Image-Text-to-Text
PEFT
Safetensors
vision-language
multimodal
llava
lora
siglip2
n-atlas
nigerian-languages
AtlasVision / logs /stage2_train_log.jsonl
UncleanCode's picture
Upload via givemeanode export_data
2a2540a verified
Raw History Blame Contribute Delete
42.2 kB
{"step": 1, "loss": 2.1018713116645813, "grad_norm": 3.935774087905884, "lr": 1.3698630136986302e-06, "s_per_step": 5.9358556270599365, "peak_gb": 28.923105792, "samples_seen": 32, "time": 1791137293.9179838}
{"step": 25, "loss": 1.8595843004683654, "grad_norm": 0.8364684581756592, "lr": 3.424657534246575e-05, "s_per_step": 3.0314967930316925, "peak_gb": 32.089119744, "samples_seen": 800, "time": 1791137366.67442}
{"step": 50, "loss": 1.4337403464317322, "grad_norm": 0.641377329826355, "lr": 6.84931506849315e-05, "s_per_step": 2.7474777412414553, "peak_gb": 32.089119744, "samples_seen": 1600, "time": 1791137435.3618677}
{"step": 75, "loss": 1.3591693234443665, "grad_norm": 0.46830347180366516, "lr": 0.00010273972602739728, "s_per_step": 2.675526475906372, "peak_gb": 32.18382848, "samples_seen": 2400, "time": 1791137502.2504642}
{"step": 100, "loss": 1.3316362035274505, "grad_norm": 0.6638643145561218, "lr": 0.000136986301369863, "s_per_step": 2.702469034194946, "peak_gb": 34.275917312, "samples_seen": 3200, "time": 1791137569.8126426}
{"step": 125, "loss": 1.3198813837766648, "grad_norm": 0.5527892112731934, "lr": 0.00017123287671232877, "s_per_step": 2.699006910324097, "peak_gb": 34.275917312, "samples_seen": 4000, "time": 1791137637.2882571}
{"step": 150, "loss": 1.3081526547670363, "grad_norm": 0.5911878347396851, "lr": 0.00019999980323762506, "s_per_step": 2.6959174919128417, "peak_gb": 34.275917312, "samples_seen": 4800, "time": 1791137704.6866806}
{"step": 175, "loss": 1.33544615983963, "grad_norm": 0.5037556290626526, "lr": 0.000199982860294911, "s_per_step": 2.5416007328033445, "peak_gb": 34.275917312, "samples_seen": 5600, "time": 1791137768.2271826}
{"step": 200, "loss": 1.30276043176651, "grad_norm": 0.6148776412010193, "lr": 0.00019993859454180504, "s_per_step": 2.7514454460144044, "peak_gb": 34.275917312, "samples_seen": 6400, "time": 1791137837.0137653}
{"step": 225, "loss": 1.3027793610095977, "grad_norm": 0.5531913042068481, "lr": 0.00019986701807502827, "s_per_step": 2.6572889137268065, "peak_gb": 34.275917312, "samples_seen": 7200, "time": 1791137903.4464118}
{"step": 250, "loss": 1.3026298081874848, "grad_norm": 0.5650343298912048, "lr": 0.00019976815045463558, "s_per_step": 2.581279354095459, "peak_gb": 34.275917312, "samples_seen": 8000, "time": 1791137967.9797318}
{"step": 275, "loss": 1.2859191417694091, "grad_norm": 0.5168231725692749, "lr": 0.00019964201869867025, "s_per_step": 2.7289039039611818, "peak_gb": 34.275917312, "samples_seen": 8800, "time": 1791138036.2027671}
{"step": 300, "loss": 1.3106050491333008, "grad_norm": 0.5257666707038879, "lr": 0.0001994886572757806, "s_per_step": 2.456781349182129, "peak_gb": 34.275917312, "samples_seen": 9600, "time": 1791138097.6227736}
{"step": 325, "loss": 1.285406960248947, "grad_norm": 0.5512126088142395, "lr": 0.00019930810809580063, "s_per_step": 2.6005754470825195, "peak_gb": 34.275917312, "samples_seen": 10400, "time": 1791138162.6376011}
{"step": 350, "loss": 1.2840537762641906, "grad_norm": 0.592390239238739, "lr": 0.00019910042049829714, "s_per_step": 2.6476001262664797, "peak_gb": 34.275917312, "samples_seen": 11200, "time": 1791138228.8280518}
{"step": 375, "loss": 1.310118284225464, "grad_norm": 0.4393337070941925, "lr": 0.00019886565123908637, "s_per_step": 2.5076206874847413, "peak_gb": 34.275917312, "samples_seen": 12000, "time": 1791138291.5190346}
{"step": 400, "loss": 1.3007353556156158, "grad_norm": 0.572140097618103, "lr": 0.0001986038644747241, "s_per_step": 2.54843355178833, "peak_gb": 34.275917312, "samples_seen": 12800, "time": 1791138355.230326}
{"step": 425, "loss": 1.3010186761617661, "grad_norm": 0.5119914412498474, "lr": 0.00019831513174497332, "s_per_step": 2.463373165130615, "peak_gb": 34.454321664, "samples_seen": 13600, "time": 1791138416.8150551}
{"step": 450, "loss": 1.2758523070812224, "grad_norm": 0.46384191513061523, "lr": 0.00019799953195325412, "s_per_step": 2.629770526885986, "peak_gb": 34.454321664, "samples_seen": 14400, "time": 1791138482.5597115}
{"step": 475, "loss": 1.2857936775684358, "grad_norm": 0.5037622451782227, "lr": 0.0001976571513450814, "s_per_step": 2.5591455364227294, "peak_gb": 34.454321664, "samples_seen": 15200, "time": 1791138546.5387669}
{"step": 500, "loss": 1.296420032978058, "grad_norm": 0.5816029906272888, "lr": 0.00019728808348449617, "s_per_step": 2.425617971420288, "peak_gb": 34.454321664, "samples_seen": 16000, "time": 1791138607.1797073}
{"step": 525, "loss": 1.2788980293273926, "grad_norm": 0.5487325191497803, "lr": 0.0001968924292284968, "s_per_step": 2.719025077819824, "peak_gb": 34.454321664, "samples_seen": 16800, "time": 1791138675.1558762}
{"step": 550, "loss": 1.2836597490310668, "grad_norm": 0.4508974850177765, "lr": 0.0001964702966994773, "s_per_step": 2.5938339710235594, "peak_gb": 35.16160256, "samples_seen": 17600, "time": 1791138740.0021875}
{"step": 575, "loss": 1.272069708108902, "grad_norm": 0.4157426059246063, "lr": 0.00019602180125568024, "s_per_step": 2.557501964569092, "peak_gb": 35.16160256, "samples_seen": 18400, "time": 1791138803.9402196}
