Bc-AI commited on
Commit
25c7af6
·
verified ·
1 Parent(s): f4c5a09

Upload metrics_session_002.jsonl with huggingface_hub

Browse files
Files changed (1) hide show
  1. metrics_session_002.jsonl +48 -0
metrics_session_002.jsonl CHANGED
@@ -9893,3 +9893,51 @@
9893
  {"timestamp": 1787564967.7574763, "elapsed_hours": 10.651074713601007, "session_id": 2, "event": "train_step", "step": 87560, "epoch": 1, "loss": 1.768518133163452, "loss_raw": 1.2078866958618164, "perplexity": 5.862159981290797, "muon_lr": 0.004406913499048426, "adamw_lr": 0.00013220740497145276, "tokens_per_sec": 149698.3656336748, "vram_gb": 27.299458026885986, "grad_norm": 0.1318359375, "tokens_processed": 5738332160, "tokens_processed_billions": 5.73833216}
9894
  {"timestamp": 1787564971.855847, "elapsed_hours": 10.652213149865469, "session_id": 2, "event": "train_step", "step": 87570, "epoch": 1, "loss": 1.7325332129001618, "loss_raw": 1.7205485105514526, "perplexity": 5.654960999477388, "muon_lr": 0.004406172231086835, "adamw_lr": 0.00013218516693260505, "tokens_per_sec": 149699.4570343949, "vram_gb": 27.710740089416504, "grad_norm": 0.138671875, "tokens_processed": 5738987520, "tokens_processed_billions": 5.73898752}
9895
  {"timestamp": 1787564975.8563972, "elapsed_hours": 10.653324413961835, "session_id": 2, "event": "train_step", "step": 87580, "epoch": 1, "loss": 1.7301462030410766, "loss_raw": 2.5616397857666016, "perplexity": 5.641478649471749, "muon_lr": 0.0044054309946684085, "adamw_lr": 0.00013216292984005222, "tokens_per_sec": 149700.93055693613, "vram_gb": 27.710740089416504, "grad_norm": 0.134765625, "tokens_processed": 5739642880, "tokens_processed_billions": 5.73964288}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9893
  {"timestamp": 1787564967.7574763, "elapsed_hours": 10.651074713601007, "session_id": 2, "event": "train_step", "step": 87560, "epoch": 1, "loss": 1.768518133163452, "loss_raw": 1.2078866958618164, "perplexity": 5.862159981290797, "muon_lr": 0.004406913499048426, "adamw_lr": 0.00013220740497145276, "tokens_per_sec": 149698.3656336748, "vram_gb": 27.299458026885986, "grad_norm": 0.1318359375, "tokens_processed": 5738332160, "tokens_processed_billions": 5.73833216}
9894
  {"timestamp": 1787564971.855847, "elapsed_hours": 10.652213149865469, "session_id": 2, "event": "train_step", "step": 87570, "epoch": 1, "loss": 1.7325332129001618, "loss_raw": 1.7205485105514526, "perplexity": 5.654960999477388, "muon_lr": 0.004406172231086835, "adamw_lr": 0.00013218516693260505, "tokens_per_sec": 149699.4570343949, "vram_gb": 27.710740089416504, "grad_norm": 0.138671875, "tokens_processed": 5738987520, "tokens_processed_billions": 5.73898752}
9895
  {"timestamp": 1787564975.8563972, "elapsed_hours": 10.653324413961835, "session_id": 2, "event": "train_step", "step": 87580, "epoch": 1, "loss": 1.7301462030410766, "loss_raw": 2.5616397857666016, "perplexity": 5.641478649471749, "muon_lr": 0.0044054309946684085, "adamw_lr": 0.00013216292984005222, "tokens_per_sec": 149700.93055693613, "vram_gb": 27.710740089416504, "grad_norm": 0.134765625, "tokens_processed": 5739642880, "tokens_processed_billions": 5.73964288}
9896
