SPB Git

spb/wp31_uqo

Public
1{"step": 0, "loss": 0.42698904871940613, "lr": 1e-05, "grad_norm": 0.1901317685842514, "tokens": 139, "tok_per_s": 295.0936471236116, "t": 1.06}2{"step": 50, "loss": 0.3161904811859131, "lr": 0.00051, "grad_norm": 0.2068859189748764, "tokens": 8357, "tok_per_s": 204.58035786616816, "t": 41.44}3{"step": 100, "loss": 0.3214646577835083, "lr": 0.001, "grad_norm": 0.09587925672531128, "tokens": 16659, "tok_per_s": 199.36001320954014, "t": 84.15}4{"step": 150, "loss": 0.4550296664237976, "lr": 0.0009993400362330058, "grad_norm": 0.06907088309526443, "tokens": 25169, "tok_per_s": 200.1656392452418, "t": 126.33}5{"step": 200, "loss": 0.4864121973514557, "lr": 0.0009973620807194618, "grad_norm": 0.10461719334125519, "tokens": 33572, "tok_per_s": 197.0027311771507, "t": 171.0}6{"step": 250, "loss": 0.41645348072052, "lr": 0.000994071935143687, "grad_norm": 0.04575813561677933, "tokens": 41743, "tok_per_s": 190.617692293641, "t": 219.58}7{"step": 300, "loss": 0.3962055444717407, "lr": 0.000989479250069539, "grad_norm": 0.024577278643846512, "tokens": 49922, "tok_per_s": 185.71227266683982, "t": 269.4}8{"step": 350, "loss": 0.39045464992523193, "lr": 0.0009835974966336503, "grad_norm": 0.06709545850753784, "tokens": 58442, "tok_per_s": 183.76774210560163, "t": 318.61}9{"step": 400, "loss": 0.34576067328453064, "lr": 0.0009764439270322612, "grad_norm": 0.08723907917737961, "tokens": 66780, "tok_per_s": 181.98057311093837, "t": 367.55}10{"step": 450, "loss": 0.48750680685043335, "lr": 0.0009680395239175562, "grad_norm": 0.06860753148794174, "tokens": 74983, "tok_per_s": 179.9980128611568, "t": 417.17}11{"step": 499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4597795917930246, "val_loss_b2": 0.45789645962552994, "val_loss_b4": 0.45562516368040606, "val_loss_b8": 0.4560862334859142, "t": 478.69}12{"step": 500, "loss": 0.32694029808044434, "lr": 0.0009584089388519307, "grad_norm": 0.058815162628889084, "tokens": 83177, "tok_per_s": 173.63904084913634, "t": 479.61}13{"step": 550, "loss": 0.4060991406440735, "lr": 0.0009475804200007103, "grad_norm": 0.11365605890750885, "tokens": 91423, "tok_per_s": 173.71757008165594, "t": 526.86}14{"step": 600, "loss": 0.37998640537261963, "lr": 0.0009355857292754152, "grad_norm": 0.06720273196697235, "tokens": 99986, "tok_per_s": 175.103409645723, "t": 571.6}15{"step": 650, "loss": 0.3558715283870697, "lr": 0.0009224600491706008, "grad_norm": 0.07355039566755295, "tokens": 108206, "tok_per_s": 175.7103929134845, "t": 616.41}16{"step": 700, "loss": 0.442195862531662, "lr": 0.0009082418795675396, "grad_norm": 0.2318994253873825, "tokens": 116415, "tok_per_s": 176.18298868615204, "t": 661.35}17{"step": 750, "loss": 0.33867934346199036, "lr": 0.0008929729248074364, "grad_norm": 0.06900604814291, "tokens": 124709, "tok_per_s": 176.27393192350695, "t": 708.06}18{"step": 800, "loss": 0.4265964925289154, "lr": 0.0008766979713654089, "grad_norm": 0.07373394817113876, "tokens": 132874, "tok_per_s": 177.1465043429252, "t": 750.67}19{"step": 850, "loss": 0.36213603615760803, "lr": 0.0008594647564840406, "grad_norm": 0.07029276341199875, "tokens": 141506, "tok_per_s": 179.43006124153663, "t": 789.23}20{"step": 900, "loss": 0.29294875264167786, "lr": 0.0008413238281518224, "grad_norm": 0.052500732243061066, "tokens": 149769, "tok_per_s": 181.12673042708838, "t": 827.46}21{"step": 950, "loss": 0.359129935503006, "lr": 0.0008223283968371944, "grad_norm": 0.06976951658725739, "tokens": 158176, "tok_per_s": 182.75721998553678, "t": 866.09}22{"step": 999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4579638146954607, "val_loss_b2": 0.45529223686959014, "val_loss_b4": 0.4527359300202604, "val_loss_b8": 0.4554919764113109, "t": 914.97}23{"step": 1000, "loss": 0.41376566886901855, "lr": 0.000802534179413072, "grad_norm": 0.07638819515705109, "tokens": 166573, "tok_per_s": 182.02336116369588, "t": 