Save 95% checkpoint at 28,501,344,256 tokens
Browse files- checkpoint_metadata.json +4 -4
- model.safetensors +1 -1
- training_metrics.jsonl +143 -0
checkpoint_metadata.json
CHANGED
|
@@ -50,10 +50,10 @@
|
|
| 50 |
"model_type": "tiger_alpha",
|
| 51 |
"output_attentions": false
|
| 52 |
},
|
| 53 |
-
"training_percent":
|
| 54 |
-
"step":
|
| 55 |
"total_steps": 28611,
|
| 56 |
-
"tokens_seen":
|
| 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":
|
| 73 |
}
|
|
|
|
| 50 |
"model_type": "tiger_alpha",
|
| 51 |
"output_attentions": false
|
| 52 |
},
|
| 53 |
+
"training_percent": 95,
|
| 54 |
+
"step": 27181,
|
| 55 |
"total_steps": 28611,
|
| 56 |
+
"tokens_seen": 28501344256,
|
| 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": 8706.567631721497
|
| 73 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12811532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50f9289fd0da9768170c6640c154071758808ff6426706c37d7e5d51961b5dc1
|
| 3 |
size 12811532
|
training_metrics.jsonl
CHANGED
|
@@ -2574,3 +2574,146 @@
|
|
| 2574 |
{"step": 25730, "total_steps": 28611, "tokens": 26979860480, "loss": 2.7777997255325317, "ce_loss": 2.7767510414123535, "z_loss": 10.487375974655151, "muon_lr": 0.022698876891773304, "adamw_lr": 0.0022698876891773306, "grad_norm": 0.3550080358982086, "tokens_per_second": 4172575.5496717193, "eta_seconds": 724.0006609916686, "data_wait_seconds": 1.4007091522216797e-05}
|
| 2575 |
{"step": 25740, "total_steps": 28611, "tokens": 26990346240, "loss": 2.7517773509025574, "ce_loss": 2.75069659948349, "z_loss": 10.807626247406006, "muon_lr": 0.022604397807203854, "adamw_lr": 0.002260439780720386, "grad_norm": 0.2949717044830322, "tokens_per_second": 3034245.430952122, "eta_seconds": 992.161565208435, "data_wait_seconds": 0.17376583814620972}
|
| 2576 |
{"step": 25750, "total_steps": 28611, "tokens": 27000832000, "loss": 2.7545379400253296, "ce_loss": 2.7532994151115417, "z_loss": 12.384948015213013, "muon_lr": 0.022509510921858156, "adamw_lr": 0.0022509510921858156, "grad_norm": 0.32795292139053345, "tokens_per_second": 4531445.935418408, "eta_seconds": 662.0350278377533, "data_wait_seconds": 0.26803356409072876}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2574 |
{"step": 25730, "total_steps": 28611, "tokens": 26979860480, "loss": 2.7777997255325317, "ce_loss": 2.7767510414123535, "z_loss": 10.487375974655151, "muon_lr": 0.022698876891773304, "adamw_lr": 0.0022698876891773306, "grad_norm": 0.3550080358982086, "tokens_per_second": 4172575.5496717193, "eta_seconds": 724.0006609916686, "data_wait_seconds": 1.4007091522216797e-05}
|
| 2575 |
{"step": 25740, "total_steps": 28611, "tokens": 26990346240, "loss": 2.7517773509025574, "ce_loss": 2.75069659948349, "z_loss": 10.807626247406006, "muon_lr": 0.022604397807203854, "adamw_lr": 0.002260439780720386, "grad_norm": 0.2949717044830322, "tokens_per_second": 3034245.430952122, "eta_seconds": 992.161565208435, "data_wait_seconds": 0.17376583814620972}
|
| 2576 |
{"step": 25750, "total_steps": 28611, "tokens": 27000832000, "loss": 2.7545379400253296, "ce_loss": 2.7532994151115417, "z_loss": 12.384948015213013, "muon_lr": 0.022509510921858156, "adamw_lr": 0.0022509510921858156, "grad_norm": 0.32795292139053345, "tokens_per_second": 4531445.935418408, "eta_seconds": 662.0350278377533, "data_wait_seconds": 0.26803356409072876}
|
| 2577 |
+
{"step": 25760, "total_steps": 28611, "tokens": 27011317760, "loss": 2.7280033230781555, "ce_loss": 2.7270310521125793, "z_loss": 9.72235369682312, "muon_lr": 0.0224142213242319, "adamw_lr": 0.0022414221324231903, "grad_norm": 0.3570299744606018, "tokens_per_second": 8443106.982717346, "eta_seconds": 354.0746531009674, "data_wait_seconds": 1.919269561767578e-05}
|
| 2578 |
+
{"step": 25770, "total_steps": 28611, "tokens": 27021803520, "loss": 2.7388890385627747, "ce_loss": 2.7377877235412598, "z_loss": 11.013124704360962, "muon_lr": 0.022318534124417023, "adamw_lr": 0.002231853412441702, "grad_norm": 0.26231008768081665, "tokens_per_second": 4345722.706006866, "eta_seconds": 685.5026465177535, "data_wait_seconds": 1.4543533325195312e-05}
|
| 2579 |
+
{"step": 25780, "total_steps": 28611, "tokens": 27032289280, "loss": 2.707013487815857, "ce_loss": 2.70604544878006, "z_loss": 9.680734157562256, "muon_lr": 0.022222454453827645, "adamw_lr": 0.002222245445382765, "grad_norm": 0.3358791470527649, "tokens_per_second": 3736051.1284012315, "eta_seconds": 794.560500907898, "data_wait_seconds": 1.4901161193847656e-05}
|
| 2580 |
+
{"step": 25790, "total_steps": 28611, "tokens": 27042775040, "loss": 2.745744049549103, "ce_loss": 2.7447622418403625, "z_loss": 9.817897081375122, "muon_lr": 0.022125987464924925, "adamw_lr": 0.002212598746492493, "grad_norm": 0.30345916748046875, "tokens_per_second": 4126132.327645967, "eta_seconds": 716.9020916223526, "data_wait_seconds": 1.6033649444580078e-05}
|
| 2581 |
+
{"step": 25800, "total_steps": 28611, "tokens": 27053260800, "loss": 2.7401782870292664, "ce_loss": 2.7392181754112244, "z_loss": 9.60147738456726, "muon_lr": 0.022029138330940706, "adamw_lr": 0.0022029138330940706, "grad_norm": 0.33223673701286316, "tokens_per_second": 2935539.564289906, "eta_seconds": 1004.0904138565063, "data_wait_seconds": 0.2810283303260803}
|
| 2582 |
+
{"step": 25810, "total_steps": 28611, "tokens": 27063746560, "loss": 2.7663768529891968, "ce_loss": 2.7655182480812073, "z_loss": 8.585944175720215, "muon_lr": 0.02193191224560013, "adamw_lr": 0.002193191224560013, "grad_norm": 0.34890103340148926, "tokens_per_second": 4001818.461585497, "eta_seconds": 733.9316873550415, "data_wait_seconds": 1.5437602996826172e-05}
|
| 2583 |
+
{"step": 25820, "total_steps": 28611, "tokens": 27074232320, "loss": 2.725997030735016, "ce_loss": 2.725208103656769, "z_loss": 7.88913357257843, "muon_lr": 0.021834314422843077, "adamw_lr": 0.0021834314422843077, "grad_norm": 0.34683454036712646, "tokens_per_second": 2895357.4448865848, "eta_seconds": 1010.782147526741, "data_wait_seconds": 1.9073486328125e-05}
|
| 2584 |
+
{"step": 25830, "total_steps": 28611, "tokens": 27084718080, "loss": 2.7669034600257874, "ce_loss": 2.765900194644928, "z_loss": 10.032347679138184, "muon_lr": 0.0217363500965446, "adamw_lr": 0.00217363500965446, "grad_norm": 0.33955416083335876, "tokens_per_second": 3111666.255676361, "eta_seconds": 937.1473726272583, "data_wait_seconds": 0.23727160692214966}
|
| 2585 |
+
{"step": 25840, "total_steps": 28611, "tokens": 27095203840, "loss": 2.7697770595550537, "ce_loss": 2.7687623500823975, "z_loss": 10.147218465805054, "muon_lr": 0.021638024520234212, "adamw_lr": 0.002163802452023421, "grad_norm": 0.2988835573196411, "tokens_per_second": 3574240.249228698, "eta_seconds": 812.9291523218154, "data_wait_seconds": 1.5735626220703125e-05}
|
| 2586 |
+
{"step": 25850, "total_steps": 28611, "tokens": 27105689600, "loss": 2.7726851105690002, "ce_loss": 2.7719212770462036, "z_loss": 7.6378562450408936, "muon_lr": 0.02153934296681415, "adamw_lr": 0.0021539342966814153, "grad_norm": 0.2862865626811981, "tokens_per_second": 4079083.0220992514, "eta_seconds": 709.7473428010941, "data_wait_seconds": 1.5795230865478516e-05}
|
| 2587 |
+
