Save 65% checkpoint at 19,501,416,448 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": 65,
|
| 54 |
+
"step": 18598,
|
| 55 |
"total_steps": 28611,
|
| 56 |
+
"tokens_seen": 19501416448,
|
| 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": 5967.757341623306
|
| 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:ca4bb1a4301a74641074569286de94db41b9faadcfe6251f5b5e4964bf9d90bf
|
| 3 |
size 12811532
|
training_metrics.jsonl
CHANGED
|
@@ -1715,3 +1715,146 @@
|
|
| 1715 |
{"step": 17140, "total_steps": 28611, "tokens": 17972592640, "loss": 2.818785548210144, "ce_loss": 2.817770838737488, "z_loss": 10.146932601928711, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3433619737625122, "tokens_per_second": 3100223.06926733, "eta_seconds": 3879.7902690410615, "data_wait_seconds": 1.627206802368164e-05}
|
| 1716 |
{"step": 17150, "total_steps": 28611, "tokens": 17983078400, "loss": 2.836238384246826, "ce_loss": 2.8351078629493713, "z_loss": 11.305237054824829, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3987787365913391, "tokens_per_second": 2933330.472802118, "eta_seconds": 4096.957246184349, "data_wait_seconds": 1.436471939086914e-05}
|
| 1717 |
{"step": 17160, "total_steps": 28611, "tokens": 17993564160, "loss": 2.7924272418022156, "ce_loss": 2.791376531124115, "z_loss": 10.50710678100586, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3608931005001068, "tokens_per_second": 2899097.453602901, "eta_seconds": 4141.717885708809, "data_wait_seconds": 1.3887882232666016e-05}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1715 |
{"step": 17140, "total_steps": 28611, "tokens": 17972592640, "loss": 2.818785548210144, "ce_loss": 2.817770838737488, "z_loss": 10.146932601928711, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3433619737625122, "tokens_per_second": 3100223.06926733, "eta_seconds": 3879.7902690410615, "data_wait_seconds": 1.627206802368164e-05}
|
| 1716 |
{"step": 17150, "total_steps": 28611, "tokens": 17983078400, "loss": 2.836238384246826, "ce_loss": 2.8351078629493713, "z_loss": 11.305237054824829, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3987787365913391, "tokens_per_second": 2933330.472802118, "eta_seconds": 4096.957246184349, "data_wait_seconds": 1.436471939086914e-05}
|
| 1717 |
{"step": 17160, "total_steps": 28611, "tokens": 17993564160, "loss": 2.7924272418022156, "ce_loss": 2.791376531124115, "z_loss": 10.50710678100586, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3608931005001068, "tokens_per_second": 2899097.453602901, "eta_seconds": 4141.717885708809, "data_wait_seconds": 1.3887882232666016e-05}
|
| 1718 |
+
{"step": 17170, "total_steps": 28611, "tokens": 18004049920, "loss": 2.7713926434516907, "ce_loss": 2.770189881324768, "z_loss": 12.027111768722534, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3103561997413635, "tokens_per_second": 7393083.014866698, "eta_seconds": 1622.7002986272175, "data_wait_seconds": 1.424551010131836e-05}
|
| 1719 |
+
{"step": 17180, "total_steps": 28611, "tokens": 18014535680, "loss": 2.835640013217926, "ce_loss": 2.8345144391059875, "z_loss": 11.255395650863647, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32212135195732117, "tokens_per_second": 3189082.3096513967, "eta_seconds": 3758.5333623170854, "data_wait_seconds": 2.0682811737060547e-05}
|
| 1720 |
+
{"step": 17190, "total_steps": 28611, "tokens": 18025021440, "loss": 2.8401829600334167, "ce_loss": 2.8389649391174316, "z_loss": 12.180311918258667, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3423958420753479, "tokens_per_second": 4129915.078560521, "eta_seconds": 2899.7657986164095, "data_wait_seconds": 2.3543834686279297e-05}
|
| 1721 |
+
{"step": 17200, "total_steps": 28611, "tokens": 18035507200, "loss": 2.8274378180503845, "ce_loss": 2.8263403177261353, "z_loss": 10.974366426467896, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34167230129241943, "tokens_per_second": 2925744.9468595074, "eta_seconds": 4089.659540843964, "data_wait_seconds": 1.4185905456542969e-05}
|
| 1722 |
+
{"step": 17210, "total_steps": 28611, "tokens": 18045992960, "loss": 2.809409022331238, "ce_loss": 2.808490812778473, "z_loss": 9.182373762130737, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2941962778568268, "tokens_per_second": 2926733.2300252235, "eta_seconds": 4084.69581489563, "data_wait_seconds": 1.6629695892333984e-05}
|
| 1723 |
+
{"step": 17220, "total_steps": 28611, "tokens": 18056478720, "loss": 2.7858296036720276, "ce_loss": 2.784666657447815, "z_loss": 11.629342555999756, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.36252591013908386, "tokens_per_second": 4031020.4836586835, "eta_seconds": 2963.103081321716, "data_wait_seconds": 1.6868114471435547e-05}
|
| 1724 |
+
{"step": 17230, "total_steps": 28611, "tokens": 18066964480, "loss": 2.7967474460601807, "ce_loss": 2.7955453395843506, "z_loss": 12.020740985870361, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32354646921157837, "tokens_per_second": 2898359.79553797, "eta_seconds": 4117.447210788727, "data_wait_seconds": 1.519918441772461e-05}
|
| 1725 |
+
{"step": 17240, "total_steps": 28611, "tokens": 18077450240, "loss": 2.8363821506500244, "ce_loss": 2.8352134823799133, "z_loss": 11.686614513397217, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30377787351608276, "tokens_per_second": 3166629.4862388796, "eta_seconds": 3765.3150606393815, "data_wait_seconds": 0.24869853258132935}
|
| 1726 |
+
{"step": 17250, "total_steps": 28611, "tokens": 18087936000, "loss": 2.7984050512313843, "ce_loss": 2.7971081137657166, "z_loss": 12.969021797180176, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28396883606910706, "tokens_per_second": 3960346.2691906597, "eta_seconds": 3008.0379659414293, "data_wait_seconds": 1.3649463653564453e-05}
|
| 1727 |
+
{"step": 17260, "total_steps": 28611, "tokens": 18098421760, "loss": 2.7943369150161743, "ce_loss": 2.793134868144989, "z_loss": 12.021177053451538, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3459072411060333, "tokens_per_second": 2835619.1984889237, "eta_seconds": 4197.4557734489445, "data_wait_seconds": 0.5219045281410217}
|
| 1728 |
+
{"step": 17270, "total_steps": 28611, "tokens": 18108907520, "loss": 2.832614541053772, "ce_loss": 2.8313701152801514, "z_loss": 12.444232940673828, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3108185827732086, "tokens_per_second": 3873064.2686775625, "eta_seconds": 3070.4113309383392, "data_wait_seconds": 1.430511474609375e-05}
|
| 1729 |
+
