Banaxi-Tech commited on
Commit
49c1ac0
·
verified ·
1 Parent(s): f3f9eb0

Save 40% checkpoint at 12,000,952,320 tokens

Browse files
checkpoint_metadata.json CHANGED
@@ -50,10 +50,10 @@
50
  "model_type": "tiger_alpha",
51
  "output_attentions": false
52
  },
53
- "training_percent": 35,
54
- "step": 10014,
55
  "total_steps": 28611,
56
- "tokens_seen": 10500440064,
57
  "target_tokens": 30000000000,
58
  "trained_token_target": 30000807936,
59
  "tokens_per_step": 1048576,
@@ -69,5 +69,5 @@
69
  "dataset_id": "HuggingFaceFW/fineweb-edu",
70
  "dataset_config": "sample-100BT",
71
  "dataset_revision": "87f09149ef4734204d70ed1d046ddc9ca3f2b8f9",
72
- "elapsed_seconds": 3217.9480624198914
73
  }
 
50
  "model_type": "tiger_alpha",
51
  "output_attentions": false
52
  },
53
+ "training_percent": 40,
54
+ "step": 11445,
55
  "total_steps": 28611,
56
+ "tokens_seen": 12000952320,
57
  "target_tokens": 30000000000,
58
  "trained_token_target": 30000807936,
59
  "tokens_per_step": 1048576,
 
69
  "dataset_id": "HuggingFaceFW/fineweb-edu",
70
  "dataset_config": "sample-100BT",
71
  "dataset_revision": "87f09149ef4734204d70ed1d046ddc9ca3f2b8f9",
72
+ "elapsed_seconds": 3674.9573051929474
73
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2eb87d43b96f8e99a7baaf929af5e73897d0e4f464a113490f822d26b4df17a
3
  size 12811532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b79cc0e88383f6dd332f988e4bc5a403c6740ebd2a41142d8fe929bda0a5f146
3
  size 12811532
training_metrics.jsonl CHANGED
@@ -1000,3 +1000,146 @@
1000
  {"step": 9990, "total_steps": 28611, "tokens": 10475274240, "loss": 2.799479305744171, "ce_loss": 2.797928512096405, "z_loss": 15.508025884628296, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29077285528182983, "tokens_per_second": 2976363.7469898304, "eta_seconds": 6560.197393798828, "data_wait_seconds": 1.5616416931152344e-05}
1001
  {"step": 10000, "total_steps": 28611, "tokens": 10485760000, "loss": 2.8447009325027466, "ce_loss": 2.8436545729637146, "z_loss": 10.463164806365967, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32812371850013733, "tokens_per_second": 2952908.8604886844, "eta_seconds": 6608.753895902634, "data_wait_seconds": 2.777576446533203e-05}
1002
  {"step": 10010, "total_steps": 28611, "tokens": 10496245760, "loss": 2.8154792189598083, "ce_loss": 2.8140763640403748, "z_loss": 14.02950644493103, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3401806652545929, "tokens_per_second": 4103180.473381481, "eta_seconds": 4753.522859287262, "data_wait_seconds": 1.6450881958007812e-05}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1000
  {"step": 9990, "total_steps": 28611, "tokens": 10475274240, "loss": 2.799479305744171, "ce_loss": 2.797928512096405, "z_loss": 15.508025884628296, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29077285528182983, "tokens_per_second": 2976363.7469898304, "eta_seconds": 6560.197393798828, "data_wait_seconds": 1.5616416931152344e-05}
1001
  {"step": 10000, "total_steps": 28611, "tokens": 10485760000, "loss": 2.8447009325027466, "ce_loss": 2.8436545729637146, "z_loss": 10.463164806365967, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32812371850013733, "tokens_per_second": 2952908.8604886844, "eta_seconds": 6608.753895902634, "data_wait_seconds": 2.777576446533203e-05}
1002
  {"step": 10010, "total_steps": 28611, "tokens": 10496245760, "loss": 2.8154792189598083, "ce_loss": 2.8140763640403748, "z_loss": 14.02950644493103, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3401806652545929, "tokens_per_second": 4103180.473381481, "eta_seconds": 4753.522859287262, "data_wait_seconds": 1.6450881958007812e-05}
1003
+ {"step": 10020, "total_steps": 28611, "tokens": 10506731520, "loss": 2.7962347269058228, "ce_loss": 2.794734477996826, "z_loss": 15.0022451877594, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27906936407089233, "tokens_per_second": 3466933.371235688, "eta_seconds": 5622.8586847782135, "data_wait_seconds": 0.254544198513031}
1004
+ {"step": 10030, "total_steps": 28611, "tokens": 10517217280, "loss": 2.79549378156662, "ce_loss": 2.7940309047698975, "z_loss": 14.629600286483765, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3388982117176056, "tokens_per_second": 4478339.556683693, "eta_seconds": 4350.628265094757, "data_wait_seconds": 1.3649463653564453e-05}
1005
+ {"step": 10040, "total_steps": 28611, "tokens": 10527703040, "loss": 2.791917145252228, "ce_loss": 2.7907679080963135, "z_loss": 11.49280071258545, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32449600100517273, "tokens_per_second": 2975241.4304441507, "eta_seconds": 6545.05032658577, "data_wait_seconds": 1.5139579772949219e-05}
1006
+ {"step": 10050, "total_steps": 28611, "tokens": 10538188800, "loss": 2.8227691054344177, "ce_loss": 2.8217186331748962, "z_loss": 10.504422903060913, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35100123286247253, "tokens_per_second": 2891510.155157662, "eta_seconds": 6730.95306315422, "data_wait_seconds": 0.24410849809646606}
1007
+ {"step": 10060, "total_steps": 28611, "tokens": 10548674560, "loss": 2.8378074765205383, "ce_loss": 2.8365275859832764, "z_loss": 12.798944473266602, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32958993315696716, "tokens_per_second": 4001794.0651091742, "eta_seconds": 4860.853172230721, "data_wait_seconds": 2.2590160369873047e-05}
1008
+ {"step": 10070, "total_steps": 28611, "tokens": 10559160320, "loss": 2.768132269382477, "ce_loss": 2.767003059387207, "z_loss": 11.29201865196228, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2921784520149231, "tokens_per_second": 2937447.0723146005, "eta_seconds": 6618.55248363018, "data_wait_seconds": 2.0205974578857422e-05}
1009
+ {"step": 10080, "total_steps": 28611, "tokens": 10569646080, "loss": 2.851889967918396, "ce_loss": 2.850500226020813, "z_loss": 13.897307872772217, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2798449397087097, "tokens_per_second": 4360282.540052856, "eta_seconds": 4456.3997120618815, "data_wait_seconds": 1.5676021575927734e-05}
1010
+ {"step": 10090, "total_steps": 28611, "tokens": 10580131840, "loss": 2.797576904296875, "ce_loss": 2.7960397601127625, "z_loss": 15.37178349494934, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.22910892963409424, "tokens_per_second": 2906697.7797928085, "eta_seconds": 6681.353744792938, "data_wait_seconds": 1.5079975128173828e-05}
1011
+ {"step": 10100, "total_steps": 28611, "tokens": 10590617600, "loss": 2.7704508304595947, "ce_loss": 2.7690720558166504, "z_loss": 13.78757095336914, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28817394375801086, "tokens_per_second": 3745904.407118097, "eta_seconds": 5181.7100028276445, "data_wait_seconds": 1.5437602996826172e-05}