{"step": 600, "loss": 1.2735493952035903, "grad_norm": 0.4135555326938629, "lr": 0.00019554706545967223, "s_per_step": 2.681543912887573, "peak_gb": 35.16160256, "samples_seen": 19200, "time": 1791138871.1860206}
{"step": 625, "loss": 1.2743602776527405, "grad_norm": 0.527656078338623, "lr": 0.00019504621904485055, "s_per_step": 2.574559545516968, "peak_gb": 35.16160256, "samples_seen": 20000, "time": 1791138935.5505657}
{"step": 650, "loss": 1.2700351548194886, "grad_norm": 0.47019869089126587, "lr": 0.00019451939887999044, "s_per_step": 2.5688095760345457, "peak_gb": 35.16160256, "samples_seen": 20800, "time": 1791138999.7712135}
{"step": 675, "loss": 1.278431007862091, "grad_norm": 0.49949219822883606, "lr": 0.0001939667489318421, "s_per_step": 2.5981833267211916, "peak_gb": 35.16160256, "samples_seen": 21600, "time": 1791139064.7262437}
{"step": 700, "loss": 1.2902556908130647, "grad_norm": 0.4944266378879547, "lr": 0.00019338842022578826, "s_per_step": 2.3775853538513183, "peak_gb": 35.16160256, "samples_seen": 22400, "time": 1791139124.16638}
{"step": 725, "loss": 1.2667275273799896, "grad_norm": 0.3541528880596161, "lr": 0.00019278457080457287, "s_per_step": 2.660867967605591, "peak_gb": 35.16160256, "samples_seen": 23200, "time": 1791139190.6885371}
{"step": 750, "loss": 1.2670336496829986, "grad_norm": 0.4926910996437073, "lr": 0.00019215536568511165, "s_per_step": 2.5423004722595213, "peak_gb": 35.16160256, "samples_seen": 24000, "time": 1791139254.246462}
{"step": 775, "loss": 1.2607650971412658, "grad_norm": 0.5327316522598267, "lr": 0.0001915009768133975, "s_per_step": 2.632803087234497, "peak_gb": 35.16160256, "samples_seen": 24800, "time": 1791139320.0670488}
{"step": 800, "loss": 1.298940641283989, "grad_norm": 0.5895273685455322, "lr": 0.00019082158301751158, "s_per_step": 2.3035424613952635, "peak_gb": 35.16160256, "samples_seen": 25600, "time": 1791139377.6561027}
{"step": 825, "loss": 1.2994678497314454, "grad_norm": 0.5701431632041931, "lr": 0.00019011736995875442, "s_per_step": 2.4659962368011477, "peak_gb": 35.16160256, "samples_seen": 26400, "time": 1791139439.3064585}
{"step": 850, "loss": 1.2705088353157044, "grad_norm": 0.4701496958732605, "lr": 0.0001893885300809091, "s_per_step": 2.506269245147705, "peak_gb": 35.16160256, "samples_seen": 27200, "time": 1791139501.96361}
{"step": 875, "loss": 1.2747311300039292, "grad_norm": 0.5782403349876404, "lr": 0.00018863526255765125, "s_per_step": 2.4462522220611573, "peak_gb": 35.16160256, "samples_seen": 28000, "time": 1791139563.1204047}
{"step": 900, "loss": 1.2845921885967255, "grad_norm": 0.5439372062683105, "lr": 0.00018785777323811998, "s_per_step": 2.414919261932373, "peak_gb": 35.16160256, "samples_seen": 28800, "time": 1791139623.4938784}
{"step": 925, "loss": 1.2421265226602554, "grad_norm": 0.4805165231227875, "lr": 0.00018705627459066429, "s_per_step": 2.59889892578125, "peak_gb": 35.16160256, "samples_seen": 29600, "time": 1791139688.4667766}
{"step": 950, "loss": 1.256026518344879, "grad_norm": 0.4744698405265808, "lr": 0.00018623098564478095, "s_per_step": 2.4729893398284912, "peak_gb": 35.16160256, "samples_seen": 30400, "time": 1791139750.3143578}
{"step": 975, "loss": 1.2527462810277938, "grad_norm": 0.45646801590919495, "lr": 0.00018538213193125915, "s_per_step": 2.529736156463623, "peak_gb": 35.16160256, "samples_seen": 31200, "time": 1791139813.5582156}
{"step": 1000, "loss": 1.2478597414493562, "grad_norm": 0.6265877485275269, "lr": 0.00018450994542054856, "s_per_step": 2.5998341178894044, "peak_gb": 35.16160256, "samples_seen": 32000, "time": 1791139878.5545025}
{"step": 1025, "loss": 1.2808118069171905, "grad_norm": 0.4756571054458618, "lr": 0.0001836146644593677, "s_per_step": 2.5343000221252443, "peak_gb": 35.16160256, "samples_seen": 32800, "time": 1791139941.9124794}
{"step": 1050, "loss": 1.2551424139738083, "grad_norm": 0.6432344913482666, "lr": 0.00018269653370556972, "s_per_step": 2.568102979660034, "peak_gb": 35.16160256, "samples_seen": 33600, "time": 1791140006.1155303}
{"step": 1075, "loss": 1.2568443739414215, "grad_norm": 0.5057801008224487, "lr": 0.0001817558040612835, "s_per_step": 2.6142832756042482, "peak_gb": 35.16160256, "samples_seen": 34400, "time": 1791140071.4731367}
{"step": 1100, "loss": 1.2462696027755737, "grad_norm": 0.537843644618988, "lr": 0.00018079273260434846, "s_per_step": 2.5834513759613036, "peak_gb": 35.16160256, "samples_seen": 35200, "time": 1791140136.05996}
{"step": 1125, "loss": 1.2574056977033614, "grad_norm": 0.5526939630508423, "lr": 0.00017980758251806152, "s_per_step": 2.4060669994354247, "peak_gb": 35.16160256, "samples_seen": 36000, "time": 1791140196.2120588}
{"step": 1150, "loss": 1.2388004493713378, "grad_norm": 0.5050171613693237, "lr": 0.00017880062301925582, "s_per_step": 2.5375908184051514, "peak_gb": 35.16160256, "samples_seen": 36800, "time": 1791140259.6522965}
{"step": 1175, "loss": 1.263253116607666, "grad_norm": 0.4916113317012787, "lr": 0.00017777212928473044, "s_per_step": 2.5061941528320313, "peak_gb": 35.16160256, "samples_seen": 37600, "time": 1791140322.3075662}
{"step": 1200, "loss": 1.2475608468055726, "grad_norm": 0.5672100186347961, "lr": 0.00017672238237605146, "s_per_step": 2.3854447269439696, "peak_gb": 35.16160256, "samples_seen": 38400, "time": 1791140381.9441311}