{"step": 17280, "total_steps": 28611, "tokens": 18119393280, "loss": 2.8218498826026917, "ce_loss": 2.82061505317688, "z_loss": 12.348334789276123, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3017202317714691, "tokens_per_second": 2937685.6606079154, "eta_seconds": 4044.4812783479692, "data_wait_seconds": 1.823902130126953e-05}
|
| 1730 |
+
{"step": 17290, "total_steps": 28611, "tokens": 18129879040, "loss": 2.7851597666740417, "ce_loss": 2.783927083015442, "z_loss": 12.327497243881226, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34909653663635254, "tokens_per_second": 3930756.594810312, "eta_seconds": 3020.0111886024474, "data_wait_seconds": 1.3589859008789062e-05}
|
| 1731 |
+
{"step": 17300, "total_steps": 28611, "tokens": 18140364800, "loss": 2.7878458499908447, "ce_loss": 2.7868353128433228, "z_loss": 10.10496211051941, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29031458497047424, "tokens_per_second": 2931282.748626367, "eta_seconds": 4046.161408877373, "data_wait_seconds": 1.722574234008789e-05}
|
| 1732 |
+
{"step": 17310, "total_steps": 28611, "tokens": 18150850560, "loss": 2.7951478362083435, "ce_loss": 2.794043719768524, "z_loss": 11.041050910949707, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2819560766220093, "tokens_per_second": 4324292.247390949, "eta_seconds": 2740.3229703426364, "data_wait_seconds": 1.531839370727539e-05}
|
| 1733 |
+
{"step": 17320, "total_steps": 28611, "tokens": 18161336320, "loss": 2.7960299253463745, "ce_loss": 2.7949575185775757, "z_loss": 10.724635124206543, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29360082745552063, "tokens_per_second": 2985679.6905353325, "eta_seconds": 3965.41921544075, "data_wait_seconds": 1.519918441772461e-05}
|
| 1734 |
+
{"step": 17330, "total_steps": 28611, "tokens": 18171822080, "loss": 2.811747133731842, "ce_loss": 2.8106241822242737, "z_loss": 11.229665756225586, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3004351854324341, "tokens_per_second": 2998589.907965808, "eta_seconds": 3944.8494856119155, "data_wait_seconds": 1.8537044525146484e-05}
|
| 1735 |
+
{"step": 17340, "total_steps": 28611, "tokens": 18182307840, "loss": 2.7893069982528687, "ce_loss": 2.78803151845932, "z_loss": 12.754926919937134, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2971964180469513, "tokens_per_second": 3828337.450279362, "eta_seconds": 3087.1103317022325, "data_wait_seconds": 1.233816146850586e-05}
|
| 1736 |
+
{"step": 17350, "total_steps": 28611, "tokens": 18192793600, "loss": 2.7683677077293396, "ce_loss": 2.7669745683670044, "z_loss": 13.931695461273193, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30301082134246826, "tokens_per_second": 2773863.4634731202, "eta_seconds": 4256.883762121201, "data_wait_seconds": 2.3066997528076172e-05}
|
| 1737 |
+
{"step": 17360, "total_steps": 28611, "tokens": 18203279360, "loss": 2.7832601070404053, "ce_loss": 2.7823343873023987, "z_loss": 9.257062673568726, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3036210536956787, "tokens_per_second": 4276841.673446851, "eta_seconds": 2758.4674572467807, "data_wait_seconds": 1.3828277587890625e-05}
|
| 1738 |
+
{"step": 17370, "total_steps": 28611, "tokens": 18213765120, "loss": 2.796834707260132, "ce_loss": 2.795678436756134, "z_loss": 11.562764406204224, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33625850081443787, "tokens_per_second": 2877103.458057306, "eta_seconds": 4096.843574738503, "data_wait_seconds": 1.7821788787841797e-05}
|
| 1739 |
+
{"step": 17380, "total_steps": 28611, "tokens": 18224250880, "loss": 2.7966448068618774, "ce_loss": 2.795611798763275, "z_loss": 10.329644918441772, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3354463279247284, "tokens_per_second": 3794340.7213812633, "eta_seconds": 3103.7162766218185, "data_wait_seconds": 1.5020370483398438e-05}
|
| 1740 |
+
{"step": 17390, "total_steps": 28611, "tokens": 18234736640, "loss": 2.768733561038971, "ce_loss": 2.7676842212677, "z_loss": 10.493656158447266, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3264288306236267, "tokens_per_second": 2980908.567733314, "eta_seconds": 3947.1426340818407, "data_wait_seconds": 1.5974044799804688e-05}
|
| 1741 |
+
{"step": 17400, "total_steps": 28611, "tokens": 18245222400, "loss": 2.783950924873352, "ce_loss": 2.7829678654670715, "z_loss": 9.830241441726685, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3476589322090149, "tokens_per_second": 2804740.6574069113, "eta_seconds": 4191.327103614807, "data_wait_seconds": 0.23350822925567627}
|
| 1742 |
+
{"step": 17410, "total_steps": 28611, "tokens": 18255708160, "loss": 2.7455576062202454, "ce_loss": 2.7444527745246887, "z_loss": 11.0477454662323, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31752267479896545, "tokens_per_second": 3039597.7096299836, "eta_seconds": 3864.030999493599, "data_wait_seconds": 1.4126300811767578e-05}
|
| 1743 |
+
{"step": 17420, "total_steps": 28611, "tokens": 18266193920, "loss": 2.777856945991516, "ce_loss": 2.7767372131347656, "z_loss": 11.197433471679688, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3174450695514679, "tokens_per_second": 3004642.602706213, "eta_seconds": 3905.494119477272, "data_wait_seconds": 1.6391277313232422e-05}
|
| 1744 |
+
{"step": 17430, "total_steps": 28611, "tokens": 18276679680, "loss": 2.822231709957123, "ce_loss": 2.8212204575538635, "z_loss": 10.112035751342773, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33362284302711487, "tokens_per_second": 2258404.9652669923, "eta_seconds": 5191.331243205071, "data_wait_seconds": 0.25693368911743164}
|
| 1745 |
+
{"step": 17440, "total_steps": 28611, "tokens": 18287165440, "loss": 2.7810391187667847, "ce_loss": 2.779891848564148, "z_loss": 11.472943305969238, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3368508517742157, "tokens_per_second": 2724211.9557597116, "eta_seconds": 4299.8278717756275, "data_wait_seconds": 2.2649765014648438e-05}
|
| 1746 |
+
{"step": 17450, "total_steps": 28611, "tokens": 18297651200, "loss": 2.791569173336029, "ce_loss": 2.790456712245941, "z_loss": 11.124277830123901, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3090916872024536, "tokens_per_second": 4075119.3809293844, "eta_seconds": 2871.856169605255, "data_wait_seconds": 1.436471939086914e-05}
|
| 1747 |
+
{"step": 17460, "total_steps": 28611, "tokens": 18308136960, "loss": 2.79162061214447, "ce_loss": 2.790742039680481, "z_loss": 8.785392999649048, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30828914046287537, "tokens_per_second": 2975487.0032562227, "eta_seconds": 3929.666290998459, "data_wait_seconds": 1.806020736694336e-05}
|
| 1748 |
+