915.71}24{"step": 1050, "loss": 0.35814306139945984, "lr": 0.0007819992357296598, "grad_norm": 0.06560231745243073, "tokens": 174773, "tok_per_s": 185.9730128731322, "t": 940.36}25{"step": 1100, "loss": 0.4352353513240814, "lr": 0.0007607837983149056, "grad_norm": 0.04778369516134262, "tokens": 183200, "tok_per_s": 190.36774856302483, "t": 962.93}26{"step": 1150, "loss": 0.4685201644897461, "lr": 0.0007389500957021191, "grad_norm": 0.17405419051647186, "tokens": 191474, "tok_per_s": 196.27727992944833, "t": 976.11}27{"step": 1200, "loss": 0.39651963114738464, "lr": 0.0007165621699029615, "grad_norm": 0.1089477688074112, "tokens": 200061, "tok_per_s": 202.67376477889394, "t": 987.7}28{"step": 1250, "loss": 0.3917563259601593, "lr": 0.000693685688561191, "grad_norm": 0.1168973445892334, "tokens": 208455, "tok_per_s": 208.73290159327564, "t": 999.26}29{"step": 1300, "loss": 0.3728666603565216, "lr": 0.0006703877523381495, "grad_norm": 0.18062421679496765, "tokens": 216814, "tok_per_s": 214.6548744357263, "t": 1010.65}30{"step": 1350, "loss": 0.34079739451408386, "lr": 0.0006467366980949609, "grad_norm": 0.11795547604560852, "tokens": 225136, "tok_per_s": 220.4064453594716, "t": 1022.04}31{"step": 1400, "loss": 0.3488686680793762, "lr": 0.0006228018984487442, "grad_norm": 0.0765005424618721, "tokens": 233471, "tok_per_s": 225.98093726784313, "t": 1033.73}32{"step": 1450, "loss": 0.30764755606651306, "lr": 0.0005986535582907738, "grad_norm": 0.07714161276817322, "tokens": 241795, "tok_per_s": 231.40893317837717, "t": 1045.47}33{"step": 1499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4561558521810337, "val_loss_b2": 0.45300636742724876, "val_loss_b4": 0.45217685408049346, "val_loss_b8": 0.46338707334951795, "t": 1059.67}34{"step": 1500, "loss": 0.31216439604759216, "lr": 0.000574362508863438, "grad_norm": 0.07397142797708511, "tokens": 250085, "tok_per_s": 236.07609866036296, "t": 1059.93}35{"step": 1550, "loss": 0.3870960772037506, "lr": 0.00055, "grad_norm": 0.11012793332338333, "tokens": 258187, "tok_per_s": 241.11356095590205, "t": 1071.4}36{"step": 1600, "loss": 0.35771283507347107, "lr": 0.0005256374911365621, "grad_norm": 0.17008201777935028, "tokens": 266247, "tok_per_s": 245.97948221319967, "t": 1082.98}37{"step": 1650, "loss": 0.31530770659446716, "lr": 0.0005013464417092262, "grad_norm": 0.14058318734169006, "tokens": 274738, "tok_per_s": 251.15381468811216, "t": 1094.49}38{"step": 1700, "loss": 0.3683518171310425, "lr": 0.00047719810155125587, "grad_norm": 0.06617994606494904, "tokens": 283093, "tok_per_s": 256.0553402889908, "t": 1106.18}39{"step": 1750, "loss": 0.3860456943511963, "lr": 0.0004532633019050392, "grad_norm": 0.10011892020702362, "tokens": 291261, "tok_per_s": 260.7148836862475, "t": 1117.75}40{"step": 1800, "loss": 0.3968793749809265, "lr": 0.0004296122476618507, "grad_norm": 0.10075835883617401, "tokens": 299555, "tok_per_s": 265.39711809920664, "t": 1129.29}41{"step": 1850, "loss": 0.4114893972873688, "lr": 0.00040631431143880916, "grad_norm": 0.1257578730583191, "tokens": 307521, "tok_per_s": 269.7072356500045, "t": 1140.79}42{"step": 1900, "loss": 0.386040598154068, "lr": 0.00038343783009703845, "grad_norm": 0.07321565598249435, "tokens": 315892, "tok_per_s": 274.277208782634, "t": 1152.31}43{"step": 1950, "loss": 0.3491448163986206, "lr": 0.000361049904297881, "grad_norm": 0.0617687962949276, "tokens": 324298, "tok_per_s": 278.74977306046503, "t": 1163.99}44{"step": 1999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45600447318658505, "val_loss_b2": 0.4532953058339622, "val_loss_b4": 0.45314812037438346, "val_loss_b8": 0.46309177366720156, "t": 1178.12}45{"step": 2000, "loss": 0.28462520241737366, "lr": 0.0003392162016850945, "grad_norm": 0.12711481750011444, "tokens": 332486, "tok_per_s": 282.30164698849813, "t": 1178.36}46{"step": 2050, "loss": 0.4564434289932251, "lr": 0.0003180007642703402, "grad_norm": 