996857881546, "tokens_per_second": 1136802.1259891966, "synthetic": false, "world_size": 8} {"step": 72320, "tokens": 18958254080, "loss": 2.3522077560424806, "optimizer_updates": 37160, "effective_batch": 512, "lr": 2.1211430209366074e-05, "gradient_norm": 0.22973915934562683, "tokens_per_second": 1130108.5906076108, "synthetic": false, "world_size": 8} {"step": 72340, "tokens": 18963496960, "loss": 2.356648826599121, "optimizer_updates": 37170, "effective_batch": 512, "lr": 2.1199300507098417e-05, "gradient_norm": 0.24641352891921997, "tokens_per_second": 1134459.3455700062, "synthetic": false, "world_size": 8} {"step": 72360, "tokens": 18968739840, "loss": 2.3720205307006834, "optimizer_updates": 37180, "effective_batch": 512, "lr": 2.1187231429054725e-05, "gradient_norm": 0.24164272844791412, "tokens_per_second": 1137722.480483727, "synthetic": false, "world_size": 8} {"step": 72380, "tokens": 18973982720, "loss": 2.355438804626465, "optimizer_updates": 37190, "effective_batch": 512, "lr": 2.117522298347458e-05, "gradient_norm": 0.2653205692768097, "tokens_per_second": 1128186.3824971786, "synthetic": false, "world_size": 8} {"step": 72400, "tokens": 18979225600, "loss": 2.359330749511719, "optimizer_updates": 37200, "effective_batch": 512, "lr": 2.116327517855613e-05, "gradient_norm": 0.24858398735523224, "tokens_per_second": 1126487.252733926, "synthetic": false, "world_size": 8} {"step": 72420, "tokens": 18984468480, "loss": 2.347584533691406, "optimizer_updates": 37210, "effective_batch": 512, "lr": 2.1151388022456144e-05, "gradient_norm": 0.2768903076648712, "tokens_per_second": 1122092.1060477414, "synthetic": false, "world_size": 8} {"step": 72440, "tokens": 18989711360, "loss": 2.3488216400146484, "optimizer_updates": 37220, "effective_batch": 512, "lr": 2.1139561523289975e-05, "gradient_norm": 0.24354898929595947, "tokens_per_second": 1132669.5621811533, "synthetic": false, "world_size": 8} {"step": 72460, "tokens": 18994954240, "loss": 2.341145896911621, "optimizer_updates": 37230, "effective_batch": 512, "lr": 2.1127795689131583e-05, "gradient_norm": 0.2523902356624603, "tokens_per_second": 1124034.1676015921, "synthetic": false, "world_size": 8} {"step": 72480, "tokens": 19000197120, "loss": 2.3492918014526367, "optimizer_updates": 37240, "effective_batch": 512, "lr": 2.1116090528013494e-05, "gradient_norm": 0.3062882721424103, "tokens_per_second": 1129043.3708512106, "synthetic": false, "world_size": 8} {"step": 72500, "tokens": 19005440000, "loss": 2.335565948486328, "optimizer_updates": 37250, "effective_batch": 512, "lr": 2.1104446047926825e-05, "gradient_norm": 0.24463912844657898, "tokens_per_second": 1128990.2714780169, "synthetic": false, "world_size": 8} {"step": 72520, "tokens": 19010682880, "loss": 2.346017074584961, "optimizer_updates": 37260, "effective_batch": 512, "lr": 2.1092862256821256e-05, "gradient_norm": 0.2413727343082428, "tokens_per_second": 1135661.845056761, "synthetic": false, "world_size": 8} {"step": 72540, "tokens": 19015925760, "loss": 2.3476734161376953, "optimizer_updates": 37270, "effective_batch": 512, "lr": 2.108133916260504e-05, "gradient_norm": 0.23760706186294556, "tokens_per_second": 1133009.8128479787, "synthetic": false, "world_size": 8} {"step": 72560, "tokens": 19021168640, "loss": 2.3451128005981445, "optimizer_updates": 37280, "effective_batch": 512, "lr": 2.1069876773144997e-05, "gradient_norm": 0.2924901843070984, "tokens_per_second": 752427.6592826827, "synthetic": false, "world_size": 8} {"step": 72580, "tokens": 19026411520, "loss": 2.3572904586791994, "optimizer_updates": 37290, "effective_batch": 512, "lr": 2.1058475096266497e-05, "gradient_norm": 0.23667411506175995, "tokens_per_second": 1139230.3600421317, "synthetic": false, "world_size": 8} {"step": 72600, "tokens": 19031654400, "loss": 2.3561775207519533, "optimizer_updates": 37300, "effective_batch": 512, "lr": 2.104713413975344e-05, "gradient_norm": 0.2679399847984314, "tokens_per_second": 1136456.4180641915, "synthetic": false, "world_size": 8} {"step": 72620, "tokens": 19036897280, "loss": 2.3721282958984373, "optimizer_updates": 37310, "effective_batch": 512, "lr": 2.103585391134834e-05, "gradient_norm": 0.2944013476371765, "tokens_per_second": 1058358.8148198181, "synthetic": false, "world_size": 8} {"step": 72640, "tokens": 19042140160, "loss": 2.3448156356811523, "optimizer_updates": 37320, "effective_batch": 512, "lr": 2.102463441875217e-05, "gradient_norm": 0.2713184058666229, "tokens_per_second": 805542.7512921297, "synthetic": false, "world_size": 8} {"step": 72660, "tokens": 19047383040, "loss": 2.3557825088500977, "optimizer_updates": 37330, "effective_batch": 512, "lr": 2.101347566962449e-05, "gradient_norm": 0.272565633058548, "tokens_per_second": 1132815.2139913265, "synthetic": false, "world_size": 8} {"step": 72680, "tokens": 19052625920, "loss": 2.358526420593262, "optimizer_updates": 37340, "effective_batch": 512, "lr": 2.100237767158338e-05, "gradient_norm": 0.2381671518087387, "tokens_per_second": 1139308.9043567828, "synthetic": false, "world_size": 8} {"step": 72700, "tokens": 19057868800, "loss": 2.3382936477661134, "optimizer_updates": 37350, "effective_batch": 512, "lr": 2.0991340432205425e-05, "gradient_norm": 0.2502381503582001, "tokens_per_second": 1017038.0042110536, "synthetic": false, "world_size": 8} {"step": 72720, "tokens": 19063111680, "loss": 2.3586828231811525, "optimizer_updates": 37360, "effective_batch": 512, "lr": 2.0980363959025775e-05, "gradient_norm": 0.2539898753166199, "tokens_per_second": 1142427.4261514386, "synthetic": false, "world_size": 8} {"step": 72740, "tokens": 19068354560, "loss": 2.362599182128906, "optimizer_updates": 37370, "effective_batch": 512, "lr": 2.0969448259538035e-05, "gradient_norm": 0.2667381465435028, "tokens_per_second": 1139132.577722489, "synthetic": false, "world_size": 8} {"step": 72760, "tokens": 19073597440, "loss": 2.339536666870117, "optimizer_updates": 37380, "effective_batch": 512, "lr": 2.095859334119438e-05, "gradient_norm": 0.2898012697696686, "tokens_per_second": 1134909.4745985088, "synthetic": false, "world_size": 8} {"step": 72780, "tokens": 19078840320, "loss": 2.3512990951538084, "optimizer_updates": 37390, "effective_batch": 512, "lr": 2.0947799211405438e-05, "gradient_norm": 0.2356250137090683, "tokens_per_second": 1130569.8335093535, "synthetic": false, "world_size": 8} {"step": 72800, "tokens": 19084083200, "loss": 2.3598453521728517, "optimizer_updates": 37400, "effective_batch": 512, "lr": 2.0937065877540368e-05, "gradient_norm": 