+ {"timestamp": 1787564980.7652414, "elapsed_hours": 10.65468798187044, "session_id": 2, "event": "train_step", "step": 87590, "epoch": 1, "loss": 1.7479306137561799, "loss_raw": 1.8430664539337158, "perplexity": 5.742706493532846, "muon_lr": 0.004404689789814519, "adamw_lr": 0.00013214069369443554, "tokens_per_sec": 149698.85711825965, "vram_gb": 27.710740089416504, "grad_norm": 0.1328125, "tokens_processed": 5740298240, "tokens_processed_billions": 5.74029824}
9897
+ {"timestamp": 1787564984.9410286, "elapsed_hours": 10.655847922563552, "session_id": 2, "event": "train_step", "step": 87600, "epoch": 1, "loss": 1.7307681143283844, "loss_raw": 0.9910641312599182, "perplexity": 5.644988239934805, "muon_lr": 0.004403207474885849, "adamw_lr": 0.00013209622424657544, "tokens_per_sec": 149699.64581830968, "vram_gb": 27.299458026885986, "grad_norm": 0.1279296875, "tokens_processed": 5740953600, "tokens_processed_billions": 5.7409536}
9898
+ {"timestamp": 1787564984.9481487, "elapsed_hours": 10.655849900576804, "session_id": 2, "event": "lambda_stats", "step": 87600, "epoch": 1, "lambda_min": 1.078125, "lambda_max": 2.015625, "lambda_mean": 1.1892361111111112, "lambda_std": 0.20446532211957086, "lambda_all": [2.015625, 1.25, 1.1875, 1.140625, 1.140625, 1.140625, 1.140625, 1.21875, 1.140625, 1.109375, 1.140625, 1.1171875, 1.140625, 1.109375, 1.109375, 1.078125, 1.1015625, 1.125], "local_layers": 9, "global_layers": 9}
9899
+ {"timestamp": 1787564988.9324853, "elapsed_hours": 10.656956660615073, "session_id": 2, "event": "train_step", "step": 87610, "epoch": 1, "loss": 1.774180542230606, "loss_raw": 2.645340919494629, "perplexity": 5.895448085611181, "muon_lr": 0.0044024663648538145, "adamw_lr": 0.0001320739909456144, "tokens_per_sec": 149701.15413977468, "vram_gb": 27.710740089416504, "grad_norm": 0.134765625, "tokens_processed": 5741608960, "tokens_processed_billions": 5.74160896}
9900
+ {"timestamp": 1787564993.033722, "elapsed_hours": 10.658095892998908, "session_id": 2, "event": "train_step", "step": 87620, "epoch": 1, "loss": 1.7087367188930511, "loss_raw": 1.1669131517410278, "perplexity": 5.521981254968274, "muon_lr": 0.004401725286471811, "adamw_lr": 0.0001320517585941543, "tokens_per_sec": 149702.2330154041, "vram_gb": 27.710740089416504, "grad_norm": 0.1416015625, "tokens_processed": 5742264320, "tokens_processed_billions": 5.74226432}
9901
+ {"timestamp": 1787564997.016426, "elapsed_hours": 10.659202199644513, "session_id": 2, "event": "train_step", "step": 87630, "epoch": 1, "loss": 1.6579509556293488, "loss_raw": 1.562361240386963, "perplexity": 5.248545316456506, "muon_lr": 0.004400984239761207, "adamw_lr": 0.00013202952719283619, "tokens_per_sec": 149703.774858194, "vram_gb": 27.710740089416504, "grad_norm": 0.12353515625, "tokens_processed": 5742919680, "tokens_processed_billions": 5.74291968}
9902
+ {"timestamp": 1787565001.2999463, "elapsed_hours": 10.66039206650522, "session_id": 2, "event": "train_step", "step": 87640, "epoch": 1, "loss": 1.6751167559623719, "loss_raw": 1.8624292612075806, "perplexity": 5.339418521629236, "muon_lr": 0.004399502241439683, "adamw_lr": 0.00013198506724319047, "tokens_per_sec": 149704.14196187345, "vram_gb": 27.299458026885986, "grad_norm": 0.142578125, "tokens_processed": 5743575040, "tokens_processed_billions": 5.74357504}