{"step": 1225, "loss": 1.2634010112285614, "grad_norm": 0.45946162939071655, "lr": 0.0001756516691627449, "s_per_step": 2.559474468231201, "peak_gb": 35.16160256, "samples_seen": 39200, "time": 1791140445.9314318}
{"step": 1250, "loss": 1.2636224496364594, "grad_norm": 0.5660274028778076, "lr": 0.00017456028224390258, "s_per_step": 2.3614064121246336, "peak_gb": 35.16160256, "samples_seen": 40000, "time": 1791140504.967005}
{"step": 1275, "loss": 1.2519952070713043, "grad_norm": 0.630153477191925, "lr": 0.00017344851986822186, "s_per_step": 2.604766302108765, "peak_gb": 35.16160256, "samples_seen": 40800, "time": 1791140570.0865934}
{"step": 1300, "loss": 1.248630976676941, "grad_norm": 0.603481650352478, "lr": 0.000172316685852502, "s_per_step": 2.5879988288879394, "peak_gb": 35.16160256, "samples_seen": 41600, "time": 1791140634.7870479}
{"step": 1325, "loss": 1.2556267881393433, "grad_norm": 0.5644108057022095, "lr": 0.00017116508949861846, "s_per_step": 2.4682638454437256, "peak_gb": 35.16160256, "samples_seen": 42400, "time": 1791140696.4940681}
{"step": 1350, "loss": 1.2743791633844375, "grad_norm": 0.552125871181488, "lr": 0.00016999404550899856, "s_per_step": 2.4177276992797854, "peak_gb": 35.16160256, "samples_seen": 43200, "time": 1791140756.9376965}
{"step": 1375, "loss": 1.2419914174079896, "grad_norm": 0.5084569454193115, "lr": 0.00016880387390062117, "s_per_step": 2.5251627922058106, "peak_gb": 35.16160256, "samples_seen": 44000, "time": 1791140820.067213}
{"step": 1400, "loss": 1.2473990058898925, "grad_norm": 0.48340925574302673, "lr": 0.00016759489991756402, "s_per_step": 2.5814351272583007, "peak_gb": 35.16160256, "samples_seen": 44800, "time": 1791140884.6035194}
{"step": 1425, "loss": 1.2643068969249724, "grad_norm": 0.6564701795578003, "lr": 0.0001663674539421228, "s_per_step": 2.4565196990966798, "peak_gb": 35.16160256, "samples_seen": 45600, "time": 1791140946.0169346}
{"step": 1450, "loss": 1.2657874739170074, "grad_norm": 0.5559526681900024, "lr": 0.0001651218714045258, "s_per_step": 2.38125319480896, "peak_gb": 35.16160256, "samples_seen": 46400, "time": 1791141005.5487158}
{"step": 1475, "loss": 1.2623559749126434, "grad_norm": 0.633904218673706, "lr": 0.00016385849269126923, "s_per_step": 2.3729316806793213, "peak_gb": 35.16160256, "samples_seen": 47200, "time": 1791141064.8724935}
{"step": 1500, "loss": 1.2323721277713775, "grad_norm": 0.5630310773849487, "lr": 0.00016257766305209824, "s_per_step": 2.5675553035736085, "peak_gb": 35.16160256, "samples_seen": 48000, "time": 1791141129.06184}
{"step": 1525, "loss": 1.2649996304512023, "grad_norm": 0.5584118962287903, "lr": 0.0001612797325056588, "s_per_step": 2.5546645450592043, "peak_gb": 35.16160256, "samples_seen": 48800, "time": 1791141192.9288673}
{"step": 1550, "loss": 1.2378357803821565, "grad_norm": 0.5218235850334167, "lr": 0.00015996505574384623, "s_per_step": 2.511321334838867, "peak_gb": 35.16160256, "samples_seen": 49600, "time": 1791141255.712335}
{"step": 1575, "loss": 1.2511804521083831, "grad_norm": 0.6376656889915466, "lr": 0.00015863399203487695, "s_per_step": 2.461472635269165, "peak_gb": 35.16160256, "samples_seen": 50400, "time": 1791141317.2496617}
{"step": 1600, "loss": 1.2562532049417496, "grad_norm": 0.5086262822151184, "lr": 0.00015728690512510944, "s_per_step": 2.506492853164673, "peak_gb": 35.16160256, "samples_seen": 51200, "time": 1791141379.912437}
{"step": 1625, "loss": 1.2379037940502167, "grad_norm": 0.5947778224945068, "lr": 0.00015592416313964136, "s_per_step": 2.4982398319244385, "peak_gb": 35.16160256, "samples_seen": 52000, "time": 1791141442.3688512}
{"step": 1650, "loss": 1.237431339621544, "grad_norm": 0.5146723985671997, "lr": 0.0001545461384817104, "s_per_step": 2.4878829956054687, "peak_gb": 35.16160256, "samples_seen": 52800, "time": 1791141504.5663276}
{"step": 1675, "loss": 1.2310943824052811, "grad_norm": 0.5532039403915405, "lr": 0.00015315320773092562, "s_per_step": 2.601818952560425, "peak_gb": 35.16160256, "samples_seen": 53600, "time": 1791141569.612219}
{"step": 1700, "loss": 1.233572164773941, "grad_norm": 0.491245836019516, "lr": 0.00015174575154035776, "s_per_step": 2.525400400161743, "peak_gb": 35.16160256, "samples_seen": 54400, "time": 1791141632.7476742}
{"step": 1725, "loss": 1.2353800696134567, "grad_norm": 0.5083756446838379, "lr": 0.00015032415453251628, "s_per_step": 2.500525407791138, "peak_gb": 35.16160256, "samples_seen": 55200, "time": 1791141695.2612443}
{"step": 1750, "loss": 1.2415151298046112, "grad_norm": 0.4848071336746216, "lr": 0.00014888880519424167, "s_per_step": 2.497219123840332, "peak_gb": 35.16160256, "samples_seen": 56000, "time": 1791141757.6921887}
{"step": 1775, "loss": 1.25896546125412, "grad_norm": 0.5702372193336487, "lr": 0.00014744009577054174, "s_per_step": 2.511766996383667, "peak_gb": 35.16160256, "samples_seen": 56800, "time": 1791141820.4869192}
{"step": 1800, "loss": 1.2329586499929428, "grad_norm": 0.5330091714859009, "lr": 0.0001459784221574008, "s_per_step": 2.550053768157959, "peak_gb": 35.34578432, "samples_seen": 57600, "time": 1791141884.2394202}