0.2797573208808899, "tokens_per_second": 1137406.6312219263, "synthetic": false, "world_size": 8} {"step": 72820, "tokens": 19089326080, "loss": 2.351925086975098, "optimizer_updates": 37410, "effective_batch": 512, "lr": 2.0926393346926824e-05, "gradient_norm": 0.27185580134391785, "tokens_per_second": 1136946.856900873, "synthetic": false, "world_size": 8} {"step": 72840, "tokens": 19094568960, "loss": 2.3460050582885743, "optimizer_updates": 37420, "effective_batch": 512, "lr": 2.0915781626850932e-05, "gradient_norm": 0.24759754538536072, "tokens_per_second": 1130532.5325942487, "synthetic": false, "world_size": 8} {"step": 72860, "tokens": 19099811840, "loss": 2.3363925933837892, "optimizer_updates": 37430, "effective_batch": 512, "lr": 2.0905230724557316e-05, "gradient_norm": 0.2365262508392334, "tokens_per_second": 1139087.4074416982, "synthetic": false, "world_size": 8} {"step": 72880, "tokens": 19105054720, "loss": 2.350075340270996, "optimizer_updates": 37440, "effective_batch": 512, "lr": 2.0894740647249064e-05, "gradient_norm": 0.272710382938385, "tokens_per_second": 1131264.9462921813, "synthetic": false, "world_size": 8} {"step": 72900, "tokens": 19110297600, "loss": 2.344301223754883, "optimizer_updates": 37450, "effective_batch": 512, "lr": 2.0884311402087763e-05, "gradient_norm": 0.35765159130096436, "tokens_per_second": 1137494.462662365, "synthetic": false, "world_size": 8} {"step": 72920, "tokens": 19115540480, "loss": 2.345991325378418, "optimizer_updates": 37460, "effective_batch": 512, "lr": 2.087394299619345e-05, "gradient_norm": 0.2407417744398117, "tokens_per_second": 1137856.2982578499, "synthetic": false, "world_size": 8} {"step": 72940, "tokens": 19120783360, "loss": 2.3615922927856445, "optimizer_updates": 37470, "effective_batch": 512, "lr": 2.086363543664464e-05, "gradient_norm": 0.2552686333656311, "tokens_per_second": 1132205.916034432, "synthetic": false, "world_size": 8} {"step": 72960, "tokens": 19126026240, "loss": 2.3370853424072267, "optimizer_updates": 37480, "effective_batch": 512, "lr": 2.08533887304783e-05, "gradient_norm": 0.24677817523479462, "tokens_per_second": 1141697.2442582834, "synthetic": false, "world_size": 8} {"step": 72980, "tokens": 19131269120, "loss": 2.360098648071289, "optimizer_updates": 37490, "effective_batch": 512, "lr": 2.0843202884689846e-05, "gradient_norm": 0.2384667545557022, "tokens_per_second": 1143671.2440106573, "synthetic": false, "world_size": 8} {"step": 73000, "tokens": 19136512000, "loss": 2.3513935089111326, "optimizer_updates": 37500, "effective_batch": 512, "lr": 2.0833077906233167e-05, "gradient_norm": 0.30938485264778137, "tokens_per_second": 1129127.0585372897, "synthetic": false, "world_size": 8} {"step": 73020, "tokens": 19141754880, "loss": 2.3493370056152343, "optimizer_updates": 37510, "effective_batch": 512, "lr": 2.0823013802020586e-05, "gradient_norm": 0.23307764530181885, "tokens_per_second": 833708.2111341133, "synthetic": false, "world_size": 8} {"step": 73040, "tokens": 19146997760, "loss": 2.355885696411133, "optimizer_updates": 37520, "effective_batch": 512, "lr": 2.081301057892285e-05, "gradient_norm": 0.24313797056674957, "tokens_per_second": 1138378.8062092594, "synthetic": false, "world_size": 8} {"step": 73060, "tokens": 19152240640, "loss": 2.3485240936279297, "optimizer_updates": 37530, "effective_batch": 512, "lr": 2.0803068243769164e-05, "gradient_norm": 0.2384326457977295, "tokens_per_second": 1143499.5759393314, "synthetic": false, "world_size": 8} {"step": 73080, "tokens": 19157483520, "loss": 2.346755599975586, "optimizer_updates": 37540, "effective_batch": 512, "lr": 2.0793186803347163e-05, "gradient_norm": 0.25991466641426086, "tokens_per_second": 1139161.3210768315, "synthetic": false, "world_size": 8} {"step": 73100, "tokens": 19162726400, "loss": 2.3529899597167967, "optimizer_updates": 37550, "effective_batch": 512, "lr": 2.0783366264402902e-05, "gradient_norm": 0.2623242735862732, "tokens_per_second": 1137715.4732931245, "synthetic": false, "world_size": 8} {"step": 73120, "tokens": 19167969280, "loss": 2.3587791442871096, "optimizer_updates": 37560, "effective_batch": 512, "lr": 2.077360663364087e-05, "gradient_norm": 0.23246154189109802, "tokens_per_second": 801576.4957038347, "synthetic": false, "world_size": 8} {"step": 73140, "tokens": 19173212160, "loss": 2.3491783142089844, "optimizer_updates": 37570, "effective_batch": 512, "lr": 2.0763907917723947e-05, "gradient_norm": 0.2611556351184845, "tokens_per_second": 1144389.8497505432, "synthetic": false, "world_size": 8} {"step": 73160, "tokens": 19178455040, "loss": 2.352339172363281, "optimizer_updates": 37580, "effective_batch": 512, "lr": 2.0754270123273465e-05, "gradient_norm": 0.257702112197876, "tokens_per_second": 1135089.637955094, "synthetic": false, "world_size": 8} {"step": 73180, "tokens": 19183697920, "loss": 2.359170150756836, "optimizer_updates": 37590, "effective_batch": 512, "lr": 2.074469325686913e-05, "gradient_norm": 0.29307347536087036, "tokens_per_second": 1139048.6827233208, "synthetic": false, "world_size": 8} {"step": 73200, "tokens": 19188940800, "loss": 2.347711944580078, "optimizer_updates": 37600, "effective_batch": 512, "lr": 2.0735177325049064e-05, "gradient_norm": 0.23785419762134552, "tokens_per_second": 1138994.6192557155, "synthetic": false, "world_size": 8} {"step": 73220, "tokens": 19194183680, "loss": 2.3440488815307616, "optimizer_updates": 37610, "effective_batch": 512, "lr": 2.072572233430981e-05, "gradient_norm": 0.26288673281669617, "tokens_per_second": 1133938.6949461568, "synthetic": false, "world_size": 8} {"step": 73240, "tokens": 19199426560, "loss": 2.3486000061035157, "optimizer_updates": 37620, "effective_batch": 512, "lr": 2.0716328291106274e-05, "gradient_norm": 0.2605152130126953, "tokens_per_second": 1131866.3838062545, "synthetic": false, "world_size": 8} {"step": 73260, "tokens": 19204669440, "loss": 2.3494285583496093, "optimizer_updates": 37630, "effective_batch": 512, "lr": 2.070699520185178e-05, "gradient_norm": 0.2544451653957367, "tokens_per_second": 1145028.4092559132, "synthetic": false, "world_size": 8} {"step": 73280, "tokens": 19209912320, "loss": 2.3591777801513674, "optimizer_updates": 37640, "effective_batch": 512, "lr": 2.0697723072918013e-05, "gradient_norm": 0.2506971061229706, "tokens_per_second": 1141757.6913598592, "synthetic": false, "world_size": 8} {"step": 73300, "tokens": 19215155200, "loss": 2.348293685913086, "optimizer_updates": 37650, "effective_batch": 512, "lr": 