{"step": 17470, "total_steps": 28611, "tokens": 18318622720, "loss": 2.779526114463806, "ce_loss": 2.7783390283584595, "z_loss": 11.871091842651367, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33750465512275696, "tokens_per_second": 3852809.6094468, "eta_seconds": 3032.121075320244, "data_wait_seconds": 2.1755695343017578e-05}
|
| 1749 |
+
{"step": 17480, "total_steps": 28611, "tokens": 18329108480, "loss": 2.7977691888809204, "ce_loss": 2.7966230511665344, "z_loss": 11.46177077293396, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30010300874710083, "tokens_per_second": 2780817.036316467, "eta_seconds": 4197.219487500191, "data_wait_seconds": 1.722574234008789e-05}
|
| 1750 |
+
{"step": 17490, "total_steps": 28611, "tokens": 18339594240, "loss": 2.8033647537231445, "ce_loss": 2.801982820034027, "z_loss": 13.81897521018982, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37261173129081726, "tokens_per_second": 4172985.3115924173, "eta_seconds": 2794.4535686731338, "data_wait_seconds": 1.7404556274414062e-05}
|
| 1751 |
+
{"step": 17500, "total_steps": 28611, "tokens": 18350080000, "loss": 2.816722333431244, "ce_loss": 2.815569758415222, "z_loss": 11.525304079055786, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3765016198158264, "tokens_per_second": 2675605.27848145, "eta_seconds": 4354.427026176453, "data_wait_seconds": 1.3530254364013672e-05}
|
| 1752 |
+
{"step": 17510, "total_steps": 28611, "tokens": 18360565760, "loss": 2.8054808974266052, "ce_loss": 2.804395854473114, "z_loss": 10.850908041000366, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3063336908817291, "tokens_per_second": 2699335.1782711586, "eta_seconds": 4312.262615513801, "data_wait_seconds": 0.30336254835128784}
|
| 1753 |
+
{"step": 17520, "total_steps": 28611, "tokens": 18371051520, "loss": 2.8181583881378174, "ce_loss": 2.817029297351837, "z_loss": 11.290541172027588, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3236967623233795, "tokens_per_second": 4567298.726948003, "eta_seconds": 2546.3095609188076, "data_wait_seconds": 1.4185905456542969e-05}
|
| 1754 |
+
{"step": 17530, "total_steps": 28611, "tokens": 18381537280, "loss": 2.8120272159576416, "ce_loss": 2.8108994364738464, "z_loss": 11.277864933013916, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37038999795913696, "tokens_per_second": 2864548.3590987986, "eta_seconds": 4056.2312795639036, "data_wait_seconds": 0.26958709955215454}
|
| 1755 |
+
{"step": 17540, "total_steps": 28611, "tokens": 18392023040, "loss": 2.7713441848754883, "ce_loss": 2.7699551582336426, "z_loss": 13.889867305755615, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3145246207714081, "tokens_per_second": 3981187.1534695206, "eta_seconds": 2915.910367560387, "data_wait_seconds": 1.2516975402832031e-05}
|
| 1756 |
+
{"step": 17550, "total_steps": 28611, "tokens": 18402508800, "loss": 2.7792580127716064, "ce_loss": 2.7781991362571716, "z_loss": 10.588834285736084, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2967996895313263, "tokens_per_second": 3078244.329597951, "eta_seconds": 3767.82928647995, "data_wait_seconds": 1.4007091522216797e-05}
|
| 1757 |
+
{"step": 17560, "total_steps": 28611, "tokens": 18412994560, "loss": 2.8398080468177795, "ce_loss": 2.83864164352417, "z_loss": 11.663818597793579, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31533023715019226, "tokens_per_second": 3037724.16437326, "eta_seconds": 3814.6364676237104, "data_wait_seconds": 0.5252720713615417}
|
| 1758 |
+
{"step": 17570, "total_steps": 28611, "tokens": 18423480320, "loss": 2.783795118331909, "ce_loss": 2.7828181385993958, "z_loss": 9.770354509353638, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.317178875207901, "tokens_per_second": 4424184.593683482, "eta_seconds": 2616.8274335861206, "data_wait_seconds": 1.2934207916259766e-05}
|
| 1759 |
+
{"step": 17580, "total_steps": 28611, "tokens": 18433966080, "loss": 2.778396248817444, "ce_loss": 2.7772459983825684, "z_loss": 11.502692699432373, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3379238247871399, "tokens_per_second": 2921641.0674386416, "eta_seconds": 3959.0222032785414, "data_wait_seconds": 1.424551010131836e-05}
|
| 1760 |
+
{"step": 17590, "total_steps": 28611, "tokens": 18444451840, "loss": 2.814911663532257, "ce_loss": 2.8139745593070984, "z_loss": 9.371593713760376, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3123178482055664, "tokens_per_second": 2869460.695265975, "eta_seconds": 4027.361697292328, "data_wait_seconds": 0.2564352750778198}
|
| 1761 |
+
{"step": 17600, "total_steps": 28611, "tokens": 18454937600, "loss": 2.7651020288467407, "ce_loss": 2.763955056667328, "z_loss": 11.470515251159668, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29919546842575073, "tokens_per_second": 4061330.1566125797, "eta_seconds": 2842.8790299654006, "data_wait_seconds": 1.8596649169921875e-05}
|
| 1762 |
+
{"step": 17610, "total_steps": 28611, "tokens": 18465423360, "loss": 2.791638672351837, "ce_loss": 2.7902733087539673, "z_loss": 13.653907537460327, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.4027114510536194, "tokens_per_second": 3144663.5103368815, "eta_seconds": 3668.241304063797, "data_wait_seconds": 1.8775463104248047e-05}
|
| 1763 |
+
{"step": 17620, "total_steps": 28611, "tokens": 18475909120, "loss": 2.7966429591178894, "ce_loss": 2.7955435514450073, "z_loss": 10.99396538734436, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27900126576423645, "tokens_per_second": 3954876.141750686, "eta_seconds": 2914.098546433449, "data_wait_seconds": 1.3232231140136719e-05}
|
| 1764 |
+
{"step": 17630, "total_steps": 28611, "tokens": 18486394880, "loss": 2.7921477556228638, "ce_loss": 2.7911782264709473, "z_loss": 9.69560194015503, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.297717809677124, "tokens_per_second": 2548614.841962923, "eta_seconds": 4517.910225749016, "data_wait_seconds": 1.3947486877441406e-05}
|
| 1765 |
+
{"step": 17640, "total_steps": 28611, "tokens": 18496880640, "loss": 2.7758084535598755, "ce_loss": 2.774768650531769, "z_loss": 10.397369623184204, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28757449984550476, "tokens_per_second": 3103102.788525358, "eta_seconds": 3707.2337205648423, "data_wait_seconds": 0.1900213360786438}
|
| 1766 |
+
{"step": 17650, "total_steps": 28611, "tokens": 18507366400, "loss": 2.805437445640564, "ce_loss": 2.8041303157806396, "z_loss": 13.071166515350342, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3652377128601074, "tokens_per_second": 3407715.3572004153, "eta_seconds": 3372.7704139709476, "data_wait_seconds": 1.7881393432617188e-05}