1012
+ {"step": 10110, "total_steps": 28611, "tokens": 10601103360, "loss": 2.8098157048225403, "ce_loss": 2.8085299730300903, "z_loss": 12.856971502304077, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.290237158536911, "tokens_per_second": 3662574.7620821428, "eta_seconds": 5296.739544224739, "data_wait_seconds": 2.104043960571289e-05}
1013
+ {"step": 10120, "total_steps": 28611, "tokens": 10611589120, "loss": 2.8253462314605713, "ce_loss": 2.8241447806358337, "z_loss": 12.014949321746826, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31898683309555054, "tokens_per_second": 7953323.834119796, "eta_seconds": 2437.876191186905, "data_wait_seconds": 1.7464160919189453e-05}
1014
+ {"step": 10130, "total_steps": 28611, "tokens": 10622074880, "loss": 2.7961683869361877, "ce_loss": 2.794696569442749, "z_loss": 14.71859860420227, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29598456621170044, "tokens_per_second": 3007047.2128112256, "eta_seconds": 6444.439240407944, "data_wait_seconds": 1.6927719116210938e-05}
1015
+ {"step": 10140, "total_steps": 28611, "tokens": 10632560640, "loss": 2.793733537197113, "ce_loss": 2.792460322380066, "z_loss": 12.732669115066528, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2521531283855438, "tokens_per_second": 3748744.155097151, "eta_seconds": 5166.596197199821, "data_wait_seconds": 1.6689300537109375e-05}
1016
+ {"step": 10150, "total_steps": 28611, "tokens": 10643046400, "loss": 2.8163923025131226, "ce_loss": 2.815369427204132, "z_loss": 10.228524208068848, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37322357296943665, "tokens_per_second": 4312646.620201447, "eta_seconds": 4488.603690671921, "data_wait_seconds": 1.537799835205078e-05}
1017
+ {"step": 10160, "total_steps": 28611, "tokens": 10653532160, "loss": 2.7790677547454834, "ce_loss": 2.777654767036438, "z_loss": 14.130163192749023, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.294552206993103, "tokens_per_second": 2916990.8083288693, "eta_seconds": 6632.614583754539, "data_wait_seconds": 1.7344951629638672e-05}
1018
+ {"step": 10170, "total_steps": 28611, "tokens": 10664017920, "loss": 2.7691884636878967, "ce_loss": 2.7676507234573364, "z_loss": 15.377358436584473, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2619907855987549, "tokens_per_second": 4151996.6957177487, "eta_seconds": 4657.226735258102, "data_wait_seconds": 1.3470649719238281e-05}
1019
+ {"step": 10180, "total_steps": 28611, "tokens": 10674503680, "loss": 2.7892927527427673, "ce_loss": 2.7877955436706543, "z_loss": 14.971941471099854, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2854222357273102, "tokens_per_second": 3144931.326813045, "eta_seconds": 6145.222978711128, "data_wait_seconds": 1.5079975128173828e-05}
1020
+ {"step": 10190, "total_steps": 28611, "tokens": 10684989440, "loss": 2.7978939414024353, "ce_loss": 2.7966774702072144, "z_loss": 12.164283037185669, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3462679386138916, "tokens_per_second": 2829749.522270241, "eta_seconds": 6825.981714630127, "data_wait_seconds": 2.771615982055664e-05}
1021
+ {"step": 10200, "total_steps": 28611, "tokens": 10695475200, "loss": 2.7900829911231995, "ce_loss": 2.788847863674164, "z_loss": 12.351804256439209, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30160194635391235, "tokens_per_second": 4469975.569985987, "eta_seconds": 4318.8899880409235, "data_wait_seconds": 1.329183578491211e-05}
1022
+ {"step": 10210, "total_steps": 28611, "tokens": 10705960960, "loss": 2.7786555886268616, "ce_loss": 2.7771353721618652, "z_loss": 15.202658653259277, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30973249673843384, "tokens_per_second": 2619759.671522066, "eta_seconds": 7365.121001648903, "data_wait_seconds": 1.4603137969970703e-05}
1023
+ {"step": 10220, "total_steps": 28611, "tokens": 10716446720, "loss": 2.795612394809723, "ce_loss": 2.7943195700645447, "z_loss": 12.928211450576782, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32308831810951233, "tokens_per_second": 3692268.6249844898, "eta_seconds": 5222.903091478348, "data_wait_seconds": 1.6808509826660156e-05}
1024
+ {"step": 10230, "total_steps": 28611, "tokens": 10726932480, "loss": 2.7758309841156006, "ce_loss": 2.77455073595047, "z_loss": 12.801871299743652, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28988829255104065, "tokens_per_second": 2920000.992646429, "eta_seconds": 6600.640035581589, "data_wait_seconds": 0.3037620186805725}
1025
+ {"step": 10240, "total_steps": 28611, "tokens": 10737418240, "loss": 2.7639182209968567, "ce_loss": 2.7623243927955627, "z_loss": 15.938848972320557, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2579622268676758, "tokens_per_second": 4326788.20350171, "eta_seconds": 4452.122172379494, "data_wait_seconds": 1.4960765838623047e-05}
1026
+ {"step": 10250, "total_steps": 28611, "tokens": 10747904000, "loss": 2.8054296374320984, "ce_loss": 2.80423641204834, "z_loss": 11.932334184646606, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2991107404232025, "tokens_per_second": 2697976.0125011033, "eta_seconds": 7136.054526352883, "data_wait_seconds": 1.7940998077392578e-05}
1027
+ {"step": 10260, "total_steps": 28611, "tokens": 10758389760, "loss": 2.818877339363098, "ce_loss": 2.8176172375679016, "z_loss": 12.600911855697632, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32315269112586975, "tokens_per_second": 3804339.730955234, "eta_seconds": 5058.01782617569, "data_wait_seconds": 1.5735626220703125e-05}
1028
+ {"step": 10270, "total_steps": 28611, "tokens": 10768875520, "loss": 2.798077404499054, "ce_loss": 2.7968732118606567, "z_loss": 12.04213261604309, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3035954535007477, "tokens_per_second": 3072693.379466563, "eta_seconds": 6258.981955218315, "data_wait_seconds": 0.25635218620300293}
1029
+ {"step": 10280, "total_steps": 28611, "tokens": 10779361280, "loss": 2.7890206575393677, "ce_loss": 2.7875488996505737, "z_loss": 14.71706748008728, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30879148840904236, "tokens_per_second": 3802125.0101829823, "eta_seconds": 5055.44836230278, "data_wait_seconds": 1.33514404296875e-05}
1030
+ {"step": 10290, "total_steps": 28611, "tokens": 10789847040, "loss": 2.7820903062820435, "ce_loss": 2.780640721321106, "z_loss": 14.495848417282104, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30048465728759766, "tokens_per_second": 2694456.9645946096, "eta_seconds": 7129.808027529716, "data_wait_seconds": 0.13494032621383667}