2.0688511910635063e-05, "gradient_norm": 0.24889828264713287, "tokens_per_second": 1132510.438790727, "synthetic": false, "world_size": 8} {"step": 73320, "tokens": 19220398080, "loss": 2.3563560485839843, "optimizer_updates": 37660, "effective_batch": 512, "lr": 2.0679361721291385e-05, "gradient_norm": 0.24667488038539886, "tokens_per_second": 1030883.4607607542, "synthetic": false, "world_size": 8} {"step": 73340, "tokens": 19225640960, "loss": 2.353458595275879, "optimizer_updates": 37670, "effective_batch": 512, "lr": 2.0670272511133813e-05, "gradient_norm": 0.24630336463451385, "tokens_per_second": 1123292.6829129793, "synthetic": false, "world_size": 8} {"step": 73360, "tokens": 19230883840, "loss": 2.340275001525879, "optimizer_updates": 37680, "effective_batch": 512, "lr": 2.066124428636755e-05, "gradient_norm": 0.2511838972568512, "tokens_per_second": 1120826.7038611963, "synthetic": false, "world_size": 8} {"step": 73380, "tokens": 19236126720, "loss": 2.356007194519043, "optimizer_updates": 37690, "effective_batch": 512, "lr": 2.0652277053156172e-05, "gradient_norm": 0.2284698337316513, "tokens_per_second": 1122491.6097996058, "synthetic": false, "world_size": 8} {"step": 73400, "tokens": 19241369600, "loss": 2.3434303283691404, "optimizer_updates": 37700, "effective_batch": 512, "lr": 2.0643370817621586e-05, "gradient_norm": 0.2617507576942444, "tokens_per_second": 1117321.9977090596, "synthetic": false, "world_size": 8} {"step": 73420, "tokens": 19246612480, "loss": 2.350352096557617, "optimizer_updates": 37710, "effective_batch": 512, "lr": 2.0634525585844106e-05, "gradient_norm": 0.2279311716556549, "tokens_per_second": 1119513.8043544563, "synthetic": false, "world_size": 8} {"step": 73440, "tokens": 19251855360, "loss": 2.3406244277954102, "optimizer_updates": 37720, "effective_batch": 512, "lr": 2.062574136386235e-05, "gradient_norm": 0.26854798197746277, "tokens_per_second": 1123391.0784666045, "synthetic": false, "world_size": 8} {"step": 73460, "tokens": 19257098240, "loss": 2.3493864059448244, "optimizer_updates": 37730, "effective_batch": 512, "lr": 2.061701815767331e-05, "gradient_norm": 0.2552768886089325, "tokens_per_second": 1127079.2890068158, "synthetic": false, "world_size": 8} {"step": 73480, "tokens": 19262341120, "loss": 2.343487548828125, "optimizer_updates": 37740, "effective_batch": 512, "lr": 2.060835597323231e-05, "gradient_norm": 0.25137585401535034, "tokens_per_second": 1125712.615674478, "synthetic": false, "world_size": 8} {"step": 73500, "tokens": 19267584000, "loss": 2.3381511688232424, "optimizer_updates": 37750, "effective_batch": 512, "lr": 2.059975481645304e-05, "gradient_norm": 0.234447181224823, "tokens_per_second": 1123874.0487668384, "synthetic": false, "world_size": 8} {"step": 73520, "tokens": 19272826880, "loss": 2.3384618759155273, "optimizer_updates": 37760, "effective_batch": 512, "lr": 2.0591214693207497e-05, "gradient_norm": 0.24201780557632446, "tokens_per_second": 1129621.9796361097, "synthetic": false, "world_size": 8} {"step": 73540, "tokens": 19278069760, "loss": 2.3550376892089844, "optimizer_updates": 37770, "effective_batch": 512, "lr": 2.058273560932602e-05, "gradient_norm": 0.2618163824081421, "tokens_per_second": 1133641.1870272981, "synthetic": false, "world_size": 8} {"step": 73560, "tokens": 19283312640, "loss": 2.360866928100586, "optimizer_updates": 37780, "effective_batch": 512, "lr": 2.0574317570597284e-05, "gradient_norm": 0.24373319745063782, "tokens_per_second": 1126098.7914293536, "synthetic": false, "world_size": 8} {"step": 73580, "tokens": 19288555520, "loss": 2.3555532455444337, "optimizer_updates": 37790, "effective_batch": 512, "lr": 2.0565960582768273e-05, "gradient_norm": 0.254404217004776, "tokens_per_second": 1125653.6744913782, "synthetic": false, "world_size": 8} {"step": 73600, "tokens": 19293798400, "loss": 2.3550083160400392, "optimizer_updates": 37800, "effective_batch": 512, "lr": 2.0557664651544316e-05, "gradient_norm": 0.24240340292453766, "tokens_per_second": 1132071.1596192329, "synthetic": false, "world_size": 8} {"step": 73620, "tokens": 19299041280, "loss": 2.3565927505493165, "optimizer_updates": 37810, "effective_batch": 512, "lr": 2.054942978258903e-05, "gradient_norm": 0.26521337032318115, "tokens_per_second": 1135199.37441024, "synthetic": false, "world_size": 8} {"step": 73640, "tokens": 19304284160, "loss": 2.350805473327637, "optimizer_updates": 37820, "effective_batch": 512, "lr": 2.0541255981524377e-05, "gradient_norm": 0.24770550429821014, "tokens_per_second": 1130476.9452144313, "synthetic": false, "world_size": 8} {"step": 73660, "tokens": 19309527040, "loss": 2.3513954162597654, "optimizer_updates": 37830, "effective_batch": 512, "lr": 2.0533143253930583e-05, "gradient_norm": 0.24152925610542297, "tokens_per_second": 1131992.8733692402, "synthetic": false, "world_size": 8} {"step": 73680, "tokens": 19314769920, "loss": 2.3559179306030273, "optimizer_updates": 37840, "effective_batch": 512, "lr": 2.052509160534623e-05, "gradient_norm": 0.2540898621082306, "tokens_per_second": 1137871.6331686117, "synthetic": false, "world_size": 8} {"step": 73700, "tokens": 19320012800, "loss": 2.350739669799805, "optimizer_updates": 37850, "effective_batch": 512, "lr": 2.0517101041268163e-05, "gradient_norm": 0.2984405755996704, "tokens_per_second": 1131108.0147735872, "synthetic": false, "world_size": 8} {"step": 73720, "tokens": 19325255680, "loss": 2.359149360656738, "optimizer_updates": 37860, "effective_batch": 512, "lr": 2.0509171567151554e-05, "gradient_norm": 0.269822895526886, "tokens_per_second": 1134681.813244618, "synthetic": false, "world_size": 8} {"step": 73740, "tokens": 19330498560, "loss": 2.3425817489624023, "optimizer_updates": 37870, "effective_batch": 512, "lr": 2.0501303188409846e-05, "gradient_norm": 0.2302575558423996, "tokens_per_second": 1132076.9490356145, "synthetic": false, "world_size": 8} {"step": 73760, "tokens": 19335741440, "loss": 2.351833724975586, "optimizer_updates": 37880, "effective_batch": 512, "lr": 2.0493495910414765e-05, "gradient_norm": 0.2387900948524475, "tokens_per_second": 1137123.6533209411, "synthetic": false, "world_size": 8} {"step": 73780, "tokens": 19340984320, "loss": 2.346150207519531, "optimizer_updates": 37890, "effective_batch": 512, "lr": 2.0485749738496358e-05, "gradient_norm": 0.26029765605926514, "tokens_per_second": 1017936.6146227485, "synthetic": false, "world_size": 8} {"step": 73800, "tokens": 19346227200, "loss": 2.341446113586426, "optimizer_updates": 37900, "effective_batch": 