0.13428080081939697, "tokens": 340738, "tok_per_s": 286.4902531855085, "t": 1189.94}47{"step": 2100, "loss": 0.36808857321739197, "lr": 0.000297465820586928, "grad_norm": 0.08889605849981308, "tokens": 349148, "tok_per_s": 290.7261445561406, "t": 1201.54}48{"step": 2150, "loss": 0.339792937040329, "lr": 0.0002776716031628058, "grad_norm": 0.12118899077177048, "tokens": 357576, "tok_per_s": 294.8748603518309, "t": 1213.22}49{"step": 2200, "loss": 0.34901300072669983, "lr": 0.00025867617184817756, "grad_norm": 0.19013236463069916, "tokens": 366097, "tok_per_s": 299.06051832616623, "t": 1224.74}50{"step": 2250, "loss": 0.2722165584564209, "lr": 0.00024053524351595949, "grad_norm": 0.11010696738958359, "tokens": 374285, "tok_per_s": 302.86467645843976, "t": 1236.4}51{"step": 2300, "loss": 0.37353822588920593, "lr": 0.0002233020286345913, "grad_norm": 0.10270766168832779, "tokens": 382864, "tok_per_s": 306.90100911134067, "t": 1248.1}52{"step": 2350, "loss": 0.44861525297164917, "lr": 0.00020702707519256364, "grad_norm": 0.12010861933231354, "tokens": 391427, "tok_per_s": 310.89161244348867, "t": 1259.63}53{"step": 2400, "loss": 0.6376331448554993, "lr": 0.00019175812043246033, "grad_norm": 0.17807637155056, "tokens": 399797, "tok_per_s": 314.6122937593665, "t": 1271.35}54{"step": 2450, "loss": 0.35117626190185547, "lr": 0.00017753995082939931, "grad_norm": 0.18827882409095764, "tokens": 407948, "tok_per_s": 318.113039532695, "t": 1282.99}55{"step": 2499, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.4545630854065633, "val_loss_b2": 0.4507208636619, "val_loss_b4": 0.44825561320388063, "val_loss_b8": 0.4540032687123742, "t": 1297.07}56{"step": 2500, "loss": 0.4006892442703247, "lr": 0.00016441427072458494, "grad_norm": 0.12415807694196701, "tokens": 416019, "tok_per_s": 320.82720157103705, "t": 1297.29}57{"step": 2550, "loss": 0.3197712302207947, "lr": 0.0001524195799992897, "grad_norm": 0.0902567207813263, "tokens": 424449, "tok_per_s": 324.46963872282004, "t": 1308.72}58{"step": 2600, "loss": 0.3739716112613678, "lr": 0.0001415910611480694, "grad_norm": 0.14749449491500854, "tokens": 432494, "tok_per_s": 327.73134536868014, "t": 1320.25}59{"step": 2650, "loss": 0.3050442337989807, "lr": 0.00013196047608244387, "grad_norm": 0.168471097946167, "tokens": 440693, "tok_per_s": 331.03022899733963, "t": 1331.86}60{"step": 2700, "loss": 0.39263057708740234, "lr": 0.00012355607296773896, "grad_norm": 0.18951644003391266, "tokens": 449079, "tok_per_s": 334.44776874986877, "t": 1343.33}61{"step": 2750, "loss": 0.302759051322937, "lr": 0.00011640250336634969, "grad_norm": 0.08737623691558838, "tokens": 457686, "tok_per_s": 337.9663643392734, "t": 1354.82}62{"step": 2800, "loss": 0.4198930859565735, "lr": 0.00011052074993046101, "grad_norm": 0.15651190280914307, "tokens": 466220, "tok_per_s": 341.33736104543374, "t": 1366.45}63{"step": 2850, "loss": 0.4660772979259491, "lr": 0.00010592806485631325, "grad_norm": 0.17438970506191254, "tokens": 474198, "tok_per_s": 344.285053668433, "t": 1377.93}64{"step": 2900, "loss": 0.4459766745567322, "lr": 0.00010263791928053818, "grad_norm": 0.22878025472164154, "tokens": 482297, "tok_per_s": 347.2079410794458, "t": 1389.66}65{"step": 2950, "loss": 0.4056680500507355, "lr": 0.0001006599637669943, "grad_norm": 0.16179512441158295, "tokens": 490516, "tok_per_s": 350.17658985847766, "t": 1401.35}66{"step": 2999, "loss": 0.512488067150116, "lr": 0.0001000002640500325, "grad_norm": 0.19625777006149292, "tokens": 498543, "tok_per_s": 353.10425539778805, "t": 1412.47}67{"step": 2999, "val_loss_b0": 0.4621244837580907, "val_loss_b1": 0.45328951046465654, "val_loss_b2": 0.450377365119825, "val_loss_b4": 0.4507006113607934, "val_loss_b8": 0.4621606754398863, "t": 1415.32}68{"step": 2999, "checkpoint_sha256": "1bf30758cec69e8b90d8883422f2d37540f7d714a0afe033a8da68747ef89cd4", "t": 1415.35}69
Files · main
Menu

Theme