9903
+ {"timestamp": 1787565005.38202, "elapsed_hours": 10.661525975995593, "session_id": 2, "event": "train_step", "step": 87650, "epoch": 1, "loss": 1.706166126728058, "loss_raw": 1.8990532159805298, "perplexity": 5.507804722067691, "muon_lr": 0.004398761289871497, "adamw_lr": 0.00013196283869614488, "tokens_per_sec": 149705.2959046043, "vram_gb": 27.710740089416504, "grad_norm": 0.1396484375, "tokens_processed": 5744230400, "tokens_processed_billions": 5.7442304}
9904
+ {"timestamp": 1787565009.3625398, "elapsed_hours": 10.662631675601006, "session_id": 2, "event": "train_step", "step": 87660, "epoch": 1, "loss": 1.740618679523468, "loss_raw": 2.436861515045166, "perplexity": 5.700869342980645, "muon_lr": 0.004398020370060186, "adamw_lr": 0.00013194061110180557, "tokens_per_sec": 149706.84477898965, "vram_gb": 27.710740089416504, "grad_norm": 0.1494140625, "tokens_processed": 5744885760, "tokens_processed_billions": 5.74488576}
9905
+ {"timestamp": 1787565013.450919, "elapsed_hours": 10.663767336540753, "session_id": 2, "event": "train_step", "step": 87670, "epoch": 1, "loss": 1.8509170365333558, "loss_raw": 2.2177352905273438, "perplexity": 6.365654384431434, "muon_lr": 0.004397279482027117, "adamw_lr": 0.00013191838446081347, "tokens_per_sec": 149707.97312646368, "vram_gb": 27.710740089416504, "grad_norm": 0.142578125, "tokens_processed": 5745541120, "tokens_processed_billions": 5.74554112}
9906
+ {"timestamp": 1787565017.603571, "elapsed_hours": 10.66492085105843, "session_id": 2, "event": "train_step", "step": 87680, "epoch": 1, "loss": 1.8968790209293365, "loss_raw": 2.746941566467285, "perplexity": 6.665060433819584, "muon_lr": 0.004395797801381163, "adamw_lr": 0.00013187393404143484, "tokens_per_sec": 149708.85053826135, "vram_gb": 27.299458026885986, "grad_norm": 0.1318359375, "tokens_processed": 5746196480, "tokens_processed_billions": 5.74619648}
9907
+ {"timestamp": 1787565021.6089513, "elapsed_hours": 10.66603345659044, "session_id": 2, "event": "train_step", "step": 87690, "epoch": 1, "loss": 1.9711763954162598, "loss_raw": 4.142892837524414, "perplexity": 7.179117003016964, "muon_lr": 0.004395057008811003, "adamw_lr": 0.00013185171026433007, "tokens_per_sec": 149710.3018490971, "vram_gb": 27.710740089416504, "grad_norm": 0.154296875, "tokens_processed": 5746851840, "tokens_processed_billions": 5.74685184}
9908
+ {"timestamp": 1787565025.6777823, "elapsed_hours": 10.667163687547047, "session_id": 2, "event": "train_step", "step": 87700, "epoch": 1, "loss": 1.9747181725502014, "loss_raw": 1.5575673580169678, "perplexity": 7.204588916753929, "muon_lr": 0.004394316248104542, "adamw_lr": 0.00013182948744313623, "tokens_per_sec": 149711.5059188951, "vram_gb": 27.710740089416504, "grad_norm": 0.1455078125, "tokens_processed": 5747507200, "tokens_processed_billions": 5.7475072}
9909
+ {"timestamp": 1787565025.6852531, "elapsed_hours": 10.667165763179462, "session_id": 2, "event": "lambda_stats", "step": 87700, "epoch": 1, "lambda_min": 1.078125, "lambda_max": 2.015625, "lambda_mean": 1.1892361111111112, "lambda_std": 0.20446532211957086, "lambda_all": [2.015625, 1.25, 1.1875, 1.140625, 1.140625, 1.140625, 1.140625, 1.21875, 1.140625, 1.109375, 1.140625, 1.1171875, 1.140625, 1.109375, 1.109375, 1.078125, 1.1015625, 1.125], "local_layers": 9, "global_layers": 9}