512, "lr": 2.0478064677942926e-05, "gradient_norm": 0.24448350071907043, "tokens_per_second": 1135842.3293143415, "synthetic": false, "world_size": 8} {"step": 73820, "tokens": 19351470080, "loss": 2.343307113647461, "optimizer_updates": 37910, "effective_batch": 512, "lr": 2.0470440734001058e-05, "gradient_norm": 0.2861296832561493, "tokens_per_second": 1134976.1630187726, "synthetic": false, "world_size": 8} {"step": 73840, "tokens": 19356712960, "loss": 2.3444894790649413, "optimizer_updates": 37920, "effective_batch": 512, "lr": 2.0462877911875627e-05, "gradient_norm": 0.25443363189697266, "tokens_per_second": 1123069.2293806125, "synthetic": false, "world_size": 8} {"step": 73860, "tokens": 19361955840, "loss": 2.348514366149902, "optimizer_updates": 37930, "effective_batch": 512, "lr": 2.0455376216729763e-05, "gradient_norm": 0.25639861822128296, "tokens_per_second": 1133113.9008828716, "synthetic": false, "world_size": 8} {"step": 73880, "tokens": 19367198720, "loss": 2.3458080291748047, "optimizer_updates": 37940, "effective_batch": 512, "lr": 2.0447935653684884e-05, "gradient_norm": 0.24115248024463654, "tokens_per_second": 1136914.4400402743, "synthetic": false, "world_size": 8} {"step": 73900, "tokens": 19372441600, "loss": 2.3430789947509765, "optimizer_updates": 37950, "effective_batch": 512, "lr": 2.044055622782065e-05, "gradient_norm": 0.2579927444458008, "tokens_per_second": 1134142.1423858062, "synthetic": false, "world_size": 8} {"step": 73920, "tokens": 19377684480, "loss": 2.366030693054199, "optimizer_updates": 37960, "effective_batch": 512, "lr": 2.0433237944174993e-05, "gradient_norm": 0.3002156615257263, "tokens_per_second": 1130054.7693817334, "synthetic": false, "world_size": 8} {"step": 73940, "tokens": 19382927360, "loss": 2.3473394393920897, "optimizer_updates": 37970, "effective_batch": 512, "lr": 2.04259808077441e-05, "gradient_norm": 0.2413209080696106, "tokens_per_second": 1129613.5570761398, "synthetic": false, "world_size": 8} {"step": 73960, "tokens": 19388170240, "loss": 2.345937728881836, "optimizer_updates": 37980, "effective_batch": 512, "lr": 2.0418784823482434e-05, "gradient_norm": 0.24413162469863892, "tokens_per_second": 1132102.667242515, "synthetic": false, "world_size": 8} {"step": 73980, "tokens": 19393413120, "loss": 2.3547380447387694, "optimizer_updates": 37990, "effective_batch": 512, "lr": 2.0411649996302677e-05, "gradient_norm": 0.24089355766773224, "tokens_per_second": 1135947.2818292573, "synthetic": false, "world_size": 8} {"step": 74000, "tokens": 19398656000, "loss": 2.342474365234375, "optimizer_updates": 38000, "effective_batch": 512, "lr": 2.0404576331075782e-05, "gradient_norm": 0.2523256242275238, "tokens_per_second": 1124672.7282085326, "synthetic": false, "world_size": 8} {"step": 74020, "tokens": 19403898880, "loss": 2.3549123764038087, "optimizer_updates": 38010, "effective_batch": 512, "lr": 2.039756383263095e-05, "gradient_norm": 0.2557011544704437, "tokens_per_second": 601132.4950364352, "synthetic": false, "world_size": 8} {"step": 74040, "tokens": 19409141760, "loss": 2.3398410797119142, "optimizer_updates": 38020, "effective_batch": 512, "lr": 2.0390612505755584e-05, "gradient_norm": 0.23233187198638916, "tokens_per_second": 1139642.2661568983, "synthetic": false, "world_size": 8} {"step": 74060, "tokens": 19414384640, "loss": 2.3476943969726562, "optimizer_updates": 38030, "effective_batch": 512, "lr": 2.0383722355195382e-05, "gradient_norm": 0.2417163848876953, "tokens_per_second": 1139657.763218872, "synthetic": false, "world_size": 8} {"step": 74080, "tokens": 19419627520, "loss": 2.350772476196289, "optimizer_updates": 38040, "effective_batch": 512, "lr": 2.0376893385654232e-05, "gradient_norm": 0.2476654350757599, "tokens_per_second": 1138640.0255209592, "synthetic": false, "world_size": 8} {"step": 74100, "tokens": 19424870400, "loss": 2.3487682342529297, "optimizer_updates": 38050, "effective_batch": 512, "lr": 2.037012560179427e-05, "gradient_norm": 0.24240341782569885, "tokens_per_second": 1142864.035902562, "synthetic": false, "world_size": 8} {"step": 74120, "tokens": 19430113280, "loss": 2.351031684875488, "optimizer_updates": 38060, "effective_batch": 512, "lr": 2.036341900823588e-05, "gradient_norm": 0.26396656036376953, "tokens_per_second": 1130474.6634109856, "synthetic": false, "world_size": 8} {"step": 74140, "tokens": 19435356160, "loss": 2.358123779296875, "optimizer_updates": 38070, "effective_batch": 512, "lr": 2.035677360955763e-05, "gradient_norm": 0.2550069987773895, "tokens_per_second": 1134813.419562354, "synthetic": false, "world_size": 8} {"step": 74160, "tokens": 19440599040, "loss": 2.3465652465820312, "optimizer_updates": 38080, "effective_batch": 512, "lr": 2.0350189410296333e-05, "gradient_norm": 0.23409560322761536, "tokens_per_second": 1132542.5905517975, "synthetic": false, "world_size": 8} {"step": 74180, "tokens": 19445841920, "loss": 2.3488462448120115, "optimizer_updates": 38090, "effective_batch": 512, "lr": 2.0343666414947038e-05, "gradient_norm": 0.27321794629096985, "tokens_per_second": 1136093.383247023, "synthetic": false, "world_size": 8} {"step": 74200, "tokens": 19451084800, "loss": 2.348336029052734, "optimizer_updates": 38100, "effective_batch": 512, "lr": 2.0337204627962986e-05, "gradient_norm": 0.2446317970752716, "tokens_per_second": 1137481.5171492305, "synthetic": false, "world_size": 8} {"step": 74220, "tokens": 19456327680, "loss": 2.3393184661865236, "optimizer_updates": 38110, "effective_batch": 512, "lr": 2.033080405375563e-05, "gradient_norm": 0.25538361072540283, "tokens_per_second": 1143730.057756014, "synthetic": false, "world_size": 8} {"step": 74240, "tokens": 19461570560, "loss": 2.3485918045043945, "optimizer_updates": 38120, "effective_batch": 512, "lr": 2.032446469669465e-05, "gradient_norm": 0.3141533136367798, "tokens_per_second": 1130996.1032677717, "synthetic": false, "world_size": 8} {"step": 74260, "tokens": 19466813440, "loss": 2.3569854736328124, "optimizer_updates": 38130, "effective_batch": 512, "lr": 2.031818656110792e-05, "gradient_norm": 0.25716426968574524, "tokens_per_second": 1142811.4201446117, "synthetic": false, "world_size": 8} {"step": 74280, "tokens": 19472056320, "loss": 2.3376754760742187, "optimizer_updates": 38140, "effective_batch": 512, "lr": 2.031196965128152e-05, "gradient_norm": 0.23796510696411133, "tokens_per_second": 802871.7391447404, "synthetic": false, "world_size": 8} {"step": 74300, "tokens": 19477299200, "loss": 2.3563825607299806, "optimizer_updates": 