{"step": 25860, "total_steps": 28611, "tokens": 27116175360, "loss": 2.7698046565055847, "ce_loss": 2.7688491344451904, "z_loss": 9.555034637451172, "muon_lr": 0.021440310728276665, "adamw_lr": 0.0021440310728276664, "grad_norm": 0.3466080129146576, "tokens_per_second": 2830297.838464293, "eta_seconds": 1019.1975334882736, "data_wait_seconds": 1.4960765838623047e-05}
|
| 2588 |
+
{"step": 25870, "total_steps": 28611, "tokens": 27126661120, "loss": 2.721916913986206, "ce_loss": 2.72108656167984, "z_loss": 8.303326725959778, "muon_lr": 0.02134093311542014, "adamw_lr": 0.0021340933115420145, "grad_norm": 0.29357653856277466, "tokens_per_second": 2999633.753300807, "eta_seconds": 958.1659137010574, "data_wait_seconds": 1.3828277587890625e-05}
|
| 2589 |
+
{"step": 25880, "total_steps": 28611, "tokens": 27137146880, "loss": 2.7742071747779846, "ce_loss": 2.7731341123580933, "z_loss": 10.730347394943237, "muon_lr": 0.021241215457564376, "adamw_lr": 0.002124121545756438, "grad_norm": 0.3738099932670593, "tokens_per_second": 2626435.1250535375, "eta_seconds": 1090.3224026679993, "data_wait_seconds": 1.728534698486328e-05}
|
| 2590 |
+
{"step": 25890, "total_steps": 28611, "tokens": 27147632640, "loss": 2.7652647495269775, "ce_loss": 2.7642091512680054, "z_loss": 10.556446075439453, "muon_lr": 0.02114116310226473, "adamw_lr": 0.002114116310226473, "grad_norm": 0.25665420293807983, "tokens_per_second": 2843290.0300384792, "eta_seconds": 1003.4766998291014, "data_wait_seconds": 1.4901161193847656e-05}
|
| 2591 |
+
{"step": 25900, "total_steps": 28611, "tokens": 27158118400, "loss": 2.740252375602722, "ce_loss": 2.7394623160362244, "z_loss": 7.901273488998413, "muon_lr": 0.021040781415025366, "adamw_lr": 0.002104078141502537, "grad_norm": 0.3058062195777893, "tokens_per_second": 2890001.522592831, "eta_seconds": 983.6290790081024, "data_wait_seconds": 2.002716064453125e-05}
|
| 2592 |
+
{"step": 25910, "total_steps": 28611, "tokens": 27168604160, "loss": 2.7578280568122864, "ce_loss": 2.756823241710663, "z_loss": 10.048173666000366, "muon_lr": 0.02094007577901154, "adamw_lr": 0.0020940075779011537, "grad_norm": 0.3278745710849762, "tokens_per_second": 3976559.4436492315, "eta_seconds": 712.224679684639, "data_wait_seconds": 1.5079975128173828e-05}
|
| 2593 |
+
{"step": 25920, "total_steps": 28611, "tokens": 27179089920, "loss": 2.776896119117737, "ce_loss": 2.7759292125701904, "z_loss": 9.66933298110962, "muon_lr": 0.020839051594760873, "adamw_lr": 0.0020839051594760873, "grad_norm": 0.31263864040374756, "tokens_per_second": 2730916.1469229767, "eta_seconds": 1033.249599838257, "data_wait_seconds": 1.7523765563964844e-05}
|
| 2594 |
+
{"step": 25930, "total_steps": 28611, "tokens": 27189575680, "loss": 2.7375928163528442, "ce_loss": 2.7365384101867676, "z_loss": 10.544347286224365, "muon_lr": 0.020737714279893783, "adamw_lr": 0.002073771427989378, "grad_norm": 0.31249621510505676, "tokens_per_second": 3097180.7369677005, "eta_seconds": 907.6745901346206, "data_wait_seconds": 0.2547341585159302}
|
| 2595 |
+
{"step": 25940, "total_steps": 28611, "tokens": 27200061440, "loss": 2.7539639472961426, "ce_loss": 2.7529351115226746, "z_loss": 10.28830337524414, "muon_lr": 0.020636069268822922, "adamw_lr": 0.0020636069268822922, "grad_norm": 0.33277618885040283, "tokens_per_second": 3688874.111921337, "eta_seconds": 759.2415493249894, "data_wait_seconds": 1.424551010131836e-05}
|
| 2596 |
+
{"step": 25950, "total_steps": 28611, "tokens": 27210547200, "loss": 2.725883662700653, "ce_loss": 2.7248491048812866, "z_loss": 10.346124172210693, "muon_lr": 0.020534122012461756, "adamw_lr": 0.0020534122012461757, "grad_norm": 0.25943776965141296, "tokens_per_second": 2724368.050614482, "eta_seconds": 1024.186410999298, "data_wait_seconds": 0.2771071195602417}
|
| 2597 |
+
{"step": 25960, "total_steps": 28611, "tokens": 27221032960, "loss": 2.756795287132263, "ce_loss": 2.7558713555336, "z_loss": 9.23953628540039, "muon_lr": 0.02043187797793225, "adamw_lr": 0.0020431877977932253, "grad_norm": 0.3225611746311188, "tokens_per_second": 2960602.5988430614, "eta_seconds": 938.9220211744309, "data_wait_seconds": 1.71661376953125e-05}
|
| 2598 |
+
{"step": 25970, "total_steps": 28611, "tokens": 27231518720, "loss": 2.747161030769348, "ce_loss": 2.7460939288139343, "z_loss": 10.67127275466919, "muon_lr": 0.020329342648271683, "adamw_lr": 0.002032934264827168, "grad_norm": 0.28017422556877136, "tokens_per_second": 3060543.2170882, "eta_seconds": 904.8358476161957, "data_wait_seconds": 1.341104507446289e-05}
|
| 2599 |
+
{"step": 25980, "total_steps": 28611, "tokens": 27242004480, "loss": 2.746878504753113, "ce_loss": 2.7460092902183533, "z_loss": 8.6920166015625, "muon_lr": 0.020226521522138604, "adamw_lr": 0.0020226521522138607, "grad_norm": 0.3544571101665497, "tokens_per_second": 2270022.7573331078, "eta_seconds": 1215.3197350502014, "data_wait_seconds": 0.2521402835845947}
|
| 2600 |
+
{"step": 25990, "total_steps": 28611, "tokens": 27252490240, "loss": 2.7384780049324036, "ce_loss": 2.737614095211029, "z_loss": 8.63839864730835, "muon_lr": 0.020123420113517962, "adamw_lr": 0.002012342011351796, "grad_norm": 0.3038792908191681, "tokens_per_second": 2902332.598851657, "eta_seconds": 946.9340960741043, "data_wait_seconds": 0.2501416802406311}
|
| 2601 |
+
{"step": 26000, "total_steps": 28611, "tokens": 27262976000, "loss": 2.7809871435165405, "ce_loss": 2.7800447940826416, "z_loss": 9.424033403396606, "muon_lr": 0.0200200439514254, "adamw_lr": 0.00200200439514254, "grad_norm": 0.2948572635650635, "tokens_per_second": 3710831.6588676465, "eta_seconds": 737.7947014808655, "data_wait_seconds": 1.722574234008789e-05}
|
| 2602 |
+
{"step": 26010, "total_steps": 28611, "tokens": 27273461760, "loss": 2.7561429142951965, "ce_loss": 2.7553150057792664, "z_loss": 8.279312372207642, "muon_lr": 0.01991639857961077, "adamw_lr": 0.001991639857961077, "grad_norm": 0.29694411158561707, "tokens_per_second": 3017324.3292314713, "eta_seconds": 903.8955970287324, "data_wait_seconds": 1.5974044799804688e-05}
|
| 2603 |
+
{"step": 26020, "total_steps": 28611, "tokens": 27283947520, "loss": 2.745647370815277, "ce_loss": 2.744762122631073, "z_loss": 8.852691650390625, "muon_lr": 0.01981248955626081, "adamw_lr": 0.0019812489556260814, "grad_norm": 0.36700305342674255, "tokens_per_second": 2502508.178076098, "eta_seconds": 1085.6549600124358, "data_wait_seconds": 1.8715858459472656e-05}
|
| 2604 |
+
{"step": 26030, "total_steps": 28611, "tokens": 27294433280, "loss": 2.745263934135437, "ce_loss": 2.7443029284477234, "z_loss": 9.609911918640137, "muon_lr": 0.019708322453701098, "adamw_lr": 0.0019708322453701097, "grad_norm": 0.29231971502304077, "tokens_per_second": 4037232.205595207, "eta_seconds": 670.3539747476577, "data_wait_seconds": 1.7523765563964844e-05}
|
| 2605 |
+
{"step": 26040, "total_steps": 28611, "tokens": 27304919040, "loss": 2.7158934473991394, "ce_loss": 2.7150962352752686, "z_loss": 7.971992135047913, "muon_lr": 0.01960390285809721, "adamw_lr": 0.001960390285809721, "grad_norm": 0.3238885998725891, "tokens_per_second": 2949853.2340150564, "eta_seconds": 913.9061106204987, "data_wait_seconds": 1.436471939086914e-05}
|
| 2606 |
+