9910
+ {"timestamp": 1787565029.6932693, "elapsed_hours": 10.668279100722737, "session_id": 2, "event": "train_step", "step": 87710, "epoch": 1, "loss": 1.9285468029975892, "loss_raw": 1.3990012407302856, "perplexity": 6.879505696997866, "muon_lr": 0.004393575519283138, "adamw_lr": 0.0001318072655784941, "tokens_per_sec": 149712.91754922728, "vram_gb": 27.710740089416504, "grad_norm": 0.140625, "tokens_processed": 5748162560, "tokens_processed_billions": 5.74816256}
9911
+ {"timestamp": 1787565033.944708, "elapsed_hours": 10.669460055828095, "session_id": 2, "event": "train_step", "step": 87720, "epoch": 1, "loss": 1.8269247019290924, "loss_raw": 1.8127752542495728, "perplexity": 6.214745047075795, "muon_lr": 0.0043920941573809495, "adamw_lr": 0.00013176282472142844, "tokens_per_sec": 149713.40853937628, "vram_gb": 27.299458026885986, "grad_norm": 0.125, "tokens_processed": 5748817920, "tokens_processed_billions": 5.74881792}
9912
+ {"timestamp": 1787565038.2124665, "elapsed_hours": 10.670645544197825, "session_id": 2, "event": "train_step", "step": 87730, "epoch": 1, "loss": 1.8666264915466309, "loss_raw": 2.5137617588043213, "perplexity": 6.466444955274766, "muon_lr": 0.0043913535243428805, "adamw_lr": 0.0001317406057302864, "tokens_per_sec": 149713.83667869502, "vram_gb": 27.710740089416504, "grad_norm": 0.140625, "tokens_processed": 5749473280, "tokens_processed_billions": 5.74947328}
9913
+ {"timestamp": 1787565042.2021842, "elapsed_hours": 10.671753799054358, "session_id": 2, "event": "train_step", "step": 87740, "epoch": 1, "loss": 1.8258564245700837, "loss_raw": 1.094326138496399, "perplexity": 6.208109520572404, "muon_lr": 0.004390612923275308, "adamw_lr": 0.00013171838769825923, "tokens_per_sec": 149715.34733677268, "vram_gb": 27.710740089416504, "grad_norm": 0.16015625, "tokens_processed": 5750128640, "tokens_processed_billions": 5.75012864}
9914
+ {"timestamp": 1787565046.3265817, "elapsed_hours": 10.672899465097322, "session_id": 2, "event": "train_step", "step": 87750, "epoch": 1, "loss": 1.8382629930973053, "loss_raw": 1.3630895614624023, "perplexity": 6.2856106240421745, "muon_lr": 0.004389872354199588, "adamw_lr": 0.00013169617062598762, "tokens_per_sec": 149716.3337508844, "vram_gb": 27.710740089416504, "grad_norm": 0.1396484375, "tokens_processed": 5750784000, "tokens_processed_billions": 5.750784}
9915
+ {"timestamp": 1787565050.5392604, "elapsed_hours": 10.67406965361701, "session_id": 2, "event": "train_step", "step": 87760, "epoch": 1, "loss": 1.880513960123062, "loss_raw": 1.1118075847625732, "perplexity": 6.5568739680754815, "muon_lr": 0.004388391312109131, "adamw_lr": 0.0001316517393632739, "tokens_per_sec": 149716.9753511834, "vram_gb": 27.299458026885986, "grad_norm": 0.1396484375, "tokens_processed": 5751439360, "tokens_processed_billions": 5.75143936}
9916
+ {"timestamp": 1787565054.5231886, "elapsed_hours": 10.675176300472684, "session_id": 2, "event": "train_step", "step": 87770, "epoch": 1, "loss": 1.9270678400993346, "loss_raw": 2.388263463973999, "perplexity": 6.86933868348478, "muon_lr": 0.004387650839137101, "adamw_lr": 0.000131629525174113, "tokens_per_sec": 149718.50867989293, "vram_gb": 27.710740089416504, "grad_norm": 0.134765625, "tokens_processed": 5752094720, "tokens_processed_billions": 5.75209472}