{"step": 1825, "loss": 1.2399318504333496, "grad_norm": 0.5269576907157898, "lr": 0.00014450418379359145, "s_per_step": 2.3936056327819824, "peak_gb": 35.34578432, "samples_seen": 58400, "time": 1791141944.0801225}
{"step": 1850, "loss": 1.1970552122592926, "grad_norm": 0.5154424905776978, "lr": 0.00014301778355151762, "s_per_step": 2.6440818309783936, "peak_gb": 35.34578432, "samples_seen": 59200, "time": 1791142010.1826928}
{"step": 1875, "loss": 1.2424454951286317, "grad_norm": 0.5999359488487244, "lr": 0.00014151962762711998, "s_per_step": 2.516843738555908, "peak_gb": 35.709385216, "samples_seen": 60000, "time": 1791142073.1044393}
{"step": 1900, "loss": 1.2413146513700486, "grad_norm": 0.5478770732879639, "lr": 0.0001400101254288724, "s_per_step": 2.479934730529785, "peak_gb": 35.709385216, "samples_seen": 60800, "time": 1791142135.1033275}
{"step": 1925, "loss": 1.2434303241968154, "grad_norm": 0.6004431247711182, "lr": 0.00013848968946590133, "s_per_step": 2.4324647426605224, "peak_gb": 35.709385216, "samples_seen": 61600, "time": 1791142195.9162219}
{"step": 1950, "loss": 1.2015808641910553, "grad_norm": 0.5266046524047852, "lr": 0.000136958735235257, "s_per_step": 2.506597595214844, "peak_gb": 35.709385216, "samples_seen": 62400, "time": 1791142258.5817263}
{"step": 1975, "loss": 1.2200964736938475, "grad_norm": 0.5610483884811401, "lr": 0.00013541768110836863, "s_per_step": 2.5384847927093506, "peak_gb": 35.709385216, "samples_seen": 63200, "time": 1791142322.0443137}
{"step": 2000, "loss": 1.2384649211168288, "grad_norm": 0.6361256241798401, "lr": 0.00013386694821671414, "s_per_step": 2.4207293224334716, "peak_gb": 35.709385216, "samples_seen": 64000, "time": 1791142382.5630329}
{"step": 2025, "loss": 1.214077221751213, "grad_norm": 0.6302129030227661, "lr": 0.0001323069603367351, "s_per_step": 2.6198851585388185, "peak_gb": 35.709385216, "samples_seen": 64800, "time": 1791142448.0606163}
{"step": 2050, "loss": 1.2055979889631272, "grad_norm": 0.509576141834259, "lr": 0.00013073814377402974, "s_per_step": 2.627358932495117, "peak_gb": 35.709385216, "samples_seen": 65600, "time": 1791142513.7450488}
{"step": 2075, "loss": 1.2103803342580794, "grad_norm": 0.5196846723556519, "lr": 0.00012916092724685383, "s_per_step": 2.598076095581055, "peak_gb": 35.709385216, "samples_seen": 66400, "time": 1791142578.6973796}
{"step": 2100, "loss": 1.2209484434127809, "grad_norm": 0.5177134871482849, "lr": 0.00012757574176896312, "s_per_step": 2.5112220001220704, "peak_gb": 35.709385216, "samples_seen": 67200, "time": 1791142641.47846}
{"step": 2125, "loss": 1.2264458799362183, "grad_norm": 0.5397101640701294, "lr": 0.0001259830205318278, "s_per_step": 2.3952220344543456, "peak_gb": 35.709385216, "samples_seen": 68000, "time": 1791142701.3594959}
{"step": 2150, "loss": 1.209760498404503, "grad_norm": 0.5998483300209045, "lr": 0.00012438319878625226, "s_per_step": 2.5326212215423585, "peak_gb": 35.709385216, "samples_seen": 68800, "time": 1791142764.675523}
{"step": 2175, "loss": 1.2117489975690843, "grad_norm": 0.5707188844680786, "lr": 0.00012277671372343195, "s_per_step": 2.4900473594665526, "peak_gb": 35.709385216, "samples_seen": 69600, "time": 1791142826.9271343}
{"step": 2200, "loss": 1.2348184549808503, "grad_norm": 0.5396585464477539, "lr": 0.00012116400435547992, "s_per_step": 2.492477035522461, "peak_gb": 35.709385216, "samples_seen": 70400, "time": 1791142889.2394576}
{"step": 2225, "loss": 1.2173430824279785, "grad_norm": 0.39253613352775574, "lr": 0.00011954551139545588, "s_per_step": 2.49932147026062, "peak_gb": 35.709385216, "samples_seen": 71200, "time": 1791142951.7229047}
{"step": 2250, "loss": 1.2054871225357056, "grad_norm": 0.5584589838981628, "lr": 0.00011792167713693036, "s_per_step": 2.4481615734100344, "peak_gb": 35.709385216, "samples_seen": 72000, "time": 1791143012.9273942}
{"step": 2275, "loss": 1.2060042411088943, "grad_norm": 0.5810075402259827, "lr": 0.0001162929453331168, "s_per_step": 2.66895037651062, "peak_gb": 35.709385216, "samples_seen": 72800, "time": 1791143079.6516283}
{"step": 2300, "loss": 1.2204527378082275, "grad_norm": 0.5374050140380859, "lr": 0.00011465976107560521, "s_per_step": 2.4989648342132567, "peak_gb": 35.709385216, "samples_seen": 73600, "time": 1791143142.12621}
{"step": 2325, "loss": 1.2322663950920105, "grad_norm": 0.5682536959648132, "lr": 0.00011302257067272952, "s_per_step": 2.3952228927612307, "peak_gb": 35.709385216, "samples_seen": 74400, "time": 1791143202.0071743}
{"step": 2350, "loss": 1.1958238542079926, "grad_norm": 0.4648407995700836, "lr": 0.00011138182152760286, "s_per_step": 2.6400107955932617, "peak_gb": 35.709385216, "samples_seen": 75200, "time": 1791143268.0078988}
{"step": 2375, "loss": 1.1953755247592925, "grad_norm": 0.4725061058998108, "lr": 0.00010973796201585335, "s_per_step": 2.4706161880493163, "peak_gb": 35.709385216, "samples_seen": 76000, "time": 1791143329.774484}
{"step": 2400, "loss": 1.2082021981477737, "grad_norm": 0.5769761800765991, "lr": 0.00010809144136309454, "s_per_step": 2.4323978424072266, "peak_gb": 35.709385216, "samples_seen": 76800, "time": 1791143390.5849032}
{"step": 2425, "loss": 1.2111977207660676, "grad_norm": 0.5421669483184814, "lr": 0.000106442709522163, "s_per_step": 2.4998205661773683, "peak_gb": 35.709385216, "samples_seen": 77600, "time": 1791143453.0808678}