1031
+ {"step": 10300, "total_steps": 28611, "tokens": 10800332800, "loss": 2.8074129819869995, "ce_loss": 2.806309998035431, "z_loss": 11.030060291290283, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29228925704956055, "tokens_per_second": 2967613.484444755, "eta_seconds": 6470.005355024337, "data_wait_seconds": 1.9490718841552734e-05}
1032
+ {"step": 10310, "total_steps": 28611, "tokens": 10810818560, "loss": 2.7882012128829956, "ce_loss": 2.7870243191719055, "z_loss": 11.769143104553223, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34869855642318726, "tokens_per_second": 4654985.413479099, "eta_seconds": 4122.459615111351, "data_wait_seconds": 2.1278858184814453e-05}
1033
+ {"step": 10320, "total_steps": 28611, "tokens": 10821304320, "loss": 2.771827757358551, "ce_loss": 2.770309329032898, "z_loss": 15.184203147888184, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2953237295150757, "tokens_per_second": 2749916.503653824, "eta_seconds": 6974.576715517044, "data_wait_seconds": 1.52587890625e-05}
1034
+ {"step": 10330, "total_steps": 28611, "tokens": 10831790080, "loss": 2.7899873852729797, "ce_loss": 2.7885494232177734, "z_loss": 14.379798173904419, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31064075231552124, "tokens_per_second": 3919932.7104087197, "eta_seconds": 4890.139518237113, "data_wait_seconds": 1.531839370727539e-05}
1035
+ {"step": 10340, "total_steps": 28611, "tokens": 10842275840, "loss": 2.795703947544098, "ce_loss": 2.7944366335868835, "z_loss": 12.673013925552368, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2993025481700897, "tokens_per_second": 4521648.950315129, "eta_seconds": 4237.0675624132155, "data_wait_seconds": 2.008676528930664e-05}
1036
+ {"step": 10350, "total_steps": 28611, "tokens": 10852761600, "loss": 2.796346366405487, "ce_loss": 2.794686257839203, "z_loss": 16.601113319396973, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31896963715553284, "tokens_per_second": 2962775.7311649653, "eta_seconds": 6462.874032139778, "data_wait_seconds": 1.424551010131836e-05}
1037
+ {"step": 10360, "total_steps": 28611, "tokens": 10863247360, "loss": 2.771928548812866, "ce_loss": 2.770493268966675, "z_loss": 14.35269546508789, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3313918709754944, "tokens_per_second": 2909776.8401441216, "eta_seconds": 6576.985668444634, "data_wait_seconds": 1.3649463653564453e-05}
1038
+ {"step": 10370, "total_steps": 28611, "tokens": 10873733120, "loss": 2.7913013696670532, "ce_loss": 2.7899240255355835, "z_loss": 13.773190021514893, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2641565799713135, "tokens_per_second": 4102055.7079986534, "eta_seconds": 4662.802306342125, "data_wait_seconds": 1.2874603271484375e-05}
1039
+ {"step": 10380, "total_steps": 28611, "tokens": 10884218880, "loss": 2.80915766954422, "ce_loss": 2.8079217076301575, "z_loss": 12.359519004821777, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31796011328697205, "tokens_per_second": 2999065.9291124595, "eta_seconds": 6374.180997633935, "data_wait_seconds": 0.2742553949356079}
1040
+ {"step": 10390, "total_steps": 28611, "tokens": 10894704640, "loss": 2.7878376245498657, "ce_loss": 2.7859814763069153, "z_loss": 18.56126832962036, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3148317039012909, "tokens_per_second": 4093811.244070762, "eta_seconds": 4667.069915270805, "data_wait_seconds": 1.3768672943115234e-05}
1041
+ {"step": 10400, "total_steps": 28611, "tokens": 10905190400, "loss": 2.7856321334838867, "ce_loss": 2.7843366265296936, "z_loss": 12.95517349243164, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28013506531715393, "tokens_per_second": 2837353.9902974875, "eta_seconds": 6730.079363131523, "data_wait_seconds": 0.2656850218772888}
1042
+ {"step": 10410, "total_steps": 28611, "tokens": 10915676160, "loss": 2.7618680596351624, "ce_loss": 2.7605457305908203, "z_loss": 13.223793983459473, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31771478056907654, "tokens_per_second": 3887545.331988706, "eta_seconds": 4909.301409029961, "data_wait_seconds": 1.4543533325195312e-05}
1043
+ {"step": 10420, "total_steps": 28611, "tokens": 10926161920, "loss": 2.8086649775505066, "ce_loss": 2.8073285818099976, "z_loss": 13.363742589950562, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26776739954948425, "tokens_per_second": 2750237.382812236, "eta_seconds": 6935.636223697663, "data_wait_seconds": 1.7642974853515625e-05}
1044
+ {"step": 10430, "total_steps": 28611, "tokens": 10936647680, "loss": 2.803745448589325, "ce_loss": 2.80234956741333, "z_loss": 13.958423852920532, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3714444041252136, "tokens_per_second": 4161065.5082766293, "eta_seconds": 4581.557348251343, "data_wait_seconds": 1.1920928955078125e-05}
1045
+ {"step": 10440, "total_steps": 28611, "tokens": 10947133440, "loss": 2.7925641536712646, "ce_loss": 2.7913302183151245, "z_loss": 12.339592456817627, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2827337980270386, "tokens_per_second": 2713391.5259198644, "eta_seconds": 7022.088155722618, "data_wait_seconds": 0.27720212936401367}
1046
+ {"step": 10450, "total_steps": 28611, "tokens": 10957619200, "loss": 2.8069769144058228, "ce_loss": 2.8055230379104614, "z_loss": 14.5385000705719, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3378409743309021, "tokens_per_second": 4042139.744524397, "eta_seconds": 4711.165357851982, "data_wait_seconds": 1.4066696166992188e-05}
1047
+ {"step": 10460, "total_steps": 28611, "tokens": 10968104960, "loss": 2.807276666164398, "ce_loss": 2.806125521659851, "z_loss": 11.511521100997925, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29765579104423523, "tokens_per_second": 2935937.56592789, "eta_seconds": 6482.666115546227, "data_wait_seconds": 1.6868114471435547e-05}
1048
+ {"step": 10470, "total_steps": 28611, "tokens": 10978590720, "loss": 2.8112133145332336, "ce_loss": 2.809938430786133, "z_loss": 12.748863458633423, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3393419086933136, "tokens_per_second": 2927424.0226374413, "eta_seconds": 6497.937117719651, "data_wait_seconds": 1.710653305053711e-05}
1049
+ {"step": 10480, "total_steps": 28611, "tokens": 10989076480, "loss": 2.7847668528556824, "ce_loss": 2.7833335399627686, "z_loss": 14.333158016204834, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3098030686378479, "tokens_per_second": 4391669.368014706, "eta_seconds": 4329.044348025322, "data_wait_seconds": 1.239776611328125e-05}