9917
+ {"timestamp": 1787565058.6005177, "elapsed_hours": 10.676308891773225, "session_id": 2, "event": "train_step", "step": 87780, "epoch": 1, "loss": 1.9421992957592011, "loss_raw": 0.9383321404457092, "perplexity": 6.9740721638784, "muon_lr": 0.0043869103982423436, "adamw_lr": 0.0001316073119472703, "tokens_per_sec": 149719.67709627375, "vram_gb": 27.710740089416504, "grad_norm": 0.150390625, "tokens_processed": 5752750080, "tokens_processed_billions": 5.75275008}
9918
+ {"timestamp": 1787565062.6327786, "elapsed_hours": 10.67742896437645, "session_id": 2, "event": "train_step", "step": 87790, "epoch": 1, "loss": 1.8493147802352905, "loss_raw": 0.9198104739189148, "perplexity": 6.355463141274707, "muon_lr": 0.004386169989446209, "adamw_lr": 0.00013158509968338623, "tokens_per_sec": 149721.02153081022, "vram_gb": 27.710740089416504, "grad_norm": 0.134765625, "tokens_processed": 5753405440, "tokens_processed_billions": 5.75340544}
9919
+ {"timestamp": 1787565066.8943727, "elapsed_hours": 10.67861274043719, "session_id": 2, "event": "train_step", "step": 87800, "epoch": 1, "loss": 1.853240133523941, "loss_raw": 2.50455641746521, "perplexity": 6.380459607300983, "muon_lr": 0.0043846892682352185, "adamw_lr": 0.00013154067804705652, "tokens_per_sec": 149721.47158831454, "vram_gb": 27.299458026885986, "grad_norm": 0.1484375, "tokens_processed": 5754060800, "tokens_processed_billions": 5.7540608}
9920
+ {"timestamp": 1787565066.8981996, "elapsed_hours": 10.678613803651597, "session_id": 2, "event": "lambda_stats", "step": 87800, "epoch": 1, "lambda_min": 1.078125, "lambda_max": 2.015625, "lambda_mean": 1.1892361111111112, "lambda_std": 0.20446532211957086, "lambda_all": [2.015625, 1.25, 1.1875, 1.140625, 1.140625, 1.140625, 1.140625, 1.21875, 1.140625, 1.109375, 1.140625, 1.1171875, 1.140625, 1.109375, 1.109375, 1.078125, 1.1015625, 1.125], "local_layers": 9, "global_layers": 9}
9921
+ {"timestamp": 1787565071.0065906, "elapsed_hours": 10.679755023121833, "session_id": 2, "event": "train_step", "step": 87810, "epoch": 1, "loss": 1.7452840495109558, "loss_raw": 0.8958064913749695, "perplexity": 5.7275281459517275, "muon_lr": 0.00438394895586306, "adamw_lr": 0.00013151846867589178, "tokens_per_sec": 149722.50372582753, "vram_gb": 27.710740089416504, "grad_norm": 0.205078125, "tokens_processed": 5754716160, "tokens_processed_billions": 5.75471616}
9922
+ {"timestamp": 1787565074.9963953, "elapsed_hours": 10.680863302283816, "session_id": 2, "event": "train_step", "step": 87820, "epoch": 1, "loss": 1.6765364253520965, "loss_raw": 0.9312942624092102, "perplexity": 5.347004113905862, "muon_lr": 0.004383208675674927, "adamw_lr": 0.0001314962602702478, "tokens_per_sec": 149724.01273505902, "vram_gb": 27.710740089416504, "grad_norm": 0.11962890625, "tokens_processed": 5755371520, "tokens_processed_billions": 5.75537152}
9923