{"step": 26050, "total_steps": 28611, "tokens": 27315404800, "loss": 2.7456600666046143, "ce_loss": 2.7448039650917053, "z_loss": 8.561556339263916, "muon_lr": 0.019499236369155157, "adamw_lr": 0.001949923636915516, "grad_norm": 0.2797442376613617, "tokens_per_second": 3056366.014447744, "eta_seconds": 878.6261603832245, "data_wait_seconds": 1.5437602996826172e-05}
|
| 2607 |
+
{"step": 26060, "total_steps": 28611, "tokens": 27325890560, "loss": 2.7346982955932617, "ce_loss": 2.733512580394745, "z_loss": 11.85734748840332, "muon_lr": 0.019394328599821105, "adamw_lr": 0.0019394328599821105, "grad_norm": 0.32828786969184875, "tokens_per_second": 2438394.46623594, "eta_seconds": 1096.9994449377061, "data_wait_seconds": 0.25059330463409424}
|
| 2608 |
+
{"step": 26070, "total_steps": 28611, "tokens": 27336376320, "loss": 2.753467321395874, "ce_loss": 2.7526164054870605, "z_loss": 8.50939416885376, "muon_lr": 0.019289185175980335, "adamw_lr": 0.0019289185175980336, "grad_norm": 0.3030056059360504, "tokens_per_second": 3652816.132074069, "eta_seconds": 729.4184869050979, "data_wait_seconds": 1.239776611328125e-05}
|
| 2609 |
+
{"step": 26080, "total_steps": 28611, "tokens": 27346862080, "loss": 2.7501017451286316, "ce_loss": 2.7491641640663147, "z_loss": 9.3759765625, "muon_lr": 0.019183811736155583, "adamw_lr": 0.0019183811736155586, "grad_norm": 0.3475590944290161, "tokens_per_second": 2678007.69483944, "eta_seconds": 991.0150225162507, "data_wait_seconds": 1.7344951629638672e-05}
|
| 2610 |
+
{"step": 26090, "total_steps": 28611, "tokens": 27357347840, "loss": 2.7413219809532166, "ce_loss": 2.7404264211654663, "z_loss": 8.956261157989502, "muon_lr": 0.01907821393120463, "adamw_lr": 0.0019078213931204631, "grad_norm": 0.3451547622680664, "tokens_per_second": 3170245.585547466, "eta_seconds": 833.8344852685929, "data_wait_seconds": 1.8417835235595703e-05}
|
| 2611 |
+
{"step": 26100, "total_steps": 28611, "tokens": 27367833600, "loss": 2.743073582649231, "ce_loss": 2.7421253323554993, "z_loss": 9.4817214012146, "muon_lr": 0.018972397424017285, "adamw_lr": 0.0018972397424017284, "grad_norm": 0.30747079849243164, "tokens_per_second": 2902149.89168787, "eta_seconds": 907.2496026277543, "data_wait_seconds": 1.704692840576172e-05}
|
| 2612 |
+
{"step": 26110, "total_steps": 28611, "tokens": 27378319360, "loss": 2.734444260597229, "ce_loss": 2.733582556247711, "z_loss": 8.617541551589966, "muon_lr": 0.018866367889211685, "adamw_lr": 0.0018866367889211685, "grad_norm": 0.30559241771698, "tokens_per_second": 3088052.6004694803, "eta_seconds": 849.2370161056518, "data_wait_seconds": 0.25848132371902466}
|
| 2613 |
+
{"step": 26120, "total_steps": 28611, "tokens": 27388805120, "loss": 2.7857247591018677, "ce_loss": 2.78473299741745, "z_loss": 9.91786003112793, "muon_lr": 0.01876013101283001, "adamw_lr": 0.001876013101283001, "grad_norm": 0.36906448006629944, "tokens_per_second": 3031830.1651943927, "eta_seconds": 861.526758980751, "data_wait_seconds": 1.7464160919189453e-05}
|
| 2614 |
+
{"step": 26130, "total_steps": 28611, "tokens": 27399290880, "loss": 2.7574514746665955, "ce_loss": 2.7564321756362915, "z_loss": 10.193514108657837, "muon_lr": 0.018653692492033514, "adamw_lr": 0.0018653692492033513, "grad_norm": 0.2751200795173645, "tokens_per_second": 3179746.624377496, "eta_seconds": 818.1523131608963, "data_wait_seconds": 2.1696090698242188e-05}
|
| 2615 |
+
{"step": 26140, "total_steps": 28611, "tokens": 27409776640, "loss": 2.7674952149391174, "ce_loss": 2.7666309475898743, "z_loss": 8.64303994178772, "muon_lr": 0.01854705803479706, "adamw_lr": 0.001854705803479706, "grad_norm": 0.34931865334510803, "tokens_per_second": 2331680.85697219, "eta_seconds": 1111.228960967064, "data_wait_seconds": 1.817941665649414e-05}
|
| 2616 |
+
{"step": 26150, "total_steps": 28611, "tokens": 27420262400, "loss": 2.7524168491363525, "ce_loss": 2.7514127492904663, "z_loss": 10.041414737701416, "muon_lr": 0.01844023335960296, "adamw_lr": 0.001844023335960296, "grad_norm": 0.2606354057788849, "tokens_per_second": 2722096.5684826267, "eta_seconds": 947.9992612600327, "data_wait_seconds": 1.7642974853515625e-05}
|
| 2617 |
+
{"step": 26160, "total_steps": 28611, "tokens": 27430748160, "loss": 2.734165132045746, "ce_loss": 2.733318269252777, "z_loss": 8.4686518907547, "muon_lr": 0.018333224195134345, "adamw_lr": 0.0018333224195134347, "grad_norm": 0.255130410194397, "tokens_per_second": 3968988.1733019873, "eta_seconds": 647.5352567911148, "data_wait_seconds": 2.014636993408203e-05}
|
| 2618 |
+
{"step": 26170, "total_steps": 28611, "tokens": 27441233920, "loss": 2.7032116651535034, "ce_loss": 2.702150881290436, "z_loss": 10.607527017593384, "muon_lr": 0.01822603627996796, "adamw_lr": 0.0018226036279967962, "grad_norm": 0.35061755776405334, "tokens_per_second": 2861003.3566044895, "eta_seconds": 894.6420877456665, "data_wait_seconds": 0.25451022386550903}
|
| 2619 |
+
{"step": 26180, "total_steps": 28611, "tokens": 27451719680, "loss": 2.7211732268333435, "ce_loss": 2.720089614391327, "z_loss": 10.836058378219604, "muon_lr": 0.018118675362266388, "adamw_lr": 0.0018118675362266388, "grad_norm": 0.30266058444976807, "tokens_per_second": 4332806.575928923, "eta_seconds": 588.3226521492005, "data_wait_seconds": 1.4185905456542969e-05}
|
| 2620 |
+
{"step": 26190, "total_steps": 28611, "tokens": 27462205440, "loss": 2.744102358818054, "ce_loss": 2.7432456612586975, "z_loss": 8.567132115364075, "muon_lr": 0.018011147199469835, "adamw_lr": 0.0018011147199469835, "grad_norm": 0.31957799196243286, "tokens_per_second": 2868839.0887938053, "eta_seconds": 884.8884226083755, "data_wait_seconds": 1.811981201171875e-05}
|
| 2621 |
+
{"step": 26200, "total_steps": 28611, "tokens": 27472691200, "loss": 2.7470551133155823, "ce_loss": 2.745973825454712, "z_loss": 10.81281852722168, "muon_lr": 0.017903457557987317, "adamw_lr": 0.001790345755798732, "grad_norm": 0.29609036445617676, "tokens_per_second": 3083862.727281014, "eta_seconds": 819.7889982700348, "data_wait_seconds": 2.2351741790771484e-05}
|
| 2622 |
+
{"step": 26210, "total_steps": 28611, "tokens": 27483176960, "loss": 2.716933310031891, "ce_loss": 2.715983271598816, "z_loss": 9.501035928726196, "muon_lr": 0.017795612212887515, "adamw_lr": 0.0017795612212887517, "grad_norm": 0.30377644300460815, "tokens_per_second": 3698785.5539511954, "eta_seconds": 680.6642178297043, "data_wait_seconds": 1.5437602996826172e-05}
|
| 2623 |
+
{"step": 26220, "total_steps": 28611, "tokens": 27493662720, "loss": 2.6642075181007385, "ce_loss": 2.66290420293808, "z_loss": 13.033342003822327, "muon_lr": 0.017687616947588972, "adamw_lr": 0.0017687616947588973, "grad_norm": 1.0633467435836792, "tokens_per_second": 4292810.829309964, "eta_seconds": 584.0334726333618, "data_wait_seconds": 1.817941665649414e-05}
|
| 2624 |
+
{"step": 26230, "total_steps": 28611, "tokens": 27504148480, "loss": 2.750116467475891, "ce_loss": 2.7491856813430786, "z_loss": 9.3081636428833, "muon_lr": 0.017579477553550025, "adamw_lr": 0.0017579477553550027, "grad_norm": 0.3124008774757385, "tokens_per_second": 2821774.676748213, "eta_seconds": 884.7834224939347, "data_wait_seconds": 1.3768672943115234e-05}
|
| 2625 |
+