{"step": 2450, "loss": 1.2098423671722411, "grad_norm": 0.484115332365036, "lr": 0.00010479221705015759, "s_per_step": 2.5170133399963377, "peak_gb": 35.709385216, "samples_seen": 78400, "time": 1791143516.0066352}
{"step": 2475, "loss": 1.223331753015518, "grad_norm": 0.49125203490257263, "lr": 0.00010314041498531371, "s_per_step": 2.4067738342285154, "peak_gb": 35.709385216, "samples_seen": 79200, "time": 1791143576.176388}
{"step": 2500, "loss": 1.2110005378723145, "grad_norm": 0.5610998868942261, "lr": 0.00010148775472374543, "s_per_step": 2.5736419677734377, "peak_gb": 35.709385216, "samples_seen": 80000, "time": 1791143640.5179398}
{"step": 2525, "loss": 1.2331609898805618, "grad_norm": 0.5671659708023071, "lr": 9.983468789609067e-05, "s_per_step": 2.5041617870330812, "peak_gb": 35.709385216, "samples_seen": 80800, "time": 1791143703.1224139}
{"step": 2550, "loss": 1.214245287179947, "grad_norm": 0.4357548654079437, "lr": 9.818166624409161e-05, "s_per_step": 2.4907432842254638, "peak_gb": 35.709385216, "samples_seen": 81600, "time": 1791143765.391451}
{"step": 2575, "loss": 1.214305859208107, "grad_norm": 0.5925732254981995, "lr": 9.6529141497145e-05, "s_per_step": 2.4908134937286377, "peak_gb": 35.709385216, "samples_seen": 82400, "time": 1791143827.6623023}
{"step": 2600, "loss": 1.1959744757413864, "grad_norm": 0.5484082698822021, "lr": 9.487756524885599e-05, "s_per_step": 2.544646863937378, "peak_gb": 35.709385216, "samples_seen": 83200, "time": 1791143891.2789044}
{"step": 2625, "loss": 1.2088198286294938, "grad_norm": 0.5090175271034241, "lr": 9.322738883362871e-05, "s_per_step": 2.5154834175109864, "peak_gb": 35.709385216, "samples_seen": 84000, "time": 1791143954.166384}
{"step": 2650, "loss": 1.2010453754663468, "grad_norm": 0.5693520307540894, "lr": 9.157906320332812e-05, "s_per_step": 2.5574374485015867, "peak_gb": 35.709385216, "samples_seen": 84800, "time": 1791144018.102869}
{"step": 2675, "loss": 1.214320752620697, "grad_norm": 0.5067724585533142, "lr": 8.993303880404592e-05, "s_per_step": 2.516569652557373, "peak_gb": 35.709385216, "samples_seen": 85600, "time": 1791144081.0175457}
{"step": 2700, "loss": 1.1918057614564896, "grad_norm": 0.49570122361183167, "lr": 8.828976545300505e-05, "s_per_step": 2.6196873950958253, "peak_gb": 35.709385216, "samples_seen": 86400, "time": 1791144146.5105312}
{"step": 2725, "loss": 1.1909438091516495, "grad_norm": 0.49999526143074036, "lr": 8.664969221563594e-05, "s_per_step": 2.577509126663208, "peak_gb": 35.709385216, "samples_seen": 87200, "time": 1791144210.9487243}
{"step": 2750, "loss": 1.2046889424324037, "grad_norm": 0.4591648280620575, "lr": 8.501326728285814e-05, "s_per_step": 2.463228282928467, "peak_gb": 35.709385216, "samples_seen": 88000, "time": 1791144272.529925}
{"step": 2775, "loss": 1.187312572002411, "grad_norm": 0.4475753605365753, "lr": 8.338093784860098e-05, "s_per_step": 2.65875358581543, "peak_gb": 35.709385216, "samples_seen": 88800, "time": 1791144338.9991896}
{"step": 2800, "loss": 1.2058877384662627, "grad_norm": 0.43829211592674255, "lr": 8.175314998759658e-05, "s_per_step": 2.525215663909912, "peak_gb": 35.709385216, "samples_seen": 89600, "time": 1791144402.1299999}
{"step": 2825, "loss": 1.1879939883947372, "grad_norm": 0.4615590274333954, "lr": 8.013034853347902e-05, "s_per_step": 2.61760648727417, "peak_gb": 35.709385216, "samples_seen": 90400, "time": 1791144467.5705826}
{"step": 2850, "loss": 1.1962288463115691, "grad_norm": 0.5492228269577026, "lr": 7.851297695722228e-05, "s_per_step": 2.416270399093628, "peak_gb": 35.709385216, "samples_seen": 91200, "time": 1791144527.9778004}
{"step": 2875, "loss": 1.189599106311798, "grad_norm": 0.4402064085006714, "lr": 7.690147724595069e-05, "s_per_step": 2.5021799850463866, "peak_gb": 35.709385216, "samples_seen": 92000, "time": 1791144590.5327408}
{"step": 2900, "loss": 1.1737463009357452, "grad_norm": 0.41730257868766785, "lr": 7.529628978215513e-05, "s_per_step": 2.671381711959839, "peak_gb": 35.709385216, "samples_seen": 92800, "time": 1791144657.317731}
{"step": 2925, "loss": 1.1911302745342254, "grad_norm": 0.5390501022338867, "lr": 7.369785322334733e-05, "s_per_step": 2.4857681655883788, "peak_gb": 35.709385216, "samples_seen": 93600, "time": 1791144719.4624217}
{"step": 2950, "loss": 1.1944737762212754, "grad_norm": 0.5601727962493896, "lr": 7.210660438218596e-05, "s_per_step": 2.4794444179534914, "peak_gb": 35.709385216, "samples_seen": 94400, "time": 1791144781.4489458}
{"step": 2975, "loss": 1.1881670886278153, "grad_norm": 0.5373884439468384, "lr": 7.052297810710643e-05, "s_per_step": 2.483798608779907, "peak_gb": 35.709385216, "samples_seen": 95200, "time": 1791144843.5443158}
{"step": 3000, "loss": 1.2002181720733642, "grad_norm": 0.5904892683029175, "lr": 6.894740716348797e-05, "s_per_step": 2.475346622467041, "peak_gb": 35.709385216, "samples_seen": 96000, "time": 1791144905.4283826}
{"step": 3025, "loss": 1.1833700090646744, "grad_norm": 0.5156553387641907, "lr": 6.738032211538946e-05, "s_per_step": 2.6700209045410155, "peak_gb": 35.709385216, "samples_seen": 96800, "time": 1791144972.179436}
{"step": 3050, "loss": 1.1821686124801636, "grad_norm": 0.5594586730003357, "lr": 6.582215120788719e-05, "s_per_step": 2.4451071548461916, "peak_gb": 35.709385216, "samples_seen": 97600, "time": 1791145033.3075602}