|
| 1767 |
+
{"step": 17660, "total_steps": 28611, "tokens": 18517852160, "loss": 2.8257921934127808, "ce_loss": 2.824809968471527, "z_loss": 9.8222177028656, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29196369647979736, "tokens_per_second": 4450643.774162677, "eta_seconds": 2580.0662462949754, "data_wait_seconds": 1.2516975402832031e-05}
|
| 1768 |
+
{"step": 17670, "total_steps": 28611, "tokens": 18528337920, "loss": 2.791632354259491, "ce_loss": 2.7906389236450195, "z_loss": 9.934547185897827, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31861063838005066, "tokens_per_second": 2811038.476691477, "eta_seconds": 4081.2212679147724, "data_wait_seconds": 1.4543533325195312e-05}
|
| 1769 |
+
{"step": 17680, "total_steps": 28611, "tokens": 18538823680, "loss": 2.783607304096222, "ce_loss": 2.7825307846069336, "z_loss": 10.765007495880127, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33895421028137207, "tokens_per_second": 3004857.330639512, "eta_seconds": 3814.4853464841844, "data_wait_seconds": 1.8656253814697266e-05}
|
| 1770 |
+
{"step": 17690, "total_steps": 28611, "tokens": 18549309440, "loss": 2.792678117752075, "ce_loss": 2.7916247844696045, "z_loss": 10.534002542495728, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.23568332195281982, "tokens_per_second": 4121792.0544198253, "eta_seconds": 2778.281471943855, "data_wait_seconds": 1.52587890625e-05}
|
| 1771 |
+
{"step": 17700, "total_steps": 28611, "tokens": 18559795200, "loss": 2.7975831627845764, "ce_loss": 2.796238601207733, "z_loss": 13.445723295211792, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3077761232852936, "tokens_per_second": 4185646.3077803184, "eta_seconds": 2733.392144179344, "data_wait_seconds": 1.621246337890625e-05}
|
| 1772 |
+
{"step": 17710, "total_steps": 28611, "tokens": 18570280960, "loss": 2.784689426422119, "ce_loss": 2.7836727499961853, "z_loss": 10.167229413986206, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27537834644317627, "tokens_per_second": 2866737.0574865304, "eta_seconds": 3987.295223379135, "data_wait_seconds": 1.4662742614746094e-05}
|
| 1773 |
+
{"step": 17720, "total_steps": 28611, "tokens": 18580766720, "loss": 2.8324652314186096, "ce_loss": 2.83109849691391, "z_loss": 13.667036771774292, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27593111991882324, "tokens_per_second": 2874204.5037641684, "eta_seconds": 3973.2876352548597, "data_wait_seconds": 1.531839370727539e-05}
|
| 1774 |
+
{"step": 17730, "total_steps": 28611, "tokens": 18591252480, "loss": 2.7947444915771484, "ce_loss": 2.7936132550239563, "z_loss": 11.311609506607056, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3279320001602173, "tokens_per_second": 4049050.357762683, "eta_seconds": 2817.8349113702775, "data_wait_seconds": 1.3172626495361328e-05}
|
| 1775 |
+
{"step": 17740, "total_steps": 28611, "tokens": 18601738240, "loss": 2.7845539450645447, "ce_loss": 2.7833778262138367, "z_loss": 11.760954141616821, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3134772777557373, "tokens_per_second": 3052534.9105550097, "eta_seconds": 3734.2962586879735, "data_wait_seconds": 0.2550206184387207}
|
| 1776 |
+
{"step": 17750, "total_steps": 28611, "tokens": 18612224000, "loss": 2.800295114517212, "ce_loss": 2.799000382423401, "z_loss": 12.947115898132324, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2988283336162567, "tokens_per_second": 3847128.1431802325, "eta_seconds": 2960.28193295002, "data_wait_seconds": 1.3887882232666016e-05}
|
| 1777 |
+
{"step": 17760, "total_steps": 28611, "tokens": 18622709760, "loss": 2.7714059948921204, "ce_loss": 2.770354986190796, "z_loss": 10.509808540344238, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29244324564933777, "tokens_per_second": 2655383.105061555, "eta_seconds": 4284.917740988732, "data_wait_seconds": 1.6033649444580078e-05}
|
| 1778 |
+
{"step": 17770, "total_steps": 28611, "tokens": 18633195520, "loss": 2.77790904045105, "ce_loss": 2.776586949825287, "z_loss": 13.22097373008728, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24988558888435364, "tokens_per_second": 4169701.5614637183, "eta_seconds": 2726.2412545442585, "data_wait_seconds": 1.5139579772949219e-05}
|
| 1779 |
+
{"step": 17780, "total_steps": 28611, "tokens": 18643681280, "loss": 2.793402850627899, "ce_loss": 2.7923583388328552, "z_loss": 10.444962501525879, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29226186871528625, "tokens_per_second": 3206382.5666084667, "eta_seconds": 3542.037302184105, "data_wait_seconds": 1.2934207916259766e-05}
|
| 1780 |
+
{"step": 17790, "total_steps": 28611, "tokens": 18654167040, "loss": 2.7792463302612305, "ce_loss": 2.7781943678855896, "z_loss": 10.519270896911621, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2943674921989441, "tokens_per_second": 2929683.744786344, "eta_seconds": 3872.991723489761, "data_wait_seconds": 1.609325408935547e-05}
|
| 1781 |
+
{"step": 17800, "total_steps": 28611, "tokens": 18664652800, "loss": 2.830414831638336, "ce_loss": 2.829355001449585, "z_loss": 10.598184823989868, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33967843651771545, "tokens_per_second": 4098711.4647650137, "eta_seconds": 2765.7851091623306, "data_wait_seconds": 1.6510486602783203e-05}
|
| 1782 |
+
{"step": 17810, "total_steps": 28611, "tokens": 18675138560, "loss": 2.771609127521515, "ce_loss": 2.770565390586853, "z_loss": 10.4382963180542, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3191136419773102, "tokens_per_second": 2684543.3169519734, "eta_seconds": 4218.8439666748045, "data_wait_seconds": 1.5020370483398438e-05}
|
| 1783 |
+
{"step": 17820, "total_steps": 28611, "tokens": 18685624320, "loss": 2.84018737077713, "ce_loss": 2.8392650485038757, "z_loss": 9.222946643829346, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3749561309814453, "tokens_per_second": 2713601.6338596647, "eta_seconds": 4169.802772378921, "data_wait_seconds": 0.28693902492523193}
|
| 1784 |
+
{"step": 17830, "total_steps": 28611, "tokens": 18696110080, "loss": 2.8104350566864014, "ce_loss": 2.8090758323669434, "z_loss": 13.591564655303955, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33339446783065796, "tokens_per_second": 3583473.5265781255, "eta_seconds": 3154.6759790897368, "data_wait_seconds": 1.4483928680419922e-05}
|
| 1785 |
+
{"step": 17840, "total_steps": 28611, "tokens": 18706595840, "loss": 2.794906258583069, "ce_loss": 2.793880522251129, "z_loss": 10.257548093795776, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27929800748825073, "tokens_per_second": 2923994.117172207, "eta_seconds": 3862.5974073171615, "data_wait_seconds": 1.4066696166992188e-05}