{"step": 26240, "total_steps": 28611, "tokens": 27514634240, "loss": 2.7270076870918274, "ce_loss": 2.726110100746155, "z_loss": 8.975627660751343, "muon_lr": 0.017471199829958192, "adamw_lr": 0.0017471199829958192, "grad_norm": 0.3253708481788635, "tokens_per_second": 2784887.2209247043, "eta_seconds": 892.7376582145691, "data_wait_seconds": 1.6927719116210938e-05}
|
| 2626 |
+
{"step": 26250, "total_steps": 28611, "tokens": 27525120000, "loss": 2.7480649948120117, "ce_loss": 2.747147262096405, "z_loss": 9.177495241165161, "muon_lr": 0.017362789583419178, "adamw_lr": 0.0017362789583419177, "grad_norm": 0.28613579273223877, "tokens_per_second": 3886313.808571997, "eta_seconds": 637.0272854804992, "data_wait_seconds": 1.722574234008789e-05}
|
| 2627 |
+
{"step": 26260, "total_steps": 28611, "tokens": 27535605760, "loss": 2.7484087347984314, "ce_loss": 2.747315466403961, "z_loss": 10.932509183883667, "muon_lr": 0.017254252627645496, "adamw_lr": 0.0017254252627645498, "grad_norm": 0.31188154220581055, "tokens_per_second": 2805135.28932834, "eta_seconds": 878.8175691127776, "data_wait_seconds": 1.7821788787841797e-05}
|
| 2628 |
+
{"step": 26270, "total_steps": 28611, "tokens": 27546091520, "loss": 2.726708471775055, "ce_loss": 2.7256909012794495, "z_loss": 10.175805568695068, "muon_lr": 0.017145594783144695, "adamw_lr": 0.0017145594783144697, "grad_norm": 0.29064473509788513, "tokens_per_second": 4349915.995587622, "eta_seconds": 564.313522028923, "data_wait_seconds": 1.2814998626708984e-05}
|
| 2629 |
+
{"step": 26280, "total_steps": 28611, "tokens": 27556577280, "loss": 2.743116617202759, "ce_loss": 2.742255687713623, "z_loss": 8.609194040298462, "muon_lr": 0.017036821876907218, "adamw_lr": 0.001703682187690722, "grad_norm": 0.33513307571411133, "tokens_per_second": 2820294.6920947935, "eta_seconds": 866.6578931808473, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2630 |
+
{"step": 26290, "total_steps": 28611, "tokens": 27567063040, "loss": 2.743142783641815, "ce_loss": 2.742128074169159, "z_loss": 10.147326231002808, "muon_lr": 0.016927939742093917, "adamw_lr": 0.001692793974209392, "grad_norm": 0.26523131132125854, "tokens_per_second": 4126641.043640691, "eta_seconds": 589.7641375303268, "data_wait_seconds": 2.0325183868408203e-05}
|
| 2631 |
+
{"step": 26300, "total_steps": 28611, "tokens": 27577548800, "loss": 2.7544147968292236, "ce_loss": 2.7533925771713257, "z_loss": 10.222290515899658, "muon_lr": 0.016818954217723243, "adamw_lr": 0.0016818954217723244, "grad_norm": 0.2887011766433716, "tokens_per_second": 2966959.438493686, "eta_seconds": 816.74831969738, "data_wait_seconds": 1.5616416931152344e-05}
|
| 2632 |
+
{"step": 26310, "total_steps": 28611, "tokens": 27588034560, "loss": 2.7742941975593567, "ce_loss": 2.773468554019928, "z_loss": 8.25600266456604, "muon_lr": 0.016709871148358108, "adamw_lr": 0.0016709871148358109, "grad_norm": 0.3076413869857788, "tokens_per_second": 4447381.311997994, "eta_seconds": 542.515517950058, "data_wait_seconds": 1.704692840576172e-05}
|
| 2633 |
+
{"step": 26320, "total_steps": 28611, "tokens": 27598520320, "loss": 2.739617168903351, "ce_loss": 2.7387306094169617, "z_loss": 8.865971565246582, "muon_lr": 0.01660069638379248, "adamw_lr": 0.0016600696383792478, "grad_norm": 0.30879274010658264, "tokens_per_second": 2945034.907203253, "eta_seconds": 815.7076882600784, "data_wait_seconds": 1.436471939086914e-05}
|
| 2634 |
+
{"step": 26330, "total_steps": 28611, "tokens": 27609006080, "loss": 2.7318525910377502, "ce_loss": 2.730934500694275, "z_loss": 9.181196689605713, "muon_lr": 0.016491435778737646, "adamw_lr": 0.0016491435778737647, "grad_norm": 0.32196831703186035, "tokens_per_second": 4222377.04747023, "eta_seconds": 566.458615398407, "data_wait_seconds": 1.3530254364013672e-05}
|
| 2635 |
+
{"step": 26340, "total_steps": 28611, "tokens": 27619491840, "loss": 2.707832932472229, "ce_loss": 2.707021951675415, "z_loss": 8.109513401985168, "muon_lr": 0.016382095192508276, "adamw_lr": 0.0016382095192508277, "grad_norm": 0.3283020853996277, "tokens_per_second": 3002201.6671149214, "eta_seconds": 793.1899186134339, "data_wait_seconds": 1.4007091522216797e-05}
|
| 2636 |
+
{"step": 26350, "total_steps": 28611, "tokens": 27629977600, "loss": 2.7013733983039856, "ce_loss": 2.700375020503998, "z_loss": 9.983871459960938, "muon_lr": 0.01627268048870817, "adamw_lr": 0.001627268048870817, "grad_norm": 0.32504522800445557, "tokens_per_second": 2998982.2873060107, "eta_seconds": 790.5449612140656, "data_wait_seconds": 1.710653305053711e-05}
|
| 2637 |
+
{"step": 26360, "total_steps": 28611, "tokens": 27640463360, "loss": 2.744956314563751, "ce_loss": 2.7440329790115356, "z_loss": 9.23298168182373, "muon_lr": 0.016163197534915838, "adamw_lr": 0.001616319753491584, "grad_norm": 0.26271113753318787, "tokens_per_second": 4286966.493591892, "eta_seconds": 550.5861964464187, "data_wait_seconds": 1.2040138244628906e-05}
|
| 2638 |
+
{"step": 26370, "total_steps": 28611, "tokens": 27650949120, "loss": 2.7548627257347107, "ce_loss": 2.7539567351341248, "z_loss": 9.05975604057312, "muon_lr": 0.01605365220236983, "adamw_lr": 0.0016053652202369833, "grad_norm": 0.330095499753952, "tokens_per_second": 4619492.024164792, "eta_seconds": 508.6833798408509, "data_wait_seconds": 1.3649463653564453e-05}
|
| 2639 |
+
{"step": 26380, "total_steps": 28611, "tokens": 27661434880, "loss": 2.728697955608368, "ce_loss": 2.7278314232826233, "z_loss": 8.665394067764282, "muon_lr": 0.01594405036565388, "adamw_lr": 0.001594405036565388, "grad_norm": 0.28431859612464905, "tokens_per_second": 3087498.928445617, "eta_seconds": 757.6919410228729, "data_wait_seconds": 1.341104507446289e-05}
|
| 2640 |
+
{"step": 26390, "total_steps": 28611, "tokens": 27671920640, "loss": 2.698328375816345, "ce_loss": 2.697299540042877, "z_loss": 10.2877516746521, "muon_lr": 0.01583439790238186, "adamw_lr": 0.0015834397902381862, "grad_norm": 0.2682998478412628, "tokens_per_second": 2924544.7577318246, "eta_seconds": 796.324723649025, "data_wait_seconds": 1.3828277587890625e-05}
|
| 2641 |
+
{"step": 26400, "total_steps": 28611, "tokens": 27682406400, "loss": 2.691671311855316, "ce_loss": 2.6906750798225403, "z_loss": 9.962318658828735, "muon_lr": 0.015724700692882607, "adamw_lr": 0.0015724700692882605, "grad_norm": 0.29334965348243713, "tokens_per_second": 3038308.6120036654, "eta_seconds": 763.0566318511962, "data_wait_seconds": 0.19542378187179565}
|
| 2642 |
+
{"step": 26410, "total_steps": 28611, "tokens": 27692892160, "loss": 2.7106226682662964, "ce_loss": 2.7097838521003723, "z_loss": 8.388031721115112, "muon_lr": 0.015614964619884545, "adamw_lr": 0.0015614964619884545, "grad_norm": 0.2682245969772339, "tokens_per_second": 4469583.990708892, "eta_seconds": 516.3603102207184, "data_wait_seconds": 1.8715858459472656e-05}
|
| 2643 |
+
{"step": 26420, "total_steps": 28611, "tokens": 27703377920, "loss": 2.696223199367523, "ce_loss": 2.6954286694526672, "z_loss": 7.94494366645813, "muon_lr": 0.015505195568200235, "adamw_lr": 0.0015505195568200235, "grad_norm": 0.28988513350486755, "tokens_per_second": 4330360.806517725, "eta_seconds": 530.540090918541, "data_wait_seconds": 1.233816146850586e-05}
|
| 2644 |
+