{"step": 3075, "loss": 1.1715920561552047, "grad_norm": 0.44480738043785095, "lr": 6.427332025004628e-05, "s_per_step": 2.616603384017944, "peak_gb": 35.709385216, "samples_seen": 98400, "time": 1791145098.7230656}
{"step": 3100, "loss": 1.178504084944725, "grad_norm": 0.527042031288147, "lr": 6.273425249855752e-05, "s_per_step": 2.5396651363372804, "peak_gb": 35.709385216, "samples_seen": 99200, "time": 1791145162.2151375}
{"step": 3125, "loss": 1.1844954544305801, "grad_norm": 0.521228551864624, "lr": 6.120536854207215e-05, "s_per_step": 2.5937981700897215, "peak_gb": 35.709385216, "samples_seen": 100000, "time": 1791145227.0605233}
{"step": 3150, "loss": 1.197044386267662, "grad_norm": 0.5560638308525085, "lr": 5.968708618626539e-05, "s_per_step": 2.4499312114715575, "peak_gb": 35.709385216, "samples_seen": 100800, "time": 1791145288.309198}
{"step": 3175, "loss": 1.1869262939691543, "grad_norm": 0.5193493962287903, "lr": 5.817982033966059e-05, "s_per_step": 2.4811374282836915, "peak_gb": 35.709385216, "samples_seen": 101600, "time": 1791145350.3380346}
{"step": 3200, "loss": 1.17697389960289, "grad_norm": 0.5577865839004517, "lr": 5.668398290024517e-05, "s_per_step": 2.537874908447266, "peak_gb": 35.709385216, "samples_seen": 102400, "time": 1791145413.7853076}
{"step": 3225, "loss": 1.1980028331279755, "grad_norm": 0.41638582944869995, "lr": 5.5199982642909375e-05, "s_per_step": 2.443896884918213, "peak_gb": 35.709385216, "samples_seen": 103200, "time": 1791145474.8831582}
{"step": 3250, "loss": 1.2014775633811952, "grad_norm": 0.5623952150344849, "lr": 5.37282251077381e-05, "s_per_step": 2.4464002323150633, "peak_gb": 35.709385216, "samples_seen": 104000, "time": 1791145536.0436106}
{"step": 3275, "loss": 1.2081005316972733, "grad_norm": 0.5129700899124146, "lr": 5.2269112489187e-05, "s_per_step": 2.5506320571899415, "peak_gb": 35.709385216, "samples_seen": 104800, "time": 1791145599.8098936}
{"step": 3300, "loss": 1.1788170540332794, "grad_norm": 0.505996823310852, "lr": 5.082304352617291e-05, "s_per_step": 2.4294992446899415, "peak_gb": 35.709385216, "samples_seen": 105600, "time": 1791145660.547851}
{"step": 3325, "loss": 1.1952128916978837, "grad_norm": 0.48522287607192993, "lr": 4.939041339310858e-05, "s_per_step": 2.348098773956299, "peak_gb": 35.709385216, "samples_seen": 106400, "time": 1791145719.2507544}
{"step": 3350, "loss": 1.164835900068283, "grad_norm": 0.4022349715232849, "lr": 4.797161359191104e-05, "s_per_step": 2.542964315414429, "peak_gb": 35.709385216, "samples_seen": 107200, "time": 1791145782.8253438}
{"step": 3375, "loss": 1.1721830260753632, "grad_norm": 0.5090497136116028, "lr": 4.656703184501427e-05, "s_per_step": 2.52671706199646, "peak_gb": 35.709385216, "samples_seen": 108000, "time": 1791145845.9937546}
{"step": 3400, "loss": 1.1724821329116821, "grad_norm": 0.5728841423988342, "lr": 4.517705198941442e-05, "s_per_step": 2.4924769973754883, "peak_gb": 35.709385216, "samples_seen": 108800, "time": 1791145908.3061934}
{"step": 3425, "loss": 1.1960626763105393, "grad_norm": 0.562131941318512, "lr": 4.380205387177645e-05, "s_per_step": 2.408029260635376, "peak_gb": 35.709385216, "samples_seen": 109600, "time": 1791145968.5073981}
{"step": 3450, "loss": 1.1602804332971572, "grad_norm": 0.4601585268974304, "lr": 4.244241324463182e-05, "s_per_step": 2.5518965339660644, "peak_gb": 35.709385216, "samples_seen": 110400, "time": 1791146032.3052933}
{"step": 3475, "loss": 1.1917330080270767, "grad_norm": 0.5174102187156677, "lr": 4.109850166369465e-05, "s_per_step": 2.4686901664733885, "peak_gb": 35.709385216, "samples_seen": 111200, "time": 1791146094.0923746}
{"step": 3500, "loss": 1.176536915898323, "grad_norm": 0.46731457114219666, "lr": 3.977068638632486e-05, "s_per_step": 2.5151400184631347, "peak_gb": 35.709385216, "samples_seen": 112000, "time": 1791146156.9713702}
{"step": 3525, "loss": 1.1758270978927612, "grad_norm": 0.5187398195266724, "lr": 3.845933027116595e-05, "s_per_step": 2.5711546421051024, "peak_gb": 35.709385216, "samples_seen": 112800, "time": 1791146221.2507052}
{"step": 3550, "loss": 1.1746439105272293, "grad_norm": 0.46097496151924133, "lr": 3.716479167898476e-05, "s_per_step": 2.4746162128448486, "peak_gb": 35.709385216, "samples_seen": 113600, "time": 1791146283.1165752}
{"step": 3575, "loss": 1.1660949611663818, "grad_norm": 0.5945229530334473, "lr": 3.588742437474063e-05, "s_per_step": 2.5315122985839844, "peak_gb": 35.709385216, "samples_seen": 114400, "time": 1791146346.4049218}
{"step": 3600, "loss": 1.177633284330368, "grad_norm": 0.42318975925445557, "lr": 3.4627577430910066e-05, "s_per_step": 2.5272295093536377, "peak_gb": 35.709385216, "samples_seen": 115200, "time": 1791146409.5861077}
{"step": 3625, "loss": 1.1747868591547013, "grad_norm": 0.5484309792518616, "lr": 3.3385595132094104e-05, "s_per_step": 2.5058855533599855, "peak_gb": 35.709385216, "samples_seen": 116000, "time": 1791146472.2342918}
{"step": 3650, "loss": 1.1845440715551376, "grad_norm": 0.5164344906806946, "lr": 3.2161816880933996e-05, "s_per_step": 2.420202522277832, "peak_gb": 35.709385216, "samples_seen": 116800, "time": 1791146532.7397869}
{"step": 3675, "loss": 1.1623845690488814, "grad_norm": 0.44582146406173706, "lr": 3.095657710536086e-05, "s_per_step": 2.5247189235687255, "peak_gb": 35.709385216, "samples_seen": 117600, "time": 1791146595.8581657}