|
| 1786 |
+
{"step": 17850, "total_steps": 28611, "tokens": 18717081600, "loss": 2.7864806056022644, "ce_loss": 2.785412609577179, "z_loss": 10.68008041381836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27941155433654785, "tokens_per_second": 2268463.1820167135, "eta_seconds": 4974.172129154205, "data_wait_seconds": 0.28006285429000854}
|
| 1787 |
+
{"step": 17860, "total_steps": 28611, "tokens": 18727567360, "loss": 2.7836955189704895, "ce_loss": 2.782417356967926, "z_loss": 12.781760692596436, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3245677649974823, "tokens_per_second": 3984767.54101762, "eta_seconds": 2829.0836190462114, "data_wait_seconds": 1.3887882232666016e-05}
|
| 1788 |
+
{"step": 17870, "total_steps": 28611, "tokens": 18738053120, "loss": 2.787566304206848, "ce_loss": 2.7864420413970947, "z_loss": 11.242785453796387, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33699801564216614, "tokens_per_second": 2886159.3527039085, "eta_seconds": 3902.3329759836197, "data_wait_seconds": 0.29741859436035156}
|
| 1789 |
+
{"step": 17880, "total_steps": 28611, "tokens": 18748538880, "loss": 2.807584047317505, "ce_loss": 2.806246757507324, "z_loss": 13.37309217453003, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3129070997238159, "tokens_per_second": 4100146.282782178, "eta_seconds": 2744.35795211792, "data_wait_seconds": 1.3649463653564453e-05}
|
| 1790 |
+
{"step": 17890, "total_steps": 28611, "tokens": 18759024640, "loss": 2.7903242111206055, "ce_loss": 2.789270758628845, "z_loss": 10.534469604492188, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.291187584400177, "tokens_per_second": 2871263.3974416517, "eta_seconds": 3915.274128460884, "data_wait_seconds": 1.33514404296875e-05}
|
| 1791 |
+
{"step": 17900, "total_steps": 28611, "tokens": 18769510400, "loss": 2.7894200682640076, "ce_loss": 2.788219630718231, "z_loss": 12.00386381149292, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3008941113948822, "tokens_per_second": 3016332.0590555635, "eta_seconds": 3723.4950649023053, "data_wait_seconds": 1.6808509826660156e-05}
|
| 1792 |
+
{"step": 17910, "total_steps": 28611, "tokens": 18779996160, "loss": 2.775642156600952, "ce_loss": 2.774586796760559, "z_loss": 10.553691387176514, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3976791799068451, "tokens_per_second": 4097293.682393972, "eta_seconds": 2738.5910422325132, "data_wait_seconds": 1.7404556274414062e-05}
|
| 1793 |
+
{"step": 17920, "total_steps": 28611, "tokens": 18790481920, "loss": 2.7946059703826904, "ce_loss": 2.793358266353607, "z_loss": 12.477275848388672, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25549501180648804, "tokens_per_second": 2907643.631054469, "eta_seconds": 3855.4676702022557, "data_wait_seconds": 1.710653305053711e-05}
|
| 1794 |
+
{"step": 17930, "total_steps": 28611, "tokens": 18800967680, "loss": 2.8184205889701843, "ce_loss": 2.8173428773880005, "z_loss": 10.777398347854614, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.36796292662620544, "tokens_per_second": 4315102.050990074, "eta_seconds": 2595.498350596428, "data_wait_seconds": 1.3768672943115234e-05}
|
| 1795 |
+
{"step": 17940, "total_steps": 28611, "tokens": 18811453440, "loss": 2.8304284811019897, "ce_loss": 2.829286754131317, "z_loss": 11.417613983154297, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35259348154067993, "tokens_per_second": 2816881.0418378627, "eta_seconds": 3972.2495660305026, "data_wait_seconds": 1.6927719116210938e-05}
|
| 1796 |
+
{"step": 17950, "total_steps": 28611, "tokens": 18821939200, "loss": 2.808678984642029, "ce_loss": 2.8074779510498047, "z_loss": 12.010610342025757, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3167878985404968, "tokens_per_second": 2767590.729577781, "eta_seconds": 4039.2058755397798, "data_wait_seconds": 0.27222657203674316}
|
| 1797 |
+
{"step": 17960, "total_steps": 28611, "tokens": 18832424960, "loss": 2.7540555596351624, "ce_loss": 2.7527527809143066, "z_loss": 13.027109622955322, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29204386472702026, "tokens_per_second": 4249420.069576513, "eta_seconds": 2628.213448691368, "data_wait_seconds": 0.3014504313468933}
|
| 1798 |
+
{"step": 17970, "total_steps": 28611, "tokens": 18842910720, "loss": 2.8144251704216003, "ce_loss": 2.8132230639457703, "z_loss": 12.021289348602295, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31203097105026245, "tokens_per_second": 4404818.920193798, "eta_seconds": 2533.1114441156387, "data_wait_seconds": 1.4722347259521484e-05}
|
| 1799 |
+
{"step": 17980, "total_steps": 28611, "tokens": 18853396480, "loss": 2.798752546310425, "ce_loss": 2.7976787090301514, "z_loss": 10.738332748413086, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2995471656322479, "tokens_per_second": 2738324.147843533, "eta_seconds": 4070.8881980896, "data_wait_seconds": 1.5735626220703125e-05}
|
| 1800 |
+
{"step": 17990, "total_steps": 28611, "tokens": 18863882240, "loss": 2.769083619117737, "ce_loss": 2.768088638782501, "z_loss": 9.949488639831543, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27584871649742126, "tokens_per_second": 3062828.698599185, "eta_seconds": 3636.1568967580797, "data_wait_seconds": 0.20074784755706787}
|
| 1801 |
+
{"step": 18000, "total_steps": 28611, "tokens": 18874368000, "loss": 2.737674832344055, "ce_loss": 2.7365384697914124, "z_loss": 11.363185405731201, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.39263397455215454, "tokens_per_second": 3623491.2051795437, "eta_seconds": 3070.64080080986, "data_wait_seconds": 1.3530254364013672e-05}
|
| 1802 |
+
{"step": 18010, "total_steps": 28611, "tokens": 18884853760, "loss": 2.78309166431427, "ce_loss": 2.781924307346344, "z_loss": 11.67392611503601, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31071391701698303, "tokens_per_second": 2954889.6396698677, "eta_seconds": 3761.8847170352933, "data_wait_seconds": 1.5676021575927734e-05}
|
| 1803 |
+
{"step": 18020, "total_steps": 28611, "tokens": 18895339520, "loss": 2.7991467714309692, "ce_loss": 2.7976791858673096, "z_loss": 14.675938606262207, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3982604742050171, "tokens_per_second": 2855718.776817289, "eta_seconds": 3888.8522588968276, "data_wait_seconds": 1.4007091522216797e-05}
|
| 1804 |
+
{"step": 18030, "total_steps": 28611, "tokens": 18905825280, "loss": 2.80088347196579, "ce_loss": 2.7998745441436768, "z_loss": 10.089646100997925, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3332854211330414, "tokens_per_second": 2897085.0159670645, "eta_seconds": 3829.705581593513, "data_wait_seconds": 1.7642974853515625e-05}