1050
+ {"step": 10490, "total_steps": 28611, "tokens": 10999562240, "loss": 2.7469093203544617, "ce_loss": 2.7457709312438965, "z_loss": 11.384095668792725, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28699490427970886, "tokens_per_second": 2839002.571151185, "eta_seconds": 6692.93007659912, "data_wait_seconds": 1.424551010131836e-05}
1051
+ {"step": 10500, "total_steps": 28611, "tokens": 11010048000, "loss": 2.7797441482543945, "ce_loss": 2.7785868048667908, "z_loss": 11.57315182685852, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31148937344551086, "tokens_per_second": 3946788.8313554428, "eta_seconds": 4811.699015951157, "data_wait_seconds": 1.4066696166992188e-05}
1052
+ {"step": 10510, "total_steps": 28611, "tokens": 11020533760, "loss": 2.8276549577713013, "ce_loss": 2.826002061367035, "z_loss": 16.52841305732727, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3459116220474243, "tokens_per_second": 2846124.9015654363, "eta_seconds": 6668.812800717354, "data_wait_seconds": 1.4901161193847656e-05}
1053
+ {"step": 10520, "total_steps": 28611, "tokens": 11031019520, "loss": 2.818402647972107, "ce_loss": 2.8171252012252808, "z_loss": 12.774265766143799, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33940014243125916, "tokens_per_second": 2781537.057520351, "eta_seconds": 6819.894189333916, "data_wait_seconds": 1.5079975128173828e-05}
1054
+ {"step": 10530, "total_steps": 28611, "tokens": 11041505280, "loss": 2.8043494820594788, "ce_loss": 2.8029861450195312, "z_loss": 13.633641481399536, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27813228964805603, "tokens_per_second": 2745508.4824602692, "eta_seconds": 6905.570599079132, "data_wait_seconds": 1.4722347259521484e-05}
1055
+ {"step": 10540, "total_steps": 28611, "tokens": 11051991040, "loss": 2.8138166666030884, "ce_loss": 2.8127095699310303, "z_loss": 11.071556568145752, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3203548491001129, "tokens_per_second": 3995411.6943900306, "eta_seconds": 4742.644399476051, "data_wait_seconds": 1.4603137969970703e-05}
1056
+ {"step": 10550, "total_steps": 28611, "tokens": 11062476800, "loss": 2.8034210801124573, "ce_loss": 2.8023852705955505, "z_loss": 10.357663631439209, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2901478409767151, "tokens_per_second": 2804185.927614002, "eta_seconds": 6753.593244123459, "data_wait_seconds": 1.436471939086914e-05}
1057
+ {"step": 10560, "total_steps": 28611, "tokens": 11072962560, "loss": 2.8022642731666565, "ce_loss": 2.8011210560798645, "z_loss": 11.432010173797607, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34575527906417847, "tokens_per_second": 2824317.5608429145, "eta_seconds": 6701.741205883026, "data_wait_seconds": 0.30016326904296875}
1058
+ {"step": 10570, "total_steps": 28611, "tokens": 11083448320, "loss": 2.805923879146576, "ce_loss": 2.804827392101288, "z_loss": 10.964697360992432, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31048449873924255, "tokens_per_second": 3984188.890140641, "eta_seconds": 4748.108118772507, "data_wait_seconds": 1.3530254364013672e-05}
1059
+ {"step": 10580, "total_steps": 28611, "tokens": 11093934080, "loss": 2.863360643386841, "ce_loss": 2.862065374851227, "z_loss": 12.953135251998901, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33105894923210144, "tokens_per_second": 2876427.5534149497, "eta_seconds": 6573.0401704549795, "data_wait_seconds": 0.26409536600112915}
1060
+ {"step": 10590, "total_steps": 28611, "tokens": 11104419840, "loss": 2.7814733386039734, "ce_loss": 2.7802926898002625, "z_loss": 11.806755304336548, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30188897252082825, "tokens_per_second": 4095631.2435287056, "eta_seconds": 4613.791372418404, "data_wait_seconds": 1.4722347259521484e-05}
1061
+ {"step": 10600, "total_steps": 28611, "tokens": 11114905600, "loss": 2.82624214887619, "ce_loss": 2.8246979117393494, "z_loss": 15.442501783370972, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3526361286640167, "tokens_per_second": 2938733.0820696345, "eta_seconds": 6426.5456605196005, "data_wait_seconds": 1.6033649444580078e-05}
1062
+ {"step": 10610, "total_steps": 28611, "tokens": 11125391360, "loss": 2.8719621300697327, "ce_loss": 2.870852530002594, "z_loss": 11.095970392227173, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3170166611671448, "tokens_per_second": 4127804.9030295215, "eta_seconds": 4572.749201917648, "data_wait_seconds": 1.6570091247558594e-05}
1063
+ {"step": 10620, "total_steps": 28611, "tokens": 11135877120, "loss": 2.8028395771980286, "ce_loss": 2.801525056362152, "z_loss": 13.145007133483887, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.23883245885372162, "tokens_per_second": 2308665.3515273277, "eta_seconds": 8171.357881522179, "data_wait_seconds": 0.30974090099334717}
1064
+ {"step": 10630, "total_steps": 28611, "tokens": 11146362880, "loss": 2.812191903591156, "ce_loss": 2.810566544532776, "z_loss": 16.25410294532776, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33621376752853394, "tokens_per_second": 4436038.519399545, "eta_seconds": 4250.288849735261, "data_wait_seconds": 1.4126300811767578e-05}
1065
+ {"step": 10640, "total_steps": 28611, "tokens": 11156848640, "loss": 2.8085532784461975, "ce_loss": 2.807244896888733, "z_loss": 13.083586692810059, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3264976143836975, "tokens_per_second": 2865627.7265146277, "eta_seconds": 6575.85740172863, "data_wait_seconds": 0.5504788160324097}
1066
+ {"step": 10650, "total_steps": 28611, "tokens": 11167334400, "loss": 2.8003652095794678, "ce_loss": 2.799091875553131, "z_loss": 12.733178615570068, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2727406620979309, "tokens_per_second": 4196442.28956157, "eta_seconds": 4487.962001252175, "data_wait_seconds": 1.4841556549072266e-05}
1067
+ {"step": 10660, "total_steps": 28611, "tokens": 11177820160, "loss": 2.800356090068817, "ce_loss": 2.799224078655243, "z_loss": 11.320991277694702, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3264901638031006, "tokens_per_second": 3021338.3446881925, "eta_seconds": 6230.0165120840065, "data_wait_seconds": 1.4960765838623047e-05}
1068
+ {"step": 10670, "total_steps": 28611, "tokens": 11188305920, "loss": 2.7990368008613586, "ce_loss": 2.7978668212890625, "z_loss": 11.699519872665405, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28511151671409607, "tokens_per_second": 3995582.6576321544, "eta_seconds": 4708.325074958801, "data_wait_seconds": 1.4007091522216797e-05}
1069