{"step": 3700, "loss": 1.177596697807312, "grad_norm": 0.6056506633758545, "lr": 2.977020516720501e-05, "s_per_step": 2.4129674339294436, "peak_gb": 35.709385216, "samples_seen": 118400, "time": 1791146656.1832361}
{"step": 3725, "loss": 1.1791141772270202, "grad_norm": 0.5385143160820007, "lr": 2.860302527218951e-05, "s_per_step": 2.466406307220459, "peak_gb": 35.709385216, "samples_seen": 119200, "time": 1791146717.8438177}
{"step": 3750, "loss": 1.1454178375005721, "grad_norm": 0.5121068954467773, "lr": 2.745535638133304e-05, "s_per_step": 2.5826826667785645, "peak_gb": 35.709385216, "samples_seen": 120000, "time": 1791146782.4113297}
{"step": 3775, "loss": 1.1689221292734147, "grad_norm": 0.5559164881706238, "lr": 2.632751212378568e-05, "s_per_step": 2.653624095916748, "peak_gb": 35.709385216, "samples_seen": 120800, "time": 1791146848.7524045}
{"step": 3800, "loss": 1.182214805483818, "grad_norm": 0.4873104691505432, "lr": 2.5219800711121976e-05, "s_per_step": 2.498158531188965, "peak_gb": 35.709385216, "samples_seen": 121600, "time": 1791146911.2068315}
{"step": 3825, "loss": 1.1555895429849625, "grad_norm": 0.576235294342041, "lr": 2.4132524853114456e-05, "s_per_step": 2.463836088180542, "peak_gb": 35.709385216, "samples_seen": 122400, "time": 1791146972.803223}
{"step": 3850, "loss": 1.163134110569954, "grad_norm": 0.49555864930152893, "lr": 2.306598167501064e-05, "s_per_step": 2.5268060398101806, "peak_gb": 35.709385216, "samples_seen": 123200, "time": 1791147035.973819}
{"step": 3875, "loss": 1.1696758967638017, "grad_norm": 0.519751250743866, "lr": 2.2020462636336137e-05, "s_per_step": 2.439229755401611, "peak_gb": 35.709385216, "samples_seen": 124000, "time": 1791147096.9549644}
{"step": 3900, "loss": 1.1512171399593354, "grad_norm": 0.42172372341156006, "lr": 2.0996253451246017e-05, "s_per_step": 2.601565704345703, "peak_gb": 35.709385216, "samples_seen": 124800, "time": 1791147161.9945152}
{"step": 3925, "loss": 1.1549856066703796, "grad_norm": 0.5235016942024231, "lr": 1.9993634010446448e-05, "s_per_step": 2.5241199016571043, "peak_gb": 35.709385216, "samples_seen": 125600, "time": 1791147225.0979981}
{"step": 3950, "loss": 1.1684985667467118, "grad_norm": 0.5432916283607483, "lr": 1.9012878304707403e-05, "s_per_step": 2.5513547325134276, "peak_gb": 35.709385216, "samples_seen": 126400, "time": 1791147288.8822782}
{"step": 3975, "loss": 1.1723533356189728, "grad_norm": 0.5285301804542542, "lr": 1.805425434998782e-05, "s_per_step": 2.436748571395874, "peak_gb": 35.709385216, "samples_seen": 127200, "time": 1791147349.801405}
{"step": 4000, "loss": 1.1497523707151414, "grad_norm": 0.44535908102989197, "lr": 1.711802411419384e-05, "s_per_step": 2.6349299812316893, "peak_gb": 35.709385216, "samples_seen": 128000, "time": 1791147415.675062}
{"step": 4025, "loss": 1.1554417186975479, "grad_norm": 0.4447822570800781, "lr": 1.6204443445589225e-05, "s_per_step": 2.693064069747925, "peak_gb": 35.709385216, "samples_seen": 128800, "time": 1791147483.002096}
{"step": 4050, "loss": 1.1771225923299788, "grad_norm": 0.5996832251548767, "lr": 1.5313762002878586e-05, "s_per_step": 2.506432514190674, "peak_gb": 35.709385216, "samples_seen": 129600, "time": 1791147545.6633337}
{"step": 4075, "loss": 1.156247045993805, "grad_norm": 0.5294703841209412, "lr": 1.444622318698191e-05, "s_per_step": 2.4499019813537597, "peak_gb": 35.709385216, "samples_seen": 130400, "time": 1791147606.9112895}
{"step": 4100, "loss": 1.1654343736171722, "grad_norm": 0.472944051027298, "lr": 1.3602064074519216e-05, "s_per_step": 2.5358735370635985, "peak_gb": 35.709385216, "samples_seen": 131200, "time": 1791147670.3085465}
{"step": 4125, "loss": 1.164423559308052, "grad_norm": 0.41716107726097107, "lr": 1.2781515353023365e-05, "s_per_step": 2.4599155235290526, "peak_gb": 35.709385216, "samples_seen": 132000, "time": 1791147731.8068397}
{"step": 4150, "loss": 1.1569818568229675, "grad_norm": 0.6027914881706238, "lr": 1.1984801257898925e-05, "s_per_step": 2.5184785079956056, "peak_gb": 35.709385216, "samples_seen": 132800, "time": 1791147794.76921}
{"step": 4175, "loss": 1.1682433980703353, "grad_norm": 0.5346322059631348, "lr": 1.1212139511144448e-05, "s_per_step": 2.3972896575927733, "peak_gb": 35.709385216, "samples_seen": 133600, "time": 1791147854.701882}
{"step": 4200, "loss": 1.1649791526794433, "grad_norm": 0.5470781326293945, "lr": 1.0463741261854288e-05, "s_per_step": 2.492423486709595, "peak_gb": 35.709385216, "samples_seen": 134400, "time": 1791147917.01288}
{"step": 4225, "loss": 1.1546978533267975, "grad_norm": 0.4576592743396759, "lr": 9.739811028516932e-06, "s_per_step": 2.527438831329346, "peak_gb": 35.709385216, "samples_seen": 135200, "time": 1791147980.1992562}
{"step": 4250, "loss": 1.1561020785570144, "grad_norm": 0.5178248286247253, "lr": 9.040546643125203e-06, "s_per_step": 2.517265033721924, "peak_gb": 35.709385216, "samples_seen": 136000, "time": 1791148043.1313138}
{"step": 4275, "loss": 1.1623137599229814, "grad_norm": 0.47821733355522156, "lr": 8.366139197113831e-06, "s_per_step": 2.5566812801361083, "peak_gb": 35.709385216, "samples_seen": 136800, "time": 1791148107.0487514}