38150, "effective_batch": 512, "lr": 2.0305813971459736e-05, "gradient_norm": 0.2686919867992401, "tokens_per_second": 1129713.0729050373, "synthetic": false, "world_size": 8} {"step": 74320, "tokens": 19482542080, "loss": 2.3530742645263674, "optimizer_updates": 38160, "effective_batch": 512, "lr": 2.0299719525845057e-05, "gradient_norm": 0.3317382335662842, "tokens_per_second": 1137860.047418475, "synthetic": false, "world_size": 8} {"step": 74340, "tokens": 19487784960, "loss": 2.3571557998657227, "optimizer_updates": 38170, "effective_batch": 512, "lr": 2.0293686318598155e-05, "gradient_norm": 0.2620362639427185, "tokens_per_second": 1131996.9562429425, "synthetic": false, "world_size": 8} {"step": 74360, "tokens": 19493027840, "loss": 2.3384426116943358, "optimizer_updates": 38180, "effective_batch": 512, "lr": 2.0287714353837887e-05, "gradient_norm": 0.2780921757221222, "tokens_per_second": 1138928.547187581, "synthetic": false, "world_size": 8} {"step": 74380, "tokens": 19498270720, "loss": 2.3459959030151367, "optimizer_updates": 38190, "effective_batch": 512, "lr": 2.0281803635641338e-05, "gradient_norm": 0.233789324760437, "tokens_per_second": 1136413.5042494847, "synthetic": false, "world_size": 8} {"step": 74400, "tokens": 19503513600, "loss": 2.3532209396362305, "optimizer_updates": 38200, "effective_batch": 512, "lr": 2.027595416804373e-05, "gradient_norm": 0.2636074125766754, "tokens_per_second": 1126210.079345033, "synthetic": false, "world_size": 8} {"step": 74420, "tokens": 19508756480, "loss": 2.3569807052612304, "optimizer_updates": 38210, "effective_batch": 512, "lr": 2.0270165955038503e-05, "gradient_norm": 0.24036240577697754, "tokens_per_second": 1121924.5115872587, "synthetic": false, "world_size": 8} {"step": 74440, "tokens": 19513999360, "loss": 2.343344306945801, "optimizer_updates": 38220, "effective_batch": 512, "lr": 2.0264439000577272e-05, "gradient_norm": 0.24070046842098236, "tokens_per_second": 1132510.7749283998, "synthetic": false, "world_size": 8} {"step": 74460, "tokens": 19519242240, "loss": 2.3399936676025392, "optimizer_updates": 38230, "effective_batch": 512, "lr": 2.0258773308569833e-05, "gradient_norm": 0.23949575424194336, "tokens_per_second": 1134786.0078020862, "synthetic": false, "world_size": 8} {"step": 74480, "tokens": 19524485120, "loss": 2.346591567993164, "optimizer_updates": 38240, "effective_batch": 512, "lr": 2.025316888288414e-05, "gradient_norm": 0.25688666105270386, "tokens_per_second": 1126368.8326037673, "synthetic": false, "world_size": 8} {"step": 74500, "tokens": 19529728000, "loss": 2.346331787109375, "optimizer_updates": 38250, "effective_batch": 512, "lr": 2.024762572734633e-05, "gradient_norm": 0.25446775555610657, "tokens_per_second": 1122652.1169571138, "synthetic": false, "world_size": 8} {"step": 74520, "tokens": 19534970880, "loss": 2.3676830291748048, "optimizer_updates": 38260, "effective_batch": 512, "lr": 2.0242143845740736e-05, "gradient_norm": 0.25048819184303284, "tokens_per_second": 1131983.8325385803, "synthetic": false, "world_size": 8} {"step": 74540, "tokens": 19540213760, "loss": 2.3570526123046873, "optimizer_updates": 38270, "effective_batch": 512, "lr": 2.023672324180982e-05, "gradient_norm": 0.24344739317893982, "tokens_per_second": 1128841.5989361247, "synthetic": false, "world_size": 8} {"step": 74560, "tokens": 19545456640, "loss": 2.3443140029907226, "optimizer_updates": 38280, "effective_batch": 512, "lr": 2.023136391925424e-05, "gradient_norm": 0.2686115503311157, "tokens_per_second": 1129352.6533037357, "synthetic": false, "world_size": 8} {"step": 74580, "tokens": 19550699520, "loss": 2.3568441390991213, "optimizer_updates": 38290, "effective_batch": 512, "lr": 2.0226065881732784e-05, "gradient_norm": 0.24661293625831604, "tokens_per_second": 1133111.12918185, "synthetic": false, "world_size": 8} {"step": 74600, "tokens": 19555942400, "loss": 2.347968101501465, "optimizer_updates": 38300, "effective_batch": 512, "lr": 2.022082913286244e-05, "gradient_norm": 0.25291410088539124, "tokens_per_second": 1119611.1724487625, "synthetic": false, "world_size": 8} {"step": 74620, "tokens": 19561185280, "loss": 2.3430099487304688, "optimizer_updates": 38310, "effective_batch": 512, "lr": 2.0215653676218337e-05, "gradient_norm": 0.254476934671402, "tokens_per_second": 1128706.2602349692, "synthetic": false, "world_size": 8} {"step": 74640, "tokens": 19566428160, "loss": 2.354228973388672, "optimizer_updates": 38320, "effective_batch": 512, "lr": 2.0210539515333746e-05, "gradient_norm": 0.26082929968833923, "tokens_per_second": 1131801.1905723645, "synthetic": false, "world_size": 8} {"step": 74660, "tokens": 19571671040, "loss": 2.356472396850586, "optimizer_updates": 38330, "effective_batch": 512, "lr": 2.0205486653700113e-05, "gradient_norm": 0.2647876441478729, "tokens_per_second": 1126003.620981196, "synthetic": false, "world_size": 8} {"step": 74680, "tokens": 19576913920, "loss": 2.3486862182617188, "optimizer_updates": 38340, "effective_batch": 512, "lr": 2.0200495094767026e-05, "gradient_norm": 0.2534635066986084, "tokens_per_second": 1137002.773691582, "synthetic": false, "world_size": 8} {"step": 74700, "tokens": 19582156800, "loss": 2.351612854003906, "optimizer_updates": 38350, "effective_batch": 512, "lr": 2.019556484194222e-05, "gradient_norm": 0.23645424842834473, "tokens_per_second": 1125476.4597740776, "synthetic": false, "world_size": 8} {"step": 74720, "tokens": 19587399680, "loss": 2.344669532775879, "optimizer_updates": 38360, "effective_batch": 512, "lr": 2.0190695898591568e-05, "gradient_norm": 0.26596546173095703, "tokens_per_second": 1128082.344327765, "synthetic": false, "world_size": 8} {"step": 74740, "tokens": 19592642560, "loss": 2.3590024948120116, "optimizer_updates": 38370, "effective_batch": 512, "lr": 2.0185888268039107e-05, "gradient_norm": 0.25477123260498047, "tokens_per_second": 1125882.5213306413, "synthetic": false, "world_size": 8} {"step": 74760, "tokens": 19597885440, "loss": 2.3598911285400392, "optimizer_updates": 38380, "effective_batch": 512, "lr": 2.018114195356701e-05, "gradient_norm": 0.2647687494754791, "tokens_per_second": 761913.7953235726, "synthetic": false, "world_size": 8} {"step": 74780, "tokens": 19603128320, "loss": 2.3500526428222654, "optimizer_updates": 38390, "effective_batch": 512, "lr": 2.0176456958415573e-05, "gradient_norm": 0.25711971521377563, "tokens_per_second": 1133558.7942001128, "synthetic": false, "world_size": 8} {"step": 74800, "tokens": 19608371200, "loss": 2.3522289276123045, "optimizer_updates": 