|
| 1805 |
+
{"step": 18040, "total_steps": 28611, "tokens": 18916311040, "loss": 2.791243016719818, "ce_loss": 2.790112853050232, "z_loss": 11.301141500473022, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.295768141746521, "tokens_per_second": 3220362.5154821794, "eta_seconds": 3442.0028312683107, "data_wait_seconds": 1.4483928680419922e-05}
|
| 1806 |
+
{"step": 18050, "total_steps": 28611, "tokens": 18926796800, "loss": 2.7943021655082703, "ce_loss": 2.793233096599579, "z_loss": 10.690500974655151, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31558290123939514, "tokens_per_second": 2821551.104758376, "eta_seconds": 3924.7955202102657, "data_wait_seconds": 1.4483928680419922e-05}
|
| 1807 |
+
{"step": 18060, "total_steps": 28611, "tokens": 18937282560, "loss": 2.8059451580047607, "ce_loss": 2.8048292994499207, "z_loss": 11.157770156860352, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35789790749549866, "tokens_per_second": 3212869.8924211334, "eta_seconds": 3443.5024593114854, "data_wait_seconds": 1.5974044799804688e-05}
|
| 1808 |
+
{"step": 18070, "total_steps": 28611, "tokens": 18947768320, "loss": 2.802671253681183, "ce_loss": 2.801484704017639, "z_loss": 11.865301370620728, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32780376076698303, "tokens_per_second": 2633991.0562060676, "eta_seconds": 4196.308711814881, "data_wait_seconds": 0.6267060041427612}
|
| 1809 |
+
{"step": 18080, "total_steps": 28611, "tokens": 18958254080, "loss": 2.7885547280311584, "ce_loss": 2.7873117327690125, "z_loss": 12.429437398910522, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26937568187713623, "tokens_per_second": 4439392.795908696, "eta_seconds": 2487.401850581169, "data_wait_seconds": 1.7404556274414062e-05}
|
| 1810 |
+
{"step": 18090, "total_steps": 28611, "tokens": 18968739840, "loss": 2.8082982301712036, "ce_loss": 2.8071512579917908, "z_loss": 11.469364166259766, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2910842299461365, "tokens_per_second": 2849857.4575108113, "eta_seconds": 3871.0946987628936, "data_wait_seconds": 0.2586161494255066}
|
| 1811 |
+
{"step": 18100, "total_steps": 28611, "tokens": 18979225600, "loss": 2.801092505455017, "ce_loss": 2.799904227256775, "z_loss": 11.882655382156372, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35987600684165955, "tokens_per_second": 4139067.9281850136, "eta_seconds": 2662.817457270622, "data_wait_seconds": 1.2874603271484375e-05}
|
| 1812 |
+
{"step": 18110, "total_steps": 28611, "tokens": 18989711360, "loss": 2.7806817293167114, "ce_loss": 2.779446840286255, "z_loss": 12.349140644073486, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2764423191547394, "tokens_per_second": 2956493.825714986, "eta_seconds": 3724.3766519069673, "data_wait_seconds": 1.8656253814697266e-05}
|
| 1813 |
+
{"step": 18120, "total_steps": 28611, "tokens": 19000197120, "loss": 2.8193591833114624, "ce_loss": 2.81820946931839, "z_loss": 11.496903419494629, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31940028071403503, "tokens_per_second": 4255267.396515033, "eta_seconds": 2585.174982190132, "data_wait_seconds": 1.0907649993896484e-05}
|
| 1814 |
+
{"step": 18130, "total_steps": 28611, "tokens": 19010682880, "loss": 2.834523320198059, "ce_loss": 2.8335254788398743, "z_loss": 9.979042530059814, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33283472061157227, "tokens_per_second": 1237651.4439223895, "eta_seconds": 8879.822433018684, "data_wait_seconds": 1.4722347259521484e-05}
|
| 1815 |
+
{"step": 18140, "total_steps": 28611, "tokens": 19021168640, "loss": 2.816779851913452, "ce_loss": 2.8158218264579773, "z_loss": 9.579674482345581, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33096951246261597, "tokens_per_second": 3739872.0405037976, "eta_seconds": 2935.8328779935837, "data_wait_seconds": 1.800060272216797e-05}
|
| 1816 |
+
{"step": 18150, "total_steps": 28611, "tokens": 19031654400, "loss": 2.8099769353866577, "ce_loss": 2.808683454990387, "z_loss": 12.935151815414429, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3216296136379242, "tokens_per_second": 2869138.1600042325, "eta_seconds": 3823.1527811765673, "data_wait_seconds": 1.5556812286376953e-05}
|
| 1817 |
+
{"step": 18160, "total_steps": 28611, "tokens": 19042140160, "loss": 2.8638258576393127, "ce_loss": 2.8626691102981567, "z_loss": 11.567466259002686, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3555130660533905, "tokens_per_second": 2997498.983024371, "eta_seconds": 3655.937112259865, "data_wait_seconds": 0.23781412839889526}
|
| 1818 |
+
{"step": 18170, "total_steps": 28611, "tokens": 19052625920, "loss": 2.8065130710601807, "ce_loss": 2.805428147315979, "z_loss": 10.849522829055786, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32101625204086304, "tokens_per_second": 3904012.472028641, "eta_seconds": 2804.340942668915, "data_wait_seconds": 1.5914440155029297e-05}
|
| 1819 |
+
{"step": 18180, "total_steps": 28611, "tokens": 19063111680, "loss": 2.822359621524811, "ce_loss": 2.8212558031082153, "z_loss": 11.038644790649414, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3291322886943817, "tokens_per_second": 2991478.4651905233, "eta_seconds": 3656.284470462799, "data_wait_seconds": 0.27349066734313965}
|
| 1820 |
+
{"step": 18190, "total_steps": 28611, "tokens": 19073597440, "loss": 2.78254234790802, "ce_loss": 2.781357526779175, "z_loss": 11.848195552825928, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3322095572948456, "tokens_per_second": 4153284.328405539, "eta_seconds": 2630.9806004047396, "data_wait_seconds": 1.4722347259521484e-05}
|
| 1821 |
+
{"step": 18200, "total_steps": 28611, "tokens": 19084083200, "loss": 2.826706647872925, "ce_loss": 2.8254987001419067, "z_loss": 12.07970142364502, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32456183433532715, "tokens_per_second": 2994423.412510416, "eta_seconds": 3645.685072588921, "data_wait_seconds": 1.5556812286376953e-05}
|
| 1822 |
+
{"step": 18210, "total_steps": 28611, "tokens": 19094568960, "loss": 2.73382967710495, "ce_loss": 2.7323790788650513, "z_loss": 14.505946159362793, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3461383581161499, "tokens_per_second": 4313652.911448548, "eta_seconds": 2528.307028841972, "data_wait_seconds": 1.5735626220703125e-05}
|
| 1823 |
+