+ {"timestamp": 1787565079.1113937, "elapsed_hours": 10.682006357510884, "session_id": 2, "event": "train_step", "step": 87830, "epoch": 1, "loss": 1.6255878496170044, "loss_raw": 1.6029033660888672, "perplexity": 5.081405261505493, "muon_lr": 0.004382468427692165, "adamw_lr": 0.00013147405283076493, "tokens_per_sec": 149725.03355724766, "vram_gb": 27.710740089416504, "grad_norm": 0.1328125, "tokens_processed": 5756026880, "tokens_processed_billions": 5.75602688}
9924
+ {"timestamp": 1787565083.239106, "elapsed_hours": 10.683152944180701, "session_id": 2, "event": "train_step", "step": 87840, "epoch": 1, "loss": 1.617286137342453, "loss_raw": 1.160735845565796, "perplexity": 5.039395514759383, "muon_lr": 0.004380988028428147, "adamw_lr": 0.0001314296408528444, "tokens_per_sec": 149726.00429899382, "vram_gb": 27.299458026885986, "grad_norm": 0.13671875, "tokens_processed": 5756682240, "tokens_processed_billions": 5.75668224}
9925
+ {"timestamp": 1787565087.2206943, "elapsed_hours": 10.68425894094838, "session_id": 2, "event": "train_step", "step": 87850, "epoch": 1, "loss": 1.588022402524948, "loss_raw": 1.6379636526107788, "perplexity": 4.894060869525399, "muon_lr": 0.004380247877189577, "adamw_lr": 0.0001314074363156873, "tokens_per_sec": 149727.54451326342, "vram_gb": 27.710740089416504, "grad_norm": 0.1474609375, "tokens_processed": 5757337600, "tokens_processed_billions": 5.7573376}
9926
+ {"timestamp": 1787565091.3425777, "elapsed_hours": 10.685403908491134, "session_id": 2, "event": "train_step", "step": 87860, "epoch": 1, "loss": 1.6047118413448334, "loss_raw": 1.6146115064620972, "perplexity": 4.976425396060409, "muon_lr": 0.004379507758241764, "adamw_lr": 0.0001313852327472529, "tokens_per_sec": 149728.53793761035, "vram_gb": 27.710740089416504, "grad_norm": 0.1474609375, "tokens_processed": 5757992960, "tokens_processed_billions": 5.75799296}
9927
+ {"timestamp": 1787565095.5453055, "elapsed_hours": 10.686571332944764, "session_id": 2, "event": "train_step", "step": 87870, "epoch": 1, "loss": 1.6829538094997405, "loss_raw": 1.2995398044586182, "perplexity": 5.38142823159731, "muon_lr": 0.0043787676716060455, "adamw_lr": 0.00013136303014818135, "tokens_per_sec": 149729.21648852853, "vram_gb": 27.710740089416504, "grad_norm": 0.12890625, "tokens_processed": 5758648320, "tokens_processed_billions": 5.75864832}
9928
+ {"timestamp": 1787565099.790867, "elapsed_hours": 10.687750655611357, "session_id": 2, "event": "train_step", "step": 87880, "epoch": 1, "loss": 1.6718675100803375, "loss_raw": 2.075435161590576, "perplexity": 5.322097593202005, "muon_lr": 0.004377287595356269, "adamw_lr": 0.00013131862786068806, "tokens_per_sec": 149729.72774533244, "vram_gb": 27.299458026885986, "grad_norm": 0.1357421875, "tokens_processed": 5759303680, "tokens_processed_billions": 5.75930368}
9929
+ {"timestamp": 1787565103.901552, "elapsed_hours": 10.6888925123877, "session_id": 2, "event": "train_step", "step": 87890, "epoch": 1, "loss": 1.661220715045929, "loss_raw": 2.1548335552215576, "perplexity": 5.265734884489372, "muon_lr": 0.004376547605784892, "adamw_lr": 0.0001312964281735467, "tokens_per_sec": 149730.764143082, "vram_gb": 27.710740089416504, "grad_norm": 0.123046875, "tokens_processed": 5759959040, "tokens_processed_billions": 5.75995904}
9930