{"step": 26430, "total_steps": 28611, "tokens": 27713863680, "loss": 2.7418262362480164, "ce_loss": 2.740972101688385, "z_loss": 8.541340112686157, "muon_lr": 0.015395399424410799, "adamw_lr": 0.00153953994244108, "grad_norm": 0.3134079873561859, "tokens_per_second": 3133550.0274763405, "eta_seconds": 729.8253533363342, "data_wait_seconds": 1.4781951904296875e-05}
|
| 2645 |
+
{"step": 26440, "total_steps": 28611, "tokens": 27724349440, "loss": 2.7113733887672424, "ce_loss": 2.710561454296112, "z_loss": 8.119226455688477, "muon_lr": 0.015285582076550197, "adamw_lr": 0.0015285582076550199, "grad_norm": 0.29448965191841125, "tokens_per_second": 2829093.679450866, "eta_seconds": 804.65999147892, "data_wait_seconds": 1.5914440155029297e-05}
|
| 2646 |
+
{"step": 26450, "total_steps": 28611, "tokens": 27734835200, "loss": 2.6965683698654175, "ce_loss": 2.695659339427948, "z_loss": 9.09015703201294, "muon_lr": 0.015175749413789538, "adamw_lr": 0.001517574941378954, "grad_norm": 0.2910754382610321, "tokens_per_second": 3986463.309429309, "eta_seconds": 568.416804599762, "data_wait_seconds": 2.0802021026611328e-05}
|
| 2647 |
+
{"step": 26460, "total_steps": 28611, "tokens": 27745320960, "loss": 2.702763020992279, "ce_loss": 2.701815187931061, "z_loss": 9.479024171829224, "muon_lr": 0.015065907326121179, "adamw_lr": 0.0015065907326121178, "grad_norm": 0.29871320724487305, "tokens_per_second": 2946804.517169042, "eta_seconds": 765.4009496927262, "data_wait_seconds": 0.27554214000701904}
|
| 2648 |
+
{"step": 26470, "total_steps": 28611, "tokens": 27755806720, "loss": 2.6986029148101807, "ce_loss": 2.6976646780967712, "z_loss": 9.382650375366211, "muon_lr": 0.014956061704042947, "adamw_lr": 0.0014956061704042946, "grad_norm": 0.31210842728614807, "tokens_per_second": 4368844.282153231, "eta_seconds": 513.8661556720734, "data_wait_seconds": 1.519918441772461e-05}
|
| 2649 |
+
{"step": 26480, "total_steps": 28611, "tokens": 27766292480, "loss": 2.658087909221649, "ce_loss": 2.657213032245636, "z_loss": 8.749070167541504, "muon_lr": 0.014846218438242176, "adamw_lr": 0.0014846218438242177, "grad_norm": 0.27456557750701904, "tokens_per_second": 3025452.752774489, "eta_seconds": 738.5722530126571, "data_wait_seconds": 1.4841556549072266e-05}
|
| 2650 |
+
{"step": 26490, "total_steps": 28611, "tokens": 27776778240, "loss": 2.7223902344703674, "ce_loss": 2.7214102745056152, "z_loss": 9.79960036277771, "muon_lr": 0.01473638341927986, "adamw_lr": 0.001473638341927986, "grad_norm": 0.2626742124557495, "tokens_per_second": 3034395.5314851776, "eta_seconds": 732.9399456739425, "data_wait_seconds": 0.5063472390174866}
|
| 2651 |
+
{"step": 26500, "total_steps": 28611, "tokens": 27787264000, "loss": 2.68773877620697, "ce_loss": 2.6868406534194946, "z_loss": 8.981284379959106, "muon_lr": 0.014626562537274729, "adamw_lr": 0.001462656253727473, "grad_norm": 0.29392483830451965, "tokens_per_second": 4096849.037650278, "eta_seconds": 540.3040033102036, "data_wait_seconds": 1.4722347259521484e-05}
|
| 2652 |
+
{"step": 26510, "total_steps": 28611, "tokens": 27797749760, "loss": 2.7113457918167114, "ce_loss": 2.710474908351898, "z_loss": 8.709247589111328, "muon_lr": 0.014516761681587408, "adamw_lr": 0.0014516761681587409, "grad_norm": 0.3030966520309448, "tokens_per_second": 2877194.3681275654, "eta_seconds": 765.696680212021, "data_wait_seconds": 0.2720460295677185}
|
| 2653 |
+
{"step": 26520, "total_steps": 28611, "tokens": 27808235520, "loss": 2.7248218059539795, "ce_loss": 2.723959505558014, "z_loss": 8.623264789581299, "muon_lr": 0.014406986740504548, "adamw_lr": 0.0014406986740504548, "grad_norm": 0.32446473836898804, "tokens_per_second": 4242458.994196729, "eta_seconds": 516.8164074182511, "data_wait_seconds": 1.430511474609375e-05}
|
| 2654 |
+
{"step": 26530, "total_steps": 28611, "tokens": 27818721280, "loss": 2.729949176311493, "ce_loss": 2.728961169719696, "z_loss": 9.880322217941284, "muon_lr": 0.01429724360092309, "adamw_lr": 0.001429724360092309, "grad_norm": 0.2639226019382477, "tokens_per_second": 2755849.373247653, "eta_seconds": 791.8018586874008, "data_wait_seconds": 1.5795230865478516e-05}
|
| 2655 |
+
{"step": 26540, "total_steps": 28611, "tokens": 27829207040, "loss": 2.737084984779358, "ce_loss": 2.7362740635871887, "z_loss": 8.110064506530762, "muon_lr": 0.014187538148034569, "adamw_lr": 0.001418753814803457, "grad_norm": 0.2870315611362457, "tokens_per_second": 4319009.07689768, "eta_seconds": 502.8007251977921, "data_wait_seconds": 1.609325408935547e-05}
|
| 2656 |
+
{"step": 26550, "total_steps": 28611, "tokens": 27839692800, "loss": 2.6960065960884094, "ce_loss": 2.6951830983161926, "z_loss": 8.234689950942993, "muon_lr": 0.014077876265009464, "adamw_lr": 0.0014077876265009466, "grad_norm": 0.2862098813056946, "tokens_per_second": 3003951.0014901436, "eta_seconds": 719.4242299318313, "data_wait_seconds": 1.8477439880371094e-05}
|
| 2657 |
+
{"step": 26560, "total_steps": 28611, "tokens": 27850178560, "loss": 2.758547306060791, "ce_loss": 2.757608473300934, "z_loss": 9.388425827026367, "muon_lr": 0.013968263832681772, "adamw_lr": 0.0013968263832681773, "grad_norm": 0.27352479100227356, "tokens_per_second": 4385158.53018379, "eta_seconds": 490.43366646766657, "data_wait_seconds": 1.3113021850585938e-05}
|
| 2658 |
+
{"step": 26570, "total_steps": 28611, "tokens": 27860664320, "loss": 2.774903953075409, "ce_loss": 2.7741522789001465, "z_loss": 7.516562461853027, "muon_lr": 0.01385870672923357, "adamw_lr": 0.0013858706729233572, "grad_norm": 0.3227607011795044, "tokens_per_second": 2998115.468560681, "eta_seconds": 713.8296167850494, "data_wait_seconds": 1.4841556549072266e-05}
|
| 2659 |
+
{"step": 26580, "total_steps": 28611, "tokens": 27871150080, "loss": 2.7398502826690674, "ce_loss": 2.739025294780731, "z_loss": 8.25014042854309, "muon_lr": 0.013749210829879843, "adamw_lr": 0.0013749210829879844, "grad_norm": 0.3022347092628479, "tokens_per_second": 2963758.436634632, "eta_seconds": 718.5666111230851, "data_wait_seconds": 0.5481818318367004}
|
| 2660 |
+
{"step": 26590, "total_steps": 28611, "tokens": 27881635840, "loss": 2.720327854156494, "ce_loss": 2.719475746154785, "z_loss": 8.52111804485321, "muon_lr": 0.013639782006553358, "adamw_lr": 0.001363978200655336, "grad_norm": 0.32117176055908203, "tokens_per_second": 4461942.871608293, "eta_seconds": 474.9437984704971, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2661 |
+
{"step": 26600, "total_steps": 28611, "tokens": 27892121600, "loss": 2.715973138809204, "ce_loss": 2.715210258960724, "z_loss": 7.62834358215332, "muon_lr": 0.013530426127589814, "adamw_lr": 0.0013530426127589814, "grad_norm": 0.27825942635536194, "tokens_per_second": 2984120.4208800187, "eta_seconds": 706.6358050584793, "data_wait_seconds": 0.2651174068450928}
|
| 2662 |
+
{"step": 26610, "total_steps": 28611, "tokens": 27902607360, "loss": 2.690728545188904, "ce_loss": 2.6899086236953735, "z_loss": 8.199705243110657, "muon_lr": 0.013421149057413127, "adamw_lr": 0.0013421149057413126, "grad_norm": 0.25513726472854614, "tokens_per_second": 4155532.9335295614, "eta_seconds": 504.9173257827759, "data_wait_seconds": 1.4543533325195312e-05}
|
| 2663 |
+