38400, "effective_batch": 512, "lr": 2.0171833285783247e-05, "gradient_norm": 0.23216798901557922, "tokens_per_second": 1136349.5048184544, "synthetic": false, "world_size": 8} {"step": 74820, "tokens": 19613614080, "loss": 2.3478977203369142, "optimizer_updates": 38410, "effective_batch": 512, "lr": 2.016727093882661e-05, "gradient_norm": 0.23605181276798248, "tokens_per_second": 1128952.2248864728, "synthetic": false, "world_size": 8} {"step": 74840, "tokens": 19618856960, "loss": 2.345784568786621, "optimizer_updates": 38420, "effective_batch": 512, "lr": 2.016276992066039e-05, "gradient_norm": 0.2481260448694229, "tokens_per_second": 1135383.5574115692, "synthetic": false, "world_size": 8} {"step": 74860, "tokens": 19624099840, "loss": 2.3438196182250977, "optimizer_updates": 38430, "effective_batch": 512, "lr": 2.0158330234357406e-05, "gradient_norm": 0.2848905324935913, "tokens_per_second": 1136836.9157088317, "synthetic": false, "world_size": 8} {"step": 74880, "tokens": 19629342720, "loss": 2.3510787963867186, "optimizer_updates": 38440, "effective_batch": 512, "lr": 2.015395188294866e-05, "gradient_norm": 0.28071701526641846, "tokens_per_second": 1061019.2996977107, "synthetic": false, "world_size": 8} {"step": 74900, "tokens": 19634585600, "loss": 2.347812271118164, "optimizer_updates": 38450, "effective_batch": 512, "lr": 2.014963486942322e-05, "gradient_norm": 0.2562679350376129, "tokens_per_second": 791944.3533029782, "synthetic": false, "world_size": 8} {"step": 74920, "tokens": 19639828480, "loss": 2.337804985046387, "optimizer_updates": 38460, "effective_batch": 512, "lr": 2.014537919672834e-05, "gradient_norm": 0.2447199523448944, "tokens_per_second": 828112.4361397964, "synthetic": false, "world_size": 8} {"step": 74940, "tokens": 19645071360, "loss": 2.3542043685913088, "optimizer_updates": 38470, "effective_batch": 512, "lr": 2.014118486776935e-05, "gradient_norm": 0.275351881980896, "tokens_per_second": 1131630.1429917973, "synthetic": false, "world_size": 8} {"step": 74960, "tokens": 19650314240, "loss": 2.363106536865234, "optimizer_updates": 38480, "effective_batch": 512, "lr": 2.013705188540972e-05, "gradient_norm": 0.23248714208602905, "tokens_per_second": 1124537.3037546733, "synthetic": false, "world_size": 8} {"step": 74980, "tokens": 19655557120, "loss": 2.3586095809936523, "optimizer_updates": 38490, "effective_batch": 512, "lr": 2.0132980252471042e-05, "gradient_norm": 0.2640589475631714, "tokens_per_second": 1134645.2934602005, "synthetic": false, "world_size": 8} {"step": 75000, "tokens": 19660800000, "loss": 2.3396663665771484, "optimizer_updates": 38500, "effective_batch": 512, "lr": 2.0128969971733024e-05, "gradient_norm": 0.2563058137893677, "tokens_per_second": 1130734.7500342166, "synthetic": false, "world_size": 8} {"step": 75020, "tokens": 19666042880, "loss": 2.351472091674805, "optimizer_updates": 38510, "effective_batch": 512, "lr": 2.0125021045933467e-05, "gradient_norm": 0.23620453476905823, "tokens_per_second": 830345.1035919365, "synthetic": false, "world_size": 8} {"step": 75040, "tokens": 19671285760, "loss": 2.3491350173950196, "optimizer_updates": 38520, "effective_batch": 512, "lr": 2.0121133477768314e-05, "gradient_norm": 0.22107073664665222, "tokens_per_second": 1133004.0638251018, "synthetic": false, "world_size": 8} {"step": 75060, "tokens": 19676528640, "loss": 2.3478607177734374, "optimizer_updates": 38530, "effective_batch": 512, "lr": 2.01173072698916e-05, "gradient_norm": 0.243292897939682, "tokens_per_second": 1132771.0727022223, "synthetic": false, "world_size": 8} {"step": 75080, "tokens": 19681771520, "loss": 2.3493249893188475, "optimizer_updates": 38540, "effective_batch": 512, "lr": 2.0113542424915475e-05, "gradient_norm": 0.25327572226524353, "tokens_per_second": 1134506.9067107828, "synthetic": false, "world_size": 8} {"step": 75100, "tokens": 19687014400, "loss": 2.348948860168457, "optimizer_updates": 38550, "effective_batch": 512, "lr": 2.010983894541022e-05, "gradient_norm": 0.293383926153183, "tokens_per_second": 1133865.0942909291, "synthetic": false, "world_size": 8} {"step": 75120, "tokens": 19692257280, "loss": 2.3555774688720703, "optimizer_updates": 38560, "effective_batch": 512, "lr": 2.0106196833904174e-05, "gradient_norm": 0.23567388951778412, "tokens_per_second": 1130991.3493550161, "synthetic": false, "world_size": 8} {"step": 75140, "tokens": 19697500160, "loss": 2.3508417129516603, "optimizer_updates": 38570, "effective_batch": 512, "lr": 2.010261609288381e-05, "gradient_norm": 0.2700115740299225, "tokens_per_second": 1129872.7549439883, "synthetic": false, "world_size": 8} {"step": 75160, "tokens": 19702743040, "loss": 2.3436954498291014, "optimizer_updates": 38580, "effective_batch": 512, "lr": 2.0099096724793714e-05, "gradient_norm": 0.2583124041557312, "tokens_per_second": 1135837.1735987936, "synthetic": false, "world_size": 8} {"step": 75180, "tokens": 19707985920, "loss": 2.3512170791625975, "optimizer_updates": 38590, "effective_batch": 512, "lr": 2.0095638732036548e-05, "gradient_norm": 0.23924139142036438, "tokens_per_second": 1133924.690859303, "synthetic": false, "world_size": 8} {"step": 75200, "tokens": 19713228800, "loss": 2.3505832672119142, "optimizer_updates": 38600, "effective_batch": 512, "lr": 2.0092242116973084e-05, "gradient_norm": 0.23606005311012268, "tokens_per_second": 1135741.4820334294, "synthetic": false, "world_size": 8} {"step": 75220, "tokens": 19718471680, "loss": 2.3455955505371096, "optimizer_updates": 38610, "effective_batch": 512, "lr": 2.0088906881922187e-05, "gradient_norm": 0.2652859091758728, "tokens_per_second": 1129374.3278880084, "synthetic": false, "world_size": 8} {"step": 75240, "tokens": 19723714560, "loss": 2.3560249328613283, "optimizer_updates": 38620, "effective_batch": 512, "lr": 2.008563302916083e-05, "gradient_norm": 0.2400681972503662, "tokens_per_second": 1135291.3298840283, "synthetic": false, "world_size": 8} {"step": 75260, "tokens": 19728957440, "loss": 2.3567827224731444, "optimizer_updates": 38630, "effective_batch": 512, "lr": 2.0082420560924067e-05, "gradient_norm": 0.2648240625858307, "tokens_per_second": 1113859.2846552045, "synthetic": false, "world_size": 8} {"step": 75280, "tokens": 19734200320, "loss": 2.3375205993652344, "optimizer_updates": 38640, "effective_batch": 512, "lr": 2.007926947940504e-05, "gradient_norm": 0.2440546602010727, "tokens_per_second": 1130350.3978800464, "synthetic": false, "world_size": 8} {"step": 75300, "tokens": 19739443200, "loss": 