+ {"timestamp": 1787565108.027465, "elapsed_hours": 10.690038599570592, "session_id": 2, "event": "train_step", "step": 87900, "epoch": 1, "loss": 1.7186894404888153, "loss_raw": 1.491533637046814, "perplexity": 5.577214401186055, "muon_lr": 0.004375807648610975, "adamw_lr": 0.0001312742294583292, "tokens_per_sec": 149731.7411353832, "vram_gb": 27.710740089416504, "grad_norm": 0.1533203125, "tokens_processed": 5760614400, "tokens_processed_billions": 5.7606144}
9931
+ {"timestamp": 1787565108.0310974, "elapsed_hours": 10.690039608478546, "session_id": 2, "event": "lambda_stats", "step": 87900, "epoch": 1, "lambda_min": 1.078125, "lambda_max": 2.015625, "lambda_mean": 1.1892361111111112, "lambda_std": 0.20446532211957086, "lambda_all": [2.015625, 1.25, 1.1875, 1.140625, 1.140625, 1.140625, 1.140625, 1.21875, 1.140625, 1.109375, 1.140625, 1.1171875, 1.140625, 1.109375, 1.109375, 1.078125, 1.1015625, 1.125], "local_layers": 9, "global_layers": 9}
9932
+ {"timestamp": 1787565111.9843175, "elapsed_hours": 10.691137725048595, "session_id": 2, "event": "train_step", "step": 87910, "epoch": 1, "loss": 1.723189457654953, "loss_raw": 1.3311009407043457, "perplexity": 5.602368516257553, "muon_lr": 0.004375067723855854, "adamw_lr": 0.00013125203171567557, "tokens_per_sec": 149733.37560462314, "vram_gb": 27.710740089416504, "grad_norm": 0.14453125, "tokens_processed": 5761269760, "tokens_processed_billions": 5.76126976}
9933
+ {"timestamp": 1787565116.1316001, "elapsed_hours": 10.692289748059379, "session_id": 2, "event": "train_step", "step": 87920, "epoch": 1, "loss": 1.6588769054412842, "loss_raw": 1.1881272792816162, "perplexity": 5.2534074567067455, "muon_lr": 0.004373587971687361, "adamw_lr": 0.0001312076391506208, "tokens_per_sec": 149734.26851242373, "vram_gb": 27.299458026885986, "grad_norm": 0.1376953125, "tokens_processed": 5761925120, "tokens_processed_billions": 5.76192512}
9934
+ {"timestamp": 1787565120.163448, "elapsed_hours": 10.693409705758095, "session_id": 2, "event": "train_step", "step": 87930, "epoch": 1, "loss": 1.7403270506858826, "loss_raw": 1.1084816455841064, "perplexity": 5.699207047479359, "muon_lr": 0.004372848144316656, "adamw_lr": 0.00013118544432949965, "tokens_per_sec": 149735.6113489826, "vram_gb": 27.710740089416504, "grad_norm": 0.1494140625, "tokens_processed": 5762580480, "tokens_processed_billions": 5.76258048}
9935
+ {"timestamp": 1787565124.178623, "elapsed_hours": 10.694525032175912, "session_id": 2, "event": "train_step", "step": 87940, "epoch": 1, "loss": 1.7567084503173829, "loss_raw": 2.344409704208374, "perplexity": 5.793336920266619, "muon_lr": 0.004372108349450098, "adamw_lr": 0.0001311632504835029, "tokens_per_sec": 149737.01806483127, "vram_gb": 27.710740089416504, "grad_norm": 0.11865234375, "tokens_processed": 5763235840, "tokens_processed_billions": 5.76323584}
9936
+ {"timestamp": 1787565128.324405, "elapsed_hours": 10.695676638219092, "session_id": 2, "event": "train_step", "step": 87950, "epoch": 1, "loss": 1.7746403431892395, "loss_raw": 3.277092695236206, "perplexity": 5.898159441586788, "muon_lr": 0.004371368587109013, "adamw_lr": 0.00013114105761327034, "tokens_per_sec": 149737.91646111387, "vram_gb": 27.710740089416504, "grad_norm": 0.1484375, "tokens_processed": 5763891200, "tokens_processed_billions": 5.7638912}