{"step": 26620, "total_steps": 28611, "tokens": 27913093120, "loss": 2.731367290019989, "ce_loss": 2.730376422405243, "z_loss": 9.908916473388672, "muon_lr": 0.013311956656220918, "adamw_lr": 0.0013311956656220918, "grad_norm": 0.2812521457672119, "tokens_per_second": 3043327.945014192, "eta_seconds": 685.9973206043243, "data_wait_seconds": 0.03776365518569946}
|
| 2664 |
+
{"step": 26630, "total_steps": 28611, "tokens": 27923578880, "loss": 2.6959437131881714, "ce_loss": 2.695061445236206, "z_loss": 8.82198941707611, "muon_lr": 0.013202854779670295, "adamw_lr": 0.0013202854779670295, "grad_norm": 0.2599151134490967, "tokens_per_second": 4533384.354262408, "eta_seconds": 458.2071348190308, "data_wait_seconds": 1.71661376953125e-05}
|
| 2665 |
+
{"step": 26640, "total_steps": 28611, "tokens": 27934064640, "loss": 2.7265384793281555, "ce_loss": 2.725597321987152, "z_loss": 9.411478281021118, "muon_lr": 0.01309384927856378, "adamw_lr": 0.0013093849278563781, "grad_norm": 0.3048606812953949, "tokens_per_second": 2876437.7122136843, "eta_seconds": 718.5079263925553, "data_wait_seconds": 1.4424324035644531e-05}
|
| 2666 |
+
{"step": 26650, "total_steps": 28611, "tokens": 27944550400, "loss": 2.7195887565612793, "ce_loss": 2.7186400294303894, "z_loss": 9.487252473831177, "muon_lr": 0.012984945998535601, "adamw_lr": 0.0012984945998535601, "grad_norm": 0.33748841285705566, "tokens_per_second": 2852235.535031379, "eta_seconds": 720.9283773183822, "data_wait_seconds": 1.4066696166992188e-05}
|
| 2667 |
+
{"step": 26660, "total_steps": 28611, "tokens": 27955036160, "loss": 2.70182341337204, "ce_loss": 2.700948476791382, "z_loss": 8.749439239501953, "muon_lr": 0.012876150779738138, "adamw_lr": 0.001287615077973814, "grad_norm": 0.26083657145500183, "tokens_per_second": 3016210.8378373133, "eta_seconds": 678.2588771104813, "data_wait_seconds": 0.2531042695045471}
|
| 2668 |
+
{"step": 26670, "total_steps": 28611, "tokens": 27965521920, "loss": 2.7102949619293213, "ce_loss": 2.7093895077705383, "z_loss": 9.054918766021729, "muon_lr": 0.012767469456528813, "adamw_lr": 0.0012767469456528813, "grad_norm": 0.29298341274261475, "tokens_per_second": 3939155.0387771586, "eta_seconds": 516.6808607339859, "data_wait_seconds": 1.329183578491211e-05}
|
| 2669 |
+
{"step": 26680, "total_steps": 28611, "tokens": 27976007680, "loss": 2.7170183062553406, "ce_loss": 2.71622896194458, "z_loss": 7.893064379692078, "muon_lr": 0.01265890785715716, "adamw_lr": 0.001265890785715716, "grad_norm": 0.2857241630554199, "tokens_per_second": 3086235.5917401197, "eta_seconds": 656.0744297742843, "data_wait_seconds": 1.2576580047607422e-05}
|
| 2670 |
+
{"step": 26690, "total_steps": 28611, "tokens": 27986493440, "loss": 2.733566164970398, "ce_loss": 2.7326580286026, "z_loss": 9.080649614334106, "muon_lr": 0.01255047180345228, "adamw_lr": 0.001255047180345228, "grad_norm": 0.260688453912735, "tokens_per_second": 2849503.497151272, "eta_seconds": 706.9001662969589, "data_wait_seconds": 1.3768672943115234e-05}
|
| 2671 |
+
{"step": 26700, "total_steps": 28611, "tokens": 27996979200, "loss": 2.7757818698883057, "ce_loss": 2.7749123573303223, "z_loss": 8.695124506950378, "muon_lr": 0.012442167110510643, "adamw_lr": 0.0012442167110510644, "grad_norm": 0.3239932656288147, "tokens_per_second": 2925599.7589725093, "eta_seconds": 684.929211473465, "data_wait_seconds": 2.1755695343017578e-05}
|
| 2672 |
+
{"step": 26710, "total_steps": 28611, "tokens": 28007464960, "loss": 2.719874143600464, "ce_loss": 2.719060480594635, "z_loss": 8.13677179813385, "muon_lr": 0.012333999586384254, "adamw_lr": 0.0012333999586384254, "grad_norm": 0.2646363079547882, "tokens_per_second": 4475254.0413507875, "eta_seconds": 445.4144854307175, "data_wait_seconds": 1.4066696166992188e-05}
|
| 2673 |
+
{"step": 26720, "total_steps": 28611, "tokens": 28017950720, "loss": 2.7174214720726013, "ce_loss": 2.7166696190834045, "z_loss": 7.518480181694031, "muon_lr": 0.012225975031769157, "adamw_lr": 0.001222597503176916, "grad_norm": 0.2561899423599243, "tokens_per_second": 2941555.5682288874, "eta_seconds": 674.0845685243606, "data_wait_seconds": 1.806020736694336e-05}
|
| 2674 |
+
{"step": 26730, "total_steps": 28611, "tokens": 28028436480, "loss": 2.7053146362304688, "ce_loss": 2.7045458555221558, "z_loss": 7.687265992164612, "muon_lr": 0.012118099239694372, "adamw_lr": 0.0012118099239694373, "grad_norm": 0.29231733083724976, "tokens_per_second": 4123773.123526327, "eta_seconds": 478.29291207790374, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2675 |
+
{"step": 26740, "total_steps": 28611, "tokens": 28038922240, "loss": 2.7107043862342834, "ce_loss": 2.709859788417816, "z_loss": 8.445810079574585, "muon_lr": 0.012010377995211253, "adamw_lr": 0.0012010377995211254, "grad_norm": 0.27789872884750366, "tokens_per_second": 2912689.969289261, "eta_seconds": 673.56488904953, "data_wait_seconds": 1.424551010131836e-05}
|
| 2676 |
+
{"step": 26750, "total_steps": 28611, "tokens": 28049408000, "loss": 2.7358981370925903, "ce_loss": 2.735095977783203, "z_loss": 8.02151906490326, "muon_lr": 0.01190281707508322, "adamw_lr": 0.0011902817075083222, "grad_norm": 0.2566690444946289, "tokens_per_second": 3162263.6154601565, "eta_seconds": 617.0895830631256, "data_wait_seconds": 2.0742416381835938e-05}
|
| 2677 |
+
{"step": 26760, "total_steps": 28611, "tokens": 28059893760, "loss": 2.732074022293091, "ce_loss": 2.731301784515381, "z_loss": 7.722539901733398, "muon_lr": 0.011795422247475986, "adamw_lr": 0.0011795422247475986, "grad_norm": 0.24719315767288208, "tokens_per_second": 4024304.5210670754, "eta_seconds": 482.29803829193116, "data_wait_seconds": 1.6570091247558594e-05}
|
| 2678 |
+
{"step": 26770, "total_steps": 28611, "tokens": 28070379520, "loss": 2.7122461199760437, "ce_loss": 2.7114115953445435, "z_loss": 8.345025539398193, "muon_lr": 0.011688199271648226, "adamw_lr": 0.0011688199271648228, "grad_norm": 0.2947778105735779, "tokens_per_second": 2867333.4511878802, "eta_seconds": 673.2486642599106, "data_wait_seconds": 2.1338462829589844e-05}
|
| 2679 |
+
{"step": 26780, "total_steps": 28611, "tokens": 28080865280, "loss": 2.7242159843444824, "ce_loss": 2.7233455777168274, "z_loss": 8.703934669494629, "muon_lr": 0.01158115389764274, "adamw_lr": 0.001158115389764274, "grad_norm": 0.269066721200943, "tokens_per_second": 3798664.0479113744, "eta_seconds": 505.42575805187226, "data_wait_seconds": 1.7464160919189453e-05}
|
| 2680 |
+
{"step": 26790, "total_steps": 28611, "tokens": 28091351040, "loss": 2.718165338039398, "ce_loss": 2.7173604369163513, "z_loss": 8.049169540405273, "muon_lr": 0.011474291865978066, "adamw_lr": 0.0011474291865978066, "grad_norm": 0.26774686574935913, "tokens_per_second": 2397504.6324303937, "eta_seconds": 796.4351226568222, "data_wait_seconds": 0.27995091676712036}
|
| 2681 |
+
{"step": 26800, "total_steps": 28611, "tokens": 28101836800, "loss": 2.7077722549438477, "ce_loss": 2.706968605518341, "z_loss": 8.036417126655579, "muon_lr": 0.011367618907340647, "adamw_lr": 0.0011367618907340649, "grad_norm": 0.25945064425468445, "tokens_per_second": 4339358.424160598, "eta_seconds": 437.61564507484434, "data_wait_seconds": 1.7940998077392578e-05}
|
| 2682 |
+