{"step": 18220, "total_steps": 28611, "tokens": 19105054720, "loss": 2.7910465002059937, "ce_loss": 2.789933204650879, "z_loss": 11.133033514022827, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2832988500595093, "tokens_per_second": 2946833.146754357, "eta_seconds": 3697.444908952713, "data_wait_seconds": 1.5497207641601562e-05}
|
| 1824 |
+
{"step": 18230, "total_steps": 28611, "tokens": 19115540480, "loss": 2.7886171340942383, "ce_loss": 2.787528872489929, "z_loss": 10.883071660995483, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.36888647079467773, "tokens_per_second": 4331645.418982787, "eta_seconds": 2512.9636438608172, "data_wait_seconds": 1.2934207916259766e-05}
|
| 1825 |
+
{"step": 18240, "total_steps": 28611, "tokens": 19126026240, "loss": 2.7950424551963806, "ce_loss": 2.7938588857650757, "z_loss": 11.83584213256836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37363529205322266, "tokens_per_second": 2899877.934169379, "eta_seconds": 3750.0825699806214, "data_wait_seconds": 1.4841556549072266e-05}
|
| 1826 |
+
{"step": 18250, "total_steps": 28611, "tokens": 19136512000, "loss": 2.8209962248802185, "ce_loss": 2.820086181163788, "z_loss": 9.100249528884888, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3237212896347046, "tokens_per_second": 2950458.5882587344, "eta_seconds": 3682.239764094353, "data_wait_seconds": 1.8358230590820312e-05}
|
| 1827 |
+
{"step": 18260, "total_steps": 28611, "tokens": 19146997760, "loss": 2.823543965816498, "ce_loss": 2.822400987148285, "z_loss": 11.430012226104736, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31567949056625366, "tokens_per_second": 4069267.5942648174, "eta_seconds": 2667.2638072013856, "data_wait_seconds": 1.7523765563964844e-05}
|
| 1828 |
+
{"step": 18270, "total_steps": 28611, "tokens": 19157483520, "loss": 2.7787742614746094, "ce_loss": 2.7776748538017273, "z_loss": 10.994019508361816, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3008755147457123, "tokens_per_second": 4972122.842360049, "eta_seconds": 2180.8239176273346, "data_wait_seconds": 1.4722347259521484e-05}
|
| 1829 |
+
{"step": 18280, "total_steps": 28611, "tokens": 19167969280, "loss": 2.8393272757530212, "ce_loss": 2.8380807042121887, "z_loss": 12.46525526046753, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2769436836242676, "tokens_per_second": 4126914.0365803237, "eta_seconds": 2624.92471613884, "data_wait_seconds": 1.4841556549072266e-05}
|
| 1830 |
+
{"step": 18290, "total_steps": 28611, "tokens": 19178455040, "loss": 2.8145135641098022, "ce_loss": 2.813309371471405, "z_loss": 12.042195796966553, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30613476037979126, "tokens_per_second": 3921856.988655627, "eta_seconds": 2759.497076845169, "data_wait_seconds": 1.4901161193847656e-05}
|
| 1831 |
+
{"step": 18300, "total_steps": 28611, "tokens": 19188940800, "loss": 2.783434748649597, "ce_loss": 2.782275080680847, "z_loss": 11.597184658050537, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3499545454978943, "tokens_per_second": 2867322.982722378, "eta_seconds": 3770.718262696266, "data_wait_seconds": 0.257796049118042}
|
| 1832 |
+
{"step": 18310, "total_steps": 28611, "tokens": 19199426560, "loss": 2.8076992630958557, "ce_loss": 2.8062919974327087, "z_loss": 14.071933031082153, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3235993981361389, "tokens_per_second": 3998748.3005535817, "eta_seconds": 2701.190613698959, "data_wait_seconds": 0.04485762119293213}
|
| 1833 |
+
{"step": 18320, "total_steps": 28611, "tokens": 19209912320, "loss": 2.823258399963379, "ce_loss": 2.822028398513794, "z_loss": 12.29986023902893, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30623435974121094, "tokens_per_second": 8504267.386003802, "eta_seconds": 1268.8800958633424, "data_wait_seconds": 1.2576580047607422e-05}
|
| 1834 |
+
{"step": 18330, "total_steps": 28611, "tokens": 19220398080, "loss": 2.799956440925598, "ce_loss": 2.7989118099212646, "z_loss": 10.446534156799316, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.36421558260917664, "tokens_per_second": 4136510.6607643794, "eta_seconds": 2606.1602979183194, "data_wait_seconds": 1.4543533325195312e-05}
|
| 1835 |
+
{"step": 18340, "total_steps": 28611, "tokens": 19230883840, "loss": 2.7856576442718506, "ce_loss": 2.7846630215644836, "z_loss": 9.946752548217773, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2845011055469513, "tokens_per_second": 3867391.6478800885, "eta_seconds": 2784.8030601978303, "data_wait_seconds": 1.3709068298339844e-05}
|
| 1836 |
+
{"step": 18350, "total_steps": 28611, "tokens": 19241369600, "loss": 2.804598867893219, "ce_loss": 2.803670883178711, "z_loss": 9.279602289199829, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38351064920425415, "tokens_per_second": 3937473.1851815777, "eta_seconds": 2732.5743770122526, "data_wait_seconds": 1.5974044799804688e-05}
|
| 1837 |
+
{"step": 18360, "total_steps": 28611, "tokens": 19251855360, "loss": 2.807775616645813, "ce_loss": 2.8066468834877014, "z_loss": 11.287463665008545, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3474162817001343, "tokens_per_second": 2897365.9553245124, "eta_seconds": 3709.905045390129, "data_wait_seconds": 2.0205974578857422e-05}
|
| 1838 |
+
{"step": 18370, "total_steps": 28611, "tokens": 19262341120, "loss": 2.7606066465377808, "ce_loss": 2.7594003081321716, "z_loss": 12.06361198425293, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3423118591308594, "tokens_per_second": 5008250.214800191, "eta_seconds": 2144.155414652824, "data_wait_seconds": 1.33514404296875e-05}
|
| 1839 |
+
{"step": 18380, "total_steps": 28611, "tokens": 19272826880, "loss": 2.832857668399811, "ce_loss": 2.8317751288414, "z_loss": 10.825122117996216, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29530173540115356, "tokens_per_second": 2775632.095626141, "eta_seconds": 3865.058727669716, "data_wait_seconds": 1.4007091522216797e-05}
|
| 1840 |
+
{"step": 18390, "total_steps": 28611, "tokens": 19283312640, "loss": 2.8082372546195984, "ce_loss": 2.807021200656891, "z_loss": 12.160211086273193, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31759020686149597, "tokens_per_second": 2962984.516517521, "eta_seconds": 3617.1283502340316, "data_wait_seconds": 1.5735626220703125e-05}
|
| 1841 |
+
{"step": 18400, "total_steps": 28611, "tokens": 19293798400, "loss": 2.8083587884902954, "ce_loss": 2.807235598564148, "z_loss": 11.231507062911987, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3557461202144623, "tokens_per_second": 2876136.741201505, "eta_seconds": 3722.705315995216, "data_wait_seconds": 0.09893107414245605}
|
| 1842 |
+