9937
+ {"timestamp": 1787565132.7114143, "elapsed_hours": 10.69689525200261, "session_id": 2, "event": "train_step", "step": 87960, "epoch": 1, "loss": 1.7645772218704223, "loss_raw": 1.9517674446105957, "perplexity": 5.839103191042341, "muon_lr": 0.004369889160088606, "adamw_lr": 0.00013109667480265815, "tokens_per_sec": 149737.87598653225, "vram_gb": 27.299458026885986, "grad_norm": 0.142578125, "tokens_processed": 5764546560, "tokens_processed_billions": 5.76454656}
9938
+ {"timestamp": 1787565136.7770905, "elapsed_hours": 10.698024606439802, "session_id": 2, "event": "train_step", "step": 87970, "epoch": 1, "loss": 1.8799683678150176, "loss_raw": 2.003643274307251, "perplexity": 6.553297563791733, "muon_lr": 0.004369149495451946, "adamw_lr": 0.00013107448486355836, "tokens_per_sec": 149739.0858592915, "vram_gb": 27.710740089416504, "grad_norm": 0.1533203125, "tokens_processed": 5765201920, "tokens_processed_billions": 5.76520192}
9939
+ {"timestamp": 1787565140.7758105, "elapsed_hours": 10.699135362108548, "session_id": 2, "event": "train_step", "step": 87980, "epoch": 1, "loss": 1.8009172344207764, "loss_raw": 2.9934189319610596, "perplexity": 6.055198954920744, "muon_lr": 0.0043684098634260895, "adamw_lr": 0.00013105229590278266, "tokens_per_sec": 149740.5559165216, "vram_gb": 27.710740089416504, "grad_norm": 0.12890625, "tokens_processed": 5765857280, "tokens_processed_billions": 5.76585728}
9940
+ {"timestamp": 1787565144.8806837, "elapsed_hours": 10.700275604592429, "session_id": 2, "event": "train_step", "step": 87990, "epoch": 1, "loss": 1.8794967460632324, "loss_raw": 2.2347471714019775, "perplexity": 6.550207614815576, "muon_lr": 0.004367670264032362, "adamw_lr": 0.00013103010792097082, "tokens_per_sec": 149741.61237273918, "vram_gb": 27.710740089416504, "grad_norm": 0.134765625, "tokens_processed": 5766512640, "tokens_processed_billions": 5.76651264}
9941
+ {"timestamp": 1787565149.0271149, "elapsed_hours": 10.701427391039001, "session_id": 2, "event": "train_step", "step": 88000, "epoch": 1, "loss": 1.7695394778251647, "loss_raw": 1.0373600721359253, "perplexity": 5.868150325676191, "muon_lr": 0.004366191163226614, "adamw_lr": 0.00013098573489679838, "tokens_per_sec": 149742.50725072675, "vram_gb": 27.299458026885986, "grad_norm": 0.126953125, "tokens_processed": 5767168000, "tokens_processed_billions": 5.767168}
9942
+ {"timestamp": 1787565149.0341384, "elapsed_hours": 10.701429342296388, "session_id": 2, "event": "lambda_stats", "step": 88000, "epoch": 1, "lambda_min": 1.078125, "lambda_max": 2.015625, "lambda_mean": 1.1892361111111112, "lambda_std": 0.20446532211957086, "lambda_all": [2.015625, 1.25, 1.1875, 1.140625, 1.140625, 1.140625, 1.140625, 1.21875, 1.140625, 1.109375, 1.140625, 1.1171875, 1.140625, 1.109375, 1.109375, 1.078125, 1.1015625, 1.125], "local_layers": 9, "global_layers": 9}
9943
+ {"timestamp": 1787565162.6163135, "elapsed_hours": 10.705202168689834, "session_id": 2, "event": "validation", "step": 88000, "epoch": 1, "val_loss": 1.819385432600975, "val_perplexity": 6.168066592184267, "is_best": true, "best_loss": 1.819385432600975, "best_perplexity": 6.168066592184267, "train_loss": 1.0373600721359253, "train_loss_avg": 1.7695394778251647}