{"step": 26810, "total_steps": 28611, "tokens": 28112322560, "loss": 2.7150190472602844, "ce_loss": 2.7142873406410217, "z_loss": 7.3168381452560425, "muon_lr": 0.01126114074227752, "adamw_lr": 0.001126114074227752, "grad_norm": 0.3040405511856079, "tokens_per_second": 3933998.3590659546, "eta_seconds": 480.0422378540039, "data_wait_seconds": 1.2814998626708984e-05}
|
| 2683 |
+
{"step": 26820, "total_steps": 28611, "tokens": 28122808320, "loss": 2.7075753211975098, "ce_loss": 2.7068058252334595, "z_loss": 7.694891571998596, "muon_lr": 0.011154863080889544, "adamw_lr": 0.0011154863080889545, "grad_norm": 0.25244900584220886, "tokens_per_second": 2917391.149628345, "eta_seconds": 643.7256849288941, "data_wait_seconds": 1.5139579772949219e-05}
|
| 2684 |
+
{"step": 26830, "total_steps": 28611, "tokens": 28133294080, "loss": 2.725316643714905, "ce_loss": 2.724480628967285, "z_loss": 8.36021339893341, "muon_lr": 0.01104879162252515, "adamw_lr": 0.001104879162252515, "grad_norm": 0.28434130549430847, "tokens_per_second": 2607018.6810675953, "eta_seconds": 716.3408032178879, "data_wait_seconds": 1.6450881958007812e-05}
|
| 2685 |
+
{"step": 26840, "total_steps": 28611, "tokens": 28143779840, "loss": 2.6960983276367188, "ce_loss": 2.695211708545685, "z_loss": 8.866051197052002, "muon_lr": 0.010942932055474744, "adamw_lr": 0.0010942932055474745, "grad_norm": 0.2631073594093323, "tokens_per_second": 4092567.454163357, "eta_seconds": 453.7562585830688, "data_wait_seconds": 1.728534698486328e-05}
|
| 2686 |
+
{"step": 26850, "total_steps": 28611, "tokens": 28154265600, "loss": 2.7066224813461304, "ce_loss": 2.705885648727417, "z_loss": 7.367802619934082, "muon_lr": 0.01083729005666564, "adamw_lr": 0.001083729005666564, "grad_norm": 0.2541699707508087, "tokens_per_second": 2285853.6939711897, "eta_seconds": 807.8130025863647, "data_wait_seconds": 1.919269561767578e-05}
|
| 2687 |
+
{"step": 26860, "total_steps": 28611, "tokens": 28164751360, "loss": 2.71136474609375, "ce_loss": 2.710460603237152, "z_loss": 9.041100263595581, "muon_lr": 0.010731871291357636, "adamw_lr": 0.0010731871291357637, "grad_norm": 0.24939526617527008, "tokens_per_second": 2801896.5486159907, "eta_seconds": 655.2906376600265, "data_wait_seconds": 1.6748905181884766e-05}
|
| 2688 |
+
{"step": 26870, "total_steps": 28611, "tokens": 28175237120, "loss": 2.7513043880462646, "ce_loss": 2.750434637069702, "z_loss": 8.697539806365967, "muon_lr": 0.010626681412839173, "adamw_lr": 0.0010626681412839174, "grad_norm": 0.22910821437835693, "tokens_per_second": 4854788.938245265, "eta_seconds": 376.035053062439, "data_wait_seconds": 1.6629695892333984e-05}
|
| 2689 |
+
{"step": 26880, "total_steps": 28611, "tokens": 28185722880, "loss": 2.717057228088379, "ce_loss": 2.7162771821022034, "z_loss": 7.80020272731781, "muon_lr": 0.010521726062124204, "adamw_lr": 0.0010521726062124204, "grad_norm": 0.2704777717590332, "tokens_per_second": 2779829.240842225, "eta_seconds": 652.9484003305436, "data_wait_seconds": 1.5139579772949219e-05}
|
| 2690 |
+
{"step": 26890, "total_steps": 28611, "tokens": 28196208640, "loss": 2.752108871936798, "ce_loss": 2.7512645721435547, "z_loss": 8.442891836166382, "muon_lr": 0.010417010867649677, "adamw_lr": 0.0010417010867649677, "grad_norm": 0.24187014997005463, "tokens_per_second": 3917477.4127072254, "eta_seconds": 460.6534016370773, "data_wait_seconds": 1.3589859008789062e-05}
|
| 2691 |
+
{"step": 26900, "total_steps": 28611, "tokens": 28206694400, "loss": 2.662931799888611, "ce_loss": 2.662174880504608, "z_loss": 7.569468855857849, "muon_lr": 0.010312541444973657, "adamw_lr": 0.0010312541444973656, "grad_norm": 0.2511635720729828, "tokens_per_second": 2824628.4645191752, "eta_seconds": 635.1679728984833, "data_wait_seconds": 1.6808509826660156e-05}
|
| 2692 |
+
{"step": 26910, "total_steps": 28611, "tokens": 28217180160, "loss": 2.7139148712158203, "ce_loss": 2.7131687998771667, "z_loss": 7.46078634262085, "muon_lr": 0.010208323396474248, "adamw_lr": 0.001020832339647425, "grad_norm": 0.2893194556236267, "tokens_per_second": 4484737.381638549, "eta_seconds": 397.71064038276677, "data_wait_seconds": 1.3887882232666016e-05}
|
| 2693 |
+
{"step": 26920, "total_steps": 28611, "tokens": 28227665920, "loss": 2.740458369255066, "ce_loss": 2.7395675778388977, "z_loss": 8.907934665679932, "muon_lr": 0.010104362311049109, "adamw_lr": 0.0010104362311049108, "grad_norm": 0.23631669580936432, "tokens_per_second": 2884867.6524247457, "eta_seconds": 614.6354805946349, "data_wait_seconds": 1.3828277587890625e-05}
|
| 2694 |
+
{"step": 26930, "total_steps": 28611, "tokens": 28238151680, "loss": 2.6791581511497498, "ce_loss": 2.6782453060150146, "z_loss": 9.128456830978394, "muon_lr": 0.01000066376381573, "adamw_lr": 0.001000066376381573, "grad_norm": 0.2421228140592575, "tokens_per_second": 3195216.750883979, "eta_seconds": 551.6546742916107, "data_wait_seconds": 0.16654682159423828}
|
| 2695 |
+
{"step": 26940, "total_steps": 28611, "tokens": 28248637440, "loss": 2.7287579774856567, "ce_loss": 2.7279706597328186, "z_loss": 7.872941255569458, "muon_lr": 0.009897233315812503, "adamw_lr": 0.0009897233315812504, "grad_norm": 0.24025492370128632, "tokens_per_second": 3870006.9023227803, "eta_seconds": 452.7564265966415, "data_wait_seconds": 1.436471939086914e-05}
|
| 2696 |
+
{"step": 26950, "total_steps": 28611, "tokens": 28259123200, "loss": 2.6945952773094177, "ce_loss": 2.6938775777816772, "z_loss": 7.177288293838501, "muon_lr": 0.009794076513700456, "adamw_lr": 0.0009794076513700456, "grad_norm": 0.24076420068740845, "tokens_per_second": 2868176.7875807565, "eta_seconds": 607.2445546388626, "data_wait_seconds": 2.0325183868408203e-05}
|
| 2697 |
+
{"step": 26960, "total_steps": 28611, "tokens": 28269608960, "loss": 2.691897928714752, "ce_loss": 2.691161632537842, "z_loss": 7.362866759300232, "muon_lr": 0.009691198889465825, "adamw_lr": 0.0009691198889465825, "grad_norm": 0.2604213356971741, "tokens_per_second": 3932169.72658656, "eta_seconds": 440.2655776262283, "data_wait_seconds": 1.4960765838623047e-05}
|
| 2698 |
+
{"step": 26970, "total_steps": 28611, "tokens": 28280094720, "loss": 2.7018763422966003, "ce_loss": 2.7010497450828552, "z_loss": 8.265871524810791, "muon_lr": 0.009588605960123371, "adamw_lr": 0.0009588605960123372, "grad_norm": 0.262095183134079, "tokens_per_second": 2800021.9206062756, "eta_seconds": 614.535623216629, "data_wait_seconds": 1.5497207641601562e-05}
|
| 2699 |
+
{"step": 26980, "total_steps": 28611, "tokens": 28290580480, "loss": 2.652819335460663, "ce_loss": 2.651951014995575, "z_loss": 8.682990312576294, "muon_lr": 0.009486303227420551, "adamw_lr": 0.0009486303227420551, "grad_norm": 0.2705848217010498, "tokens_per_second": 2990300.3996979, "eta_seconds": 571.9249665260315, "data_wait_seconds": 1.6868114471435547e-05}
|
| 2700 |
+
{"step": 26990, "total_steps": 28611, "tokens": 28301066240, "loss": 2.725966215133667, "ce_loss": 2.7251270413398743, "z_loss": 8.391850233078003, "muon_lr": 0.009384296177542445, "adamw_lr": 0.0009384296177542445, "grad_norm": 0.23422589898109436, "tokens_per_second": 2879922.647002028, "eta_seconds": 590.203940987587, "data_wait_seconds": 1.4424324035644531e-05}
|
| 2701 |
+