{"step": 4300, "loss": 1.1758109939098358, "grad_norm": 0.5945451855659485, "lr": 7.716772989138744e-06, "s_per_step": 2.4145172882080077, "peak_gb": 35.709385216, "samples_seen": 137600, "time": 1791148167.4120862}
{"step": 4325, "loss": 1.1620000940561295, "grad_norm": 0.4968617260456085, "lr": 7.092625474713055e-06, "s_per_step": 2.42730583190918, "peak_gb": 35.709385216, "samples_seen": 138400, "time": 1791148228.0951617}
{"step": 4350, "loss": 1.156725025177002, "grad_norm": 0.45200902223587036, "lr": 6.493867217712868e-06, "s_per_step": 2.5541227149963377, "peak_gb": 35.709385216, "samples_seen": 139200, "time": 1791148291.9486508}
{"step": 4375, "loss": 1.1519554841518402, "grad_norm": 0.5528603792190552, "lr": 5.920661843766395e-06, "s_per_step": 2.648443021774292, "peak_gb": 35.889089024, "samples_seen": 140000, "time": 1791148358.1601393}
{"step": 4400, "loss": 1.1472780203819275, "grad_norm": 0.5185584425926208, "lr": 5.3731659955391865e-06, "s_per_step": 2.5665468978881836, "peak_gb": 35.889089024, "samples_seen": 140800, "time": 1791148422.3242114}
{"step": 4425, "loss": 1.16106074988842, "grad_norm": 0.47097915410995483, "lr": 4.8515292899276695e-06, "s_per_step": 2.5675136184692384, "peak_gb": 35.889089024, "samples_seen": 141600, "time": 1791148486.5124738}
{"step": 4450, "loss": 1.1584270763397218, "grad_norm": 0.5423069596290588, "lr": 4.355894277172545e-06, "s_per_step": 2.5209413051605223, "peak_gb": 35.889089024, "samples_seen": 142400, "time": 1791148549.5364525}
{"step": 4475, "loss": 1.167509251832962, "grad_norm": 0.4573025703430176, "lr": 3.886396401903381e-06, "s_per_step": 2.452349863052368, "peak_gb": 35.889089024, "samples_seen": 143200, "time": 1791148610.8456094}
{"step": 4500, "loss": 1.15239905834198, "grad_norm": 0.5477348566055298, "lr": 3.443163966125007e-06, "s_per_step": 2.4918809604644774, "peak_gb": 35.889089024, "samples_seen": 144000, "time": 1791148673.1431098}
{"step": 4525, "loss": 1.161824835538864, "grad_norm": 0.6060011386871338, "lr": 3.0263180941558332e-06, "s_per_step": 2.6219866466522217, "peak_gb": 35.889089024, "samples_seen": 144800, "time": 1791148738.6932275}
{"step": 4550, "loss": 1.1565506535768508, "grad_norm": 0.5005341172218323, "lr": 2.6359726995275004e-06, "s_per_step": 2.566774663925171, "peak_gb": 35.889089024, "samples_seen": 145600, "time": 1791148802.8630507}
{"step": 4575, "loss": 1.162327172756195, "grad_norm": 0.5122349858283997, "lr": 2.2722344538552597e-06, "s_per_step": 2.571699342727661, "peak_gb": 35.889089024, "samples_seen": 146400, "time": 1791148867.1559367}
{"step": 4600, "loss": 1.1596791630983352, "grad_norm": 0.5953731536865234, "lr": 1.9352027576872824e-06, "s_per_step": 2.364423170089722, "peak_gb": 35.889089024, "samples_seen": 147200, "time": 1791148926.266977}
{"step": 4625, "loss": 1.1516347283124924, "grad_norm": 0.49013832211494446, "lr": 1.6249697133409069e-06, "s_per_step": 2.5397282600402833, "peak_gb": 35.889089024, "samples_seen": 148000, "time": 1791148989.760581}
{"step": 4650, "loss": 1.1604260104894637, "grad_norm": 0.44168010354042053, "lr": 1.341620099733487e-06, "s_per_step": 2.495543918609619, "peak_gb": 35.889089024, "samples_seen": 148800, "time": 1791149052.149569}
{"step": 4675, "loss": 1.144905739426613, "grad_norm": 0.47312289476394653, "lr": 1.0852313492143551e-06, "s_per_step": 2.527244834899902, "peak_gb": 35.889089024, "samples_seen": 149600, "time": 1791149115.3311636}
{"step": 4700, "loss": 1.164122424721718, "grad_norm": 0.5258249044418335, "lr": 8.558735264045714e-07, "s_per_step": 2.392429494857788, "peak_gb": 35.889089024, "samples_seen": 150400, "time": 1791149175.1423135}
{"step": 4725, "loss": 1.1654922747612, "grad_norm": 0.5145270228385925, "lr": 6.536093090499517e-07, "s_per_step": 2.493706407546997, "peak_gb": 35.889089024, "samples_seen": 151200, "time": 1791149237.4853363}
{"step": 4750, "loss": 1.170558487176895, "grad_norm": 0.6493576169013977, "lr": 4.78493970892846e-07, "s_per_step": 2.3715320777893067, "peak_gb": 35.889089024, "samples_seen": 152000, "time": 1791149296.775865}
{"step": 4775, "loss": 1.166077768802643, "grad_norm": 0.5020484328269958, "lr": 3.3057536656722065e-07, "s_per_step": 2.589771041870117, "peak_gb": 35.889089024, "samples_seen": 152800, "time": 1791149361.5205963}
{"step": 4800, "loss": 1.1575500231981277, "grad_norm": 0.4154891073703766, "lr": 2.0989391852116458e-07, "s_per_step": 2.4963897895812988, "peak_gb": 35.889089024, "samples_seen": 153600, "time": 1791149423.930882}
{"step": 4825, "loss": 1.1519961988925933, "grad_norm": 0.5121576189994812, "lr": 1.1648260597041383e-07, "s_per_step": 2.559989347457886, "peak_gb": 35.889089024, "samples_seen": 154400, "time": 1791149487.9312465}
{"step": 4850, "loss": 1.1676404130458833, "grad_norm": 0.550052285194397, "lr": 5.036695588606088e-08, "s_per_step": 2.4459603118896482, "peak_gb": 35.889089024, "samples_seen": 155200, "time": 1791149549.080826}
{"step": 4875, "loss": 1.169189488887787, "grad_norm": 0.5803373456001282, "lr": 1.1565036018568176e-08, "s_per_step": 2.4609833908081056, "peak_gb": 35.889089024, "samples_seen": 156000, "time": 1791149610.6059558}
{"step": 4897, "loss": 1.1497614966197447, "grad_norm": 0.4358130097389221, "lr": 2.1862492483037954e-11, "s_per_step": 2.5117971788753164, "peak_gb": 35.889089024, "samples_seen": 156704, "time": 1791149665.8659236}