+ {"step": 10680, "total_steps": 28611, "tokens": 11198791680, "loss": 2.8537862300872803, "ce_loss": 2.8524810671806335, "z_loss": 13.051294326782227, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3401859700679779, "tokens_per_second": 2672020.9262980823, "eta_seconds": 7036.627621793747, "data_wait_seconds": 1.728534698486328e-05}
1070
+ {"step": 10690, "total_steps": 28611, "tokens": 11209277440, "loss": 2.808406949043274, "ce_loss": 2.8072014451026917, "z_loss": 12.055113315582275, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32281118631362915, "tokens_per_second": 4227586.421751211, "eta_seconds": 4444.978439545632, "data_wait_seconds": 1.9609928131103516e-05}
1071
+ {"step": 10700, "total_steps": 28611, "tokens": 11219763200, "loss": 2.818626582622528, "ce_loss": 2.8173816800117493, "z_loss": 12.449214458465576, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28932878375053406, "tokens_per_second": 2790630.149796498, "eta_seconds": 6730.037205886841, "data_wait_seconds": 0.28206849098205566}
1072
+ {"step": 10710, "total_steps": 28611, "tokens": 11230248960, "loss": 2.7856287360191345, "ce_loss": 2.784337043762207, "z_loss": 12.916906118392944, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3136659264564514, "tokens_per_second": 3020417.89910661, "eta_seconds": 6214.556926560402, "data_wait_seconds": 1.4960765838623047e-05}
1073
+ {"step": 10720, "total_steps": 28611, "tokens": 11240734720, "loss": 2.7997190952301025, "ce_loss": 2.798270881175995, "z_loss": 14.48186993598938, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3525998294353485, "tokens_per_second": 2996912.974536185, "eta_seconds": 6259.799125099183, "data_wait_seconds": 1.817941665649414e-05}
1074
+ {"step": 10730, "total_steps": 28611, "tokens": 11251220480, "loss": 2.8088510036468506, "ce_loss": 2.8075380325317383, "z_loss": 13.129327535629272, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29389721155166626, "tokens_per_second": 2234027.6767114727, "eta_seconds": 8392.728367447853, "data_wait_seconds": 0.2524486780166626}
1075
+ {"step": 10740, "total_steps": 28611, "tokens": 11261706240, "loss": 2.791990339756012, "ce_loss": 2.7907110452651978, "z_loss": 12.792659997940063, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32986462116241455, "tokens_per_second": 2731829.0943454965, "eta_seconds": 6859.543935155869, "data_wait_seconds": 0.2670999765396118}
1076
+ {"step": 10750, "total_steps": 28611, "tokens": 11272192000, "loss": 2.812085270881653, "ce_loss": 2.810760200023651, "z_loss": 13.25040888786316, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2740553021430969, "tokens_per_second": 4656051.353547878, "eta_seconds": 4022.4246929168703, "data_wait_seconds": 1.4424324035644531e-05}
1077
+ {"step": 10760, "total_steps": 28611, "tokens": 11282677760, "loss": 2.802474319934845, "ce_loss": 2.801495850086212, "z_loss": 9.784945011138916, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31698283553123474, "tokens_per_second": 2913624.2831148976, "eta_seconds": 6424.3458858013155, "data_wait_seconds": 1.990795135498047e-05}
1078
+ {"step": 10770, "total_steps": 28611, "tokens": 11293163520, "loss": 2.7893356680870056, "ce_loss": 2.78815358877182, "z_loss": 11.820829629898071, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33525922894477844, "tokens_per_second": 4051535.680777002, "eta_seconds": 4617.420625162124, "data_wait_seconds": 1.5556812286376953e-05}
1079
+ {"step": 10780, "total_steps": 28611, "tokens": 11303649280, "loss": 2.8629708886146545, "ce_loss": 2.8618687987327576, "z_loss": 11.02085018157959, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2687501311302185, "tokens_per_second": 3014754.876289766, "eta_seconds": 6201.883543848991, "data_wait_seconds": 0.30258363485336304}
1080
+ {"step": 10790, "total_steps": 28611, "tokens": 11314135040, "loss": 2.804409623146057, "ce_loss": 2.8031259775161743, "z_loss": 12.83619475364685, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27464258670806885, "tokens_per_second": 4606302.514727601, "eta_seconds": 4056.7619769334797, "data_wait_seconds": 1.3887882232666016e-05}
1081
+ {"step": 10800, "total_steps": 28611, "tokens": 11324620800, "loss": 2.8586254715919495, "ce_loss": 2.8574485182762146, "z_loss": 11.768747091293335, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3030254542827606, "tokens_per_second": 3139145.552677203, "eta_seconds": 5949.449244260788, "data_wait_seconds": 1.3589859008789062e-05}
1082
+ {"step": 10810, "total_steps": 28611, "tokens": 11335106560, "loss": 2.8148199915885925, "ce_loss": 2.8135302662849426, "z_loss": 12.897071599960327, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34129777550697327, "tokens_per_second": 3088157.5473856544, "eta_seconds": 6044.284039783478, "data_wait_seconds": 0.26592546701431274}
1083
+ {"step": 10820, "total_steps": 28611, "tokens": 11345592320, "loss": 2.815177083015442, "ce_loss": 2.8140299916267395, "z_loss": 11.471267223358154, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35076966881752014, "tokens_per_second": 4391376.449414983, "eta_seconds": 4248.147666430474, "data_wait_seconds": 1.4722347259521484e-05}
1084
+ {"step": 10830, "total_steps": 28611, "tokens": 11356078080, "loss": 2.7839850187301636, "ce_loss": 2.7825055718421936, "z_loss": 14.7941153049469, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31422510743141174, "tokens_per_second": 2988510.4682745244, "eta_seconds": 6238.8035959482195, "data_wait_seconds": 1.6391277313232422e-05}
1085
+ {"step": 10840, "total_steps": 28611, "tokens": 11366563840, "loss": 2.83423388004303, "ce_loss": 2.8328040838241577, "z_loss": 14.298174619674683, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3097039759159088, "tokens_per_second": 4398211.4440331515, "eta_seconds": 4236.777684092522, "data_wait_seconds": 1.5497207641601562e-05}
1086
+ {"step": 10850, "total_steps": 28611, "tokens": 11377049600, "loss": 2.813742220401764, "ce_loss": 2.8124441504478455, "z_loss": 12.980409383773804, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31663787364959717, "tokens_per_second": 2918363.920049884, "eta_seconds": 6381.575035262107, "data_wait_seconds": 1.3709068298339844e-05}
1087
+ {"step": 10860, "total_steps": 28611, "tokens": 11387535360, "loss": 2.814226508140564, "ce_loss": 2.8126300573349, "z_loss": 15.96390962600708, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28073036670684814, "tokens_per_second": 3089248.420151324, "eta_seconds": 6025.178310227394, "data_wait_seconds": 1.9490718841552734e-05}
1088