2.338776397705078, "optimizer_updates": 38650, "effective_batch": 512, "lr": 2.0076179786755015e-05, "gradient_norm": 0.25870996713638306, "tokens_per_second": 1123573.5353099199, "synthetic": false, "world_size": 8} {"step": 75320, "tokens": 19744686080, "loss": 2.35176944732666, "optimizer_updates": 38660, "effective_batch": 512, "lr": 2.0073151485083306e-05, "gradient_norm": 0.2335657924413681, "tokens_per_second": 1127989.1891738127, "synthetic": false, "world_size": 8} {"step": 75340, "tokens": 19749928960, "loss": 2.3404436111450195, "optimizer_updates": 38670, "effective_batch": 512, "lr": 2.0070184576457338e-05, "gradient_norm": 0.25845879316329956, "tokens_per_second": 1141011.9476750945, "synthetic": false, "world_size": 8} {"step": 75360, "tokens": 19755171840, "loss": 2.3510082244873045, "optimizer_updates": 38680, "effective_batch": 512, "lr": 2.0067279062902618e-05, "gradient_norm": 0.24703726172447205, "tokens_per_second": 1135691.627109381, "synthetic": false, "world_size": 8} {"step": 75380, "tokens": 19760414720, "loss": 2.346238136291504, "optimizer_updates": 38690, "effective_batch": 512, "lr": 2.0064434946402746e-05, "gradient_norm": 0.22762632369995117, "tokens_per_second": 1131770.5360009111, "synthetic": false, "world_size": 8} {"step": 75400, "tokens": 19765657600, "loss": 2.3397520065307615, "optimizer_updates": 38700, "effective_batch": 512, "lr": 2.0061652228899392e-05, "gradient_norm": 0.2348237782716751, "tokens_per_second": 1132713.6035675523, "synthetic": false, "world_size": 8} {"step": 75420, "tokens": 19770900480, "loss": 2.3597267150878904, "optimizer_updates": 38710, "effective_batch": 512, "lr": 2.0058930912292324e-05, "gradient_norm": 0.31682610511779785, "tokens_per_second": 1130294.0252358378, "synthetic": false, "world_size": 8} {"step": 75440, "tokens": 19776143360, "loss": 2.3332540512084963, "optimizer_updates": 38720, "effective_batch": 512, "lr": 2.0056270998439376e-05, "gradient_norm": 0.27379316091537476, "tokens_per_second": 1134281.2472625386, "synthetic": false, "world_size": 8} {"step": 75460, "tokens": 19781386240, "loss": 2.351673126220703, "optimizer_updates": 38730, "effective_batch": 512, "lr": 2.005367248915649e-05, "gradient_norm": 0.25629764795303345, "tokens_per_second": 1141814.1246661427, "synthetic": false, "world_size": 8} {"step": 75480, "tokens": 19786629120, "loss": 2.3447025299072264, "optimizer_updates": 38740, "effective_batch": 512, "lr": 2.0051135386217643e-05, "gradient_norm": 0.2381482869386673, "tokens_per_second": 1125492.9632241682, "synthetic": false, "world_size": 8} {"step": 75500, "tokens": 19791872000, "loss": 2.3523550033569336, "optimizer_updates": 38750, "effective_batch": 512, "lr": 2.004865969135492e-05, "gradient_norm": 0.2343343198299408, "tokens_per_second": 1118597.5645217155, "synthetic": false, "world_size": 8} {"step": 75520, "tokens": 19797114880, "loss": 2.351728057861328, "optimizer_updates": 38760, "effective_batch": 512, "lr": 2.0046245406258497e-05, "gradient_norm": 0.25941988825798035, "tokens_per_second": 1136920.3685902492, "synthetic": false, "world_size": 8} {"step": 75540, "tokens": 19802357760, "loss": 2.3605684280395507, "optimizer_updates": 38770, "effective_batch": 512, "lr": 2.004389253257658e-05, "gradient_norm": 0.24296891689300537, "tokens_per_second": 1136940.3087090102, "synthetic": false, "world_size": 8} {"step": 75560, "tokens": 19807600640, "loss": 2.3612697601318358, "optimizer_updates": 38780, "effective_batch": 512, "lr": 2.004160107191549e-05, "gradient_norm": 0.27416470646858215, "tokens_per_second": 1133020.8867195416, "synthetic": false, "world_size": 8} {"step": 75580, "tokens": 19812843520, "loss": 2.356846809387207, "optimizer_updates": 38790, "effective_batch": 512, "lr": 2.0039371025839608e-05, "gradient_norm": 0.24901682138442993, "tokens_per_second": 1122485.2345552442, "synthetic": false, "world_size": 8} {"step": 75600, "tokens": 19818086400, "loss": 2.3448970794677733, "optimizer_updates": 38800, "effective_batch": 512, "lr": 2.0037202395871386e-05, "gradient_norm": 0.24132870137691498, "tokens_per_second": 1134872.2852944909, "synthetic": false, "world_size": 8} {"step": 75620, "tokens": 19823329280, "loss": 2.343402290344238, "optimizer_updates": 38810, "effective_batch": 512, "lr": 2.0035095183491338e-05, "gradient_norm": 0.2467314600944519, "tokens_per_second": 1010500.8542669485, "synthetic": false, "world_size": 8} {"step": 75640, "tokens": 19828572160, "loss": 2.3484014511108398, "optimizer_updates": 38820, "effective_batch": 512, "lr": 2.0033049390138066e-05, "gradient_norm": 0.25083544850349426, "tokens_per_second": 1129800.0831001636, "synthetic": false, "world_size": 8} {"step": 75660, "tokens": 19833815040, "loss": 2.3422977447509767, "optimizer_updates": 38830, "effective_batch": 512, "lr": 2.0031065017208233e-05, "gradient_norm": 0.24284453690052032, "tokens_per_second": 1136047.6856549159, "synthetic": false, "world_size": 8} {"step": 75680, "tokens": 19839057920, "loss": 2.3435651779174806, "optimizer_updates": 38840, "effective_batch": 512, "lr": 2.002914206605656e-05, "gradient_norm": 0.2714056670665741, "tokens_per_second": 1130540.1595227802, "synthetic": false, "world_size": 8} {"step": 75700, "tokens": 19844300800, "loss": 2.3505619049072264, "optimizer_updates": 38850, "effective_batch": 512, "lr": 2.0027280537995852e-05, "gradient_norm": 0.236174076795578, "tokens_per_second": 1025426.9172009205, "synthetic": false, "world_size": 8} {"step": 75720, "tokens": 19849543680, "loss": 2.344089698791504, "optimizer_updates": 38860, "effective_batch": 512, "lr": 2.0025480434296982e-05, "gradient_norm": 0.26764488220214844, "tokens_per_second": 1143432.9662028507, "synthetic": false, "world_size": 8} {"step": 75740, "tokens": 19854786560, "loss": 2.353700065612793, "optimizer_updates": 38870, "effective_batch": 512, "lr": 2.0023741756188875e-05, "gradient_norm": 0.23896180093288422, "tokens_per_second": 1134551.6739368357, "synthetic": false, "world_size": 8} {"step": 75760, "tokens": 19860029440, "loss": 2.348824119567871, "optimizer_updates": 38880, "effective_batch": 512, "lr": 2.002206450485852e-05, "gradient_norm": 0.24242599308490753, "tokens_per_second": 1136397.3610443291, "synthetic": false, "world_size": 8} {"step": 75780, "tokens": 19865272320, "loss": 2.3391443252563477, "optimizer_updates": 38890, "effective_batch": 512, "lr": 2.0020448681450976e-05, "gradient_norm": 0.23993270099163055, "tokens_per_second": 1135968.8238380505, "synthetic": false, "world_size": 8} {"step": 75800, "tokens": 