{"step": 27000, "total_steps": 28611, "tokens": 28311552000, "loss": 2.7237330079078674, "ce_loss": 2.7228946685791016, "z_loss": 8.383532285690308, "muon_lr": 0.009282590280817559, "adamw_lr": 0.0009282590280817559, "grad_norm": 0.25518983602523804, "tokens_per_second": 2823171.762767752, "eta_seconds": 598.3539359092713, "data_wait_seconds": 1.7464160919189453e-05}
|
| 2702 |
+
{"step": 27010, "total_steps": 28611, "tokens": 28322037760, "loss": 2.6928099393844604, "ce_loss": 2.6918818950653076, "z_loss": 9.280122995376587, "muon_lr": 0.009181190991424473, "adamw_lr": 0.0009181190991424472, "grad_norm": 0.2466496378183365, "tokens_per_second": 3153866.853083708, "eta_seconds": 532.2894891262055, "data_wait_seconds": 1.8656253814697266e-05}
|
| 2703 |
+
{"step": 27020, "total_steps": 28611, "tokens": 28332523520, "loss": 2.6607592701911926, "ce_loss": 2.659822940826416, "z_loss": 9.363300085067749, "muon_lr": 0.009080103747099348, "adamw_lr": 0.000908010374709935, "grad_norm": 0.24665901064872742, "tokens_per_second": 2691171.6802542475, "eta_seconds": 619.9100667715073, "data_wait_seconds": 1.5616416931152344e-05}
|
| 2704 |
+
{"step": 27030, "total_steps": 28611, "tokens": 28343009280, "loss": 2.706849694252014, "ce_loss": 2.7059892416000366, "z_loss": 8.605021715164185, "muon_lr": 0.00897933396884432, "adamw_lr": 0.000897933396884432, "grad_norm": 0.2579227685928345, "tokens_per_second": 4285497.351267141, "eta_seconds": 386.8392674446106, "data_wait_seconds": 1.2278556823730469e-05}
|
| 2705 |
+
{"step": 27040, "total_steps": 28611, "tokens": 28353495040, "loss": 2.666601598262787, "ce_loss": 2.665832757949829, "z_loss": 7.688785910606384, "muon_lr": 0.008878887060636763, "adamw_lr": 0.0008878887060636764, "grad_norm": 0.2448212057352066, "tokens_per_second": 2906384.2973272386, "eta_seconds": 566.7911492347718, "data_wait_seconds": 1.4483928680419922e-05}
|
| 2706 |
+
{"step": 27050, "total_steps": 28611, "tokens": 28363980800, "loss": 2.6876989603042603, "ce_loss": 2.6868178844451904, "z_loss": 8.811087608337402, "muon_lr": 0.008778768409139532, "adamw_lr": 0.0008778768409139534, "grad_norm": 0.23983736336231232, "tokens_per_second": 2860038.685616076, "eta_seconds": 572.3094391107559, "data_wait_seconds": 0.2468532919883728}
|
| 2707 |
+
{"step": 27060, "total_steps": 28611, "tokens": 28374466560, "loss": 2.677799105644226, "ce_loss": 2.6769062280654907, "z_loss": 8.929126739501953, "muon_lr": 0.008678983383412065, "adamw_lr": 0.0008678983383412066, "grad_norm": 0.27875345945358276, "tokens_per_second": 4142292.66325975, "eta_seconds": 392.61865546703336, "data_wait_seconds": 1.627206802368164e-05}
|
| 2708 |
+
{"step": 27070, "total_steps": 28611, "tokens": 28384952320, "loss": 2.699636220932007, "ce_loss": 2.698851525783539, "z_loss": 7.847413778305054, "muon_lr": 0.008579537334622455, "adamw_lr": 0.0008579537334622455, "grad_norm": 0.23739251494407654, "tokens_per_second": 2822413.183382079, "eta_seconds": 572.508527636528, "data_wait_seconds": 1.531839370727539e-05}
|
| 2709 |
+
{"step": 27080, "total_steps": 28611, "tokens": 28395438080, "loss": 2.6986940503120422, "ce_loss": 2.6978657245635986, "z_loss": 8.282936096191406, "muon_lr": 0.008480435595760493, "adamw_lr": 0.0008480435595760494, "grad_norm": 0.21601000428199768, "tokens_per_second": 4012617.725568681, "eta_seconds": 400.08043770790096, "data_wait_seconds": 1.5795230865478516e-05}
|
| 2710 |
+
{"step": 27090, "total_steps": 28611, "tokens": 28405923840, "loss": 2.694196105003357, "ce_loss": 2.6933670043945312, "z_loss": 8.291026830673218, "muon_lr": 0.008381683481351676, "adamw_lr": 0.0008381683481351676, "grad_norm": 0.2615378499031067, "tokens_per_second": 2323365.6004288723, "eta_seconds": 686.4542092323304, "data_wait_seconds": 0.2574809193611145}
|
| 2711 |
+
{"step": 27100, "total_steps": 28611, "tokens": 28416409600, "loss": 2.691493272781372, "ce_loss": 2.6907359957695007, "z_loss": 7.5731401443481445, "muon_lr": 0.008283286287172219, "adamw_lr": 0.0008283286287172219, "grad_norm": 0.26692995429039, "tokens_per_second": 2921653.10081171, "eta_seconds": 542.2951600790024, "data_wait_seconds": 2.0742416381835938e-05}
|
| 2712 |
+
{"step": 27110, "total_steps": 28611, "tokens": 28426895360, "loss": 2.684956729412079, "ce_loss": 2.6842401027679443, "z_loss": 7.166383862495422, "muon_lr": 0.008185249289965005, "adamw_lr": 0.0008185249289965005, "grad_norm": 0.22664567828178406, "tokens_per_second": 3045916.4001776557, "eta_seconds": 516.7287506341934, "data_wait_seconds": 1.5974044799804688e-05}
|
| 2713 |
+
{"step": 27120, "total_steps": 28611, "tokens": 28437381120, "loss": 2.7204118371009827, "ce_loss": 2.7196083068847656, "z_loss": 8.035340785980225, "muon_lr": 0.008087577747156675, "adamw_lr": 0.0008087577747156676, "grad_norm": 0.22383922338485718, "tokens_per_second": 3092123.213060293, "eta_seconds": 505.6159500360489, "data_wait_seconds": 1.2755393981933594e-05}
|
| 2714 |
+
{"step": 27130, "total_steps": 28611, "tokens": 28447866880, "loss": 2.683615982532501, "ce_loss": 2.6827744245529175, "z_loss": 8.414923191070557, "muon_lr": 0.007990276896575653, "adamw_lr": 0.0007990276896575654, "grad_norm": 0.2447928935289383, "tokens_per_second": 2762382.074668948, "eta_seconds": 562.1746065616608, "data_wait_seconds": 1.8656253814697266e-05}
|
| 2715 |
+
{"step": 27140, "total_steps": 28611, "tokens": 28458352640, "loss": 2.692379415035248, "ce_loss": 2.6915243268013, "z_loss": 8.550821542739868, "muon_lr": 0.007893351956171264, "adamw_lr": 0.0007893351956171264, "grad_norm": 0.1944432407617569, "tokens_per_second": 2930372.8071102165, "eta_seconds": 526.3682806015015, "data_wait_seconds": 0.2534317374229431}
|
| 2716 |
+
{"step": 27150, "total_steps": 28611, "tokens": 28468838400, "loss": 2.675416648387909, "ce_loss": 2.674636483192444, "z_loss": 7.801908373832703, "muon_lr": 0.007796808123733908, "adamw_lr": 0.0007796808123733908, "grad_norm": 0.2639256715774536, "tokens_per_second": 2930548.34530983, "eta_seconds": 522.7586633920669, "data_wait_seconds": 1.7344951629638672e-05}
|
| 2717 |
+
{"step": 27160, "total_steps": 28611, "tokens": 28479324160, "loss": 2.6452515721321106, "ce_loss": 2.6444205045700073, "z_loss": 8.310530662536621, "muon_lr": 0.007700650576616323, "adamw_lr": 0.0007700650576616324, "grad_norm": 0.2479182332754135, "tokens_per_second": 2875148.1186407716, "eta_seconds": 529.1844848394394, "data_wait_seconds": 0.2704170346260071}
|
| 2718 |
+
{"step": 27170, "total_steps": 28611, "tokens": 28489809920, "loss": 2.6768152117729187, "ce_loss": 2.675935387611389, "z_loss": 8.798644781112671, "muon_lr": 0.007604884471455939, "adamw_lr": 0.0007604884471455939, "grad_norm": 0.21416516602039337, "tokens_per_second": 2836244.2326789405, "eta_seconds": 532.7460867404938, "data_wait_seconds": 1.823902130126953e-05}
|
| 2719 |
+
{"step": 27180, "total_steps": 28611, "tokens": 28500295680, "loss": 2.6820724606513977, "ce_loss": 2.6812285780906677, "z_loss": 8.438706636428833, "muon_lr": 0.007509514943898339, "adamw_lr": 0.000750951494389834, "grad_norm": 0.25333380699157715, "tokens_per_second": 3079304.061609515, "eta_seconds": 487.2894088983536, "data_wait_seconds": 1.5437602996826172e-05}
|