+ {"step": 10870, "total_steps": 28611, "tokens": 11398021120, "loss": 2.872102379798889, "ce_loss": 2.871031880378723, "z_loss": 10.704820394515991, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3078044354915619, "tokens_per_second": 3062379.5601096344, "eta_seconds": 6074.618266892433, "data_wait_seconds": 0.27397000789642334}
1089
+ {"step": 10880, "total_steps": 28611, "tokens": 11408506880, "loss": 2.811852216720581, "ce_loss": 2.810556948184967, "z_loss": 12.952714920043945, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28971707820892334, "tokens_per_second": 4246680.383521973, "eta_seconds": 4378.078729009628, "data_wait_seconds": 1.531839370727539e-05}
1090
+ {"step": 10890, "total_steps": 28611, "tokens": 11418992640, "loss": 2.8296119570732117, "ce_loss": 2.8283298015594482, "z_loss": 12.821239709854126, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3697947859764099, "tokens_per_second": 2911262.834676838, "eta_seconds": 6382.733662748336, "data_wait_seconds": 0.5094807147979736}
1091
+ {"step": 10900, "total_steps": 28611, "tokens": 11429478400, "loss": 2.8375219106674194, "ce_loss": 2.836298704147339, "z_loss": 12.232072830200195, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3385297656059265, "tokens_per_second": 3880061.0737951053, "eta_seconds": 4786.349797797203, "data_wait_seconds": 1.4483928680419922e-05}
1092
+ {"step": 10910, "total_steps": 28611, "tokens": 11439964160, "loss": 2.8337709307670593, "ce_loss": 2.8324374556541443, "z_loss": 13.334804058074951, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2998623251914978, "tokens_per_second": 2756191.6746870913, "eta_seconds": 6734.23548386097, "data_wait_seconds": 1.6629695892333984e-05}
1093
+ {"step": 10920, "total_steps": 28611, "tokens": 11450449920, "loss": 2.8048866987228394, "ce_loss": 2.8037956953048706, "z_loss": 10.910446882247925, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3388404846191406, "tokens_per_second": 4540795.499212751, "eta_seconds": 4085.266121149063, "data_wait_seconds": 1.2278556823730469e-05}
1094
+ {"step": 10930, "total_steps": 28611, "tokens": 11460935680, "loss": 2.7942721247673035, "ce_loss": 2.7930060625076294, "z_loss": 12.66059684753418, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29098576307296753, "tokens_per_second": 2932395.797439868, "eta_seconds": 6322.431737279892, "data_wait_seconds": 1.4781951904296875e-05}
1095
+ {"step": 10940, "total_steps": 28611, "tokens": 11471421440, "loss": 2.8096104860305786, "ce_loss": 2.808437705039978, "z_loss": 11.72828221321106, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2666364908218384, "tokens_per_second": 2729436.067796787, "eta_seconds": 6788.7233977079395, "data_wait_seconds": 0.2908061742782593}
1096
+ {"step": 10950, "total_steps": 28611, "tokens": 11481907200, "loss": 2.8550827503204346, "ce_loss": 2.853747844696045, "z_loss": 13.349215269088745, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30229610204696655, "tokens_per_second": 3131094.070230452, "eta_seconds": 5914.514326500893, "data_wait_seconds": 0.24153155088424683}
1097
+ {"step": 10960, "total_steps": 28611, "tokens": 11492392960, "loss": 2.8043383359909058, "ce_loss": 2.8031777143478394, "z_loss": 11.606184005737305, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3093421161174774, "tokens_per_second": 3596167.359430428, "eta_seconds": 5146.705680274963, "data_wait_seconds": 1.6927719116210938e-05}
1098
+ {"step": 10970, "total_steps": 28611, "tokens": 11502878720, "loss": 2.7972726225852966, "ce_loss": 2.7955766320228577, "z_loss": 16.959968090057373, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3200271427631378, "tokens_per_second": 4509855.2945520645, "eta_seconds": 4101.668015456199, "data_wait_seconds": 1.627206802368164e-05}
1099
+ {"step": 10980, "total_steps": 28611, "tokens": 11513364480, "loss": 2.906401216983795, "ce_loss": 2.9052005410194397, "z_loss": 12.00692367553711, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34148672223091125, "tokens_per_second": 2942073.48102279, "eta_seconds": 6283.8143150568, "data_wait_seconds": 1.4543533325195312e-05}
1100
+ {"step": 10990, "total_steps": 28611, "tokens": 11523850240, "loss": 2.814209520816803, "ce_loss": 2.813041031360626, "z_loss": 11.68519115447998, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2859879434108734, "tokens_per_second": 2951858.0475363587, "eta_seconds": 6259.433007431031, "data_wait_seconds": 0.032219767570495605}
1101
+ {"step": 11000, "total_steps": 28611, "tokens": 11534336000, "loss": 2.81145840883255, "ce_loss": 2.8103142976760864, "z_loss": 11.441242218017578, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3158135712146759, "tokens_per_second": 3352055.6474254, "eta_seconds": 5508.9992166996, "data_wait_seconds": 0.19110357761383057}
1102
+ {"step": 11010, "total_steps": 28611, "tokens": 11544821760, "loss": 2.788999855518341, "ce_loss": 2.7876006960868835, "z_loss": 13.991387367248535, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26020121574401855, "tokens_per_second": 4535848.771888101, "eta_seconds": 4068.915676903725, "data_wait_seconds": 1.4722347259521484e-05}
1103
+ {"step": 11020, "total_steps": 28611, "tokens": 11555307520, "loss": 2.8048921823501587, "ce_loss": 2.8035873770713806, "z_loss": 13.04841685295105, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29401957988739014, "tokens_per_second": 3130223.1745123668, "eta_seconds": 5892.71096265316, "data_wait_seconds": 1.3649463653564453e-05}
1104
+ {"step": 11030, "total_steps": 28611, "tokens": 11565793280, "loss": 2.8064573407173157, "ce_loss": 2.805272936820984, "z_loss": 11.843363285064697, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26513490080833435, "tokens_per_second": 3062989.7466172357, "eta_seconds": 6018.634138870239, "data_wait_seconds": 1.5020370483398438e-05}
1105
+ {"step": 11040, "total_steps": 28611, "tokens": 11576279040, "loss": 2.8242485523223877, "ce_loss": 2.822998046875, "z_loss": 12.504551887512207, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32964959740638733, "tokens_per_second": 3285583.4419581452, "eta_seconds": 5607.688625621796, "data_wait_seconds": 0.2158631682395935}
1106
+ {"step": 11050, "total_steps": 28611, "tokens": 11586764800, "loss": 2.8260130286216736, "ce_loss": 2.82463401556015, "z_loss": 13.790266990661621, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34445270895957947, "tokens_per_second": 3891873.3544921107, "eta_seconds": 4731.408619642258, "data_wait_seconds": 1.8477439880371094e-05}
1107
+ {"step": 11060, "total_steps": 28611, "tokens": 11597250560, "loss": 2.8375352025032043, "ce_loss": 2.8363834023475647, "z_loss": 11.518030405044556, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3395726978778839, "tokens_per_second": 4513344.4073337475, "eta_seconds": 4077.5876412391667, "data_wait_seconds": 1.6510486602783203e-05}