19870515200, "loss": 2.3447975158691405, "optimizer_updates": 38900, "effective_batch": 512, "lr": 2.0018894287069375e-05, "gradient_norm": 0.2690589427947998, "tokens_per_second": 1130922.5718170805, "synthetic": false, "world_size": 8} {"step": 75820, "tokens": 19875758080, "loss": 2.3547691345214843, "optimizer_updates": 38910, "effective_batch": 512, "lr": 2.0017401322774907e-05, "gradient_norm": 0.23710116744041443, "tokens_per_second": 1129683.9375628007, "synthetic": false, "world_size": 8} {"step": 75840, "tokens": 19881000960, "loss": 2.3512475967407225, "optimizer_updates": 38920, "effective_batch": 512, "lr": 2.0015969789586795e-05, "gradient_norm": 0.2681848406791687, "tokens_per_second": 1136473.0204286943, "synthetic": false, "world_size": 8} {"step": 75860, "tokens": 19886243840, "loss": 2.3486955642700194, "optimizer_updates": 38930, "effective_batch": 512, "lr": 2.0014599688482366e-05, "gradient_norm": 0.2538103759288788, "tokens_per_second": 1119612.0826749788, "synthetic": false, "world_size": 8} {"step": 75880, "tokens": 19891486720, "loss": 2.351792907714844, "optimizer_updates": 38940, "effective_batch": 512, "lr": 2.001329102039698e-05, "gradient_norm": 0.27707144618034363, "tokens_per_second": 1129446.8732213574, "synthetic": false, "world_size": 8} {"step": 75900, "tokens": 19896729600, "loss": 2.342523384094238, "optimizer_updates": 38950, "effective_batch": 512, "lr": 2.0012043786224068e-05, "gradient_norm": 0.23586024343967438, "tokens_per_second": 1139352.7187913822, "synthetic": false, "world_size": 8} {"step": 75920, "tokens": 19901972480, "loss": 2.341603088378906, "optimizer_updates": 38960, "effective_batch": 512, "lr": 2.0010857986815112e-05, "gradient_norm": 0.24193066358566284, "tokens_per_second": 1133216.3826294178, "synthetic": false, "world_size": 8} {"step": 75940, "tokens": 19907215360, "loss": 2.3499364852905273, "optimizer_updates": 38970, "effective_batch": 512, "lr": 2.0009733622979657e-05, "gradient_norm": 0.2716878652572632, "tokens_per_second": 1129590.5527653403, "synthetic": false, "world_size": 8} {"step": 75960, "tokens": 19912458240, "loss": 2.336538314819336, "optimizer_updates": 38980, "effective_batch": 512, "lr": 2.0008670695485314e-05, "gradient_norm": 0.29628145694732666, "tokens_per_second": 1127045.0033031031, "synthetic": false, "world_size": 8} {"step": 75980, "tokens": 19917701120, "loss": 2.3434614181518554, "optimizer_updates": 38990, "effective_batch": 512, "lr": 2.0007669205057735e-05, "gradient_norm": 0.24440352618694305, "tokens_per_second": 1138090.076545682, "synthetic": false, "world_size": 8} {"step": 76000, "tokens": 19922944000, "loss": 2.3480808258056642, "optimizer_updates": 39000, "effective_batch": 512, "lr": 2.0006729152380647e-05, "gradient_norm": 0.23956793546676636, "tokens_per_second": 1129661.531105991, "synthetic": false, "world_size": 8} {"step": 76020, "tokens": 19928186880, "loss": 2.3487897872924806, "optimizer_updates": 39010, "effective_batch": 512, "lr": 2.0005850538095817e-05, "gradient_norm": 0.24276745319366455, "tokens_per_second": 656771.030193188, "synthetic": false, "world_size": 8} {"step": 76040, "tokens": 19933429760, "loss": 2.344592475891113, "optimizer_updates": 39020, "effective_batch": 512, "lr": 2.0005033362803066e-05, "gradient_norm": 0.2413463592529297, "tokens_per_second": 1140143.7125523186, "synthetic": false, "world_size": 8} {"step": 76060, "tokens": 19938672640, "loss": 2.347385025024414, "optimizer_updates": 39030, "effective_batch": 512, "lr": 2.0004277627060298e-05, "gradient_norm": 0.2483021765947342, "tokens_per_second": 1134409.433552052, "synthetic": false, "world_size": 8} {"step": 76080, "tokens": 19943915520, "loss": 2.36145133972168, "optimizer_updates": 39040, "effective_batch": 512, "lr": 2.000358333138344e-05, "gradient_norm": 0.2517464756965637, "tokens_per_second": 1133352.256844039, "synthetic": false, "world_size": 8} {"step": 76100, "tokens": 19949158400, "loss": 2.3444793701171873, "optimizer_updates": 39050, "effective_batch": 512, "lr": 2.0002950476246492e-05, "gradient_norm": 0.24343888461589813, "tokens_per_second": 1136135.9543421334, "synthetic": false, "world_size": 8} {"step": 76120, "tokens": 19954401280, "loss": 2.3519207000732423, "optimizer_updates": 39060, "effective_batch": 512, "lr": 2.0002379062081507e-05, "gradient_norm": 0.23757705092430115, "tokens_per_second": 1138569.685089213, "synthetic": false, "world_size": 8} {"step": 76140, "tokens": 19959644160, "loss": 2.368708038330078, "optimizer_updates": 39070, "effective_batch": 512, "lr": 2.000186908927859e-05, "gradient_norm": 0.24296975135803223, "tokens_per_second": 1133865.5584965819, "synthetic": false, "world_size": 8} {"step": 76160, "tokens": 19964887040, "loss": 2.3475063323974608, "optimizer_updates": 39080, "effective_batch": 512, "lr": 2.0001420558185896e-05, "gradient_norm": 0.2429574877023697, "tokens_per_second": 1143597.8245723508, "synthetic": false, "world_size": 8} {"step": 76180, "tokens": 19970129920, "loss": 2.3501075744628905, "optimizer_updates": 39090, "effective_batch": 512, "lr": 2.0001033469109632e-05, "gradient_norm": 0.24141333997249603, "tokens_per_second": 1130789.9513345938, "synthetic": false, "world_size": 8} {"step": 76200, "tokens": 19975372800, "loss": 2.3453779220581055, "optimizer_updates": 39100, "effective_batch": 512, "lr": 2.000070782231406e-05, "gradient_norm": 0.239821657538414, "tokens_per_second": 1134868.5835366587, "synthetic": false, "world_size": 8} {"step": 76220, "tokens": 19980615680, "loss": 2.3609004974365235, "optimizer_updates": 39110, "effective_batch": 512, "lr": 2.000044361802153e-05, "gradient_norm": 0.24755486845970154, "tokens_per_second": 791191.0848257681, "synthetic": false, "world_size": 8} {"step": 76240, "tokens": 19985858560, "loss": 2.3436702728271483, "optimizer_updates": 39120, "effective_batch": 512, "lr": 2.0000240856412375e-05, "gradient_norm": 0.2429083287715912, "tokens_per_second": 1136267.7861490583, "synthetic": false, "world_size": 8} {"step": 76260, "tokens": 19991101440, "loss": 2.3590946197509766, "optimizer_updates": 39130, "effective_batch": 512, "lr": 2.0000099537625045e-05, "gradient_norm": 0.25666868686676025, "tokens_per_second": 1134075.6893280968, "synthetic": false, "world_size": 8} {"step": 76280, "tokens": 19996344320, "loss": 2.3687744140625, "optimizer_updates": 39140, "effective_batch": 512, "lr": 2.0000019661756007e-05, "gradient_norm": 0.24529103934764862, "tokens_per_second": 1134731.8266012003, "synthetic": false, "world_size": 8}