{"step": 18410, "total_steps": 28611, "tokens": 19304284160, "loss": 2.7923203706741333, "ce_loss": 2.7913578748703003, "z_loss": 9.625431776046753, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3069774806499481, "tokens_per_second": 3030087.8834033413, "eta_seconds": 3530.103478050232, "data_wait_seconds": 0.29110777378082275}
|
| 1843 |
+
{"step": 18420, "total_steps": 28611, "tokens": 19314769920, "loss": 2.7856281399726868, "ce_loss": 2.784516990184784, "z_loss": 11.111339330673218, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3015395402908325, "tokens_per_second": 4462001.720362471, "eta_seconds": 2394.8977803468706, "data_wait_seconds": 1.531839370727539e-05}
|
| 1844 |
+
{"step": 18430, "total_steps": 28611, "tokens": 19325255680, "loss": 2.7713760137557983, "ce_loss": 2.7702675461769104, "z_loss": 11.084403276443481, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2983447015285492, "tokens_per_second": 4206121.602972524, "eta_seconds": 2538.0988149404525, "data_wait_seconds": 1.4185905456542969e-05}
|
| 1845 |
+
{"step": 18440, "total_steps": 28611, "tokens": 19335741440, "loss": 2.785055458545685, "ce_loss": 2.7839473485946655, "z_loss": 11.081515550613403, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28209370374679565, "tokens_per_second": 2937805.558007486, "eta_seconds": 3630.2833136558534, "data_wait_seconds": 1.4007091522216797e-05}
|
| 1846 |
+
{"step": 18450, "total_steps": 28611, "tokens": 19346227200, "loss": 2.8245277404785156, "ce_loss": 2.8234214782714844, "z_loss": 11.062767744064331, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3472136855125427, "tokens_per_second": 3136932.0637456654, "eta_seconds": 3396.497125053406, "data_wait_seconds": 1.8358230590820312e-05}
|
| 1847 |
+
{"step": 18460, "total_steps": 28611, "tokens": 19356712960, "loss": 2.764089822769165, "ce_loss": 2.7629677653312683, "z_loss": 11.221049308776855, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29378125071525574, "tokens_per_second": 3231412.7848150185, "eta_seconds": 3293.944687604904, "data_wait_seconds": 0.21997666358947754}
|
| 1848 |
+
{"step": 18470, "total_steps": 28611, "tokens": 19367198720, "loss": 2.813955843448639, "ce_loss": 2.8126940727233887, "z_loss": 12.618087530136108, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38760852813720703, "tokens_per_second": 3762490.395916227, "eta_seconds": 2826.215643644333, "data_wait_seconds": 1.6987323760986328e-05}
|
| 1849 |
+
{"step": 18480, "total_steps": 28611, "tokens": 19377684480, "loss": 2.8001421689987183, "ce_loss": 2.799024760723114, "z_loss": 11.17432188987732, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26280906796455383, "tokens_per_second": 4354002.2946913615, "eta_seconds": 2439.8525166034697, "data_wait_seconds": 1.4066696166992188e-05}
|
| 1850 |
+
{"step": 18490, "total_steps": 28611, "tokens": 19388170240, "loss": 2.767798960208893, "ce_loss": 2.766676425933838, "z_loss": 11.225648403167725, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34218066930770874, "tokens_per_second": 3019178.1765180444, "eta_seconds": 3515.0749891281125, "data_wait_seconds": 1.4960765838623047e-05}
|
| 1851 |
+
{"step": 18500, "total_steps": 28611, "tokens": 19398656000, "loss": 2.7460766434669495, "ce_loss": 2.7449516654014587, "z_loss": 11.249780178070068, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32980096340179443, "tokens_per_second": 3001679.783875881, "eta_seconds": 3532.072938942909, "data_wait_seconds": 0.28200817108154297}
|
| 1852 |
+
{"step": 18510, "total_steps": 28611, "tokens": 19409141760, "loss": 2.797399580478668, "ce_loss": 2.796216070652008, "z_loss": 11.835231065750122, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3217941224575043, "tokens_per_second": 4134427.9434587704, "eta_seconds": 2561.821446847916, "data_wait_seconds": 1.436471939086914e-05}
|
| 1853 |
+
{"step": 18520, "total_steps": 28611, "tokens": 19419627520, "loss": 2.785778760910034, "ce_loss": 2.784781575202942, "z_loss": 9.972194194793701, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29798951745033264, "tokens_per_second": 2684040.6792662675, "eta_seconds": 3942.2578419685365, "data_wait_seconds": 1.6868114471435547e-05}
|
| 1854 |
+
{"step": 18530, "total_steps": 28611, "tokens": 19430113280, "loss": 2.7964378595352173, "ce_loss": 2.795236587524414, "z_loss": 12.013369083404541, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3103245496749878, "tokens_per_second": 4024588.816468612, "eta_seconds": 2626.5278611183167, "data_wait_seconds": 1.6748905181884766e-05}
|
| 1855 |
+
{"step": 18540, "total_steps": 28611, "tokens": 19440599040, "loss": 2.7914024591445923, "ce_loss": 2.7901617884635925, "z_loss": 12.40635871887207, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33904799818992615, "tokens_per_second": 4164299.389227399, "eta_seconds": 2535.890892791748, "data_wait_seconds": 1.4543533325195312e-05}
|
| 1856 |
+
{"step": 18550, "total_steps": 28611, "tokens": 19451084800, "loss": 2.7342612743377686, "ce_loss": 2.733203709125519, "z_loss": 10.576088666915894, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34921616315841675, "tokens_per_second": 3012534.360614496, "eta_seconds": 3501.942840528488, "data_wait_seconds": 1.3887882232666016e-05}
|
| 1857 |
+
{"step": 18560, "total_steps": 28611, "tokens": 19461570560, "loss": 2.7623714208602905, "ce_loss": 2.761191666126251, "z_loss": 11.797463178634644, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3015025854110718, "tokens_per_second": 4008741.5811884636, "eta_seconds": 2629.0638003349304, "data_wait_seconds": 1.4185905456542969e-05}
|
| 1858 |
+
{"step": 18570, "total_steps": 28611, "tokens": 19472056320, "loss": 2.8408411145210266, "ce_loss": 2.8397580981254578, "z_loss": 10.830617189407349, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3461781442165375, "tokens_per_second": 2864880.5003782017, "eta_seconds": 3675.1102234840396, "data_wait_seconds": 1.3649463653564453e-05}
|
| 1859 |
+
{"step": 18580, "total_steps": 28611, "tokens": 19482542080, "loss": 2.8095773458480835, "ce_loss": 2.808592975139618, "z_loss": 9.844269514083862, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34785932302474976, "tokens_per_second": 2655425.591211757, "eta_seconds": 3961.0471070289614, "data_wait_seconds": 1.710653305053711e-05}
|
| 1860 |
+
{"step": 18590, "total_steps": 28611, "tokens": 19493027840, "loss": 2.759579837322235, "ce_loss": 2.7584012746810913, "z_loss": 11.785234212875366, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31930914521217346, "tokens_per_second": 4361393.793800281, "eta_seconds": 2409.2711167097095, "data_wait_seconds": 1.519918441772461e-05}
|