1108
+ {"step": 11070, "total_steps": 28611, "tokens": 11607736320, "loss": 2.8157320618629456, "ce_loss": 2.8144193291664124, "z_loss": 13.126498460769653, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2760205864906311, "tokens_per_second": 3030393.7500298866, "eta_seconds": 6069.531926608086, "data_wait_seconds": 1.3530254364013672e-05}
1109
+ {"step": 11080, "total_steps": 28611, "tokens": 11618222080, "loss": 2.8258216381073, "ce_loss": 2.8246577382087708, "z_loss": 11.639408588409424, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29516011476516724, "tokens_per_second": 2942347.269241597, "eta_seconds": 6247.592202377319, "data_wait_seconds": 1.5437602996826172e-05}
1110
+ {"step": 11090, "total_steps": 28611, "tokens": 11628707840, "loss": 2.818127751350403, "ce_loss": 2.8170809149742126, "z_loss": 10.46799373626709, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3165890872478485, "tokens_per_second": 2791230.54590891, "eta_seconds": 6582.079048585892, "data_wait_seconds": 1.7344951629638672e-05}
1111
+ {"step": 11100, "total_steps": 28611, "tokens": 11639193600, "loss": 2.794486105442047, "ce_loss": 2.792895793914795, "z_loss": 15.902618408203125, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3239330053329468, "tokens_per_second": 4348483.367379284, "eta_seconds": 4222.532957983017, "data_wait_seconds": 1.8656253814697266e-05}
1112
+ {"step": 11110, "total_steps": 28611, "tokens": 11649679360, "loss": 2.842562973499298, "ce_loss": 2.841224253177643, "z_loss": 13.386975526809692, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2850291132926941, "tokens_per_second": 2939487.703843931, "eta_seconds": 6242.968307709693, "data_wait_seconds": 0.5226141810417175}
1113
+ {"step": 11120, "total_steps": 28611, "tokens": 11660165120, "loss": 2.784659445285797, "ce_loss": 2.7836702466011047, "z_loss": 9.891849517822266, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3229297995567322, "tokens_per_second": 4570198.579267271, "eta_seconds": 4013.095382595063, "data_wait_seconds": 1.4722347259521484e-05}
1114
+ {"step": 11130, "total_steps": 28611, "tokens": 11670650880, "loss": 2.830263674259186, "ce_loss": 2.8288217782974243, "z_loss": 14.419147253036499, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2829802334308624, "tokens_per_second": 3183365.8019970306, "eta_seconds": 5758.10578994751, "data_wait_seconds": 1.3589859008789062e-05}
1115
+ {"step": 11140, "total_steps": 28611, "tokens": 11681136640, "loss": 2.7982051968574524, "ce_loss": 2.7968430519104004, "z_loss": 13.621324300765991, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3049653470516205, "tokens_per_second": 2909521.783080046, "eta_seconds": 6296.454421663285, "data_wait_seconds": 1.7464160919189453e-05}
1116
+ {"step": 11150, "total_steps": 28611, "tokens": 11691622400, "loss": 2.8432756066322327, "ce_loss": 2.8420127034187317, "z_loss": 12.629548788070679, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2872651219367981, "tokens_per_second": 4097274.9786534975, "eta_seconds": 4468.6250328302385, "data_wait_seconds": 1.6987323760986328e-05}
1117
+ {"step": 11160, "total_steps": 28611, "tokens": 11702108160, "loss": 2.8204590678215027, "ce_loss": 2.819357216358185, "z_loss": 11.018922567367554, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30940303206443787, "tokens_per_second": 2267226.764614501, "eta_seconds": 8070.961432528496, "data_wait_seconds": 1.901388168334961e-05}
1118
+ {"step": 11170, "total_steps": 28611, "tokens": 11712593920, "loss": 2.874363660812378, "ce_loss": 2.8732714653015137, "z_loss": 10.922658443450928, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2914932370185852, "tokens_per_second": 3257352.5818053083, "eta_seconds": 5614.441039681435, "data_wait_seconds": 1.341104507446289e-05}
1119
+ {"step": 11180, "total_steps": 28611, "tokens": 11723079680, "loss": 2.8358184695243835, "ce_loss": 2.834399938583374, "z_loss": 14.185691833496094, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33242011070251465, "tokens_per_second": 2890722.3917103005, "eta_seconds": 6322.892958664894, "data_wait_seconds": 1.5974044799804688e-05}
1120
+ {"step": 11190, "total_steps": 28611, "tokens": 11733565440, "loss": 2.815056085586548, "ce_loss": 2.813646674156189, "z_loss": 14.094276428222656, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33824944496154785, "tokens_per_second": 2907706.2995828763, "eta_seconds": 6282.354754543304, "data_wait_seconds": 1.710653305053711e-05}
1121
+ {"step": 11200, "total_steps": 28611, "tokens": 11744051200, "loss": 2.8419591188430786, "ce_loss": 2.8404677510261536, "z_loss": 14.914154767990112, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3213272988796234, "tokens_per_second": 4306465.221699342, "eta_seconds": 4239.383298397064, "data_wait_seconds": 1.823902130126953e-05}
1122
+ {"step": 11210, "total_steps": 28611, "tokens": 11754536960, "loss": 2.8143635392189026, "ce_loss": 2.8132835030555725, "z_loss": 10.800217628479004, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2805890738964081, "tokens_per_second": 3031796.5162861864, "eta_seconds": 6018.303299045563, "data_wait_seconds": 1.424551010131836e-05}
1123
+ {"step": 11220, "total_steps": 28611, "tokens": 11765022720, "loss": 2.836681365966797, "ce_loss": 2.8354833722114563, "z_loss": 11.98059892654419, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2892529368400574, "tokens_per_second": 2899841.6056433828, "eta_seconds": 6288.5452710628515, "data_wait_seconds": 1.609325408935547e-05}
1124
+ {"step": 11230, "total_steps": 28611, "tokens": 11775508480, "loss": 2.829699158668518, "ce_loss": 2.828346073627472, "z_loss": 13.530641794204712, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33387675881385803, "tokens_per_second": 2754453.4156295354, "eta_seconds": 6616.666432833671, "data_wait_seconds": 0.2641461491584778}
1125
+ {"step": 11240, "total_steps": 28611, "tokens": 11785994240, "loss": 2.7977707386016846, "ce_loss": 2.7964746952056885, "z_loss": 12.960023403167725, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3052799105644226, "tokens_per_second": 3978928.8282323275, "eta_seconds": 4577.818423581123, "data_wait_seconds": 1.5795230865478516e-05}
1126
+ {"step": 11250, "total_steps": 28611, "tokens": 11796480000, "loss": 2.839070498943329, "ce_loss": 2.838015079498291, "z_loss": 10.55444598197937, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29408174753189087, "tokens_per_second": 2960681.721803339, "eta_seconds": 6148.694674587249, "data_wait_seconds": 0.25346672534942627}
1127
+ {"step": 11260, "total_steps": 28611, "tokens": 11806965760, "loss": 2.8013757467269897, "ce_loss": 2.8001593351364136, "z_loss": 12.16375732421875, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3075242042541504, "tokens_per_second": 4257920.889386813, "eta_seconds": 4272.9403971195225, "data_wait_seconds": 1.3053417205810547e-05}
1128
+ {"step": 11270, "total_steps": 28611, "tokens": 11817451520, "loss": 2.8465884923934937, "ce_loss": 2.845089077949524, "z_loss": 14.994592905044556, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3009120523929596, "tokens_per_second": 3063078.2769134166, "eta_seconds": 5936.301580357552, "data_wait_seconds": 1.4424324035644531e-05}
1129
+ {"step": 11280, "total_steps": 28611, "tokens": 11827937280, "loss": 2.8183512687683105, "ce_loss": 2.8172367215156555, "z_loss": 11.146096467971802, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3094227910041809, "tokens_per_second": 4533873.190932597, "eta_seconds": 4008.2441415309904, "data_wait_seconds": 1.728534698486328e-05}
1130
+ {"step": 11290, "total_steps": 28611, "tokens": 11838423040, "loss": 2.813460409641266, "ce_loss": 2.8122504353523254, "z_loss": 12.100116491317749, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.269000768661499, "tokens_per_second": 2965451.4475194477, "eta_seconds": 6124.6610229253765, "data_wait_seconds": 1.2934207916259766e-05}
1131
+ {"step": 11300, "total_steps": 28611, "tokens": 11848908800, "loss": 2.8201403617858887, "ce_loss": 2.8189706206321716, "z_loss": 11.697560787200928, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2781415581703186, "tokens_per_second": 2940579.271344465, "eta_seconds": 6172.899099469185, "data_wait_seconds": 1.7821788787841797e-05}
1132
+ {"step": 11310, "total_steps": 28611, "tokens": 11859394560, "loss": 2.869509279727936, "ce_loss": 2.8681556582450867, "z_loss": 13.536017894744873, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28999757766723633, "tokens_per_second": 2981557.0553374663, "eta_seconds": 6084.543424558639, "data_wait_seconds": 1.901388168334961e-05}
1133
+ {"step": 11320, "total_steps": 28611, "tokens": 11869880320, "loss": 2.8463178873062134, "ce_loss": 2.84488981962204, "z_loss": 14.280468702316284, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3446340262889862, "tokens_per_second": 4020639.164344859, "eta_seconds": 4509.464011788368, "data_wait_seconds": 1.2814998626708984e-05}
1134
+ {"step": 11330, "total_steps": 28611, "tokens": 11880366080, "loss": 2.7748011350631714, "ce_loss": 2.7736006379127502, "z_loss": 12.005257606506348, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25946369767189026, "tokens_per_second": 3024256.3083779127, "eta_seconds": 5991.701763439179, "data_wait_seconds": 0.2418001890182495}
1135
+ {"step": 11340, "total_steps": 28611, "tokens": 11890851840, "loss": 2.819035291671753, "ce_loss": 2.8176963329315186, "z_loss": 13.389536142349243, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3127153217792511, "tokens_per_second": 4403179.297210759, "eta_seconds": 4112.9272449731825, "data_wait_seconds": 1.6689300537109375e-05}
1136
+ {"step": 11350, "total_steps": 28611, "tokens": 11901337600, "loss": 2.8316568732261658, "ce_loss": 2.8304351568222046, "z_loss": 12.21750259399414, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27919188141822815, "tokens_per_second": 2844753.2200118448, "eta_seconds": 6362.404376125335, "data_wait_seconds": 1.5497207641601562e-05}
1137
+ {"step": 11360, "total_steps": 28611, "tokens": 11911823360, "loss": 2.807019352912903, "ce_loss": 2.8058691024780273, "z_loss": 11.502272605895996, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33109423518180847, "tokens_per_second": 2676890.6686172825, "eta_seconds": 6757.4611051797865, "data_wait_seconds": 0.5603397488594055}
1138
+ {"step": 11370, "total_steps": 28611, "tokens": 11922309120, "loss": 2.840953767299652, "ce_loss": 2.839625835418701, "z_loss": 13.2799551486969, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30196914076805115, "tokens_per_second": 4586269.2961527575, "eta_seconds": 3941.8746803998947, "data_wait_seconds": 1.704692840576172e-05}
1139
+ {"step": 11380, "total_steps": 28611, "tokens": 11932794880, "loss": 2.8201229572296143, "ce_loss": 2.8186540007591248, "z_loss": 14.689458131790161, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28441810607910156, "tokens_per_second": 2710752.297368478, "eta_seconds": 6665.313194990157, "data_wait_seconds": 1.519918441772461e-05}
1140
+ {"step": 11390, "total_steps": 28611, "tokens": 11943280640, "loss": 2.802764415740967, "ce_loss": 2.801760256290436, "z_loss": 10.041690111160278, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31985700130462646, "tokens_per_second": 2904242.057697791, "eta_seconds": 6217.638522291183, "data_wait_seconds": 1.823902130126953e-05}
1141
+ {"step": 11400, "total_steps": 28611, "tokens": 11953766400, "loss": 2.8356521129608154, "ce_loss": 2.834294617176056, "z_loss": 13.575268983840942, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35543501377105713, "tokens_per_second": 4356304.833816851, "eta_seconds": 4142.74074575901, "data_wait_seconds": 1.6868114471435547e-05}
1142
+ {"step": 11410, "total_steps": 28611, "tokens": 11964252160, "loss": 2.820736289024353, "ce_loss": 2.8194665908813477, "z_loss": 12.696641206741333, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2881253957748413, "tokens_per_second": 3011345.22318536, "eta_seconds": 5989.53439052105, "data_wait_seconds": 1.6391277313232422e-05}
1143
+ {"step": 11420, "total_steps": 28611, "tokens": 11974737920, "loss": 2.812516987323761, "ce_loss": 2.8112725615501404, "z_loss": 12.444044589996338, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33891111612319946, "tokens_per_second": 3007487.2587310234, "eta_seconds": 5993.731133413315, "data_wait_seconds": 0.2641294002532959}
1144
+ {"step": 11430, "total_steps": 28611, "tokens": 11985223680, "loss": 2.841590166091919, "ce_loss": 2.8404982686042786, "z_loss": 10.918761491775513, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2533271610736847, "tokens_per_second": 4368678.506710489, "eta_seconds": 4123.806370353699, "data_wait_seconds": 1.245737075805664e-05}
1145
+ {"step": 11440, "total_steps": 28611, "tokens": 11995709440, "loss": 2.8131224513053894, "ce_loss": 2.811748206615448, "z_loss": 13.742230653762817, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24827022850513458, "tokens_per_second": 2913321.2697653975, "eta_seconds": 6180.265349674224, "data_wait_seconds": 1.6689300537109375e-05}